1 files changed, 41 insertions, 13 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fff37c8d96a4..2d9d38b82daa 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -190,7 +190,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function,
 
 	btrfs_abort_transaction(wc->trans, error);
 
-	if (wc->subvol_path->nodes[0]) {
+	if (wc->subvol_path && wc->subvol_path->nodes[0]) {
 		btrfs_crit(fs_info,
 			   "subvolume (root %llu) leaf currently being processed:",
 			   btrfs_root_id(wc->root));
@@ -5865,14 +5865,6 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
 	struct btrfs_inode *curr_inode = start_inode;
 	int ret = 0;
 
-	/*
-	 * If we are logging a new name, as part of a link or rename operation,
-	 * don't bother logging new dentries, as we just want to log the names
-	 * of an inode and that any new parents exist.
-	 */
-	if (ctx->logging_new_name)
-		return 0;
-
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -6051,6 +6043,33 @@ static int conflicting_inode_is_dir(struct btrfs_root *root, u64 ino,
 	return ret;
 }
 
+static bool can_log_conflicting_inode(const struct btrfs_trans_handle *trans,
+				      const struct btrfs_inode *inode)
+{
+	if (!S_ISDIR(inode->vfs_inode.i_mode))
+		return true;
+
+	if (inode->last_unlink_trans < trans->transid)
+		return true;
+
+	/*
+	 * If this is a directory and its unlink_trans is not from a past
+	 * transaction then we must fallback to a transaction commit in order
+	 * to avoid getting a directory with 2 hard links after log replay.
+	 *
+	 * This happens if a directory A is renamed, moved from one parent
+	 * directory to another one, a new file is created in the old parent
+	 * directory with the old name of our directory A, the new file is
+	 * fsynced, then we moved the new file to some other parent directory
+	 * and fsync again the new file. This results in a log tree where we
+	 * logged that directory A existed, with the INODE_REF item for the
+	 * new location but without having logged its old parent inode, so
+	 * that on log replay we add a new link for the new location but the
+	 * old link remains, resulting in a link count of 2.
+	 */
+	return false;
+}
+
 static int add_conflicting_inode(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 struct btrfs_path *path,
@@ -6154,6 +6173,11 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 
+	if (!can_log_conflicting_inode(trans, inode)) {
+		btrfs_add_delayed_iput(inode);
+		return BTRFS_LOG_FORCE_COMMIT;
+	}
+
 	btrfs_add_delayed_iput(inode);
 
 	ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS);
@@ -6218,6 +6242,12 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 				break;
 			}
 
+			if (!can_log_conflicting_inode(trans, inode)) {
+				btrfs_add_delayed_iput(inode);
+				ret = BTRFS_LOG_FORCE_COMMIT;
+				break;
+			}
+
 			/*
 			 * Always log the directory, we cannot make this
 			 * conditional on need_log_inode() because the directory
@@ -6311,10 +6341,8 @@ again:
 			 * and no keys greater than that, so bail out.
 			 */
 			break;
-		} else if ((min_key->type == BTRFS_INODE_REF_KEY ||
-			    min_key->type == BTRFS_INODE_EXTREF_KEY) &&
-			   (inode->generation == trans->transid ||
-			    ctx->logging_conflict_inodes)) {
+		} else if (min_key->type == BTRFS_INODE_REF_KEY ||
+			   min_key->type == BTRFS_INODE_EXTREF_KEY) {
 			u64 other_ino = 0;
 			u64 other_parent = 0;