Merge tag 'for-6.6-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - several fixes for handling directory item (inserting, removing,
   iteration, error handling)

 - fix transaction commit stalls when auto relocation is running and
   blocks other tasks that want to commit

 - fix a build error when DEBUG is enabled

 - fix lockdep warning in inode number lookup ioctl

 - fix race when finishing block group creation

 - remove link to obsolete wiki in several files

* tag 'for-6.6-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  MAINTAINERS: remove links to obsolete btrfs.wiki.kernel.org
  btrfs: assert delayed node locked when removing delayed item
  btrfs: remove BUG() after failure to insert delayed dir index item
  btrfs: improve error message after failure to add delayed dir index item
  btrfs: fix a compilation error if DEBUG is defined in btree_dirty_folio
  btrfs: check for BTRFS_FS_ERROR in pending ordered assert
  btrfs: fix lockdep splat and potential deadlock after failure running delayed items
  btrfs: do not block starts waiting on previous transaction commit
  btrfs: release path before inode lookup during the ino lookup ioctl
  btrfs: fix race between finishing block group creation and its item update

11 files changed, 128 insertions, 66 deletions

diff --git a/Documentation/filesystems/btrfs.rst b/Documentation/filesystems/btrfs.rst
index 992eddb0e11b87..a81db8f54d6893 100644
--- a/Documentation/filesystems/btrfs.rst
+++ b/Documentation/filesystems/btrfs.rst
@@ -37,7 +37,6 @@ For more information please refer to the documentation site or wiki
 
   https://btrfs.readthedocs.io
 
-  https://btrfs.wiki.kernel.org
 
 that maintains information about administration tasks, frequently asked
 questions, use cases, mount options, comprehensible changelogs, features,
diff --git a/MAINTAINERS b/MAINTAINERS
index 90f13281d29708..79630b7d946ef4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4378,7 +4378,6 @@ M:	David Sterba <dsterba@suse.com>
 L:	linux-btrfs@vger.kernel.org
 S:	Maintained
 W:	https://btrfs.readthedocs.io
-W:	https://btrfs.wiki.kernel.org/
 Q:	https://patchwork.kernel.org/project/linux-btrfs/list/
 C:	irc://irc.libera.chat/btrfs
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 3282adc84d5215..a25c9910d90b20 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -31,7 +31,7 @@ config BTRFS_FS
 	  continue to be mountable and usable by newer kernels.
 
 	  For more information, please see the web pages at
-	  http://btrfs.wiki.kernel.org.
+	  https://btrfs.readthedocs.io
 
 	  To compile this file system support as a module, choose M here. The
 	  module will be called btrfs.
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 0cb1dee965a02a..b2e5107b7cecc4 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -3028,8 +3028,16 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 fail:
 	btrfs_release_path(path);
-	/* We didn't update the block group item, need to revert @commit_used. */
-	if (ret < 0) {
+	/*
+	 * We didn't update the block group item, need to revert commit_used
+	 * unless the block group item didn't exist yet - this is to prevent a
+	 * race with a concurrent insertion of the block group item, with
+	 * insert_block_group_item(), that happened just after we attempted to
+	 * update. In that case we would reset commit_used to 0 just after the
+	 * insertion set it to a value greater than 0 - if the block group later
+	 * becomes with 0 used bytes, we would incorrectly skip its update.
+	 */
+	if (ret < 0 && ret != -ENOENT) {
 		spin_lock(&cache->lock);
 		cache->commit_used = old_commit_used;
 		spin_unlock(&cache->lock);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 53c1211dd60bab..caf0bbd028d110 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -412,6 +412,7 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root)
 
 static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 {
+	struct btrfs_delayed_node *delayed_node = delayed_item->delayed_node;
 	struct rb_root_cached *root;
 	struct btrfs_delayed_root *delayed_root;
 
@@ -419,18 +420,21 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 	if (RB_EMPTY_NODE(&delayed_item->rb_node))
 		return;
 
