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

Pull btrfs fixes from Chris Mason:
 "We've got corner cases for updating i_size that ceph was hitting,
  error handling for quotas when we run out of space, a very subtle
  snapshot deletion race, a crash while removing devices, and one
  deadlock between subvolume creation and the sb_internal code (thanks
  lockdep)."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: move d_instantiate outside the transaction during mksubvol
  Btrfs: fix EDQUOT handling in btrfs_delalloc_reserve_metadata
  Btrfs: fix possible stale data exposure
  Btrfs: fix missing i_size update
  Btrfs: fix race between snapshot deletion and getting inode
  Btrfs: fix missing release of the space/qgroup reservation in start_transaction()
  Btrfs: fix wrong sync_writers decrement in btrfs_file_aio_write()
  Btrfs: do not merge logged extents if we've removed them from the tree
  btrfs: don't try to notify udev about missing devices

fs/btrfs/extent-tree.c

@@ -4534,7 +4534,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	unsigned nr_extents = 0;
 	int extra_reserve = 0;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
-	int ret;
+	int ret = 0;
 	bool delalloc_lock = true;
 
 	/* If we are a free space inode we need to not flush since we will be in
@@ -4579,20 +4579,18 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	csum_bytes = BTRFS_I(inode)->csum_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
 
-	if (root->fs_info->quota_enabled) {
+	if (root->fs_info->quota_enabled)
 		ret = btrfs_qgroup_reserve(root, num_bytes +
 					   nr_extents * root->leafsize);
-		if (ret) {
-			spin_lock(&BTRFS_I(inode)->lock);
-			calc_csum_metadata_size(inode, num_bytes, 0);
-			spin_unlock(&BTRFS_I(inode)->lock);
-			if (delalloc_lock)
-				mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
-			return ret;
-		}
-	}
 
-	ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
+	/*
+	 * ret != 0 here means the qgroup reservation failed, we go straight to
+	 * the shared error handling then.
+	 */
+	if (ret == 0)
+		ret = reserve_metadata_bytes(root, block_rsv,
+					     to_reserve, flush);
+
 	if (ret) {
 		u64 to_free = 0;
 		unsigned dropped;

fs/btrfs/extent_map.c

@@ -288,6 +288,7 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
 {
 	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	if (em->in_tree)
 		try_merge_map(tree, em);
 }
 

fs/btrfs/file.c

@@ -293,15 +293,24 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	struct btrfs_ioctl_defrag_range_args range;
 	int num_defrag;
+	int index;
+	int ret;
 
 	/* get the inode */
 	key.objectid = defrag->root;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 	key.offset = (u64)-1;
+
+	index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
 	if (IS_ERR(inode_root)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode_root);
+		ret = PTR_ERR(inode_root);
+		goto cleanup;
+	}
+	if (btrfs_root_refs(&inode_root->root_item) == 0) {
+		ret = -ENOENT;
+		goto cleanup;
 	}
 
 	key.objectid = defrag->ino;
@@ -309,9 +318,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
 	if (IS_ERR(inode)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode);
+		ret = PTR_ERR(inode);
+		goto cleanup;
 	}
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
 	/* do a chunk of defrag */
 	clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
@@ -346,6 +356,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 
 	iput(inode);
 	return 0;
+cleanup:
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
+	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
+	return ret;
 }
 
 /*
@@ -1594,9 +1608,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		if (err < 0 && num_written > 0)
 			num_written = err;
 	}
-out:
+
 	if (sync)
 		atomic_dec(&BTRFS_I(inode)->sync_writers);
+out:
 	sb_end_write(inode->i_sb);
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;

fs/btrfs/ioctl.c

@@ -515,7 +515,6 @@ static noinline int create_subvol(struct btrfs_root *root,
 
 	BUG_ON(ret);
 
