Re: [PATCH v2 6/6] ext4: protect WRITE_ZEROES written extents with orphan list

[Jan Kara]

On Tue 07-07-26 10:13:38, Zhang Yi wrote:
> In ext4_alloc_file_blocks(), the WRITE_ZEROES path converts unwritten
> extents to written in one transaction while i_disksize is updated to
> cover them only in a later transaction. A crash in between leaves
> written extents beyond i_disksize on disk, which fsck will complain
> about this.
> 
> Add the inode to the orphan list in the same handle that does the
> conversion, and remove it once i_disksize has caught up. Fold
> ext4_convert_unwritten_extents() into the same handle so the orphan
> add and the conversion are atomic. Also add a check before conversion
> to ensure the conversion does not extend beyond the end of the file.
> 
> Reported-by: Jan Kara <jack@xxxxxxx>
> Closes: https://lore.kernel.org/linux-ext4/3f6ao5amv7glbgigndtegcucgo3n34ij3lau6l3da3hgdxgn3v@ev66wv3r5umt/
> Fixes: f4265b8d32c4 ("ext4: add FALLOC_FL_WRITE_ZEROES support")
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Zhang Yi <yi.zhang@xxxxxxxxxx>

Looks good. Feel free to add:

Reviewed-by: Jan Kara <jack@xxxxxxx>

								Honza

> ---
>  fs/ext4/extents.c | 32 ++++++++++++++++++++++++++++----
>  1 file changed, 28 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
> index c083703bf704..8c7a98405a64 100644
> --- a/fs/ext4/extents.c
> +++ b/fs/ext4/extents.c
> @@ -4585,6 +4585,7 @@ static int ext4_alloc_file_blocks(struct file *file, loff_t offset, loff_t len,
>  	loff_t epos = 0, old_size = i_size_read(inode);
>  	unsigned int blkbits = inode->i_blkbits;
>  	bool alloc_zero = false;
> +	bool orphan = false;
>  
>  	BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
>  	map.m_lblk = offset >> blkbits;
> @@ -4659,12 +4660,30 @@ static int ext4_alloc_file_blocks(struct file *file, loff_t offset, loff_t len,
>  
>  		if (alloc_zero &&
>  		    (map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN))) {
> +			WARN_ON_ONCE(map.m_lblk + map.m_len >
> +				EXT4_B_TO_LBLK(inode, new_size ?: old_size));
> +
>  			ret = ext4_issue_zeroout(inode, map.m_lblk, map.m_pblk,
>  						 map.m_len);
> -			if (likely(!ret))
> -				ret = ext4_convert_unwritten_extents(NULL,
> +			if (unlikely(ret))
> +				break;
> +
> +			handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
> +						    credits);
> +			if (IS_ERR(handle)) {
> +				ret = PTR_ERR(handle);
> +				break;
> +			}
> +
> +			ret = ext4_convert_unwritten_extents(handle,
>  					inode, (loff_t)map.m_lblk << blkbits,
>  					(loff_t)map.m_len << blkbits);
> +			if (!ret && new_size) {
> +				ret = ext4_orphan_add(handle, inode);
> +				orphan = true;
> +			}
> +			ret2 = ext4_journal_stop(handle);
> +			ret = ret ? ret : ret2;
>  			if (ret)
>  				break;
>  		}
> @@ -4687,12 +4706,17 @@ static int ext4_alloc_file_blocks(struct file *file, loff_t offset, loff_t len,
>  	if (epos > new_size)
>  		epos = new_size;
>  
> -	handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
> -	if (IS_ERR(handle))
> +	handle = ext4_journal_start(inode, EXT4_HT_MISC, 2);
> +	if (IS_ERR(handle)) {
> +		if (orphan && inode->i_nlink)
> +			ext4_orphan_del(NULL, inode);
>  		return ret ? ret : PTR_ERR(handle);
> +	}
>  
>  	ext4_update_inode_size(inode, epos);
>  	ret2 = ext4_mark_inode_dirty(handle, inode);
> +	if (orphan && inode->i_nlink)
> +		ext4_orphan_del(handle, inode);
>  	ext4_update_inode_fsync_trans(handle, inode, 1);
>  	ret3 = ext4_journal_stop(handle);
>  	ret2 = ret3 ? ret3 : ret2;
> -- 
> 2.52.0
> 
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR