Merge tag 'for-5.7/drivers-2020-03-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - floppy driver cleanup series from Willy

 - NVMe updates and fixes (Various)

 - null_blk trace improvements (Chaitanya)

 - bcache fixes (Coly)

 - md fixes (via Song)

 - loop block size change optimizations (Martijn)

 - scnprintf() use (Takashi)

* tag 'for-5.7/drivers-2020-03-29' of git://git.kernel.dk/linux-block: (81 commits)
  null_blk: add trace in null_blk_zoned.c
  null_blk: add tracepoint helpers for zoned mode
  block: add a zone condition debug helper
  nvme: cleanup namespace identifier reporting in nvme_init_ns_head
  nvme: rename __nvme_find_ns_head to nvme_find_ns_head
  nvme: refactor nvme_identify_ns_descs error handling
  nvme-tcp: Add warning on state change failure at nvme_tcp_setup_ctrl
  nvme-rdma: Add warning on state change failure at nvme_rdma_setup_ctrl
  nvme: Fix controller creation races with teardown flow
  nvme: Make nvme_uninit_ctrl symmetric to nvme_init_ctrl
  nvme: Fix ctrl use-after-free during sysfs deletion
  nvme-pci: Re-order nvme_pci_free_ctrl
  nvme: Remove unused return code from nvme_delete_ctrl_sync
  nvme: Use nvme_state_terminal helper
  nvme: release ida resources
  nvme: Add compat_ioctl handler for NVME_IOCTL_SUBMIT_IO
  nvmet-tcp: optimize tcp stack TX when data digest is used
  nvme-fabrics: Use scnprintf() for avoiding potential buffer overflow
  nvme-multipath: do not reset on unknown status
  nvmet-rdma: allocate RW ctxs according to mdts
  ...

6 files changed, 437 insertions, 76 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index fa872df4e770..72856e5f23a3 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -101,64 +101,6 @@
 
 #define insert_lock(s, b)	((b)->level <= (s)->lock)
 
-/*
- * These macros are for recursing down the btree - they handle the details of
- * locking and looking up nodes in the cache for you. They're best treated as
- * mere syntax when reading code that uses them.
- *
- * op->lock determines whether we take a read or a write lock at a given depth.
- * If you've got a read lock and find that you need a write lock (i.e. you're
- * going to have to split), set op->lock and return -EINTR; btree_root() will
- * call you again and you'll have the correct lock.
- */
-
-/**
- * btree - recurse down the btree on a specified key
- * @fn:		function to call, which will be passed the child node
- * @key:	key to recurse on
- * @b:		parent btree node
- * @op:		pointer to struct btree_op
- */
-#define btree(fn, key, b, op, ...)					\
-({									\
-	int _r, l = (b)->level - 1;					\
-	bool _w = l <= (op)->lock;					\
-	struct btree *_child = bch_btree_node_get((b)->c, op, key, l,	\
-						  _w, b);		\
-	if (!IS_ERR(_child)) {						\
-		_r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__);	\
-		rw_unlock(_w, _child);					\
-	} else								\
-		_r = PTR_ERR(_child);					\
-	_r;								\
-})
-
-/**
- * btree_root - call a function on the root of the btree
- * @fn:		function to call, which will be passed the child node
- * @c:		cache set
- * @op:		pointer to struct btree_op
- */
-#define btree_root(fn, c, op, ...)					\
-({									\
-	int _r = -EINTR;						\
-	do {								\
-		struct btree *_b = (c)->root;				\
-		bool _w = insert_lock(op, _b);				\
-		rw_lock(_w, _b, _b->level);				\
-		if (_b == (c)->root &&					\
-		    _w == insert_lock(op, _b)) {			\
-			_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);	\
-		}							\
-		rw_unlock(_w, _b);					\
-		bch_cannibalize_unlock(c);				\
-		if (_r == -EINTR)					\
-			schedule();					\
-	} while (_r == -EINTR);						\
-									\
-	finish_wait(&(c)->btree_cache_wait, &(op)->wait);		\
-	_r;								\
-})
 
 static inline struct bset *write_block(struct btree *b)
 {
@@ -1848,7 +1790,7 @@ static void bch_btree_gc(struct cache_set *c)
 
 	/* if CACHE_SET_IO_DISABLE set, gc thread should stop too */
 	do {
-		ret = btree_root(gc_root, c, &op, &writes, &stats);
+		ret = bcache_btree_root(gc_root, c, &op, &writes, &stats);
 		closure_sync(&writes);
 		cond_resched();
 
