Re: [PATCH v4 5/8] block: fail a short atomic pin in bio_iov_iter_get_pages()

[Tal Zussman]

On 9/22/26 6:16 AM, John Garry wrote:
> On 9/22/26 03:54, Tal Zussman wrote:
>> diff --git a/block/bio.c b/block/bio.c
>> index f95b63c0604a..14429a5d4e68 100644
>> --- a/block/bio.c
>> +++ b/block/bio.c
>> @@ -1285,6 +1285,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
>>   			   unsigned mem_align_mask, unsigned len_align_mask)
>>   {
>>   	iov_iter_extraction_t flags = 0;
>> +	int ret;
>>   
>>   	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
>>   		return -EIO;
>> @@ -1304,34 +1305,48 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
>>   		flags |= ITER_ALLOW_P2PDMA;
>>   
>>   	do {
>> -		ssize_t ret;
>> +		ssize_t size;
>>   
>> -		ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec,
>> +		size = iov_iter_extract_bvecs(iter, bio->bi_io_vec,
>>   				BIO_MAX_SIZE - bio->bi_iter.bi_size,
>>   				&bio->bi_vcnt, bio->bi_max_vecs,
>>   				mem_align_mask, flags);
>> -		if (ret <= 0) {
>> +		if (size <= 0) {
>>   			/*
>>   			 * A misaligned vector fails the whole I/O.  Release any
>>   			 * pages pinned by earlier iterations before returning
>>   			 * since this bio won't be submitted to release them.
>>   			 */
>> -			if (ret == -EINVAL) {
>> +			if (size == -EINVAL) {
> 
> *
> 
>>   				bio_release_pages(bio, false);
>>   				bio_clear_flag(bio, BIO_PAGE_PINNED);
>>   				bio->bi_vcnt = 0;
>>   			}
>>   			if (!bio->bi_vcnt)
>> -				return ret;
>> +				return size;
>>   			break;
>>   		}
>> -		bio->bi_iter.bi_size += ret;
>> +		bio->bi_iter.bi_size += size;
>>   	} while (iov_iter_count(iter) && !bio_full(bio, 0));
>>   
>>   	if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page))
>>   		bio->bi_opf |= REQ_NOMERGE;
>> -	return bio_iov_iter_align_down(bio, iter,
>> +	ret = bio_iov_iter_align_down(bio, iter,
>>   			&bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask);
>> +	if (ret)
>> +		return ret;
>> +
>> +	/*
>> +	 * An atomic write is submitted as a single bio, so it has to cover
>> +	 * the whole iterator or it would be torn.
>> +	 */
>> +	if ((bio->bi_opf & REQ_ATOMIC) && iov_iter_count(iter)) {
>> +		bio_release_pages(bio, false);
>> +		bio_clear_flag(bio, BIO_PAGE_PINNED);
>> +		bio->bi_vcnt = 0;
>> +		return -EINVAL;
> 
> There is some commonality here with iov_iter_extract_bvecs() failing,
> above *. You could add an error out label for both error scenarios.
> 

Will do!

> If that does not work:
> Reviewed-by: John Garry <john.garry@xxxxxxxxx>
> 
>> +	}
>> +	return 0;
>>   }
>>   
>>   static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size,
>> diff --git a/block/fops.c b/block/fops.c
>> index a3a709697b40..90777e8a9a6c 100644
>> --- a/block/fops.c
>> +++ b/block/fops.c
>> @@ -342,6 +342,12 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
>>   	bio->bi_end_io = blkdev_bio_end_io_async;
>>   	bio->bi_ioprio = iocb->ki_ioprio;
>>   
>> +	if (iocb->ki_flags & IOCB_ATOMIC)
>> +		bio->bi_opf |= REQ_ATOMIC;
>> +
>> +	if (iocb->ki_flags & IOCB_NOWAIT)
>> +		bio->bi_opf |= REQ_NOWAIT;
>> +
>>   	/*
>>   	 * Users don't rely on the iterator being in any particular
>>   	 * state for async I/O returning -EIOCBQUEUED, hence we can
>> @@ -371,12 +377,6 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
>>   			goto out_bio_put;
>>   	}
>>   
>> -	if (iocb->ki_flags & IOCB_ATOMIC)
>> -		bio->bi_opf |= REQ_ATOMIC;
>> -
>> -	if (iocb->ki_flags & IOCB_NOWAIT)
>> -		bio->bi_opf |= REQ_NOWAIT;
>> -
>>   	if (iocb->ki_flags & IOCB_HIPRI) {
>>   		bio->bi_opf |= REQ_POLLED;
>>   		submit_bio(bio);
>> 
>