Re: [PATCH 06/14] iomap: fix submission side handling of completion side errors

["Darrick J. Wong" <djwong@kernel.org>]

On Wed, Jan 14, 2026 at 08:41:04AM +0100, Christoph Hellwig wrote:
> The "if (dio->error)" in iomap_dio_bio_iter exists to stop submitting
> more bios when a completion already return an error.  Commit cfe057f7db1f
> ("iomap_dio_actor(): fix iov_iter bugs") made it revert the iov by
> "copied", which is very wrong given that we've already consumed that
> range and submitted a bio for it.

Is it possible for the error to be ENOTBLK and the caller wants to fall
back to buffered IO?  I /think/ the answer is "no" because only the
->iomap_begin methods (and therefore iomap_iter()) should be doing that,
and we mask the ENOTBLK and pretend it's a short write.  Right?

--D

> Fixes: cfe057f7db1f ("iomap_dio_actor(): fix iov_iter bugs")
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  fs/iomap/direct-io.c | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
> index 8e273408453a..6ec4940e019c 100644
> --- a/fs/iomap/direct-io.c
> +++ b/fs/iomap/direct-io.c
> @@ -442,9 +442,13 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
>  	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
>  	do {
>  		size_t n;
> -		if (dio->error) {
> -			iov_iter_revert(dio->submit.iter, copied);
> -			copied = ret = 0;
> +
> +		/*
> +		 * If completions already occurred and reported errors, give up now and
> +		 * don't bother submitting more bios.
> +		 */
> +		if (unlikely(data_race(dio->error))) {
> +			ret = 0;
>  			goto out;
>  		}
>  
> -- 
> 2.47.3
> 
>