Merge tag 'for-6.2-rc7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - one more fix for a tree-log 'write time corruption' report, update
   the last dir index directly and don't keep in the log context

 - do VFS-level inode lock around FIEMAP to prevent a deadlock with
   concurrent fsync, the extent-level lock is not sufficient

 - don't cache a single-device filesystem device to avoid cases when a
   loop device is reformatted and the entry gets stale

* tag 'for-6.2-rc7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: free device in btrfs_close_devices for a single device filesystem
  btrfs: lock the inode in shared mode before starting fiemap
  btrfs: simplify update of last_dir_index_offset when logging a directory

4 files changed, 34 insertions, 9 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9bd32daa9b9a..3bbf8703db2a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3826,6 +3826,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 	lockend = round_up(start + len, inode->root->fs_info->sectorsize);
 	prev_extent_end = lockstart;
 
+	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
 	lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 
 	ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
@@ -4019,6 +4020,7 @@ check_eof_delalloc:
 
 out_unlock:
 	unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
+	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 out:
 	free_extent_state(delalloc_cached_state);
 	btrfs_free_backref_share_ctx(backref_ctx);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d43261545264..58599189bd18 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3576,17 +3576,19 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
 }
 
 static int flush_dir_items_batch(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *log,
+				 struct btrfs_inode *inode,
 				 struct extent_buffer *src,
 				 struct btrfs_path *dst_path,
 				 int start_slot,
 				 int count)
 {
+	struct btrfs_root *log = inode->root->log_root;
 	char *ins_data = NULL;
 	struct btrfs_item_batch batch;
 	struct extent_buffer *dst;
 	unsigned long src_offset;
 	unsigned long dst_offset;
+	u64 last_index;
 	struct btrfs_key key;
 	u32 item_size;
 	int ret;
@@ -3644,6 +3646,19 @@ static int flush_dir_items_batch(struct btrfs_trans_handle *trans,
 	src_offset = btrfs_item_ptr_offset(src, start_slot + count - 1);
 	copy_extent_buffer(dst, src, dst_offset, src_offset, batch.total_data_size);
 	btrfs_release_path(dst_path);
+
+	last_index = batch.keys[count - 1].offset;
+	ASSERT(last_index > inode->last_dir_index_offset);
+
+	/*
+	 * If for some unexpected reason the last item's index is not greater
+	 * than the last index we logged, warn and return an error to fallback
+	 * to a transaction commit.
+	 */
+	if (WARN_ON(last_index <= inode->last_dir_index_offset))
+		ret = -EUCLEAN;
+	else
+		inode->last_dir_index_offset = last_index;
 out:
 	kfree(ins_data);
 
@@ -3693,7 +3708,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 		}
 
 		di = btrfs_item_ptr(src, i, struct btrfs_dir_item);
-		ctx->last_dir_item_offset = key.offset;
 
 		/*
 		 * Skip ranges of items that consist only of dir item keys created
@@ -3756,7 +3770,7 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 	if (batch_size > 0) {
 		int ret;
 
-		ret = flush_dir_items_batch(trans, log, src, dst_path,
+		ret = flush_dir_items_batch(trans, inode, src, dst_path,
 					    batch_start, batch_size);
 		if (ret < 0)
 			return ret;
@@ -4044,7 +4058,6 @@ static noinline int log_directory_changes(struct btrfs_trans_handle *trans,
 
 	min_key = BTRFS_DIR_START_INDEX;
 	max_key = 0;
-	ctx->last_dir_item_offset = inode->last_dir_index_offset;
 
 	while (1) {
 		ret = log_dir_items(trans, inode, path, dst_path,
@@ -4056,8 +4069,6 @@ static noinline int log_directory_changes(struct btrfs_trans_handle *trans,
 		min_key = max_key + 1;
 	}
 
-	inode->last_dir_index_offset = ctx->last_dir_item_offset;
-
 	return 0;
 }
 
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 85b43075ac58..85cd24cb0540 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -24,8 +24,6 @@ struct btrfs_log_ctx {
 	bool logging_new_delayed_dentries;
 	/* Indicate if the inode being logged was logged before. */
 	bool logged_before;
-	/* Tracks the last logged dir item/index key offset. */
-	u64 last_dir_item_offset;
 	struct inode *inode;
 	struct list_head list;
 	/* Only used for fast fsyncs. */
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4cdadf30163d..df43093b7a46 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -403,6 +403,7 @@ void btrfs_free_device(struct btrfs_device *device)
 static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device;
+
 	WARN_ON(fs_devices->opened);
 	while (!list_empty(&fs_devices->devices)) {
 		device = list_entry(fs_devices->devices.next,
@@ -1181,9 +1182,22 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 
 	mutex_lock(&uuid_mutex);
 	close_fs_devices(fs_devices);
-	if (!fs_devices->opened)
+	if (!fs_devices->opened) {
 		list_splice_init(&fs_devices->seed_list, &list);
 
+		/*
+		 * If the struct btrfs_fs_devices is not assembled with any
+		 * other device, it can be re-initialized during the next mount
+		 * without the needing device-scan step. Therefore, it can be
+		 * fully freed.
+		 */
+		if (fs_devices->num_devices == 1) {
+			list_del(&fs_devices->fs_list);
+			free_fs_devices(fs_devices);
+		}
+	}
+
+
 	list_for_each_entry_safe(fs_devices, tmp, &list, seed_list) {
 		close_fs_devices(fs_devices);
 		list_del(&fs_devices->seed_list);