39 files changed, 385 insertions, 681 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index ce13c272c387..48ce750bf70a 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -129,12 +129,9 @@ static inline bool can_inc_bucket_gen(struct bucket *b)
 
 bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b)
 {
-	BUG_ON(!ca->set->gc_mark_valid);
-
-	return (!GC_MARK(b) ||
-		GC_MARK(b) == GC_MARK_RECLAIMABLE) &&
-		!atomic_read(&b->pin) &&
-		can_inc_bucket_gen(b);
+	return (ca->set->gc_mark_valid || b->reclaimable_in_gc) &&
+	       ((!GC_MARK(b) || GC_MARK(b) == GC_MARK_RECLAIMABLE) &&
+	       !atomic_read(&b->pin) && can_inc_bucket_gen(b));
 }
 
 void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
@@ -148,6 +145,7 @@ void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
 	bch_inc_gen(ca, b);
 	b->prio = INITIAL_PRIO;
 	atomic_inc(&b->pin);
+	b->reclaimable_in_gc = 0;
 }
 
 static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
@@ -352,8 +350,7 @@ static int bch_allocator_thread(void *arg)
 		 */
 
 retry_invalidate:
-		allocator_wait(ca, ca->set->gc_mark_valid &&
-			       !ca->invalidate_needs_gc);
+		allocator_wait(ca, !ca->invalidate_needs_gc);
 		invalidate_buckets(ca);
 
 		/*
@@ -501,8 +498,8 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 
 	ca = c->cache;
 	b = bch_bucket_alloc(ca, reserve, wait);
-	if (b == -1)
-		goto err;
+	if (b < 0)
+		return -1;
 
 	k->ptr[0] = MAKE_PTR(ca->buckets[b].gen,
 			     bucket_to_sector(c, b),
@@ -511,10 +508,6 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 	SET_KEY_PTRS(k, 1);
 
 	return 0;
-err:
-	bch_bucket_free(c, k);
-	bkey_put(c, k);
-	return -1;
 }
 
 int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 4e6afa89921f..1d33e40d26ea 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -200,6 +200,7 @@ struct bucket {
 	uint8_t		gen;
 	uint8_t		last_gc; /* Most out of date gen in the btree */
 	uint16_t	gc_mark; /* Bitfield used by GC. See below for field */
+	uint16_t	reclaimable_in_gc:1;
 };
 
 /*
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 2bba4d6aaaa2..463eb13bd0b2 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -54,7 +54,7 @@ void bch_dump_bucket(struct btree_keys *b)
 int __bch_count_data(struct btree_keys *b)
 {
 	unsigned int ret = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k;
 
 	if (b->ops->is_extents)
@@ -67,7 +67,7 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
 {
 	va_list args;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	const char *err;
 
 	for_each_key(b, k, &iter) {
@@ -879,7 +879,7 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
 	struct bset *i = bset_tree_last(b)->data;
 	struct bkey *m, *prev = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey preceding_key_on_stack = ZERO_KEY;
 	struct bkey *preceding_key_p = &preceding_key_on_stack;
 
@@ -895,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	else
 		preceding_key(k, &preceding_key_p);
 
-	m = bch_btree_iter_init(b, &iter, preceding_key_p);
+	m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
 
-	if (b->ops->insert_fixup(b, k, &iter, replace_key))
+	if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
 		return status;
 
 	status = BTREE_INSERT_STATUS_INSERT;
@@ -1100,33 +1100,33 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 				 btree_iter_cmp));
 }
 
-static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
-					  struct btree_iter *iter,
-					  struct bkey *search,
-					  struct bset_tree *start)
+static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
+						struct btree_iter_stack *iter,
+						struct bkey *search,
+						struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 
-	iter->size = ARRAY_SIZE(iter->data);
-	iter->used = 0;
+	iter->iter.size = ARRAY_SIZE(iter->stack_data);
+	iter->iter.used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->b = b;
+	iter->iter.b = b;
 #endif
 
 	for (; start <= bset_tree_last(b); start++) {
 		ret = bch_bset_search(b, start, search);
-		bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
+		bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
 	}
 
 	return ret;
 }
 
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				 struct btree_iter_stack *iter,
 				 struct bkey *search)
 {
-	return __bch_btree_iter_init(b, iter, search, b->set);
+	return __bch_btree_iter_stack_init(b, iter, search, b->set);
 }
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
@@ -1293,10 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 			    struct bset_sort_state *state)
 {
 	size_t order = b->page_order, keys = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	int oldsize = bch_count_data(b);
 
-	__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
+	__bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
 
 	if (start) {
 		unsigned int i;
@@ -1307,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 		order = get_order(__set_bytes(b->set->data, keys));
 	}
 
-	__btree_sort(b, &iter, start, order, false, state);
+	__btree_sort(b, &iter.iter, start, order, false, state);
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
@@ -1323,11 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
 			 struct bset_sort_state *state)
 {
 	uint64_t start_time = local_clock();
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	bch_btree_iter_init(b, &iter, NULL);
+	bch_btree_iter_stack_init(b, &iter, NULL);
 
-	btree_mergesort(b, new->set->data, &iter, false, true);
+	btree_mergesort(b, new->set->data, &iter.iter, false, true);
 
 	bch_time_stats_update(&state->time, start_time);
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index d795c84246b0..011f6062c4c0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -321,7 +321,14 @@ struct btree_iter {
 #endif
 	struct btree_iter_set {
 		struct bkey *k, *end;
-	} data[MAX_BSETS];
+	} data[];
+};
+
+/* Fixed-size btree_iter that can be allocated on the stack */
+
+struct btree_iter_stack {
+	struct btree_iter iter;
+	struct btree_iter_set stack_data[MAX_BSETS];
 };
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -333,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end);
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
-				 struct bkey *search);
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				       struct btree_iter_stack *iter,
+				       struct bkey *search);
 
 struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 			       const struct bkey *search);
@@ -350,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
-#define for_each_key_filter(b, k, iter, filter)				\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
+#define for_each_key_filter(b, k, stack_iter, filter)                      \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL);           \
+	     ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+					       filter));)
 
-#define for_each_key(b, k, iter)					\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next(iter));)
+#define for_each_key(b, k, stack_iter)                           \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+	     ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
 
 /* Sorting */
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 196cdacce38f..4e6ccf2c8a0b 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1309,7 +1309,7 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bset_tree *t;
 
 	gc->nodes++;
@@ -1570,7 +1570,7 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	unsigned int ret = 0;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
@@ -1611,17 +1611,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1740,18 +1741,20 @@ static void btree_gc_start(struct cache_set *c)
 
 	mutex_lock(&c->bucket_lock);
 
-	c->gc_mark_valid = 0;
 	c->gc_done = ZERO_KEY;
 
 	ca = c->cache;
 	for_each_bucket(b, ca) {
 		b->last_gc = b->gen;
+		if (bch_can_invalidate_bucket(ca, b))
+			b->reclaimable_in_gc = 1;
 		if (!atomic_read(&b->pin)) {
 			SET_GC_MARK(b, 0);
 			SET_GC_SECTORS_USED(b, 0);
 		}
 	}
 
+	c->gc_mark_valid = 0;
 	mutex_unlock(&c->bucket_lock);
 }
 
@@ -1808,6 +1811,9 @@ static void bch_btree_gc_finish(struct cache_set *c)
 	for_each_bucket(b, ca) {
 		c->need_gc	= max(c->need_gc, bucket_gc_gen(b));
 
+		if (b->reclaimable_in_gc)
+			b->reclaimable_in_gc = 0;
+
 		if (atomic_read(&b->pin))
 			continue;
 
@@ -1911,7 +1917,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1919,10 +1925,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_init(&b->keys, &iter, NULL);
+		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1950,7 +1956,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1959,8 +1965,8 @@ static int bch_btree_check_thread(void *arg)
 	ret = 0;
 
 	/* root node keys are checked before thread created */
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1978,7 +1984,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2051,7 +2057,7 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct btree_check_state check_state;
 
 	/* check and mark root node keys */
@@ -2547,11 +2553,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter iter;
+		struct btree_iter_stack iter;
 
-		bch_btree_iter_init(&b->keys, &iter, from);
+		bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2580,11 +2586,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	bch_btree_iter_init(&b->keys, &iter, from);
+	bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 83d112bd2b1c..af345dc6fde1 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -369,10 +369,24 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	struct io *i;
 
 	if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
-	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
 	    (bio_op(bio) == REQ_OP_DISCARD))
 		goto skip;
 
+	if (c->gc_stats.in_use > CUTOFF_CACHE_ADD) {
+		/*
+		 * If cached buckets are all clean now, 'true' will be
+		 * returned and all requests will bypass the cache device.
+		 * Then c->sectors_to_gc has no chance to be negative, and
+		 * gc thread won't wake up and caching won't work forever.
+		 * Here call force_wake_up_gc() to avoid such aftermath.
+		 */
+		if (BDEV_STATE(&dc->sb) == BDEV_STATE_CLEAN &&
+		    c->gc_mark_valid)
+			force_wake_up_gc(c);
+
+		goto skip;
+	}
+
 	if (mode == CACHE_MODE_NONE ||
 	    (mode == CACHE_MODE_WRITEAROUND &&
 	     op_is_write(bio_op(bio))))
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 330bcd9ea4a9..4d11fc664cb0 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -171,7 +171,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	struct page *page;
 	unsigned int i;
 
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+	page = read_cache_page_gfp(bdev->bd_mapping,
 				   SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
 	if (IS_ERR(page))
 		return "IO error";
@@ -881,8 +881,8 @@ static void bcache_device_free(struct bcache_device *d)
 		bcache_device_detach(d);
 
 	if (disk) {
-		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(disk->first_minor));
+		ida_free(&bcache_device_idx,
+			 first_minor_to_idx(disk->first_minor));
 		put_disk(disk);
 	}
 
@@ -940,8 +940,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	if (!d->full_dirty_stripes)
 		goto out_free_stripe_sectors_dirty;
 
-	idx = ida_simple_get(&bcache_device_idx, 0,
-				BCACHE_DEVICE_IDX_MAX, GFP_KERNEL);
+	idx = ida_alloc_max(&bcache_device_idx, BCACHE_DEVICE_IDX_MAX - 1,
+			    GFP_KERNEL);
 	if (idx < 0)
 		goto out_free_full_dirty_stripes;
 
@@ -986,7 +986,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 out_bioset_exit:
 	bioset_exit(&d->bio_split);
 out_ida_remove:
-	ida_simple_remove(&bcache_device_idx, idx);
+	ida_free(&bcache_device_idx, idx);
 out_free_full_dirty_stripes:
 	kvfree(d->full_dirty_stripes);
 out_free_stripe_sectors_dirty:
@@ -1914,8 +1914,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size + 1) *
-		sizeof(struct btree_iter_set);
+	iter_size = sizeof(struct btree_iter) +
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
 	if (!c->devices)
@@ -2554,10 +2555,6 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (IS_ERR(bdev_file))
 		goto out_free_sb;
 
-	err = "failed to set blocksize";
-	if (set_blocksize(file_bdev(bdev_file), 4096))
-		goto out_blkdev_put;
-
 	err = read_super(sb, file_bdev(bdev_file), &sb_disk);
 	if (err)
 		goto out_blkdev_put;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 6956beb55326..826b14cae4e5 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -660,7 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c)
 	unsigned int bytes = 0;
 	struct bkey *k;
 	struct btree *b;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
 	goto lock_root;
 
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 8827a6f130ad..792e070ccf38 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -908,15 +908,15 @@ static int bch_dirty_init_thread(void *arg)
 	struct dirty_init_thrd_info *info = arg;
 	struct bch_dirty_init_state *state = info->state;
 	struct cache_set *c = state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
 	prev_idx = 0;
 
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -930,7 +930,7 @@ static int bch_dirty_init_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -979,7 +979,7 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	int i;
 	struct btree *b = NULL;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index fd852981ef9c..cf433b0cf742 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -321,8 +321,7 @@ static bool __unlock(struct dm_bio_prison_v2 *prison,
 {
 	BUG_ON(!cell->exclusive_lock);
 
-	bio_list_merge(bios, &cell->bios);
-	bio_list_init(&cell->bios);
+	bio_list_merge_init(bios, &cell->bios);
 
 	if (cell->shared_count) {
 		cell->exclusive_lock = false;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 911f73f7ebba..16884b585053 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -115,8 +115,7 @@ static void __commit(struct work_struct *_ws)
 	 */
 	spin_lock_irq(&b->lock);
 	list_splice_init(&b->work_items, &work_items);
-	bio_list_merge(&bios, &b->bios);
-	bio_list_init(&b->bios);
+	bio_list_merge_init(&bios, &b->bios);
 	b->commit_scheduled = false;
 	spin_unlock_irq(&b->lock);
 
@@ -565,8 +564,7 @@ static void defer_bio(struct cache *cache, struct bio *bio)
 static void defer_bios(struct cache *cache, struct bio_list *bios)
 {
 	spin_lock_irq(&cache->lock);
-	bio_list_merge(&cache->deferred_bios, bios);
-	bio_list_init(bios);
+	bio_list_merge_init(&cache->deferred_bios, bios);
 	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
@@ -1816,8 +1814,7 @@ static void process_deferred_bios(struct work_struct *ws)
 	bio_list_init(&bios);
 
 	spin_lock_irq(&cache->lock);
-	bio_list_merge(&bios, &cache->deferred_bios);
-	bio_list_init(&cache->deferred_bios);
+	bio_list_merge_init(&bios, &cache->deferred_bios);
 	spin_unlock_irq(&cache->lock);
 
 	while ((bio = bio_list_pop(&bios))) {
@@ -1847,8 +1844,7 @@ static void requeue_deferred_bios(struct cache *cache)
 	struct bio_list bios;
 
 	bio_list_init(&bios);
-	bio_list_merge(&bios, &cache->deferred_bios);
-	bio_list_init(&cache->deferred_bios);
+	bio_list_merge_init(&bios, &cache->deferred_bios);
 
 	while ((bio = bio_list_pop(&bios))) {
 		bio->bi_status = BLK_STS_DM_REQUEUE;
@@ -3394,8 +3390,8 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 
 	if (!cache->features.discard_passdown) {
 		/* No passdown is done so setting own virtual limits */
-		limits->max_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024,
-						    cache->origin_sectors);
+		limits->max_hw_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024,
+						       cache->origin_sectors);
 		limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
 		return;
 	}
@@ -3404,7 +3400,6 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 	 * cache_iterate_devices() is stacking both origin and fast device limits
 	 * but discards aren't passed to fast device, so inherit origin's limits.
 	 */
-	limits->max_discard_sectors = origin_limits->max_discard_sectors;
 	limits->max_hw_discard_sectors = origin_limits->max_hw_discard_sectors;
 	limits->discard_granularity = origin_limits->discard_granularity;
 	limits->discard_alignment = origin_limits->discard_alignment;
diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c
index c43d55672bce..47c1fa7aad8b 100644
--- a/drivers/md/dm-clone-metadata.c
+++ b/drivers/md/dm-clone-metadata.c
@@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd)
 
 /*---------------------------------------------------------------------------*/
 
-static size_t bitmap_size(unsigned long nr_bits)
-{
-	return BITS_TO_LONGS(nr_bits) * sizeof(long);
-}
-
 static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words,
 			    unsigned long nr_regions)
 {
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 94b2fc33f64b..ad79b52ffc14 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -1181,8 +1181,7 @@ static void process_deferred_discards(struct clone *clone)
 	struct bio_list discards = BIO_EMPTY_LIST;
 
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&discards, &clone->deferred_discard_bios);
-	bio_list_init(&clone->deferred_discard_bios);
+	bio_list_merge_init(&discards, &clone->deferred_discard_bios);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&discards))
@@ -1215,8 +1214,7 @@ static void process_deferred_bios(struct clone *clone)
 	struct bio_list bios = BIO_EMPTY_LIST;
 
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&bios, &clone->deferred_bios);
-	bio_list_init(&clone->deferred_bios);
+	bio_list_merge_init(&bios, &clone->deferred_bios);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios))
@@ -1237,11 +1235,9 @@ static void process_deferred_flush_bios(struct clone *clone)
 	 * before issuing them or signaling their completion.
 	 */
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&bios, &clone->deferred_flush_bios);
-	bio_list_init(&clone->deferred_flush_bios);
-
-	bio_list_merge(&bio_completions, &clone->deferred_flush_completions);
-	bio_list_init(&clone->deferred_flush_completions);
+	bio_list_merge_init(&bios, &clone->deferred_flush_bios);
+	bio_list_merge_init(&bio_completions,
+			    &clone->deferred_flush_completions);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&
@@ -2050,7 +2046,8 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits)
 	if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) {
 		/* No passdown is done so we set our own virtual limits */
 		limits->discard_granularity = clone->region_size << SECTOR_SHIFT;
-		limits->max_discard_sectors = round_down(UINT_MAX >> SECTOR_SHIFT, clone->region_size);
+		limits->max_hw_discard_sectors = round_down(UINT_MAX >> SECTOR_SHIFT,
+							    clone->region_size);
 		return;
 	}
 
@@ -2059,7 +2056,6 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits)
 	 * device limits but discards aren't passed to the source device, so
 	 * inherit destination's limits.
 	 */
-	limits->max_discard_sectors = dest_limits->max_discard_sectors;
 	limits->max_hw_discard_sectors = dest_limits->max_hw_discard_sectors;
 	limits->discard_granularity = dest_limits->discard_granularity;
 	limits->discard_alignment = dest_limits->discard_alignment;
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index e6757a30dcca..08700bfc3e23 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -140,7 +140,7 @@ struct mapped_device {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
-	unsigned int *zwp_offset;
+	void *zone_revalidate_map;
 #endif
 
 #ifdef CONFIG_IMA
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9a74c6316c5d..1b7a97cc3779 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -47,6 +47,8 @@
 
 #define DM_MSG_PREFIX "crypt"
 
+static DEFINE_IDA(workqueue_ida);
+
 /*
  * context holding the current state of a multi-part conversion
  */
@@ -137,9 +139,9 @@ struct iv_elephant_private {
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
-	     DM_CRYPT_NO_READ_WORKQUEUE, DM_CRYPT_NO_WRITE_WORKQUEUE,
-	     DM_CRYPT_WRITE_INLINE };
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_HIGH_PRIORITY,
+	     DM_CRYPT_NO_OFFLOAD, DM_CRYPT_NO_READ_WORKQUEUE,
+	     DM_CRYPT_NO_WRITE_WORKQUEUE, DM_CRYPT_WRITE_INLINE };
 
 enum cipher_flags {
 	CRYPT_MODE_INTEGRITY_AEAD,	/* Use authenticated mode for cipher */
@@ -184,6 +186,7 @@ struct crypt_config {
 		struct crypto_aead **tfms_aead;
 	} cipher_tfm;
 	unsigned int tfms_count;
+	int workqueue_id;
 	unsigned long cipher_flags;
 
 	/*
@@ -1653,8 +1656,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
 
 /*
  * Generate a new unfragmented bio with the given size
- * This should never violate the device limitations (but only because
- * max_segment_size is being constrained to PAGE_SIZE).
+ * This should never violate the device limitations (but if it did then block
+ * core should split the bio as needed).
  *
  * This function may be called concurrently. If we allocate from the mempool
  * concurrently, there is a possibility of deadlock. For example, if we have
@@ -2771,6 +2774,9 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->crypt_queue)
 		destroy_workqueue(cc->crypt_queue);
 
+	if (cc->workqueue_id)
+		ida_free(&workqueue_ida, cc->workqueue_id);
+
 	crypt_free_tfms(cc);
 
 	bioset_exit(&cc->bs);
@@ -3134,7 +3140,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 	struct crypt_config *cc = ti->private;
 	struct dm_arg_set as;
 	static const struct dm_arg _args[] = {
-		{0, 8, "Invalid number of feature args"},
+		{0, 9, "Invalid number of feature args"},
 	};
 	unsigned int opt_params, val;
 	const char *opt_string, *sval;
@@ -3161,6 +3167,8 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 
 		else if (!strcasecmp(opt_string, "same_cpu_crypt"))
 			set_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+		else if (!strcasecmp(opt_string, "high_priority"))
+			set_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags);
 
 		else if (!strcasecmp(opt_string, "submit_from_crypt_cpus"))
 			set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
@@ -3230,8 +3238,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct crypt_config *cc;
 	const char *devname = dm_table_device_name(ti->table);
-	int key_size;
+	int key_size, wq_id;
 	unsigned int align_mask;
+	unsigned int common_wq_flags;
 	unsigned long long tmpll;
 	int ret;
 	size_t iv_size_padding, additional_req_size;
@@ -3398,20 +3407,38 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		cc->tag_pool_max_sectors <<= cc->sector_shift;
 	}
 
+	wq_id = ida_alloc_min(&workqueue_ida, 1, GFP_KERNEL);
+	if (wq_id < 0) {
+		ti->error = "Couldn't get workqueue id";
+		ret = wq_id;
+		goto bad;
+	}
+	cc->workqueue_id = wq_id;
+
 	ret = -ENOMEM;
-	cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname);
+	common_wq_flags = WQ_MEM_RECLAIM | WQ_SYSFS;
+	if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+		common_wq_flags |= WQ_HIGHPRI;
+
+	cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", common_wq_flags, 1, devname, wq_id);
 	if (!cc->io_queue) {
 		ti->error = "Couldn't create kcryptd io queue";
 		goto bad;
 	}
 
-	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
-						  1, devname);
-	else
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
-						  num_online_cpus(), devname);
+	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) {
+		cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d",
+						  common_wq_flags | WQ_CPU_INTENSIVE,
+						  1, devname, wq_id);
+	} else {
+		/*
+		 * While crypt_queue is certainly CPU intensive, the use of
+		 * WQ_CPU_INTENSIVE is meaningless with WQ_UNBOUND.
+		 */
+		cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d",
+						  common_wq_flags | WQ_UNBOUND,
+						  num_online_cpus(), devname, wq_id);
+	}
 	if (!cc->crypt_queue) {
 		ti->error = "Couldn't create kcryptd queue";
 		goto bad;
@@ -3427,6 +3454,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Couldn't spawn write thread";
 		goto bad;
 	}
+	if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+		set_user_nice(cc->write_thread, MIN_NICE);
 
 	ti->num_flush_bios = 1;
 	ti->limit_swap_bios = true;
@@ -3547,6 +3576,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 
 		num_feature_args += !!ti->num_discard_bios;
 		num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+		num_feature_args += test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags);
@@ -3560,6 +3590,8 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 				DMEMIT(" allow_discards");
 			if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
 				DMEMIT(" same_cpu_crypt");
+			if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+				DMEMIT(" high_priority");
 			if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags))
 				DMEMIT(" submit_from_crypt_cpus");
 			if (test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags))
@@ -3579,6 +3611,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		DMEMIT_TARGET_NAME_VERSION(ti->type);
 		DMEMIT(",allow_discards=%c", ti->num_discard_bios ? 'y' : 'n');
 		DMEMIT(",same_cpu_crypt=%c", test_bit(DM_CRYPT_SAME_CPU, &cc->flags) ? 'y' : 'n');
+		DMEMIT(",high_priority=%c", test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags) ? 'y' : 'n');
 		DMEMIT(",submit_from_crypt_cpus=%c", test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags) ?
 		       'y' : 'n');
 		DMEMIT(",no_read_workqueue=%c", test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags) ?
@@ -3688,14 +3721,6 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct crypt_config *cc = ti->private;
 
-	/*
-	 * Unfortunate constraint that is required to avoid the potential
-	 * for exceeding underlying device's max_segments limits -- due to
-	 * crypt_alloc_buffer() possibly allocating pages for the encryption
-	 * bio that are not as physically contiguous as the original bio.
-	 */
-	limits->max_segment_size = PAGE_SIZE;
-
 	limits->logical_block_size =
 		max_t(unsigned int, limits->logical_block_size, cc->sector_size);
 	limits->physical_block_size =
@@ -3706,7 +3731,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 25, 0},
+	.version = {1, 26, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 5eabdb06c649..08f6387620c1 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -28,7 +28,8 @@ struct delay_class {
 
 struct delay_c {
 	struct timer_list delay_timer;
-	struct mutex timer_lock;
+	struct mutex process_bios_lock; /* hold while removing bios to be processed from list */
+	spinlock_t delayed_bios_lock; /* hold on all accesses to delayed_bios list */
 	struct workqueue_struct *kdelayd_wq;
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
@@ -49,8 +50,6 @@ struct dm_delay_info {
 	unsigned long expires;
 };
 