-	d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
 fail:
 	if (async_transid) {
 		*async_transid = trans->transid;
@@ -525,6 +524,10 @@ static noinline int create_subvol(struct btrfs_root *root,
 	}
 	if (err && !ret)
 		ret = err;
+
+	if (!ret)
+		d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
+
 	return ret;
 }
 

fs/btrfs/ordered-data.c

@@ -836,9 +836,16 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	 * if the disk i_size is already at the inode->i_size, or
 	 * this ordered extent is inside the disk i_size, we're done
 	 */
-	if (disk_i_size == i_size || offset <= disk_i_size) {
+	if (disk_i_size == i_size)
+		goto out;
+
+	/*
+	 * We still need to update disk_i_size if outstanding_isize is greater
+	 * than disk_i_size.
+	 */
+	if (offset <= disk_i_size &&
+	    (!ordered || ordered->outstanding_isize <= disk_i_size))
 		goto out;
-	}
 
 	/*
 	 * walk backward from this ordered extent to disk_i_size.
@@ -870,7 +877,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 			break;
 		if (test->file_offset >= i_size)
 			break;
-		if (test->file_offset >= disk_i_size) {
+		if (entry_end(test) > disk_i_size) {
 			/*
 			 * we don't update disk_i_size now, so record this
 			 * undealt i_size. Or we will not know the real

fs/btrfs/scrub.c

@@ -580,20 +580,29 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 	int corrected = 0;
 	struct btrfs_key key;
 	struct inode *inode = NULL;
+	struct btrfs_fs_info *fs_info;
 	u64 end = offset + PAGE_SIZE - 1;
 	struct btrfs_root *local_root;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
-	local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key);
-	if (IS_ERR(local_root))
+
+	fs_info = fixup->root->fs_info;
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
+	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
-	inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -606,7 +615,6 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 	}
 
 	if (PageUptodate(page)) {
-		struct btrfs_fs_info *fs_info;
 		if (PageDirty(page)) {
 			/*
 			 * we need to write the data to the defect sector. the
@@ -3180,18 +3188,25 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx)
 	u64 physical_for_dev_replace;
 	u64 len;
 	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
+
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root))
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 

fs/btrfs/transaction.c

@@ -333,12 +333,14 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type,
 					  &root->fs_info->trans_block_rsv,
 					  num_bytes, flush);
 		if (ret)
-			return ERR_PTR(ret);
+			goto reserve_fail;
 	}
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
-	if (!h)
-		return ERR_PTR(-ENOMEM);
+	if (!h) {
+		ret = -ENOMEM;
+		goto alloc_fail;
+	}
 
 	/*
 	 * If we are JOIN_NOLOCK we're already committing a transaction and
@@ -365,11 +367,7 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type,
 	if (ret < 0) {
 		/* We must get the transaction if we are JOIN_NOLOCK. */
 		BUG_ON(type == TRANS_JOIN_NOLOCK);
-
-		if (type < TRANS_JOIN_NOLOCK)
-			sb_end_intwrite(root->fs_info->sb);
-		kmem_cache_free(btrfs_trans_handle_cachep, h);
-		return ERR_PTR(ret);
+		goto join_fail;
 	}
 
 	cur_trans = root->fs_info->running_transaction;
@@ -410,6 +408,19 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type,
 	if (!current->journal_info && type != TRANS_USERSPACE)
 		current->journal_info = h;
 	return h;
+
+join_fail:
+	if (type < TRANS_JOIN_NOLOCK)
+		sb_end_intwrite(root->fs_info->sb);
+	kmem_cache_free(btrfs_trans_handle_cachep, h);
+alloc_fail:
+	if (num_bytes)
+		btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+					num_bytes);
+reserve_fail:
+	if (qgroup_reserved)
+		btrfs_qgroup_free(root, qgroup_reserved);
+	return ERR_PTR(ret);
 }
 
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,

fs/btrfs/volumes.c

@@ -1556,6 +1556,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	ret = 0;
 
 	/* Notify udev that device has changed */
+	if (bdev)
 		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 error_brelse: