Re: [PATCH v3] fs: do not update freeing inode i_io_list

[Jan Kara]

On Tue 15-11-22 20:20:01, Svyatoslav Feldsherov wrote:
> After commit cbfecb927f42 ("fs: record I_DIRTY_TIME even if inode
> already has I_DIRTY_INODE") writeback_single_inode can push inode with
> I_DIRTY_TIME set to b_dirty_time list. In case of freeing inode with
> I_DIRTY_TIME set this can happen after deletion of inode from i_io_list
> at evict. Stack trace is following.
> 
> evict
> fat_evict_inode
> fat_truncate_blocks
> fat_flush_inodes
> writeback_inode
> sync_inode_metadata(inode, sync=0)
> writeback_single_inode(inode, wbc) <- wbc->sync_mode == WB_SYNC_NONE
> 
> This will lead to use after free in flusher thread.
> 
> Similar issue can be triggered if writeback_single_inode in the
> stack trace update inode->i_io_list. Add explicit check to avoid it.
> 
> Fixes: cbfecb927f42 ("fs: record I_DIRTY_TIME even if inode already has I_DIRTY_INODE")
> Reported-by: syzbot+6ba92bd00d5093f7e371@xxxxxxxxxxxxxxxxxxxxxxxxx
> Reviewed-by: Jan Kara <jack@xxxxxxx>
> Signed-off-by: Svyatoslav Feldsherov <feldsherov@xxxxxxxxxx>

Ted, I guess you will merge this patch since you've merged the one from
Lukas this patch is fixing?

								Honza

> ---
>  V2 -> V3:
>  - fix grammar in commit message and comments
> 
>  V1 -> V2: 
>  - address review comments
>  - skip inode_cgwb_move_to_attached for freeing inode 
> 
>  fs/fs-writeback.c | 30 +++++++++++++++++++-----------
>  1 file changed, 19 insertions(+), 11 deletions(-)
> 
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 443f83382b9b..9958d4020771 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -1712,18 +1712,26 @@ static int writeback_single_inode(struct inode *inode,
>  	wb = inode_to_wb_and_lock_list(inode);
>  	spin_lock(&inode->i_lock);
>  	/*
> -	 * If the inode is now fully clean, then it can be safely removed from
> -	 * its writeback list (if any).  Otherwise the flusher threads are
> -	 * responsible for the writeback lists.
> +	 * If the inode is freeing, its i_io_list shoudn't be updated
> +	 * as it can be finally deleted at this moment.
>  	 */
> -	if (!(inode->i_state & I_DIRTY_ALL))
> -		inode_cgwb_move_to_attached(inode, wb);
> -	else if (!(inode->i_state & I_SYNC_QUEUED)) {
> -		if ((inode->i_state & I_DIRTY))
> -			redirty_tail_locked(inode, wb);
> -		else if (inode->i_state & I_DIRTY_TIME) {
> -			inode->dirtied_when = jiffies;
> -			inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
> +	if (!(inode->i_state & I_FREEING)) {
> +		/*
> +		 * If the inode is now fully clean, then it can be safely
> +		 * removed from its writeback list (if any). Otherwise the
> +		 * flusher threads are responsible for the writeback lists.
> +		 */
> +		if (!(inode->i_state & I_DIRTY_ALL))
> +			inode_cgwb_move_to_attached(inode, wb);
> +		else if (!(inode->i_state & I_SYNC_QUEUED)) {
> +			if ((inode->i_state & I_DIRTY))
> +				redirty_tail_locked(inode, wb);
> +			else if (inode->i_state & I_DIRTY_TIME) {
> +				inode->dirtied_when = jiffies;
> +				inode_io_list_move_locked(inode,
> +							  wb,
> +							  &wb->b_dirty_time);
> +			}
>  		}
>  	}
>  
> -- 
> 2.38.1.431.g37b22c650d-goog
> 
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR