1 files changed, 254 insertions, 61 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ac232b3d6d7e..561884f60d35 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -27,6 +27,7 @@
 #define LOG_INODE_ALL 0
 #define LOG_INODE_EXISTS 1
 #define LOG_OTHER_INODE 2
+#define LOG_OTHER_INODE_ALL 3
 
 /*
  * directory trouble cases
@@ -1330,6 +1331,67 @@ out:
 	return ret;
 }
 
+static int add_link(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		    struct inode *dir, struct inode *inode, const char *name,
+		    int namelen, u64 ref_index)
+{
+	struct btrfs_dir_item *dir_item;
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	struct inode *other_inode = NULL;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	dir_item = btrfs_lookup_dir_item(NULL, root, path,
+					 btrfs_ino(BTRFS_I(dir)),
+					 name, namelen, 0);
+	if (!dir_item) {
+		btrfs_release_path(path);
+		goto add_link;
+	} else if (IS_ERR(dir_item)) {
+		ret = PTR_ERR(dir_item);
+		goto out;
+	}
+
+	/*
+	 * Our inode's dentry collides with the dentry of another inode which is
+	 * in the log but not yet processed since it has a higher inode number.
+	 * So delete that other dentry.
+	 */
+	btrfs_dir_item_key_to_cpu(path->nodes[0], dir_item, &key);
+	btrfs_release_path(path);
+	other_inode = read_one_inode(root, key.objectid);
+	if (!other_inode) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), BTRFS_I(other_inode),
+				 name, namelen);
+	if (ret)
+		goto out;
+	/*
+	 * If we dropped the link count to 0, bump it so that later the iput()
+	 * on the inode will not free it. We will fixup the link count later.
+	 */
+	if (other_inode->i_nlink == 0)
+		inc_nlink(other_inode);
+
+	ret = btrfs_run_delayed_items(trans);
+	if (ret)
+		goto out;
+add_link:
+	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+			     name, namelen, 0, ref_index);
+out:
+	iput(other_inode);
+	btrfs_free_path(path);
+
+	return ret;
+}
+
 /*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
@@ -1466,9 +1528,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				goto out;
 
 			/* insert our name */
-			ret = btrfs_add_link(trans, BTRFS_I(dir),
-					BTRFS_I(inode),
-					name, namelen, 0, ref_index);
+			ret = add_link(trans, root, dir, inode, name, namelen,
+				       ref_index);
 			if (ret)
 				goto out;
 
@@ -2663,7 +2724,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 				if (trans) {
 					btrfs_tree_lock(next);
-					btrfs_set_lock_blocking(next);
+					btrfs_set_lock_blocking_write(next);
 					clean_tree_block(fs_info, next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
@@ -2747,7 +2808,7 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 
 				if (trans) {
 					btrfs_tree_lock(next);
-					btrfs_set_lock_blocking(next);
+					btrfs_set_lock_blocking_write(next);
 					clean_tree_block(fs_info, next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
@@ -2829,7 +2890,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 
 			if (trans) {
 				btrfs_tree_lock(next);
-				btrfs_set_lock_blocking(next);
+				btrfs_set_lock_blocking_write(next);
 				clean_tree_block(fs_info, next);
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
@@ -3517,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	/* find the first key from this transaction again */
+	/*
+	 * Find the first key from this transaction again.  See the note for
+	 * log_new_dir_dentries, if we're logging a directory recursively we
+	 * won't be holding its i_mutex, which means we can modify the directory
+	 * while we're logging it.  If we remove an entry between our first
+	 * search and this search we'll not find the key again and can just
+	 * bail.
+	 */
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
-	if (WARN_ON(ret != 0))
+	if (ret != 0)
 		goto done;
 
 	/*
@@ -3706,6 +3774,8 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans,
 		found_key.type = 0;
 		ret = btrfs_bin_search(path->nodes[0], &found_key, 0,
 				       &start_slot);
+		if (ret < 0)
+			break;
 
 		ret = btrfs_del_items(trans, log, path, start_slot,
 				      path->slots[0] - start_slot + 1);
@@ -4481,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				      struct btrfs_inode_item);
 		*size_ret = btrfs_inode_size(path->nodes[0], item);
+		/*
+		 * If the in-memory inode's i_size is smaller then the inode
+		 * size stored in the btree, return the inode's i_size, so
+		 * that we get a correct inode size after replaying the log
+		 * when before a power failure we had a shrinking truncate
+		 * followed by addition of a new name (rename / new hard link).
+		 * Otherwise return the inode size from the btree, to avoid
+		 * data loss when replaying a log due to previously doing a
+		 * write that expands the inode's size and logging a new name
+		 * immediately after.
+		 */
+		if (*size_ret > inode->vfs_inode.i_size)
+			*size_ret = inode->vfs_inode.i_size;
 	}
 