-	delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root;
+	/* If it's in a rbtree, then we need to have delayed node locked. */
+	lockdep_assert_held(&delayed_node->mutex);
+
+	delayed_root = delayed_node->root->fs_info->delayed_root;
 
 	BUG_ON(!delayed_root);
 
 	if (delayed_item->type == BTRFS_DELAYED_INSERTION_ITEM)
-		root = &delayed_item->delayed_node->ins_root;
+		root = &delayed_node->ins_root;
 	else
-		root = &delayed_item->delayed_node->del_root;
+		root = &delayed_node->del_root;
 
 	rb_erase_cached(&delayed_item->rb_node, root);
 	RB_CLEAR_NODE(&delayed_item->rb_node);
-	delayed_item->delayed_node->count--;
+	delayed_node->count--;
 
 	finish_one_item(delayed_root);
 }
@@ -1153,20 +1157,33 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr)
 		ret = __btrfs_commit_inode_delayed_items(trans, path,
 							 curr_node);
 		if (ret) {
-			btrfs_release_delayed_node(curr_node);
-			curr_node = NULL;
 			btrfs_abort_transaction(trans, ret);
 			break;
 		}
 
 		prev_node = curr_node;
 		curr_node = btrfs_next_delayed_node(curr_node);
+		/*
+		 * See the comment below about releasing path before releasing
+		 * node. If the commit of delayed items was successful the path
+		 * should always be released, but in case of an error, it may
+		 * point to locked extent buffers (a leaf at the very least).
+		 */
+		ASSERT(path->nodes[0] == NULL);
 		btrfs_release_delayed_node(prev_node);
 	}
 
+	/*
+	 * Release the path to avoid a potential deadlock and lockdep splat when
+	 * releasing the delayed node, as that requires taking the delayed node's
+	 * mutex. If another task starts running delayed items before we take
+	 * the mutex, it will first lock the mutex and then it may try to lock
+	 * the same btree path (leaf).
+	 */
+	btrfs_free_path(path);
+
 	if (curr_node)
 		btrfs_release_delayed_node(curr_node);
-	btrfs_free_path(path);
 	trans->block_rsv = block_rsv;
 
 	return ret;
@@ -1413,7 +1430,29 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 	btrfs_wq_run_delayed_node(delayed_root, fs_info, BTRFS_DELAYED_BATCH);
 }
 
-/* Will return 0 or -ENOMEM */
+static void btrfs_release_dir_index_item_space(struct btrfs_trans_handle *trans)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	const u64 bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
+
+	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
+		return;
+
+	/*
+	 * Adding the new dir index item does not require touching another
+	 * leaf, so we can release 1 unit of metadata that was previously
+	 * reserved when starting the transaction. This applies only to
+	 * the case where we had a transaction start and excludes the
+	 * transaction join case (when replaying log trees).
+	 */
+	trace_btrfs_space_reservation(fs_info, "transaction",
+				      trans->transid, bytes, 0);
+	btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL);
+	ASSERT(trans->bytes_reserved >= bytes);
+	trans->bytes_reserved -= bytes;
+}
+
+/* Will return 0, -ENOMEM or -EEXIST (index number collision, unexpected). */
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
@@ -1455,6 +1494,27 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&delayed_node->mutex);
 
+	/*
+	 * First attempt to insert the delayed item. This is to make the error
+	 * handling path simpler in case we fail (-EEXIST). There's no risk of
+	 * any other task coming in and running the delayed item before we do
+	 * the metadata space reservation below, because we are holding the
+	 * delayed node's mutex and that mutex must also be locked before the
+	 * node's delayed items can be run.
+	 */
+	ret = __btrfs_add_delayed_item(delayed_node, delayed_item);
+	if (unlikely(ret)) {
+		btrfs_err(trans->fs_info,
+"error adding delayed dir index item, name: %.*s, index: %llu, root: %llu, dir: %llu, dir->index_cnt: %llu, delayed_node->index_cnt: %llu, error: %d",
+			  name_len, name, index, btrfs_root_id(delayed_node->root),
+			  delayed_node->inode_id, dir->index_cnt,
+			  delayed_node->index_cnt, ret);
+		btrfs_release_delayed_item(delayed_item);
+		btrfs_release_dir_index_item_space(trans);
+		mutex_unlock(&delayed_node->mutex);
+		goto release_node;
+	}
+
 	if (delayed_node->index_item_leaves == 0 ||
 	    delayed_node->curr_index_batch_size + data_len > leaf_data_size) {
 		delayed_node->curr_index_batch_size = data_len;
@@ -1472,36 +1532,14 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 		 * impossible.
 		 */
 		if (WARN_ON(ret)) {
-			mutex_unlock(&delayed_node->mutex);
 			btrfs_release_delayed_item(delayed_item);
+			mutex_unlock(&delayed_node->mutex);
 			goto release_node;
 		}
 
 		delayed_node->index_item_leaves++;
-	} else if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
-		const u64 bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
-
-		/*
-		 * Adding the new dir index item does not require touching another
-		 * leaf, so we can release 1 unit of metadata that was previously
-		 * reserved when starting the transaction. This applies only to
-		 * the case where we had a transaction start and excludes the
-		 * transaction join case (when replaying log trees).
-		 */
-		trace_btrfs_space_reservation(fs_info, "transaction",
-					      trans->transid, bytes, 0);
-		btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL);
-		ASSERT(trans->bytes_reserved >= bytes);
-		trans->bytes_reserved -= bytes;
-	}
-
-	ret = __btrfs_add_delayed_item(delayed_node, delayed_item);
-	if (unlikely(ret)) {
-		btrfs_err(trans->fs_info,
-			  "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
-			  name_len, name, delayed_node->root->root_key.objectid,
-			  delayed_node->inode_id, ret);
-		BUG();
+	} else {
+		btrfs_release_dir_index_item_space(trans);
 	}
 	mutex_unlock(&delayed_node->mutex);
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0a96ea8c1d3a62..68f60d50e1fd0c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -520,6 +520,7 @@ static bool btree_dirty_folio(struct address_space *mapping,
 		struct folio *folio)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
+	struct btrfs_subpage_info *spi = fs_info->subpage_info;
 	struct btrfs_subpage *subpage;
 	struct extent_buffer *eb;
 	int cur_bit = 0;
@@ -533,18 +534,19 @@ static bool btree_dirty_folio(struct address_space *mapping,
 		btrfs_assert_tree_write_locked(eb);
 		return filemap_dirty_folio(mapping, folio);
 	}
+
+	ASSERT(spi);
 	subpage = folio_get_private(folio);
 
-	ASSERT(subpage->dirty_bitmap);
-	while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) {
+	for (cur_bit = spi->dirty_offset;
+	     cur_bit < spi->dirty_offset + spi->bitmap_nr_bits;
+	     cur_bit++) {
 		unsigned long flags;
 		u64 cur;
-		u16 tmp = (1 << cur_bit);
 
 		spin_lock_irqsave(&subpage->lock, flags);
-		if (!(tmp & subpage->dirty_bitmap)) {
+		if (!test_bit(cur_bit, subpage->bitmaps)) {
 			spin_unlock_irqrestore(&subpage->lock, flags);
-			cur_bit++;
 			continue;
 		}
 		spin_unlock_irqrestore(&subpage->lock, flags);
@@ -557,7 +559,7 @@ static bool btree_dirty_folio(struct address_space *mapping,
 		btrfs_assert_tree_write_locked(eb);
 		free_extent_buffer(eb);
 
-		cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits);
+		cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits) - 1;
 	}
 	return filemap_dirty_folio(mapping, folio);
 }
@@ -1547,7 +1549,7 @@ static int transaction_kthread(void *arg)
 
 		delta = ktime_get_seconds() - cur->start_time;
 		if (!test_and_clear_bit(BTRFS_FS_COMMIT_TRANS, &fs_info->flags) &&
-		    cur->state < TRANS_STATE_COMMIT_START &&
+		    cur->state < TRANS_STATE_COMMIT_PREP &&
 		    delta < fs_info->commit_interval) {
 			spin_unlock(&fs_info->trans_lock);
 			delay -= msecs_to_jiffies((delta - 1) * 1000);
@@ -2682,8 +2684,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters);
 	btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered);
 	btrfs_lockdep_init_map(fs_info, btrfs_ordered_extent);
-	btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_start,
-				     BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_prep,
+				     BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 	btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked,
 				     BTRFS_LOCKDEP_TRANS_UNBLOCKED);
 	btrfs_state_lockdep_init_map(fs_info, btrfs_trans_super_committed,
@@ -4870,7 +4872,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	while (!list_empty(&fs_info->trans_list)) {
 		t = list_first_entry(&fs_info->trans_list,
 				     struct btrfs_transaction, list);
-		if (t->state >= TRANS_STATE_COMMIT_START) {
+		if (t->state >= TRANS_STATE_COMMIT_PREP) {
 			refcount_inc(&t->use_count);
 			spin_unlock(&fs_info->trans_lock);
 			btrfs_wait_for_commit(fs_info, t->transid);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a18ee7b5a16664..75ab766fe15655 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1958,6 +1958,13 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap,
 				goto out_put;
 			}
 
+			/*
+			 * We don't need the path anymore, so release it and
+			 * avoid deadlocks and lockdep warnings in case
+			 * btrfs_iget() needs to lookup the inode from its root
+			 * btree and lock the same leaf.
+			 */
+			btrfs_release_path(path);
 			temp_inode = btrfs_iget(sb, key2.objectid, root);
 			if (IS_ERR(temp_inode)) {
 				ret = PTR_ERR(temp_inode);
@@ -1978,7 +1985,6 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap,
 				goto out_put;
 			}
 
-			btrfs_release_path(path);
 			key.objectid = key.offset;
 			key.offset = (u64)-1;
 			dirid = key.objectid;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index edb9b4a0dba15d..7d6ee1e609bf2b 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -79,7 +79,7 @@ enum btrfs_lock_nesting {
 };
 
 enum btrfs_lockdep_trans_states {
-	BTRFS_LOCKDEP_TRANS_COMMIT_START,
+	BTRFS_LOCKDEP_TRANS_COMMIT_PREP,
 	BTRFS_LOCKDEP_TRANS_UNBLOCKED,
 	BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED,
 	BTRFS_LOCKDEP_TRANS_COMPLETED,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b46ab348e8e5b7..345c449d588ccb 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -639,7 +639,7 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 			refcount_inc(&trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
-		ASSERT(trans);
+		ASSERT(trans || BTRFS_FS_ERROR(fs_info));
 		if (trans) {
 			if (atomic_dec_and_test(&trans->pending_ordered))
 				wake_up(&trans->pending_wait);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 874e4394df860d..0bf42dccb0412d 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -56,12 +56,17 @@ static struct kmem_cache *btrfs_trans_handle_cachep;
  * |  Call btrfs_commit_transaction() on any trans handle attached to
  * |  transaction N
  * V
- * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * Transaction N [[TRANS_STATE_COMMIT_PREP]]
+ * |
+ * | If there are simultaneous calls to btrfs_commit_transaction() one will win
+ * | the race and the rest will wait for the winner to commit the transaction.
+ * |
+ * | The winner will wait for previous running transaction to completely finish
+ * | if there is one.
  * |
- * | Will wait for previous running transaction to completely finish if there
- * | is one
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
  * |
- * | Then one of the following happes:
+ * | Then one of the following happens:
  * | - Wait for all other trans handle holders to release.
  * |   The btrfs_commit_transaction() caller will do the commit work.
  * | - Wait for current transaction to be committed by others.
@@ -112,6 +117,7 @@ static struct kmem_cache *btrfs_trans_handle_cachep;
  */
 static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
 	[TRANS_STATE_RUNNING]		= 0U,
+	[TRANS_STATE_COMMIT_PREP]	= 0U,
 	[TRANS_STATE_COMMIT_START]	= (__TRANS_START | __TRANS_ATTACH),
 	[TRANS_STATE_COMMIT_DOING]	= (__TRANS_START |
 					   __TRANS_ATTACH |
@@ -1982,7 +1988,7 @@ void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans)
 	 * Wait for the current transaction commit to start and block
 	 * subsequent transaction joins
 	 */
-	btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 	wait_event(fs_info->transaction_blocked_wait,
 		   cur_trans->state >= TRANS_STATE_COMMIT_START ||
 		   TRANS_ABORTED(cur_trans));
@@ -2129,7 +2135,7 @@ static void add_pending_snapshot(struct btrfs_trans_handle *trans)
 		return;
 
 	lockdep_assert_held(&trans->fs_info->trans_lock);
-	ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_START);
+	ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_PREP);
 
 	list_add(&trans->pending_snapshot->list, &cur_trans->pending_snapshots);
 }
@@ -2153,7 +2159,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	ktime_t interval;
 
 	ASSERT(refcount_read(&trans->use_count) == 1);
-	btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 
 	clear_bit(BTRFS_FS_NEED_TRANS_COMMIT, &fs_info->flags);
 
@@ -2213,7 +2219,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	}
 
 	spin_lock(&fs_info->trans_lock);
-	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
+	if (cur_trans->state >= TRANS_STATE_COMMIT_PREP) {
 		enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
 
 		add_pending_snapshot(trans);
@@ -2225,7 +2231,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 			want_state = TRANS_STATE_SUPER_COMMITTED;
 
 		btrfs_trans_state_lockdep_release(fs_info,
-						  BTRFS_LOCKDEP_TRANS_COMMIT_START);
+						  BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 		ret = btrfs_end_transaction(trans);
 		wait_for_commit(cur_trans, want_state);
 
@@ -2237,9 +2243,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		return ret;
 	}
 
-	cur_trans->state = TRANS_STATE_COMMIT_START;
+	cur_trans->state = TRANS_STATE_COMMIT_PREP;
 	wake_up(&fs_info->transaction_blocked_wait);
-	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 
 	if (cur_trans->list.prev != &fs_info->trans_list) {
 		enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
@@ -2260,11 +2266,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 			btrfs_put_transaction(prev_trans);
 			if (ret)
 				goto lockdep_release;
-		} else {
-			spin_unlock(&fs_info->trans_lock);
+			spin_lock(&fs_info->trans_lock);
 		}
 	} else {
-		spin_unlock(&fs_info->trans_lock);
 		/*
 		 * The previous transaction was aborted and was already removed
 		 * from the list of transactions at fs_info->trans_list. So we
@@ -2272,11 +2276,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		 * corrupt state (pointing to trees with unwritten nodes/leafs).
 		 */
 		if (BTRFS_FS_ERROR(fs_info)) {
+			spin_unlock(&fs_info->trans_lock);
 			ret = -EROFS;
 			goto lockdep_release;
 		}
 	}
 
+	cur_trans->state = TRANS_STATE_COMMIT_START;
+	wake_up(&fs_info->transaction_blocked_wait);
+	spin_unlock(&fs_info->trans_lock);
+
 	/*
 	 * Get the time spent on the work done by the commit thread and not
 	 * the time spent waiting on a previous commit
@@ -2586,7 +2595,7 @@ lockdep_release:
 	goto cleanup_transaction;
 
 lockdep_trans_commit_start_release:
-	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
+	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_PREP);
 	btrfs_end_transaction(trans);
 	return ret;
 }
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 8e9fa23bd7fed7..6b309f8a99a860 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -14,6 +14,7 @@
 
 enum btrfs_trans_state {
 	TRANS_STATE_RUNNING,
+	TRANS_STATE_COMMIT_PREP,
 	TRANS_STATE_COMMIT_START,
 	TRANS_STATE_COMMIT_DOING,
 	TRANS_STATE_UNBLOCKED,