1 files changed, 225 insertions, 64 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 561884f60d35..6adcd8a2c5c7 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -139,7 +139,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 	mutex_lock(&root->log_mutex);
 
 	if (root->log_root) {
-		if (btrfs_need_log_full_commit(fs_info, trans)) {
+		if (btrfs_need_log_full_commit(trans)) {
 			ret = -EAGAIN;
 			goto out;
 		}
@@ -225,6 +225,17 @@ void btrfs_end_log_trans(struct btrfs_root *root)
 	}
 }
 
+static int btrfs_write_tree_block(struct extent_buffer *buf)
+{
+	return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
+					buf->start + buf->len - 1);
+}
+
+static void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
+{
+	filemap_fdatawait_range(buf->pages[0]->mapping,
+			        buf->start, buf->start + buf->len - 1);
+}
 
 /*
  * the walk control struct is used to pass state down the chain when
@@ -304,7 +315,7 @@ static int process_one_buffer(struct btrfs_root *log,
 
 	if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) {
 		if (wc->pin && btrfs_header_level(eb) == 0)
-			ret = btrfs_exclude_logged_extents(fs_info, eb);
+			ret = btrfs_exclude_logged_extents(eb);
 		if (wc->write)
 			btrfs_write_tree_block(eb);
 		if (wc->wait)
@@ -333,7 +344,6 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 				   struct extent_buffer *eb, int slot,
 				   struct btrfs_key *key)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 	u32 item_size;
 	u64 saved_i_size = 0;
@@ -454,10 +464,9 @@ insert:
 		found_size = btrfs_item_size_nr(path->nodes[0],
 						path->slots[0]);
 		if (found_size > item_size)
-			btrfs_truncate_item(fs_info, path, item_size, 1);
+			btrfs_truncate_item(path, item_size, 1);
 		else if (found_size < item_size)
-			btrfs_extend_item(fs_info, path,
-					  item_size - found_size);
+			btrfs_extend_item(path, item_size - found_size);
 	} else if (ret) {
 		return ret;
 	}
@@ -694,9 +703,11 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			goto out;
 
 		if (ins.objectid > 0) {
+			struct btrfs_ref ref = { 0 };
 			u64 csum_start;
 			u64 csum_end;
 			LIST_HEAD(ordered_sums);
+
 			/*
 			 * is this extent already allocated in the extent
 			 * allocation tree?  If so, just add a reference
@@ -704,10 +715,13 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			ret = btrfs_lookup_data_extent(fs_info, ins.objectid,
 						ins.offset);
 			if (ret == 0) {
-				ret = btrfs_inc_extent_ref(trans, root,
-						ins.objectid, ins.offset,
-						0, root->root_key.objectid,
+				btrfs_init_generic_ref(&ref,
+						BTRFS_ADD_DELAYED_REF,
+						ins.objectid, ins.offset, 0);
+				btrfs_init_data_ref(&ref,
+						root->root_key.objectid,
 						key->objectid, offset);
+				ret = btrfs_inc_extent_ref(trans, &ref);
 				if (ret)
 					goto out;
 			} else {
@@ -2725,7 +2739,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 				if (trans) {
 					btrfs_tree_lock(next);
 					btrfs_set_lock_blocking_write(next);
-					clean_tree_block(fs_info, next);
+					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
 				} else {
@@ -2809,7 +2823,7 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 				if (trans) {
 					btrfs_tree_lock(next);
 					btrfs_set_lock_blocking_write(next);
-					clean_tree_block(fs_info, next);
+					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
 				} else {
@@ -2891,7 +2905,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 			if (trans) {
 				btrfs_tree_lock(next);
 				btrfs_set_lock_blocking_write(next);
-				clean_tree_block(fs_info, next);
+				btrfs_clean_tree_block(next);
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
 			} else {
@@ -3066,7 +3080,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	}
 
 	/* bail out if we need to do a full commit */
-	if (btrfs_need_log_full_commit(fs_info, trans)) {
+	if (btrfs_need_log_full_commit(trans)) {
 		ret = -EAGAIN;
 		mutex_unlock(&root->log_mutex);
 		goto out;
@@ -3085,7 +3099,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		blk_finish_plug(&plug);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
 	}
@@ -3127,7 +3141,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			list_del_init(&root_log_ctx.list);
 
 		blk_finish_plug(&plug);
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 
 		if (ret != -ENOSPC) {
 			btrfs_abort_transaction(trans, ret);
@@ -3173,7 +3187,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * now that we've moved on to the tree of log tree roots,
 	 * check the full commit flag again
 	 */
-	if (btrfs_need_log_full_commit(fs_info, trans)) {
+	if (btrfs_need_log_full_commit(trans)) {
 		blk_finish_plug(&plug);
 		btrfs_wait_tree_log_extents(log, mark);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -3186,7 +3200,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 					 EXTENT_DIRTY | EXTENT_NEW);
 	blk_finish_plug(&plug);
 	if (ret) {
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		btrfs_abort_transaction(trans, ret);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
@@ -3196,7 +3210,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		ret = btrfs_wait_tree_log_extents(log_root_tree,
 						  EXTENT_NEW | EXTENT_DIRTY);
 	if (ret) {
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
@@ -3218,7 +3232,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 */
 	ret = write_all_supers(fs_info, 1);
 	if (ret) {
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		btrfs_abort_transaction(trans, ret);
 		goto out_wake_log_root;
 	}
@@ -3422,7 +3436,7 @@ fail:
 out_unlock:
 	mutex_unlock(&dir->log_mutex);
 	if (ret == -ENOSPC) {
-		btrfs_set_log_full_commit(root->fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		ret = 0;
 	} else if (ret < 0)
 		btrfs_abort_transaction(trans, ret);
@@ -3438,7 +3452,6 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 			       const char *name, int name_len,
 			       struct btrfs_inode *inode, u64 dirid)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *log;
 	u64 index;
 	int ret;
@@ -3456,7 +3469,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 				  dirid, &index);
 	mutex_unlock(&inode->log_mutex);
 	if (ret == -ENOSPC) {
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		ret = 0;
 	} else if (ret < 0 && ret != -ENOENT)
 		btrfs_abort_transaction(trans, ret);
@@ -5442,7 +5455,7 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
 		 * Make sure any commits to the log are forced to be full
 		 * commits.
 		 */
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		ret = true;
 	}
 	mutex_unlock(&inode->log_mutex);
@@ -5819,6 +5832,190 @@ out:
 	return ret;
 }
 
+static int log_new_ancestors(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root,
+			     struct btrfs_path *path,
+			     struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_key found_key;
+
+	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
+
+	while (true) {
+		struct btrfs_fs_info *fs_info = root->fs_info;
+		const u64 last_committed = fs_info->last_trans_committed;
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+		struct btrfs_key search_key;
+		struct inode *inode;
+		int ret = 0;
+
+		btrfs_release_path(path);
+
+		search_key.objectid = found_key.offset;
+		search_key.type = BTRFS_INODE_ITEM_KEY;
+		search_key.offset = 0;
+		inode = btrfs_iget(fs_info->sb, &search_key, root, NULL);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+
+		if (BTRFS_I(inode)->generation > last_committed)
+			ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
+					      LOG_INODE_EXISTS,
+					      0, LLONG_MAX, ctx);
+		iput(inode);
+		if (ret)
+			return ret;
+
+		if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID)
+			break;
+
+		search_key.type = BTRFS_INODE_REF_KEY;
+		ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+		if (ret < 0)
+			return ret;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				return ret;
+			else if (ret > 0)
+				return -ENOENT;
+			leaf = path->nodes[0];
+			slot = path->slots[0];
+		}
+
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+		if (found_key.objectid != search_key.objectid ||
+		    found_key.type != BTRFS_INODE_REF_KEY)
+			return -ENOENT;
+	}
+	return 0;
+}
+
+static int log_new_ancestors_fast(struct btrfs_trans_handle *trans,
+				  struct btrfs_inode *inode,
+				  struct dentry *parent,
+				  struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct dentry *old_parent = NULL;
+	struct super_block *sb = inode->vfs_inode.i_sb;
+	int ret = 0;
+
+	while (true) {
+		if (!parent || d_really_is_negative(parent) ||
+		    sb != parent->d_sb)
+			break;
+
+		inode = BTRFS_I(d_inode(parent));
+		if (root != inode->root)
+			break;
+
+		if (inode->generation > fs_info->last_trans_committed) {
+			ret = btrfs_log_inode(trans, root, inode,
+					LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
+			if (ret)
+				break;
+		}
+		if (IS_ROOT(parent))
+			break;
+
+		parent = dget_parent(parent);
+		dput(old_parent);
+		old_parent = parent;
+	}
+	dput(old_parent);
+
+	return ret;
+}
+
+static int log_all_new_ancestors(struct btrfs_trans_handle *trans,
+				 struct btrfs_inode *inode,
+				 struct dentry *parent,
+				 struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_root *root = inode->root;
+	const u64 ino = btrfs_ino(inode);
+	struct btrfs_path *path;
+	struct btrfs_key search_key;
+	int ret;
+
+	/*
+	 * For a single hard link case, go through a fast path that does not
+	 * need to iterate the fs/subvolume tree.
+	 */
+	if (inode->vfs_inode.i_nlink < 2)
+		return log_new_ancestors_fast(trans, inode, parent, ctx);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	search_key.objectid = ino;
+	search_key.type = BTRFS_INODE_REF_KEY;
+	search_key.offset = 0;
+again:
+	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret == 0)
+		path->slots[0]++;
+
+	while (true) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+		struct btrfs_key found_key;
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+		if (found_key.objectid != ino ||
+		    found_key.type > BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		/*
+		 * Don't deal with extended references because they are rare
+		 * cases and too complex to deal with (we would need to keep
+		 * track of which subitem we are processing for each item in
+		 * this loop, etc). So just return some error to fallback to
+		 * a transaction commit.
+		 */
+		if (found_key.type == BTRFS_INODE_EXTREF_KEY) {
+			ret = -EMLINK;
+			goto out;
+		}
+
+		/*
+		 * Logging ancestors needs to do more searches on the fs/subvol
+		 * tree, so it releases the path as needed to avoid deadlocks.
+		 * Keep track of the last inode ref key and resume from that key
+		 * after logging all new ancestors for the current hard link.
+		 */
+		memcpy(&search_key, &found_key, sizeof(search_key));
+
+		ret = log_new_ancestors(trans, root, path, ctx);
+		if (ret)
+			goto out;
+		btrfs_release_path(path);
+		goto again;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
  * helper function around btrfs_log_inode to make sure newly created
  * parent directories also end up in the log.  A minimal inode and backref
@@ -5836,11 +6033,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct super_block *sb;
-	struct dentry *old_parent = NULL;
 	int ret = 0;
 	u64 last_committed = fs_info->last_trans_committed;
 	bool log_dentries = false;
-	struct btrfs_inode *orig_inode = inode;
 
 	sb = inode->vfs_inode.i_sb;
 
@@ -5946,56 +6141,22 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * and has a link count of 2.
 	 */
 	if (inode->last_unlink_trans > last_committed) {
-		ret = btrfs_log_all_parents(trans, orig_inode, ctx);
+		ret = btrfs_log_all_parents(trans, inode, ctx);
 		if (ret)
 			goto end_trans;
 	}
 
-	/*
-	 * If a new hard link was added to the inode in the current transaction
-	 * and its link count is now greater than 1, we need to fallback to a
-	 * transaction commit, otherwise we can end up not logging all its new
-	 * parents for all the hard links. Here just from the dentry used to
-	 * fsync, we can not visit the ancestor inodes for all the other hard
-	 * links to figure out if any is new, so we fallback to a transaction
-	 * commit (instead of adding a lot of complexity of scanning a btree,
-	 * since this scenario is not a common use case).
-	 */
-	if (inode->vfs_inode.i_nlink > 1 &&
-	    inode->last_link_trans > last_committed) {
-		ret = -EMLINK;
+	ret = log_all_new_ancestors(trans, inode, parent, ctx);
+	if (ret)
 		goto end_trans;
-	}
 
-	while (1) {
-		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
-			break;
-
-		inode = BTRFS_I(d_inode(parent));
-		if (root != inode->root)
-			break;
-
-		if (inode->generation > last_committed) {
-			ret = btrfs_log_inode(trans, root, inode,
-					LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
-			if (ret)
-				goto end_trans;
-		}
-		if (IS_ROOT(parent))
-			break;
-
-		parent = dget_parent(parent);
-		dput(old_parent);
-		old_parent = parent;
-	}
 	if (log_dentries)
-		ret = log_new_dir_dentries(trans, root, orig_inode, ctx);
+		ret = log_new_dir_dentries(trans, root, inode, ctx);
 	else
 		ret = 0;
 end_trans:
-	dput(old_parent);
 	if (ret < 0) {
-		btrfs_set_log_full_commit(fs_info, trans);
+		btrfs_set_log_full_commit(trans);
 		ret = 1;
 	}