-static DEFINE_MUTEX(delayed_bios_lock);
-
 static void handle_delayed_timer(struct timer_list *t)
 {
 	struct delay_c *dc = from_timer(dc, t, delay_timer);
@@ -60,12 +59,7 @@ static void handle_delayed_timer(struct timer_list *t)
 
 static void queue_timeout(struct delay_c *dc, unsigned long expires)
 {
-	mutex_lock(&dc->timer_lock);
-
-	if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires)
-		mod_timer(&dc->delay_timer, expires);
-
-	mutex_unlock(&dc->timer_lock);
+	timer_reduce(&dc->delay_timer, expires);
 }
 
 static inline bool delay_is_fast(struct delay_c *dc)
@@ -89,12 +83,16 @@ static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
 	struct bio_list flush_bio_list;
+	LIST_HEAD(local_list);
 	unsigned long next_expires = 0;
 	bool start_timer = false;
 	bio_list_init(&flush_bio_list);
 
-	mutex_lock(&delayed_bios_lock);
-	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+	mutex_lock(&dc->process_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
+	list_replace_init(&dc->delayed_bios, &local_list);
+	spin_unlock(&dc->delayed_bios_lock);
+	list_for_each_entry_safe(delayed, next, &local_list, list) {
 		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
@@ -114,7 +112,10 @@ static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 			}
 		}
 	}
-	mutex_unlock(&delayed_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
+	list_splice(&local_list, &dc->delayed_bios);
+	spin_unlock(&dc->delayed_bios_lock);
+	mutex_unlock(&dc->process_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
@@ -128,13 +129,13 @@ static int flush_worker_fn(void *data)
 
 	while (!kthread_should_stop()) {
 		flush_delayed_bios(dc, false);
-		mutex_lock(&delayed_bios_lock);
+		spin_lock(&dc->delayed_bios_lock);
 		if (unlikely(list_empty(&dc->delayed_bios))) {
 			set_current_state(TASK_INTERRUPTIBLE);
-			mutex_unlock(&delayed_bios_lock);
+			spin_unlock(&dc->delayed_bios_lock);
 			schedule();
 		} else {
-			mutex_unlock(&delayed_bios_lock);
+			spin_unlock(&dc->delayed_bios_lock);
 			cond_resched();
 		}
 	}
@@ -154,8 +155,10 @@ static void delay_dtr(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	if (dc->kdelayd_wq)
+	if (dc->kdelayd_wq) {
+		timer_shutdown_sync(&dc->delay_timer);
 		destroy_workqueue(dc->kdelayd_wq);
+	}
 
 	if (dc->read.dev)
 		dm_put_device(ti, dc->read.dev);
@@ -166,7 +169,7 @@ static void delay_dtr(struct dm_target *ti)
 	if (dc->worker)
 		kthread_stop(dc->worker);
 
-	mutex_destroy(&dc->timer_lock);
+	mutex_destroy(&dc->process_bios_lock);
 
 	kfree(dc);
 }
@@ -224,7 +227,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = dc;
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	mutex_init(&dc->timer_lock);
+	mutex_init(&dc->process_bios_lock);
+	spin_lock_init(&dc->delayed_bios_lock);
 	dc->may_delay = true;
 	dc->argc = argc;
 
@@ -240,19 +244,18 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ret = delay_class_ctr(ti, &dc->flush, argv);
 		if (ret)
 			goto bad;
-		max_delay = max(max_delay, dc->write.delay);
-		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
 	ret = delay_class_ctr(ti, &dc->write, argv + 3);
 	if (ret)
 		goto bad;
+	max_delay = max(max_delay, dc->write.delay);
+
 	if (argc == 6) {
 		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
 		if (ret)
 			goto bad;
-		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
@@ -267,8 +270,7 @@ out:
 		 * In case of small requested delays, use kthread instead of
 		 * timers and workqueue to achieve better latency.
 		 */
-		dc->worker = kthread_create(&flush_worker_fn, dc,
-					    "dm-delay-flush-worker");
+		dc->worker = kthread_run(&flush_worker_fn, dc, "dm-delay-flush-worker");
 		if (IS_ERR(dc->worker)) {
 			ret = PTR_ERR(dc->worker);
 			dc->worker = NULL;
@@ -309,14 +311,14 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	delayed->context = dc;
 	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
 
-	mutex_lock(&delayed_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
 	if (unlikely(!dc->may_delay)) {
-		mutex_unlock(&delayed_bios_lock);
+		spin_unlock(&dc->delayed_bios_lock);
 		return DM_MAPIO_REMAPPED;
 	}
 	c->ops++;
 	list_add_tail(&delayed->list, &dc->delayed_bios);
-	mutex_unlock(&delayed_bios_lock);
+	spin_unlock(&dc->delayed_bios_lock);
 
 	if (delay_is_fast(dc))
 		wake_up_process(dc->worker);
@@ -330,12 +332,12 @@ static void delay_presuspend(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	mutex_lock(&delayed_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
 	dc->may_delay = false;
-	mutex_unlock(&delayed_bios_lock);
+	spin_unlock(&dc->delayed_bios_lock);
 
 	if (!delay_is_fast(dc))
-		del_timer_sync(&dc->delay_timer);
+		timer_delete(&dc->delay_timer);
 	flush_delayed_bios(dc, true);
 }
 
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 6acfa5bf97a4..8f81e597858d 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1272,8 +1272,7 @@ static void process_deferred_bios(struct era *era)
 	bio_list_init(&marked_bios);
 
 	spin_lock(&era->deferred_lock);
-	bio_list_merge(&deferred_bios, &era->deferred_bios);
-	bio_list_init(&era->deferred_bios);
+	bio_list_merge_init(&deferred_bios, &era->deferred_bios);
 	spin_unlock(&era->deferred_lock);
 
 	if (bio_list_empty(&deferred_bios))
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 7f3dc8ee6ab8..417fddebe367 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3492,6 +3492,7 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		limits->physical_block_size = ic->sectors_per_block << SECTOR_SHIFT;
 		blk_limits_io_min(limits, ic->sectors_per_block << SECTOR_SHIFT);
 		limits->dma_alignment = limits->logical_block_size - 1;
+		limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT;
 	}
 	limits->max_integrity_segments = USHRT_MAX;
 }
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index f17a6cf2284e..8d7df8303d0a 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -871,7 +871,7 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit
 	if (!bdev_max_discard_sectors(lc->dev->bdev)) {
 		lc->device_supports_discard = false;
 		limits->discard_granularity = lc->sectorsize;
-		limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT);
+		limits->max_hw_discard_sectors = (UINT_MAX >> SECTOR_SHIFT);
 	}
 	limits->logical_block_size = bdev_logical_block_size(lc->dev->bdev);
 	limits->physical_block_size = bdev_physical_block_size(lc->dev->bdev);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 05d1328d1811..15b681b90153 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -704,8 +704,7 @@ static void process_queued_bios(struct work_struct *work)
 		return;
 	}
 
-	bio_list_merge(&bios, &m->queued_bios);
-	bio_list_init(&m->queued_bios);
+	bio_list_merge_init(&bios, &m->queued_bios);
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 0ace06d1bee3..f40c18da4000 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -2410,7 +2410,7 @@ static void snapshot_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 		/* All discards are split on chunk_size boundary */
 		limits->discard_granularity = snap->store->chunk_size;
-		limits->max_discard_sectors = snap->store->chunk_size;
+		limits->max_hw_discard_sectors = snap->store->chunk_size;
 
 		up_read(&_origins_lock);
 	}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 41f1d731ae5a..b2d5246cff21 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1963,26 +1963,23 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	bool wc = false, fua = false;
 	int r;
 
-	/*
-	 * Copy table's limits to the DM device's request_queue
-	 */
-	q->limits = *limits;
-
 	if (dm_table_supports_nowait(t))
 		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
 
 	if (!dm_table_supports_discards(t)) {
-		q->limits.max_discard_sectors = 0;
-		q->limits.max_hw_discard_sectors = 0;
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		q->limits.discard_misaligned = 0;
+		limits->max_hw_discard_sectors = 0;
+		limits->discard_granularity = 0;
+		limits->discard_alignment = 0;
+		limits->discard_misaligned = 0;
 	}
 
+	if (!dm_table_supports_write_zeroes(t))
+		limits->max_write_zeroes_sectors = 0;
+
 	if (!dm_table_supports_secure_erase(t))
-		q->limits.max_secure_erase_sectors = 0;
+		limits->max_secure_erase_sectors = 0;
 
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
@@ -2007,9 +2004,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	if (!dm_table_supports_write_zeroes(t))
-		q->limits.max_write_zeroes_sectors = 0;
-
 	dm_table_verify_integrity(t);
 