@@ -1946,7 +1888,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 			}
 
 			if (p)
-				ret = btree(check_recurse, p, b, op);
+				ret = bcache_btree(check_recurse, p, b, op);
 
 			p = k;
 		} while (p && !ret);
@@ -1955,13 +1897,176 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	return ret;
 }
 
+
+static int bch_btree_check_thread(void *arg)
+{
+	int ret;
+	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 bkey *k, *p;
+	int cur_idx, prev_idx, skip_nr;
+	int i, n;
+
+	k = p = NULL;
+	i = n = 0;
+	cur_idx = prev_idx = 0;
+	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);
+	BUG_ON(!k);
+
+	p = k;
+	while (k) {
+		/*
+		 * Fetch a root node key index, skip the keys which
+		 * should be fetched by other threads, then check the
+		 * sub-tree indexed by the fetched key.
+		 */
+		spin_lock(&check_state->idx_lock);
+		cur_idx = check_state->key_idx;
+		check_state->key_idx++;
+		spin_unlock(&check_state->idx_lock);
+
+		skip_nr = cur_idx - prev_idx;
+
+		while (skip_nr) {
+			k = bch_btree_iter_next_filter(&iter,
+						       &c->root->keys,
+						       bch_ptr_bad);
+			if (k)
+				p = k;
+			else {
+				/*
+				 * No more keys to check in root node,
+				 * current checking threads are enough,
+				 * stop creating more.
+				 */
+				atomic_set(&check_state->enough, 1);
+				/* Update check_state->enough earlier */
+				smp_mb__after_atomic();
+				goto out;
+			}
+			skip_nr--;
+			cond_resched();
+		}
+
+		if (p) {
+			struct btree_op op;
+
+			btree_node_prefetch(c->root, p);
+			c->gc_stats.nodes++;
+			bch_btree_op_init(&op, 0);
+			ret = bcache_btree(check_recurse, p, c->root, &op);
+			if (ret)
+				goto out;
+		}
+		p = NULL;
+		prev_idx = cur_idx;
+		cond_resched();
+	}
+
+out:
+	info->result = ret;
+	/* update check_state->started among all CPUs */
+	smp_mb__before_atomic();
+	if (atomic_dec_and_test(&check_state->started))
+		wake_up(&check_state->wait);
+
+	return ret;
+}
+
+
+
+static int bch_btree_chkthread_nr(void)
+{
+	int n = num_online_cpus()/2;
+
+	if (n == 0)
+		n = 1;
+	else if (n > BCH_BTR_CHKTHREAD_MAX)
+		n = BCH_BTR_CHKTHREAD_MAX;
+
+	return n;
+}
+
 int bch_btree_check(struct cache_set *c)
 {
-	struct btree_op op;
+	int ret = 0;
+	int i;
+	struct bkey *k = NULL;
+	struct btree_iter iter;
+	struct btree_check_state *check_state;
+	char name[32];
 
-	bch_btree_op_init(&op, SHRT_MAX);
+	/* check and mark root node keys */
+	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
+		bch_initial_mark_key(c, c->root->level, k);
+
+	bch_initial_mark_key(c, c->root->level + 1, &c->root->key);
+
+	if (c->root->level == 0)
+		return 0;
+
+	check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL);
+	if (!check_state)
+		return -ENOMEM;
 
-	return btree_root(check_recurse, c, &op);
+	check_state->c = c;
+	check_state->total_threads = bch_btree_chkthread_nr();
+	check_state->key_idx = 0;
+	spin_lock_init(&check_state->idx_lock);
+	atomic_set(&check_state->started, 0);
+	atomic_set(&check_state->enough, 0);
+	init_waitqueue_head(&check_state->wait);
+
+	/*
+	 * Run multiple threads to check btree nodes in parallel,
+	 * if check_state->enough is non-zero, it means current
+	 * running check threads are enough, unncessary to create
+	 * more.
+	 */
+	for (i = 0; i < check_state->total_threads; i++) {
+		/* fetch latest check_state->enough earlier */
+		smp_mb__before_atomic();
+		if (atomic_read(&check_state->enough))
+			break;
+
+		check_state->infos[i].result = 0;
+		check_state->infos[i].state = check_state;
+		snprintf(name, sizeof(name), "bch_btrchk[%u]", i);
+		atomic_inc(&check_state->started);
+
+		check_state->infos[i].thread =
+			kthread_run(bch_btree_check_thread,
+				    &check_state->infos[i],
+				    name);
+		if (IS_ERR(check_state->infos[i].thread)) {
+			pr_err("fails to run thread bch_btrchk[%d]", i);
+			for (--i; i >= 0; i--)
+				kthread_stop(check_state->infos[i].thread);
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	wait_event_interruptible(check_state->wait,
+				 atomic_read(&check_state->started) == 0 ||
+				  test_bit(CACHE_SET_IO_DISABLE, &c->flags));
+
+	for (i = 0; i < check_state->total_threads; i++) {
+		if (check_state->infos[i].result) {
+			ret = check_state->infos[i].result;
+			goto out;
+		}
+	}
+
+out:
+	kfree(check_state);
+	return ret;
 }
 
