> @@ -1207,6 +1207,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
> {
> unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
> unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
> + struct request_queue *q = bdev_get_queue(bio->bi_bdev);
> struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
> struct page **pages = (struct page **)bv;
> bool same_page = false;
> @@ -1223,6 +1224,8 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
> pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
>
> size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
> + if (size > 0)
> + size = ALIGN_DOWN(size, queue_logical_block_size(q));
So if we do get a size that is not logical block size alignment here,
we reduce it to the block size aligned one below. Why do we do that?
> + if ((pos | iov_iter_count(iter)) & (bdev_logical_block_size(bdev) - 1))
> + return -EINVAL;
> + if (iov_iter_alignment(iter) & bdev_dma_alignment(bdev))
> return -EINVAL;
Can we have a little inline helper for these checks instead of
duplicating them three times?
> diff --git a/fs/direct-io.c b/fs/direct-io.c
> index 840752006f60..64cc176be60c 100644
> --- a/fs/direct-io.c
> +++ b/fs/direct-io.c
> @@ -1131,7 +1131,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
> struct dio_submit sdio = { 0, };
> struct buffer_head map_bh = { 0, };
> struct blk_plug plug;
> - unsigned long align = offset | iov_iter_alignment(iter);
> + unsigned long align = iov_iter_alignment(iter);
I'd much prefer to not just relax this for random file systems,
and especially not the legacy direct I/O code. I think we can eventually
do iomap, but only after an audit and test of each file system, which
might require a new IOMAP_DIO_* flag at least initially.
> +static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
> +{
> + return queue_dma_alignment(bdev_get_queue(bdev));
> +}
Plase do this in a separate patch.