 	/*
@@ -2038,16 +2032,17 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 * For a zoned target, setup the zones related queue attributes
 	 * and resources necessary for zone append emulation if necessary.
 	 */
-	if (blk_queue_is_zoned(q)) {
-		r = dm_set_zones_restrictions(t, q);
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+		r = dm_set_zones_restrictions(t, q, limits);
 		if (r)
 			return r;
-		if (!static_key_enabled(&zoned_enabled.key))
-			static_branch_enable(&zoned_enabled);
 	}
 
+	r = queue_limits_set(q, limits);
+	if (r)
+		return r;
+
 	dm_update_crypto_profile(q, t);
-	disk_update_readahead(t->md->disk);
 
 	/*
 	 * Check for request-based device is left to
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 0c4efb0bef8a..652627aea11b 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -249,7 +249,6 @@ static int io_err_iterate_devices(struct dm_target *ti,
 
 static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
-	limits->max_discard_sectors = UINT_MAX;
 	limits->max_hw_discard_sectors = UINT_MAX;
 	limits->discard_granularity = 512;
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4793ad2aa1f7..991f77a5885b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -592,12 +592,6 @@ struct dm_thin_endio_hook {
 	struct dm_bio_prison_cell *cell;
 };
 
-static void __merge_bio_list(struct bio_list *bios, struct bio_list *master)
-{
-	bio_list_merge(bios, master);
-	bio_list_init(master);
-}
-
 static void error_bio_list(struct bio_list *bios, blk_status_t error)
 {
 	struct bio *bio;
@@ -616,7 +610,7 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 	bio_list_init(&bios);
 
 	spin_lock_irq(&tc->lock);
-	__merge_bio_list(&bios, master);
+	bio_list_merge_init(&bios, master);
 	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, error);
@@ -645,8 +639,8 @@ static void requeue_io(struct thin_c *tc)
 	bio_list_init(&bios);
 
 	spin_lock_irq(&tc->lock);
-	__merge_bio_list(&bios, &tc->deferred_bio_list);
-	__merge_bio_list(&bios, &tc->retry_on_resume_list);
+	bio_list_merge_init(&bios, &tc->deferred_bio_list);
+	bio_list_merge_init(&bios, &tc->retry_on_resume_list);
 	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, BLK_STS_DM_REQUEUE);
@@ -4100,7 +4094,7 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	if (pt->adjusted_pf.discard_enabled) {
 		disable_discard_passdown_if_not_supported(pt);
 		if (!pt->adjusted_pf.discard_passdown)
-			limits->max_discard_sectors = 0;
+			limits->max_hw_discard_sectors = 0;
 		/*
 		 * The pool uses the same discard limits as the underlying data
 		 * device.  DM core has already set this up.
@@ -4497,7 +4491,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	if (pool->pf.discard_enabled) {
 		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
-		limits->max_discard_sectors = pool->sectors_per_block * BIO_PRISON_MAX_RANGE;
+		limits->max_hw_discard_sectors = pool->sectors_per_block * BIO_PRISON_MAX_RANGE;
 	}
 }
 
diff --git a/drivers/md/dm-vdo/Makefile b/drivers/md/dm-vdo/Makefile
index 33e09abc6acd..9476957bfbf4 100644
--- a/drivers/md/dm-vdo/Makefile
+++ b/drivers/md/dm-vdo/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-ccflags-y := -I$(srctree)/$(src) -I$(srctree)/$(src)/indexer
+ccflags-y := -I$(src) -I$(src)/indexer
 
 obj-$(CONFIG_DM_VDO) += dm-vdo.o
 
diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c
index 94f6f1ccfb7d..ab3ea8337809 100644
--- a/drivers/md/dm-vdo/data-vio.c
+++ b/drivers/md/dm-vdo/data-vio.c
@@ -604,8 +604,7 @@ static void assign_discard_permit(struct limiter *limiter)
 
 static void get_waiters(struct limiter *limiter)
 {
-	bio_list_merge(&limiter->waiters, &limiter->new_waiters);
-	bio_list_init(&limiter->new_waiters);
+	bio_list_merge_init(&limiter->waiters, &limiter->new_waiters);
 }
 
 static inline struct data_vio *get_available_data_vio(struct data_vio_pool *pool)
diff --git a/drivers/md/dm-vdo/dm-vdo-target.c b/drivers/md/dm-vdo/dm-vdo-target.c
index 5a4b0a927f56..b423bec6458b 100644
--- a/drivers/md/dm-vdo/dm-vdo-target.c
+++ b/drivers/md/dm-vdo/dm-vdo-target.c
@@ -878,7 +878,7 @@ static int parse_device_config(int argc, char **argv, struct dm_target *ti,
 	}
 
 	if (config->version == 0) {
-		u64 device_size = i_size_read(config->owned_device->bdev->bd_inode);
+		u64 device_size = bdev_nr_bytes(config->owned_device->bdev);
 
 		config->physical_blocks = device_size / VDO_BLOCK_SIZE;
 	}
@@ -1011,7 +1011,7 @@ static void vdo_status(struct dm_target *ti, status_type_t status_type,
 
 static block_count_t __must_check get_underlying_device_block_count(const struct vdo *vdo)
 {
-	return i_size_read(vdo_get_backing_device(vdo)->bd_inode) / VDO_BLOCK_SIZE;
+	return bdev_nr_bytes(vdo_get_backing_device(vdo)) / VDO_BLOCK_SIZE;
 }
 
 static int __must_check process_vdo_message_locked(struct vdo *vdo, unsigned int argc,
diff --git a/drivers/md/dm-vdo/flush.c b/drivers/md/dm-vdo/flush.c
index 57e87f0d7069..dd4fdee2ca0c 100644
--- a/drivers/md/dm-vdo/flush.c
+++ b/drivers/md/dm-vdo/flush.c
@@ -369,8 +369,7 @@ void vdo_dump_flusher(const struct flusher *flusher)
 static void initialize_flush(struct vdo_flush *flush, struct vdo *vdo)
 {
 	bio_list_init(&flush->bios);
-	bio_list_merge(&flush->bios, &vdo->flusher->waiting_flush_bios);
-	bio_list_init(&vdo->flusher->waiting_flush_bios);
+	bio_list_merge_init(&flush->bios, &vdo->flusher->waiting_flush_bios);
 }
 
 static void launch_flush(struct vdo_flush *flush)
diff --git a/drivers/md/dm-vdo/indexer/io-factory.c b/drivers/md/dm-vdo/indexer/io-factory.c
index 515765d35794..1bee9d63dc0a 100644
--- a/drivers/md/dm-vdo/indexer/io-factory.c
+++ b/drivers/md/dm-vdo/indexer/io-factory.c
@@ -90,7 +90,7 @@ void uds_put_io_factory(struct io_factory *factory)
 
 size_t uds_get_writable_size(struct io_factory *factory)
 {
-	return i_size_read(factory->bdev->bd_inode);
+	return bdev_nr_bytes(factory->bdev);
 }
 
 /* Create a struct dm_bufio_client for an index region starting at offset. */
diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c
index 01d2743444ec..3a989efae142 100644
--- a/drivers/md/dm-vdo/murmurhash3.c
+++ b/drivers/md/dm-vdo/murmurhash3.c
@@ -137,7 +137,7 @@ void murmurhash3_128(const void *key, const int len, const u32 seed, void *out)
 			break;
 		default:
 			break;
-		};
+		}
 	}
 	/* finalization */
 
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index 3b13e6eb1aa4..9a0bb623e823 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -61,7 +61,6 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
 
 static void zero_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
-	limits->max_discard_sectors = UINT_MAX;
 	limits->max_hw_discard_sectors = UINT_MAX;
 	limits->discard_granularity = 512;
 }
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index eb9832b22b14..5d66d916730e 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -60,16 +60,23 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 	struct dm_table *map;
 	int srcu_idx, ret;
 
-	if (dm_suspended_md(md))
-		return -EAGAIN;
+	if (!md->zone_revalidate_map) {
+		/* Regular user context */
+		if (dm_suspended_md(md))
+			return -EAGAIN;
 
-	map = dm_get_live_table(md, &srcu_idx);
-	if (!map)
-		return -EIO;
+		map = dm_get_live_table(md, &srcu_idx);
+		if (!map)
+			return -EIO;
+	} else {
+		/* Zone revalidation during __bind() */
+		map = md->zone_revalidate_map;
+	}
 
 	ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data);
 
