Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "Outside of misc fixes, Filipe has a few fsync corners and we're
  pulling in one more of Josef's fixes from production use here"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs:__add_inode_ref: out of bounds memory read when looking for extended ref.
  Btrfs: fix data loss in the fast fsync path
  Btrfs: remove extra run_delayed_refs in update_cowonly_root
  Btrfs: incremental send, don't rename a directory too soon
  btrfs: fix lost return value due to variable shadowing
  Btrfs: do not ignore errors from btrfs_lookup_xattr in do_setxattr
  Btrfs: fix off-by-one logic error in btrfs_realloc_node
  Btrfs: add missing inode update when punching hole
  Btrfs: abort the transaction if we fail to update the free space cache inode
  Btrfs: fix fsync race leading to ordered extent memory leaks

9 files changed, 241 insertions, 62 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 9936421..6d67f32 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1645,14 +1645,14 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
 	parent_nritems = btrfs_header_nritems(parent);
 	blocksize = root->nodesize;
-	end_slot = parent_nritems;
+	end_slot = parent_nritems - 1;
 
-	if (parent_nritems == 1)
+	if (parent_nritems <= 1)
 		return 0;
 
 	btrfs_set_lock_blocking(parent);
 
-	for (i = start_slot; i < end_slot; i++) {
+	for (i = start_slot; i <= end_slot; i++) {
 		int close = 1;
 
 		btrfs_node_key(parent, &disk_key, i);
@@ -1669,7 +1669,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			other = btrfs_node_blockptr(parent, i - 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
-		if (!close && i < end_slot - 2) {
+		if (!close && i < end_slot) {
 			other = btrfs_node_blockptr(parent, i + 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 571f402..6f08045 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3208,6 +3208,8 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 		return 0;
 	}
 
+	if (trans->aborted)
+		return 0;
 again:
 	inode = lookup_free_space_inode(root, block_group, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
@@ -3243,6 +3245,20 @@ again:
 	 */
 	BTRFS_I(inode)->generation = 0;
 	ret = btrfs_update_inode(trans, root, inode);
+	if (ret) {
+		/*
+		 * So theoretically we could recover from this, simply set the
+		 * super cache generation to 0 so we know to invalidate the
+		 * cache, but then we'd have to keep track of the block groups
+		 * that fail this way so we know we _have_ to reset this cache
+		 * before the next commit or risk reading stale cache.  So to
+		 * limit our exposure to horrible edge cases lets just abort the
+		 * transaction, this only happens in really bad situations
+		 * anyway.
+		 */
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_put;
+	}
 	WARN_ON(ret);
 
 	if (i_size_read(inode) > 0) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b78bbba..30982bb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1811,22 +1811,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	mutex_unlock(&inode->i_mutex);
 
 	/*
-	 * we want to make sure fsync finds this change
-	 * but we haven't joined a transaction running right now.
-	 *
-	 * Later on, someone is sure to update the inode and get the
-	 * real transid recorded.
-	 *
-	 * We set last_trans now to the fs_info generation + 1,
-	 * this will either be one more than the running transaction
-	 * or the generation used for the next transaction if there isn't
-	 * one running right now.
-	 *
 	 * We also have to set last_sub_trans to the current log transid,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
-	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
@@ -1959,25 +1947,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
-	 * check the transaction that last modified this inode
-	 * and see if its already been committed
-	 */
-	if (!BTRFS_I(inode)->last_trans) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-
-	/*
-	 * if the last transaction that changed this file was before
-	 * the current transaction, we can bail out now without any
-	 * syncing
+	 * If the last transaction that changed this file was before the current
+	 * transaction and we have the full sync flag set in our inode, we can
+	 * bail out now without any syncing.
+	 *
+	 * Note that we can't bail out if the full sync flag isn't set. This is
+	 * because when the full sync flag is set we start all ordered extents
+	 * and wait for them to fully complete - when they complete they update
+	 * the inode's last_trans field through:
+	 *
+	 *     btrfs_finish_ordered_io() ->
+	 *         btrfs_update_inode_fallback() ->
+	 *             btrfs_update_inode() ->
+	 *                 btrfs_set_inode_last_trans()
+	 *
+	 * So we are sure that last_trans is up to date and can do this check to
+	 * bail out safely. For the fast path, when the full sync flag is not
+	 * set in our inode, we can not do it because we start only our ordered
+	 * extents and don't wait for them to complete (that is when
+	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
+	 * value might be less than or equals to fs_info->last_trans_committed,
+	 * and setting a speculative last_trans for an inode when a buffered
+	 * write is made (such as fs_info->generation + 1 for example) would not
+	 * be reliable since after setting the value and before fsync is called
+	 * any number of transactions can start and commit (transaction kthread
+	 * commits the current transaction periodically), and a transaction
+	 * commit does not start nor waits for ordered extents to complete.
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    BTRFS_I(inode)->last_trans <=
-	    root->fs_info->last_trans_committed) {
-		BTRFS_I(inode)->last_trans = 0;
-
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed)) {
 		/*
 		 * We'v had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2275,6 +2275,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	bool same_page;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
 	u64 ino_size;
+	bool truncated_page = false;
+	bool updated_inode = false;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
@@ -2306,13 +2308,18 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * entire page.
 	 */
 	if (same_page && len < PAGE_CACHE_SIZE) {
-		if (offset < ino_size)
+		if (offset < ino_size) {
+			truncated_page = true;
 			ret = btrfs_truncate_page(inode, offset, len, 0);
+		} else {
+			ret = 0;
+		}
 		goto out_only_mutex;
 	}
 
 	/* zero back part of the first page */
 	if (offset < ino_size) {
+		truncated_page = true;
 		ret = btrfs_truncate_page(inode, offset, 0, 0);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -2348,6 +2355,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if (!ret) {
 			/* zero the front end of the last page */
 			if (tail_start + tail_len < ino_size) {
+				truncated_page = true;
 				ret = btrfs_truncate_page(inode,
 						tail_start + tail_len, 0, 1);
 				if (ret)
@@ -2357,8 +2365,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	if (lockend < lockstart) {
-		mutex_unlock(&inode->i_mutex);
-		return 0;
+		ret = 0;
+		goto out_only_mutex;
 	}
 
 	while (1) {
@@ -2506,6 +2514,7 @@ out_trans:
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
+	updated_inode = true;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root);
 out_free:
@@ -2515,6 +2524,22 @@ out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
 out_only_mutex:
+	if (!updated_inode && truncated_page && !ret && !err) {
+		/*
+		 * If we only end up zeroing part of a page, we still need to
+		 * update the inode item, so that all the time fields are
+		 * updated as well as the necessary btrfs inode in memory fields
+		 * for detecting, at fsync time, if the inode isn't yet in the
+		 * log tree or it's there but not up to date.
+		 */
+		trans = btrfs_start_transaction(root, 1);
+		if (IS_ERR(trans)) {
+			err = PTR_ERR(trans);
+		} else {
+			err = btrfs_update_inode(trans, root, inode);
+			ret = btrfs_end_transaction(trans, root);
+		}
+	}
 	mutex_unlock(&inode->i_mutex);
 	if (ret && !err)
 		err = ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a85c23d..da828cf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7285,7 +7285,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
 		int type;
-		int ret;
 		u64 block_start, orig_start, orig_block_len, ram_bytes;
 
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 534544e..157cc54 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -452,9 +452,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 			continue;
 		if (entry_end(ordered) <= start)
 			break;
-		if (!list_empty(&ordered->log_list))
-			continue;
-		if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
 			continue;
 		list_add(&ordered->log_list, logged_list);
 		atomic_inc(&ordered->refs);
@@ -511,8 +509,7 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
 
-		if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			list_add_tail(&ordered->trans_list, &trans->ordered);
+		list_add_tail(&ordered->trans_list, &trans->ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
 	spin_unlock_irq(&log->log_extents_lock[index]);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fe58572..d6033f5 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -230,6 +230,7 @@ struct pending_dir_move {
 	u64 parent_ino;
 	u64 ino;
 	u64 gen;
+	bool is_orphan;
 	struct list_head update_refs;
 };
 
@@ -2984,7 +2985,8 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 				u64 ino_gen,
 				u64 parent_ino,
 				struct list_head *new_refs,
-				struct list_head *deleted_refs)
+				struct list_head *deleted_refs,
+				const bool is_orphan)
 {
 	struct rb_node **p = &sctx->pending_dir_moves.rb_node;
 	struct rb_node *parent = NULL;
@@ -2999,6 +3001,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 	pm->parent_ino = parent_ino;
 	pm->ino = ino;
 	pm->gen = ino_gen;
+	pm->is_orphan = is_orphan;
 	INIT_LIST_HEAD(&pm->list);
 	INIT_LIST_HEAD(&pm->update_refs);
 	RB_CLEAR_NODE(&pm->node);
@@ -3131,16 +3134,20 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	rmdir_ino = dm->rmdir_ino;
 	free_waiting_dir_move(sctx, dm);
 
-	ret = get_first_ref(sctx->parent_root, pm->ino,
-			    &parent_ino, &parent_gen, name);
-	if (ret < 0)
-		goto out;
-
-	ret = get_cur_path(sctx, parent_ino, parent_gen,
-			   from_path);
-	if (ret < 0)
-		goto out;
-	ret = fs_path_add_path(from_path, name);
+	if (pm->is_orphan) {
+		ret = gen_unique_name(sctx, pm->ino,
+				      pm->gen, from_path);
+	} else {
+		ret = get_first_ref(sctx->parent_root, pm->ino,
+				    &parent_ino, &parent_gen, name);
+		if (ret < 0)
+			goto out;
+		ret = get_cur_path(sctx, parent_ino, parent_gen,
+				   from_path);
+		if (ret < 0)
+			goto out;
+		ret = fs_path_add_path(from_path, name);
+	}
 	if (ret < 0)
 		goto out;
 
@@ -3150,7 +3157,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 		LIST_HEAD(deleted_refs);
 		ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
 		ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
-					   &pm->update_refs, &deleted_refs);
+					   &pm->update_refs, &deleted_refs,
+					   pm->is_orphan);
 		if (ret < 0)
 			goto out;
 		if (rmdir_ino) {
@@ -3283,6 +3291,127 @@ out:
 	return ret;
 }
 
+/*
+ * We might need to delay a directory rename even when no ancestor directory
+ * (in the send root) with a higher inode number than ours (sctx->cur_ino) was
+ * renamed. This happens when we rename a directory to the old name (the name
+ * in the parent root) of some other unrelated directory that got its rename
+ * delayed due to some ancestor with higher number that got renamed.
+ *
+ * Example:
+ *
+ * Parent snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 257)
+ * |     |---- file                        (ino 260)
+ * |
+ * |---- b/                                (ino 258)
+ * |---- c/                                (ino 259)
+ *
+ * Send snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 258)
+ * |---- x/                                (ino 259)
+ *       |---- y/                          (ino 257)
+ *             |----- file                 (ino 260)
+ *
+ * Here we can not rename 258 from 'b' to 'a' without the rename of inode 257
+ * from 'a' to 'x/y' happening first, which in turn depends on the rename of
+ * inode 259 from 'c' to 'x'. So the order of rename commands the send stream
+ * must issue is:
+ *
+ * 1 - rename 259 from 'c' to 'x'
+ * 2 - rename 257 from 'a' to 'x/y'
+ * 3 - rename 258 from 'b' to 'a'
+ *
+ * Returns 1 if the rename of sctx->cur_ino needs to be delayed, 0 if it can
+ * be done right away and < 0 on error.
+ */
+static int wait_for_dest_dir_move(struct send_ctx *sctx,
+				  struct recorded_ref *parent_ref,
+				  const bool is_orphan)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key di_key;
+	struct btrfs_dir_item *di;
+	u64 left_gen;
+	u64 right_gen;
+	int ret = 0;
+
+	if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
+		return 0;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = parent_ref->dir;
+	key.type = BTRFS_DIR_ITEM_KEY;
+	key.offset = btrfs_name_hash(parent_ref->name, parent_ref->name_len);
+
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0) {
+		goto out;
+	} else if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+
+	di = btrfs_match_dir_item_name(sctx->parent_root, path,
+				       parent_ref->name, parent_ref->name_len);
+	if (!di) {
+		ret = 0;
+		goto out;
+	}
+	/*
+	 * di_key.objectid has the number of the inode that has a dentry in the
+	 * parent directory with the same name that sctx->cur_ino is being
+	 * renamed to. We need to check if that inode is in the send root as
+	 * well and if it is currently marked as an inode with a pending rename,
+	 * if it is, we need to delay the rename of sctx->cur_ino as well, so
+	 * that it happens after that other inode is renamed.
+	 */
+	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &di_key);
+	if (di_key.type != BTRFS_INODE_ITEM_KEY) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = get_inode_info(sctx->parent_root, di_key.objectid, NULL,
+			     &left_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0)
+		goto out;
+	ret = get_inode_info(sctx->send_root, di_key.objectid, NULL,
+			     &right_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0) {
+		if (ret == -ENOENT)
+			ret = 0;
+		goto out;
+	}
+
+	/* Different inode, no need to delay the rename of sctx->cur_ino */
+	if (right_gen != left_gen) {
+		ret = 0;
+		goto out;
+	}
+
+	if (is_waiting_for_move(sctx, di_key.objectid)) {
+		ret = add_pending_dir_move(sctx,
+					   sctx->cur_ino,
+					   sctx->cur_inode_gen,
+					   di_key.objectid,
+					   &sctx->new_refs,
+					   &sctx->deleted_refs,
+					   is_orphan);
+		if (!ret)
+			ret = 1;
+	}
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int wait_for_parent_move(struct send_ctx *sctx,
 				struct recorded_ref *parent_ref)
 {
@@ -3349,7 +3478,8 @@ out:
 					   sctx->cur_inode_gen,
 					   ino,
 					   &sctx->new_refs,
-					   &sctx->deleted_refs);
+					   &sctx->deleted_refs,
+					   false);
 		if (!ret)
 			ret = 1;
 	}
@@ -3372,6 +3502,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	int did_overwrite = 0;
 	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
+	bool can_rename = true;
 
 verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 
@@ -3490,12 +3621,22 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			}
 		}
 
+		if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) {
+			ret = wait_for_dest_dir_move(sctx, cur, is_orphan);
+			if (ret < 0)
+				goto out;
+			if (ret == 1) {
+				can_rename = false;
+				*pending_move = 1;
+			}
+		}
+
 		/*
 		 * link/move the ref to the new place. If we have an orphan
 		 * inode, move it and update valid_path. If not, link or move
 		 * it depending on the inode mode.
 		 */
-		if (is_orphan) {
+		if (is_orphan && can_rename) {
 			ret = send_rename(sctx, valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
@@ -3503,7 +3644,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			ret = fs_path_copy(valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
-		} else {
+		} else if (can_rename) {
 			if (S_ISDIR(sctx->cur_inode_mode)) {
 				/*
 				 * Dirs can't be linked, so move it. For moved
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7e80f32..88e51ad 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1052,9 +1052,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 		if (ret)
 			return ret;
-		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-		if (ret)
-			return ret;
 	}
 
 	return 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a37f8b..c5b8ba3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1012,7 +1012,7 @@ again:
 		base = btrfs_item_ptr_offset(leaf, path->slots[0]);
 
 		while (cur_offset < item_size) {
-			extref = (struct btrfs_inode_extref *)base + cur_offset;
+			extref = (struct btrfs_inode_extref *)(base + cur_offset);
 
 			victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
 
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 47b1946..883b936 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -111,6 +111,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 					name, name_len, -1);
 		if (!di && (flags & XATTR_REPLACE))
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
 		else if (di)
 			ret = btrfs_delete_one_dir_name(trans, root, path, di);
 		goto out;
@@ -127,10 +129,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		ASSERT(mutex_is_locked(&inode->i_mutex));
 		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
 					name, name_len, 0);
-		if (!di) {
+		if (!di)
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
+		if (ret)
 			goto out;
-		}
 		btrfs_release_path(path);
 		di = NULL;
 	}