 void bch_initial_gc_finish(struct cache_set *c)
@@ -2401,7 +2506,7 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad))) {
-			ret = btree(map_nodes_recurse, k, b,
+			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
 			from = NULL;
 
@@ -2419,10 +2524,10 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 int __bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
 			  struct bkey *from, btree_map_nodes_fn *fn, int flags)
 {
-	return btree_root(map_nodes_recurse, c, op, from, fn, flags);
+	return bcache_btree_root(map_nodes_recurse, c, op, from, fn, flags);
 }
 
-static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
+int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 				      struct bkey *from, btree_map_keys_fn *fn,
 				      int flags)
 {
@@ -2435,7 +2540,8 @@ static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
-			: btree(map_keys_recurse, k, b, op, from, fn, flags);
+			: bcache_btree(map_keys_recurse, k,
+				       b, op, from, fn, flags);
 		from = NULL;
 
 		if (ret != MAP_CONTINUE)
@@ -2452,7 +2558,7 @@ static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
 		       struct bkey *from, btree_map_keys_fn *fn, int flags)
 {
-	return btree_root(map_keys_recurse, c, op, from, fn, flags);
+	return bcache_btree_root(map_keys_recurse, c, op, from, fn, flags);
 }
 
 /* Keybuf code */
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index f4dcca449391..257969980c49 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -145,6 +145,9 @@ struct btree {
 	struct bio		*bio;
 };
 
+
+
+
 #define BTREE_FLAG(flag)						\
 static inline bool btree_node_ ## flag(struct btree *b)			\
 {	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
@@ -216,6 +219,25 @@ struct btree_op {
 	unsigned int		insert_collision:1;
 };
 
+struct btree_check_state;
+struct btree_check_info {
+	struct btree_check_state	*state;
+	struct task_struct		*thread;
+	int				result;
+};
+
+#define BCH_BTR_CHKTHREAD_MAX	64
+struct btree_check_state {
+	struct cache_set		*c;
+	int				total_threads;
+	int				key_idx;
+	spinlock_t			idx_lock;
+	atomic_t			started;
+	atomic_t			enough;
+	wait_queue_head_t		wait;
+	struct btree_check_info		infos[BCH_BTR_CHKTHREAD_MAX];
+};
+
 static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
 {
 	memset(op, 0, sizeof(struct btree_op));
@@ -284,6 +306,65 @@ static inline void force_wake_up_gc(struct cache_set *c)
 	wake_up_gc(c);
 }
 
+/*
+ * These macros are for recursing down the btree - they handle the details of
+ * locking and looking up nodes in the cache for you. They're best treated as
+ * mere syntax when reading code that uses them.
+ *
+ * op->lock determines whether we take a read or a write lock at a given depth.
+ * If you've got a read lock and find that you need a write lock (i.e. you're
+ * going to have to split), set op->lock and return -EINTR; btree_root() will
+ * call you again and you'll have the correct lock.
+ */
+
+/**
+ * btree - recurse down the btree on a specified key
+ * @fn:		function to call, which will be passed the child node
+ * @key:	key to recurse on
+ * @b:		parent btree node
+ * @op:		pointer to struct btree_op
+ */
+#define bcache_btree(fn, key, b, op, ...)				\
+({									\
+	int _r, l = (b)->level - 1;					\
+	bool _w = l <= (op)->lock;					\
+	struct btree *_child = bch_btree_node_get((b)->c, op, key, l,	\
+						  _w, b);		\
+	if (!IS_ERR(_child)) {						\
+		_r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__);	\
+		rw_unlock(_w, _child);					\
+	} else								\
+		_r = PTR_ERR(_child);					\
+	_r;								\
+})
+
+/**
+ * btree_root - call a function on the root of the btree
+ * @fn:		function to call, which will be passed the child node
+ * @c:		cache set
+ * @op:		pointer to struct btree_op
+ */
+#define bcache_btree_root(fn, c, op, ...)				\
+({									\
+	int _r = -EINTR;						\
+	do {								\
+		struct btree *_b = (c)->root;				\
+		bool _w = insert_lock(op, _b);				\
+		rw_lock(_w, _b, _b->level);				\
+		if (_b == (c)->root &&					\
+		    _w == insert_lock(op, _b)) {			\
+			_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);	\
+		}							\
+		rw_unlock(_w, _b);					\
+		bch_cannibalize_unlock(c);                              \
+		if (_r == -EINTR)                                       \
+			schedule();                                     \
+	} while (_r == -EINTR);                                         \
+									\
+	finish_wait(&(c)->btree_cache_wait, &(op)->wait);               \
+	_r;                                                             \
+})
+
 #define MAP_DONE	0
 #define MAP_CONTINUE	1
 
@@ -314,6 +395,9 @@ typedef int (btree_map_keys_fn)(struct btree_op *op, struct btree *b,
 				struct bkey *k);
 int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
 		       struct bkey *from, btree_map_keys_fn *fn, int flags);
+int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
+			       struct bkey *from, btree_map_keys_fn *fn,
+			       int flags);
 
 typedef bool (keybuf_pred_fn)(struct keybuf *buf, struct bkey *k);
 
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 3470fae4eabc..323276994aab 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -154,7 +154,7 @@ static ssize_t bch_snprint_string_list(char *buf,
 	size_t i;
 
 	for (i = 0; list[i]; i++)
-		out += snprintf(out, buf + size - out,
+		out += scnprintf(out, buf + size - out,
 				i == selected ? "[%s] " : "%s ", list[i]);
 
 	out[-1] = '\n';
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 4a40f9eadeaf..3f7641fb28d5 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -183,7 +183,7 @@ static void update_writeback_rate(struct work_struct *work)
 	 */
 	set_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
 	/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
-	smp_mb();
+	smp_mb__after_atomic();
 
 	/*
 	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -193,7 +193,7 @@ static void update_writeback_rate(struct work_struct *work)
 	    test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
 		clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
 		/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
-		smp_mb();
+		smp_mb__after_atomic();
 		return;
 	}
 
@@ -229,7 +229,7 @@ static void update_writeback_rate(struct work_struct *work)
 	 */
 	clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
 	/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
-	smp_mb();
+	smp_mb__after_atomic();
 }
 
 static unsigned int writeback_delay(struct cached_dev *dc,
@@ -785,7 +785,9 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 	return MAP_CONTINUE;
 }
 
-void bch_sectors_dirty_init(struct bcache_device *d)
+static int bch_root_node_dirty_init(struct cache_set *c,
+				     struct bcache_device *d,
+				     struct bkey *k)
 {
 	struct sectors_dirty_init op;
 	int ret;
@@ -796,8 +798,13 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	op.start = KEY(op.inode, 0, 0);
 
 	do {
-		ret = bch_btree_map_keys(&op.op, d->c, &op.start,
-					 sectors_dirty_init_fn, 0);
+		ret = bcache_btree(map_keys_recurse,
+				   k,
+				   c->root,
+				   &op.op,
+				   &op.start,
+				   sectors_dirty_init_fn,
+				   0);
 		if (ret == -EAGAIN)
 			schedule_timeout_interruptible(
 				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
@@ -806,6 +813,151 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 			break;
 		}
 	} while (ret == -EAGAIN);
+
+	return ret;
+}
+
+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 bkey *k, *p;
+	int cur_idx, prev_idx, skip_nr;
+	int i;
+
+	k = p = NULL;
+	i = 0;
+	cur_idx = 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);
+	BUG_ON(!k);
+
+	p = k;
+
+	while (k) {
+		spin_lock(&state->idx_lock);
+		cur_idx = state->key_idx;
+		state->key_idx++;
+		spin_unlock(&state->idx_lock);
+
+		skip_nr = cur_idx - prev_idx;
+
+		while (skip_nr) {
+			k = bch_btree_iter_next_filter(&iter,
+						       &c->root->keys,
+						       bch_ptr_bad);
+			if (k)
+				p = k;
+			else {
+				atomic_set(&state->enough, 1);
+				/* Update state->enough earlier */
+				smp_mb__after_atomic();
+				goto out;
+			}
+			skip_nr--;
+			cond_resched();
+		}
+
+		if (p) {
+			if (bch_root_node_dirty_init(c, state->d, p) < 0)
+				goto out;
+		}
+
+		p = NULL;
+		prev_idx = cur_idx;
+		cond_resched();
+	}
+
+out:
+	/* In order to wake up state->wait in time */
+	smp_mb__before_atomic();
+	if (atomic_dec_and_test(&state->started))
+		wake_up(&state->wait);
+
+	return 0;
+}
+
+static int bch_btre_dirty_init_thread_nr(void)
+{
+	int n = num_online_cpus()/2;
+
+	if (n == 0)
+		n = 1;
+	else if (n > BCH_DIRTY_INIT_THRD_MAX)
+		n = BCH_DIRTY_INIT_THRD_MAX;
+
+	return n;
+}
+
+void bch_sectors_dirty_init(struct bcache_device *d)
+{
+	int i;
+	struct bkey *k = NULL;
+	struct btree_iter iter;
+	struct sectors_dirty_init op;
+	struct cache_set *c = d->c;
+	struct bch_dirty_init_state *state;
+	char name[32];
+
+	/* Just count root keys if no leaf node */
+	if (c->root->level == 0) {
+		bch_btree_op_init(&op.op, -1);
+		op.inode = d->id;
+		op.count = 0;
+		op.start = KEY(op.inode, 0, 0);
+
+		for_each_key_filter(&c->root->keys,
+				    k, &iter, bch_ptr_invalid)
+			sectors_dirty_init_fn(&op.op, c->root, k);
+		return;
+	}
+
+	state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
+	if (!state) {
+		pr_warn("sectors dirty init failed: cannot allocate memory");
+		return;
+	}
+
+	state->c = c;
+	state->d = d;
+	state->total_threads = bch_btre_dirty_init_thread_nr();
+	state->key_idx = 0;
+	spin_lock_init(&state->idx_lock);
+	atomic_set(&state->started, 0);
+	atomic_set(&state->enough, 0);
+	init_waitqueue_head(&state->wait);
+
+	for (i = 0; i < state->total_threads; i++) {
+		/* Fetch latest state->enough earlier */
+		smp_mb__before_atomic();
+		if (atomic_read(&state->enough))
+			break;
+
+		state->infos[i].state = state;
+		atomic_inc(&state->started);
+		snprintf(name, sizeof(name), "bch_dirty_init[%d]", i);
+
+		state->infos[i].thread =
+			kthread_run(bch_dirty_init_thread,
+				    &state->infos[i],
+				    name);
+		if (IS_ERR(state->infos[i].thread)) {
+			pr_err("fails to run thread bch_dirty_init[%d]", i);
+			for (--i; i >= 0; i--)
+				kthread_stop(state->infos[i].thread);
+			goto out;
+		}
+	}
+
+	wait_event_interruptible(state->wait,
+		 atomic_read(&state->started) == 0 ||
+		 test_bit(CACHE_SET_IO_DISABLE, &c->flags));
+
+out:
+	kfree(state);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 4e4c6810dc3c..b029843ce5b6 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -16,6 +16,7 @@
 
 #define BCH_AUTO_GC_DIRTY_THRESHOLD	50
 
+#define BCH_DIRTY_INIT_THRD_MAX	64
 /*
  * 14 (16384ths) is chosen here as something that each backing device
  * should be a reasonable fraction of the share, and not to blow up
@@ -23,6 +24,24 @@
  */
 #define WRITEBACK_SHARE_SHIFT   14
 
+struct bch_dirty_init_state;
+struct dirty_init_thrd_info {
+	struct bch_dirty_init_state	*state;
+	struct task_struct		*thread;
+};
+
+struct bch_dirty_init_state {
+	struct cache_set		*c;
+	struct bcache_device		*d;
+	int				total_threads;
+	int				key_idx;
+	spinlock_t			idx_lock;
+	atomic_t			started;
+	atomic_t			enough;
+	wait_queue_head_t		wait;
+	struct dirty_init_thrd_info	infos[BCH_DIRTY_INIT_THRD_MAX];
+};
+
 static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 {
 	uint64_t i, ret = 0;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index cd1210a0d957..271e8a587354 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6185,7 +6185,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 static void mddev_detach(struct mddev *mddev)
 {
 	md_bitmap_wait_behind_writes(mddev);
-	if (mddev->pers && mddev->pers->quiesce) {
+	if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
 	}