-	dm_put_live_table(md, srcu_idx);
+	if (!md->zone_revalidate_map)
+		dm_put_live_table(md, srcu_idx);
 
 	return ret;
 }
@@ -138,81 +145,17 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 	}
 }
 
-void dm_cleanup_zoned_dev(struct mapped_device *md)
-{
-	if (md->disk) {
-		bitmap_free(md->disk->conv_zones_bitmap);
-		md->disk->conv_zones_bitmap = NULL;
-		bitmap_free(md->disk->seq_zones_wlock);
-		md->disk->seq_zones_wlock = NULL;
-	}
-
-	kvfree(md->zwp_offset);
-	md->zwp_offset = NULL;
-	md->nr_zones = 0;
-}
-
-static unsigned int dm_get_zone_wp_offset(struct blk_zone *zone)
-{
-	switch (zone->cond) {
-	case BLK_ZONE_COND_IMP_OPEN:
-	case BLK_ZONE_COND_EXP_OPEN:
-	case BLK_ZONE_COND_CLOSED:
-		return zone->wp - zone->start;
-	case BLK_ZONE_COND_FULL:
-		return zone->len;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_NOT_WP:
-	case BLK_ZONE_COND_OFFLINE:
-	case BLK_ZONE_COND_READONLY:
-	default:
-		/*
-		 * Conventional, offline and read-only zones do not have a valid
-		 * write pointer. Use 0 as for an empty zone.
-		 */
-		return 0;
-	}
-}
-
-static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx,
-				 void *data)
+/*
+ * Count conventional zones of a mapped zoned device. If the device
+ * only has conventional zones, do not expose it as zoned.
+ */
+static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
+			     void *data)
 {
-	struct mapped_device *md = data;
-	struct gendisk *disk = md->disk;
+	unsigned int *nr_conv_zones = data;
 
-	switch (zone->type) {
-	case BLK_ZONE_TYPE_CONVENTIONAL:
-		if (!disk->conv_zones_bitmap) {
-			disk->conv_zones_bitmap = bitmap_zalloc(disk->nr_zones,
-								GFP_NOIO);
-			if (!disk->conv_zones_bitmap)
-				return -ENOMEM;
-		}
-		set_bit(idx, disk->conv_zones_bitmap);
-		break;
-	case BLK_ZONE_TYPE_SEQWRITE_REQ:
-	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		if (!disk->seq_zones_wlock) {
-			disk->seq_zones_wlock = bitmap_zalloc(disk->nr_zones,
-							      GFP_NOIO);
-			if (!disk->seq_zones_wlock)
-				return -ENOMEM;
-		}
-		if (!md->zwp_offset) {
-			md->zwp_offset =
-				kvcalloc(disk->nr_zones, sizeof(unsigned int),
-					 GFP_KERNEL);
-			if (!md->zwp_offset)
-				return -ENOMEM;
-		}
-		md->zwp_offset[idx] = dm_get_zone_wp_offset(zone);
-
-		break;
-	default:
-		DMERR("Invalid zone type 0x%x at sectors %llu",
-		      (int)zone->type, zone->start);
-		return -ENODEV;
-	}
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		(*nr_conv_zones)++;
 
 	return 0;
 }
@@ -226,41 +169,32 @@ static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx,
 static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
 {
 	struct gendisk *disk = md->disk;
-	unsigned int noio_flag;
 	int ret;
 
-	/*
-	 * Check if something changed. If yes, cleanup the current resources
-	 * and reallocate everything.
-	 */
+	/* Revalidate only if something changed. */
 	if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
-		dm_cleanup_zoned_dev(md);
+		md->nr_zones = 0;
+
 	if (md->nr_zones)
 		return 0;
 
 	/*
-	 * Scan all zones to initialize everything. Ensure that all vmalloc
-	 * operations in this context are done as if GFP_NOIO was specified.
+	 * Our table is not live yet. So the call to dm_get_live_table()
+	 * in dm_blk_report_zones() will fail. Set a temporary pointer to
+	 * our table for dm_blk_report_zones() to use directly.
 	 */
-	noio_flag = memalloc_noio_save();
-	ret = dm_blk_do_report_zones(md, t, 0, disk->nr_zones,
-				     dm_zone_revalidate_cb, md);
-	memalloc_noio_restore(noio_flag);
-	if (ret < 0)
-		goto err;
-	if (ret != disk->nr_zones) {
-		ret = -EIO;
-		goto err;
+	md->zone_revalidate_map = t;
+	ret = blk_revalidate_disk_zones(disk);
+	md->zone_revalidate_map = NULL;
+
+	if (ret) {
+		DMERR("Revalidate zones failed %d", ret);
+		return ret;
 	}
 
 	md->nr_zones = disk->nr_zones;
 
 	return 0;
-
-err:
-	DMERR("Revalidate zones failed %d", ret);
-	dm_cleanup_zoned_dev(md);
-	return ret;
 }
 
 static int device_not_zone_append_capable(struct dm_target *ti,
@@ -286,297 +220,68 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 	return true;
 }
 
-int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
+int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+		struct queue_limits *lim)
 {
 	struct mapped_device *md = t->md;
+	struct gendisk *disk = md->disk;
+	unsigned int nr_conv_zones = 0;
+	int ret;
 
 	/*
-	 * For a zoned target, the number of zones should be updated for the
-	 * correct value to be exposed in sysfs queue/nr_zones.
+	 * Check if zone append is natively supported, and if not, set the
+	 * mapped device queue as needing zone append emulation.
 	 */
 	WARN_ON_ONCE(queue_is_mq(q));
-	md->disk->nr_zones = bdev_nr_zones(md->disk->part0);
-
-	/* Check if zone append is natively supported */
 	if (dm_table_supports_zone_append(t)) {
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-		dm_cleanup_zoned_dev(md);
-		return 0;
+	} else {
+		set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		lim->max_zone_append_sectors = 0;
 	}
 
-	/*
-	 * Mark the mapped device as needing zone append emulation and
-	 * initialize the emulation resources once the capacity is set.
-	 */
-	set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
 	if (!get_capacity(md->disk))
 		return 0;
 
-	return dm_revalidate_zones(md, t);
-}
-
-static int dm_update_zone_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
-				       void *data)
-{
-	unsigned int *wp_offset = data;
-
-	*wp_offset = dm_get_zone_wp_offset(zone);
-
-	return 0;
-}
-
-static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
-				    unsigned int *wp_ofst)
-{
-	sector_t sector = zno * bdev_zone_sectors(md->disk->part0);
-	unsigned int noio_flag;
-	struct dm_table *t;
-	int srcu_idx, ret;
-
-	t = dm_get_live_table(md, &srcu_idx);
-	if (!t)
-		return -EIO;
-
-	/*
-	 * Ensure that all memory allocations in this context are done as if
-	 * GFP_NOIO was specified.
-	 */
-	noio_flag = memalloc_noio_save();
-	ret = dm_blk_do_report_zones(md, t, sector, 1,
-				     dm_update_zone_wp_offset_cb, wp_ofst);
-	memalloc_noio_restore(noio_flag);
-
-	dm_put_live_table(md, srcu_idx);
-
-	if (ret != 1)
-		return -EIO;
-
-	return 0;
-}
-
-struct orig_bio_details {
-	enum req_op op;
-	unsigned int nr_sectors;
-};
-
-/*
- * First phase of BIO mapping for targets with zone append emulation:
- * check all BIO that change a zone writer pointer and change zone
- * append operations into regular write operations.
- */
-static bool dm_zone_map_bio_begin(struct mapped_device *md,
-				  unsigned int zno, struct bio *clone)
-{
-	sector_t zsectors = bdev_zone_sectors(md->disk->part0);
-	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-
-	/*
-	 * If the target zone is in an error state, recover by inspecting the
-	 * zone to get its current write pointer position. Note that since the
-	 * target zone is already locked, a BIO issuing context should never
-	 * see the zone write in the DM_ZONE_UPDATING_WP_OFST state.
-	 */
-	if (zwp_offset == DM_ZONE_INVALID_WP_OFST) {
-		if (dm_update_zone_wp_offset(md, zno, &zwp_offset))
-			return false;
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset);
-	}
-
-	switch (bio_op(clone)) {
-	case REQ_OP_ZONE_RESET:
-	case REQ_OP_ZONE_FINISH:
-		return true;
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-		/* Writes must be aligned to the zone write pointer */
-		if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset)
-			return false;
-		break;
-	case REQ_OP_ZONE_APPEND:
-		/*
-		 * Change zone append operations into a non-mergeable regular
-		 * writes directed at the current write pointer position of the
-		 * target zone.
-		 */
-		clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE |
-			(clone->bi_opf & (~REQ_OP_MASK));
-		clone->bi_iter.bi_sector += zwp_offset;
-		break;
-	default:
-		DMWARN_LIMIT("Invalid BIO operation");
-		return false;
-	}
-
-	/* Cannot write to a full zone */
-	if (zwp_offset >= zsectors)
-		return false;
-
-	return true;
-}
-
-/*
- * Second phase of BIO mapping for targets with zone append emulation:
- * update the zone write pointer offset array to account for the additional
- * data written to a zone. Note that at this point, the remapped clone BIO
- * may already have completed, so we do not touch it.
- */
-static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno,
-					struct orig_bio_details *orig_bio_details,
-					unsigned int nr_sectors)
-{
-	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-
-	/* The clone BIO may already have been completed and failed */
-	if (zwp_offset == DM_ZONE_INVALID_WP_OFST)
-		return BLK_STS_IOERR;
-
-	/* Update the zone wp offset */
-	switch (orig_bio_details->op) {
-	case REQ_OP_ZONE_RESET:
-		WRITE_ONCE(md->zwp_offset[zno], 0);
-		return BLK_STS_OK;
-	case REQ_OP_ZONE_FINISH:
-		WRITE_ONCE(md->zwp_offset[zno],
-			   bdev_zone_sectors(md->disk->part0));
-		return BLK_STS_OK;
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
-		return BLK_STS_OK;
-	case REQ_OP_ZONE_APPEND:
-		/*
-		 * Check that the target did not truncate the write operation
-		 * emulating a zone append.
-		 */
-		if (nr_sectors != orig_bio_details->nr_sectors) {
-			DMWARN_LIMIT("Truncated write for zone append");
-			return BLK_STS_IOERR;
-		}
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
-		return BLK_STS_OK;
-	default:
-		DMWARN_LIMIT("Invalid BIO operation");
-		return BLK_STS_IOERR;
-	}
-}
-
-static inline void dm_zone_lock(struct gendisk *disk, unsigned int zno,
-				struct bio *clone)
-{
-	if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)))
-		return;
-
-	wait_on_bit_lock_io(disk->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE);
-	bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED);
-}
-
-static inline void dm_zone_unlock(struct gendisk *disk, unsigned int zno,
-				  struct bio *clone)
-{
-	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
-		return;
-
-	WARN_ON_ONCE(!test_bit(zno, disk->seq_zones_wlock));
-	clear_bit_unlock(zno, disk->seq_zones_wlock);
-	smp_mb__after_atomic();
-	wake_up_bit(disk->seq_zones_wlock, zno);
-
-	bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
-}
-
-static bool dm_need_zone_wp_tracking(struct bio *bio)
-{
 	/*
-	 * Special processing is not needed for operations that do not need the
-	 * zone write lock, that is, all operations that target conventional
-	 * zones and all operations that do not modify directly a sequential
-	 * zone write pointer.
+	 * Count conventional zones to check that the mapped device will indeed 
+	 * have sequential write required zones.
 	 */
-	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
-		return false;
-	switch (bio_op(bio)) {
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-	case REQ_OP_ZONE_RESET:
-	case REQ_OP_ZONE_FINISH:
-	case REQ_OP_ZONE_APPEND:
-		return bio_zone_is_seq(bio);
-	default:
-		return false;
+	md->zone_revalidate_map = t;
+	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
+				  dm_check_zoned_cb, &nr_conv_zones);
+	md->zone_revalidate_map = NULL;
+	if (ret < 0) {
+		DMERR("Check zoned failed %d", ret);
+		return ret;
 	}
-}
-
-/*
- * Special IO mapping for targets needing zone append emulation.
- */
-int dm_zone_map_bio(struct dm_target_io *tio)
-{
-	struct dm_io *io = tio->io;
-	struct dm_target *ti = tio->ti;
-	struct mapped_device *md = io->md;
-	struct bio *clone = &tio->clone;
-	struct orig_bio_details orig_bio_details;
-	unsigned int zno;
-	blk_status_t sts;
-	int r;
 
 	/*
-	 * IOs that do not change a zone write pointer do not need
-	 * any additional special processing.
+	 * If we only have conventional zones, expose the mapped device as
+	 * a regular device.
 	 */
-	if (!dm_need_zone_wp_tracking(clone))
-		return ti->type->map(ti, clone);
-
-	/* Lock the target zone */
-	zno = bio_zone_no(clone);
-	dm_zone_lock(md->disk, zno, clone);
-
-	orig_bio_details.nr_sectors = bio_sectors(clone);
-	orig_bio_details.op = bio_op(clone);
-
-	/*
-	 * Check that the bio and the target zone write pointer offset are
-	 * both valid, and if the bio is a zone append, remap it to a write.
-	 */
-	if (!dm_zone_map_bio_begin(md, zno, clone)) {
-		dm_zone_unlock(md->disk, zno, clone);
-		return DM_MAPIO_KILL;
+	if (nr_conv_zones >= ret) {
+		lim->max_open_zones = 0;
+		lim->max_active_zones = 0;
+		lim->zoned = false;
+		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		disk->nr_zones = 0;
+		return 0;
 	}
 
-	/* Let the target do its work */
-	r = ti->type->map(ti, clone);
-	switch (r) {
-	case DM_MAPIO_SUBMITTED:
-		/*
-		 * The target submitted the clone BIO. The target zone will
-		 * be unlocked on completion of the clone.
-		 */
-		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
-					  *tio->len_ptr);
-		break;
-	case DM_MAPIO_REMAPPED:
-		/*
-		 * The target only remapped the clone BIO. In case of error,
-		 * unlock the target zone here as the clone will not be
-		 * submitted.
-		 */
-		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
-					  *tio->len_ptr);
-		if (sts != BLK_STS_OK)
-			dm_zone_unlock(md->disk, zno, clone);
-		break;
-	case DM_MAPIO_REQUEUE:
-	case DM_MAPIO_KILL:
-	default:
-		dm_zone_unlock(md->disk, zno, clone);
-		sts = BLK_STS_IOERR;
-		break;
+	if (!md->disk->nr_zones) {
+		DMINFO("%s using %s zone append",
+		       md->disk->disk_name,
+		       queue_emulates_zone_append(q) ? "emulated" : "native");
 	}
 
-	if (sts != BLK_STS_OK)
-		return DM_MAPIO_KILL;
+	ret = dm_revalidate_zones(md, t);
+	if (ret < 0)
+		return ret;
 
-	return r;
+	if (!static_key_enabled(&zoned_enabled.key))
+		static_branch_enable(&zoned_enabled);
+	return 0;
 }
 
 /*
@@ -587,61 +292,17 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone)
 	struct mapped_device *md = io->md;
 	struct gendisk *disk = md->disk;
 	struct bio *orig_bio = io->orig_bio;
-	unsigned int zwp_offset;
-	unsigned int zno;
 
 	/*
-	 * For targets that do not emulate zone append, we only need to
-	 * handle native zone-append bios.
+	 * Get the offset within the zone of the written sector
+	 * and add that to the original bio sector position.
 	 */
-	if (!dm_emulate_zone_append(md)) {
-		/*
-		 * Get the offset within the zone of the written sector
-		 * and add that to the original bio sector position.
-		 */
-		if (clone->bi_status == BLK_STS_OK &&
-		    bio_op(clone) == REQ_OP_ZONE_APPEND) {
-			sector_t mask =
-				(sector_t)bdev_zone_sectors(disk->part0) - 1;
-
-			orig_bio->bi_iter.bi_sector +=
-				clone->bi_iter.bi_sector & mask;
-		}
-
-		return;
-	}
+	if (clone->bi_status == BLK_STS_OK &&
+	    bio_op(clone) == REQ_OP_ZONE_APPEND) {
+		sector_t mask = bdev_zone_sectors(disk->part0) - 1;
 
-	/*
-	 * For targets that do emulate zone append, if the clone BIO does not
-	 * own the target zone write lock, we have nothing to do.
-	 */
-	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
-		return;
-
-	zno = bio_zone_no(orig_bio);
-
-	if (clone->bi_status != BLK_STS_OK) {
-		/*
-		 * BIOs that modify a zone write pointer may leave the zone
-		 * in an unknown state in case of failure (e.g. the write
-		 * pointer was only partially advanced). In this case, set
-		 * the target zone write pointer as invalid unless it is
-		 * already being updated.
-		 */
-		WRITE_ONCE(md->zwp_offset[zno], DM_ZONE_INVALID_WP_OFST);
-	} else if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
-		/*
-		 * Get the written sector for zone append operation that were
-		 * emulated using regular write operations.
-		 */
-		zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-		if (WARN_ON_ONCE(zwp_offset < bio_sectors(orig_bio)))
-			WRITE_ONCE(md->zwp_offset[zno],
-				   DM_ZONE_INVALID_WP_OFST);
-		else
-			orig_bio->bi_iter.bi_sector +=
-				zwp_offset - bio_sectors(orig_bio);
+		orig_bio->bi_iter.bi_sector += clone->bi_iter.bi_sector & mask;
 	}
 
-	dm_zone_unlock(disk, zno, clone);
+	return;
 }
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 621794a9edd6..12236e6f46f3 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1001,7 +1001,6 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	limits->discard_alignment = 0;
 	limits->discard_granularity = DMZ_BLOCK_SIZE;
-	limits->max_discard_sectors = chunk_sectors;
 	limits->max_hw_discard_sectors = chunk_sectors;
 	limits->max_write_zeroes_sectors = chunk_sectors;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 56aa2a8b9d71..13037d6a6f62 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -765,7 +765,7 @@ static struct table_device *open_table_device(struct mapped_device *md,
 	return td;
 
 out_blkdev_put:
-	fput(bdev_file);
+	__fput_sync(bdev_file);
 out_free_td:
 	kfree(td);
 	return ERR_PTR(r);
@@ -778,7 +778,13 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
 {
 	if (md->disk->slave_dir)
 		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
-	fput(td->dm_dev.bdev_file);
+
+	/* Leverage async fput() if DMF_DEFERRED_REMOVE set */
+	if (unlikely(test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
+		fput(td->dm_dev.bdev_file);
+	else
+		__fput_sync(td->dm_dev.bdev_file);
+
 	put_dax(td->dm_dev.dax_dev);
 	list_del(&td->list);
 	kfree(td);
@@ -1080,7 +1086,7 @@ void disable_discard(struct mapped_device *md)
 	struct queue_limits *limits = dm_get_queue_limits(md);
 
 	/* device doesn't really support DISCARD, disable it */
-	limits->max_discard_sectors = 0;
+	limits->max_hw_discard_sectors = 0;
 }
 
 void disable_write_zeroes(struct mapped_device *md)
@@ -1422,25 +1428,12 @@ static void __map_bio(struct bio *clone)
 		down(&md->swap_bios_semaphore);
 	}
 
-	if (static_branch_unlikely(&zoned_enabled)) {
-		/*
-		 * Check if the IO needs a special mapping due to zone append
-		 * emulation on zoned target. In this case, dm_zone_map_bio()
-		 * calls the target map operation.
-		 */
-		if (unlikely(dm_emulate_zone_append(md)))
-			r = dm_zone_map_bio(tio);
-		else
-			goto do_map;
-	} else {
-do_map:
-		if (likely(ti->type->map == linear_map))
-			r = linear_map(ti, clone);
-		else if (ti->type->map == stripe_map)
-			r = stripe_map(ti, clone);
-		else
-			r = ti->type->map(ti, clone);
-	}
+	if (likely(ti->type->map == linear_map))
+		r = linear_map(ti, clone);
+	else if (ti->type->map == stripe_map)
+		r = stripe_map(ti, clone);
+	else
+		r = ti->type->map(ti, clone);
 
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
@@ -1768,6 +1761,33 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 		ci->sector_count = 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	/*
+	 * For mapped device that need zone append emulation, we must
+	 * split any large BIO that straddles zone boundaries.
+	 */
+	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
+		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+}
+#else
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	return false;
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return false;
+}
+#endif
+
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */
@@ -1777,19 +1797,32 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 	struct clone_info ci;
 	struct dm_io *io;
 	blk_status_t error = BLK_STS_OK;
-	bool is_abnormal;
+	bool is_abnormal, need_split;
 
-	is_abnormal = is_abnormal_io(bio);
-	if (unlikely(is_abnormal)) {
+	need_split = is_abnormal = is_abnormal_io(bio);
+	if (static_branch_unlikely(&zoned_enabled))
+		need_split = is_abnormal || dm_zone_bio_needs_split(md, bio);
+
+	if (unlikely(need_split)) {
 		/*
 		 * Use bio_split_to_limits() for abnormal IO (e.g. discard, etc)
 		 * otherwise associated queue_limits won't be imposed.
+		 * Also split the BIO for mapped devices needing zone append
+		 * emulation to ensure that the BIO does not cross zone
+		 * boundaries.
 		 */
 		bio = bio_split_to_limits(bio);
 		if (!bio)
 			return;
 	}
 
+	/*
+	 * Use the block layer zone write plugging for mapped devices that
+	 * need zone append emulation (e.g. dm-crypt).
+	 */
+	if (static_branch_unlikely(&zoned_enabled) && dm_zone_plug_bio(md, bio))
+		return;
+
 	/* Only support nowait for normal IO */
 	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
 		io = alloc_io(md, bio, GFP_NOWAIT);
@@ -2010,7 +2043,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		md->dax_dev = NULL;
 	}
 
-	dm_cleanup_zoned_dev(md);
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 7f1acbf6bd9e..53ef8207fe2c 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -101,16 +101,15 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 /*
  * Zoned targets related functions.
  */
-int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q);
+int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+		struct queue_limits *lim);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
-void dm_cleanup_zoned_dev(struct mapped_device *md);
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_map_bio(struct dm_target_io *io);
 #else
-static inline void dm_cleanup_zoned_dev(struct mapped_device *md) {}
 #define dm_blk_report_zones	NULL
 static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 {
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 059afc24c08b..0a2d37eb38ef 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1424,7 +1424,7 @@ __acquires(bitmap->lock)
 	sector_t chunk = offset >> bitmap->chunkshift;
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
-	sector_t csize;
+	sector_t csize = ((sector_t)1) << bitmap->chunkshift;
 	int err;
 
 	if (page >= bitmap->pages) {
@@ -1433,6 +1433,7 @@ __acquires(bitmap->lock)
 		 * End-of-device while looking for a whole page or
 		 * user set a huge number to sysfs bitmap_set_bits.
 		 */
+		*blocks = csize - (offset & (csize - 1));
 		return NULL;
 	}
 	err = md_bitmap_checkpage(bitmap, page, create, 0);
@@ -1441,8 +1442,7 @@ __acquires(bitmap->lock)
 	    bitmap->bp[page].map == NULL)
 		csize = ((sector_t)1) << (bitmap->chunkshift +
 					  PAGE_COUNTER_SHIFT);
-	else
-		csize = ((sector_t)1) << bitmap->chunkshift;
+
 	*blocks = csize - (offset & (csize - 1));
 
 	if (err < 0)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e575e74aabf5..aff9118ff697 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8087,7 +8087,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread)
 	if (t) {
 		pr_debug("md: waking up MD thread %s.\n", t->tsk->comm);
 		set_bit(THREAD_WAKEUP, &t->flags);
-		wake_up(&t->wqueue);
+		if (wq_has_sleeper(&t->wqueue))
+			wake_up(&t->wqueue);
 	}
 	rcu_read_unlock();
 }
@@ -8582,6 +8583,10 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
+
+		if (!init && !blk_queue_io_stat(disk->queue))
+			continue;
+
 		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 097d9dbd69b8..ca085ecad504 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -621,7 +621,8 @@ extern void mddev_unlock(struct mddev *mddev);
 
 static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
 {
-	atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
+	if (blk_queue_io_stat(bdev->bd_disk->queue))
+		atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
 }
 
 static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d874abfc1836..2bd1ce9b3922 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,7 +36,6 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -6734,6 +6733,9 @@ static void raid5d(struct md_thread *thread)
 		int batch_size, released;
 		unsigned int offset;
 
+		if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+			break;
+
 		released = release_stripe_list(conf, conf->temp_inactive_list);
 		if (released)
 			clear_bit(R5_DID_ALLOC, &conf->cache_state);
@@ -6770,18 +6772,7 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
-
-			/*
-			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
-			 * seeing md_check_recovery() is needed to clear
-			 * the flag when using mdmon.
-			 */
-			continue;
 		}
-
-		wait_event_lock_irq(mddev->sb_wait,
-			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
-			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);