 	btrfs_release_path(path);
@@ -4642,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 
 		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(leaf, extent);
-			ASSERT(len == i_size ||
-			       (len == fs_info->sectorsize &&
-				btrfs_file_extent_compression(leaf, extent) !=
-				BTRFS_COMPRESS_NONE) ||
-			       (len < i_size && i_size < fs_info->sectorsize));
+		    BTRFS_FILE_EXTENT_INLINE)
 			return 0;
-		}
 
 		len = btrfs_file_extent_num_bytes(leaf, extent);
 		/* Last extent goes beyond i_size, no need to log a hole. */
@@ -4717,7 +4793,7 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 					 const int slot,
 					 const struct btrfs_key *key,
 					 struct btrfs_inode *inode,
-					 u64 *other_ino)
+					 u64 *other_ino, u64 *other_parent)
 {
 	int ret;
 	struct btrfs_path *search_path;
@@ -4780,8 +4856,13 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 			btrfs_dir_item_key_to_cpu(search_path->nodes[0],
 						  di, &di_key);
 			if (di_key.type == BTRFS_INODE_ITEM_KEY) {
-				ret = 1;
-				*other_ino = di_key.objectid;
+				if (di_key.objectid != key->objectid) {
+					ret = 1;
+					*other_ino = di_key.objectid;
+					*other_parent = parent;
+				} else {
+					ret = 0;
+				}
 			} else {
 				ret = -EAGAIN;
 			}
@@ -4801,6 +4882,144 @@ out:
 	return ret;
 }
 
+struct btrfs_ino_list {
+	u64 ino;
+	u64 parent;
+	struct list_head list;
+};
+
+static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct btrfs_path *path,
+				  struct btrfs_log_ctx *ctx,
+				  u64 ino, u64 parent)
+{
+	struct btrfs_ino_list *ino_elem;
+	LIST_HEAD(inode_list);
+	int ret = 0;
+
+	ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS);
+	if (!ino_elem)
+		return -ENOMEM;
+	ino_elem->ino = ino;
+	ino_elem->parent = parent;
+	list_add_tail(&ino_elem->list, &inode_list);
+
+	while (!list_empty(&inode_list)) {
+		struct btrfs_fs_info *fs_info = root->fs_info;
+		struct btrfs_key key;
+		struct inode *inode;
+
+		ino_elem = list_first_entry(&inode_list, struct btrfs_ino_list,
+					    list);
+		ino = ino_elem->ino;
+		parent = ino_elem->parent;
+		list_del(&ino_elem->list);
+		kfree(ino_elem);
+		if (ret)
+			continue;
+
+		btrfs_release_path(path);
+
+		key.objectid = ino;
+		key.type = BTRFS_INODE_ITEM_KEY;
+		key.offset = 0;
+		inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+		/*
+		 * If the other inode that had a conflicting dir entry was
+		 * deleted in the current transaction, we need to log its parent
+		 * directory.
+		 */
+		if (IS_ERR(inode)) {
+			ret = PTR_ERR(inode);
+			if (ret == -ENOENT) {
+				key.objectid = parent;
+				inode = btrfs_iget(fs_info->sb, &key, root,
+						   NULL);
+				if (IS_ERR(inode)) {
+					ret = PTR_ERR(inode);
+				} else {
+					ret = btrfs_log_inode(trans, root,
+						      BTRFS_I(inode),
+						      LOG_OTHER_INODE_ALL,
+						      0, LLONG_MAX, ctx);
+					iput(inode);
+				}
+			}
+			continue;
+		}
+		/*
+		 * We are safe logging the other inode without acquiring its
+		 * lock as long as we log with the LOG_INODE_EXISTS mode. We
+		 * are safe against concurrent renames of the other inode as
+		 * well because during a rename we pin the log and update the
+		 * log with the new name before we unpin it.
+		 */
+		ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
+				      LOG_OTHER_INODE, 0, LLONG_MAX, ctx);
+		if (ret) {
+			iput(inode);
+			continue;
+		}
+
+		key.objectid = ino;
+		key.type = BTRFS_INODE_REF_KEY;
+		key.offset = 0;
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0) {
+			iput(inode);
+			continue;
+		}
+
+		while (true) {
+			struct extent_buffer *leaf = path->nodes[0];
+			int slot = path->slots[0];
+			u64 other_ino = 0;
+			u64 other_parent = 0;
+
+			if (slot >= btrfs_header_nritems(leaf)) {
+				ret = btrfs_next_leaf(root, path);
+				if (ret < 0) {
+					break;
+				} else if (ret > 0) {
+					ret = 0;
+					break;
+				}
+				continue;
+			}
+
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+			if (key.objectid != ino ||
+			    (key.type != BTRFS_INODE_REF_KEY &&
+			     key.type != BTRFS_INODE_EXTREF_KEY)) {
+				ret = 0;
+				break;
+			}
+
+			ret = btrfs_check_ref_name_override(leaf, slot, &key,
+					BTRFS_I(inode), &other_ino,
+					&other_parent);
+			if (ret < 0)
+				break;
+			if (ret > 0) {
+				ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS);
+				if (!ino_elem) {
+					ret = -ENOMEM;
+					break;
+				}
+				ino_elem->ino = other_ino;
+				ino_elem->parent = other_parent;
+				list_add_tail(&ino_elem->list, &inode_list);
+				ret = 0;
+			}
+			path->slots[0]++;
+		}
+		iput(inode);
+	}
+
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4840,6 +5059,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	u64 logged_isize = 0;
 	bool need_log_inode_item = true;
 	bool xattrs_logged = false;
+	bool recursive_logging = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4885,8 +5105,12 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	if (inode_only == LOG_OTHER_INODE) {
-		inode_only = LOG_INODE_EXISTS;
+	if (inode_only == LOG_OTHER_INODE || inode_only == LOG_OTHER_INODE_ALL) {
+		recursive_logging = true;
+		if (inode_only == LOG_OTHER_INODE)
+			inode_only = LOG_INODE_EXISTS;
+		else
+			inode_only = LOG_INODE_ALL;
 		mutex_lock_nested(&inode->log_mutex, SINGLE_DEPTH_NESTING);
 	} else {
 		mutex_lock(&inode->log_mutex);
@@ -4981,20 +5205,19 @@ again:
 
 		if ((min_key.type == BTRFS_INODE_REF_KEY ||
 		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
-		    inode->generation == trans->transid) {
+		    inode->generation == trans->transid &&
+		    !recursive_logging) {
 			u64 other_ino = 0;
+			u64 other_parent = 0;
 
 			ret = btrfs_check_ref_name_override(path->nodes[0],
 					path->slots[0], &min_key, inode,
-					&other_ino);
+					&other_ino, &other_parent);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			} else if (ret > 0 && ctx &&
 				   other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
-				struct btrfs_key inode_key;
-				struct inode *other_inode;
-
 				if (ins_nr > 0) {
 					ins_nr++;
 				} else {
@@ -5010,43 +5233,13 @@ again:
 					goto out_unlock;
 				}
 				ins_nr = 0;
-				btrfs_release_path(path);
-				inode_key.objectid = other_ino;
-				inode_key.type = BTRFS_INODE_ITEM_KEY;
-				inode_key.offset = 0;
-				other_inode = btrfs_iget(fs_info->sb,
-							 &inode_key, root,
-							 NULL);
-				/*
-				 * If the other inode that had a conflicting dir
-				 * entry was deleted in the current transaction,
-				 * we don't need to do more work nor fallback to
-				 * a transaction commit.
-				 */
-				if (other_inode == ERR_PTR(-ENOENT)) {
-					goto next_key;
-				} else if (IS_ERR(other_inode)) {
-					err = PTR_ERR(other_inode);
-					goto out_unlock;
-				}
-				/*
-				 * We are safe logging the other inode without
-				 * acquiring its i_mutex as long as we log with
-				 * the LOG_INODE_EXISTS mode. We're safe against
-				 * concurrent renames of the other inode as well
-				 * because during a rename we pin the log and
-				 * update the log with the new name before we
-				 * unpin it.
-				 */
-				err = btrfs_log_inode(trans, root,
-						BTRFS_I(other_inode),
-						LOG_OTHER_INODE, 0, LLONG_MAX,
-						ctx);
-				iput(other_inode);
+
+				err = log_conflicting_inodes(trans, root, path,
+						ctx, other_ino, other_parent);
 				if (err)
 					goto out_unlock;
-				else
-					goto next_key;
+				btrfs_release_path(path);
+				goto next_key;
 			}
 		}