Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 8d19514f authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
parents 95436ada 1a65e24b

fs/btrfs/extent-tree.c

+10 −12
Original line number Diff line number Diff line
@@ -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

+2 −1
Original line number Diff line number Diff line
@@ -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

+20 −5
Original line number Diff line number Diff line
@@ -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

+4 −1
Original line number Diff line number Diff line
@@ -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

+10 −3
Original line number Diff line number Diff line
@@ -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