linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Keith Busch <kbusch@fb.com>
Cc: linux-fsdevel@vger.kernel.org, linux-block@vger.kernel.org,
	axboe@kernel.dk, Kernel Team <Kernel-team@fb.com>,
	hch@lst.de, bvanassche@acm.org, damien.lemoal@opensource.wdc.com,
	ebiggers@kernel.org, Keith Busch <kbusch@kernel.org>
Subject: Re: [PATCHv3 6/6] block: relax direct io memory alignment
Date: Tue, 24 May 2022 08:12:44 +0200	[thread overview]
Message-ID: <20220524061244.GF24737@lst.de> (raw)
In-Reply-To: <20220523210119.2500150-7-kbusch@fb.com>

On Mon, May 23, 2022 at 02:01:19PM -0700, Keith Busch wrote:
>   Removed iomap support for now

Do you plan to add a separate patch for it?  It would be a shame to
miss it especially as you said you already tested xfs.

> +	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;
>  	ssize_t size, left;
> @@ -1219,7 +1220,19 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>  	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
>  	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
>  
> +	/*
> +	 * Each segment in the iov is required to be a block size multiple.
> +	 * However, we may not be able to get the entire segment if it spans
> +	 * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the
> +	 * result to ensure the bio's total size is correct. The remainder of
> +	 * the iov data will be picked up in the next bio iteration.
> +	 *
> +	 * If the result is ever 0, that indicates the iov fails the segment
> +	 * size requirement and is an error.
> +	 */
>  	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
> +	if (size > 0)
> +		size = ALIGN_DOWN(size, queue_logical_block_size(q));

I think we can simply use bdev_logical_block_size here and remove the need
for the q local variable.

Given that bio_iov_iter_get_pages is used by more than the block device
direct I/O code maybe split this up further?

> @@ -42,6 +42,16 @@ static unsigned int dio_bio_write_op(struct kiocb *iocb)
>  	return op;
>  }
>  
> +static int blkdev_dio_aligned(struct block_device *bdev, loff_t pos,
> +			      struct iov_iter *iter)
> +{
> +	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;
> +	return 0;
> +}

I'd also split adding this helper into another prep patch to see
the actual change in behavior more easily.

  reply	other threads:[~2022-05-24  6:12 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-23 21:01 [PATCHv3 0/6] direct io dma alignment Keith Busch
2022-05-23 21:01 ` [PATCHv3 1/6] block/bio: remove duplicate append pages code Keith Busch
2022-05-24  6:00   ` Christoph Hellwig
2022-05-24  6:24   ` Johannes Thumshirn
2022-05-24 14:17   ` Pankaj Raghav
2022-05-24 15:38     ` Keith Busch
2022-05-25  7:49       ` Pankaj Raghav
2022-05-25  8:30         ` Damien Le Moal
2022-05-25 13:37         ` Keith Busch
2022-05-25 14:25           ` Pankaj Raghav
2022-05-23 21:01 ` [PATCHv3 2/6] block: export dma_alignment attribute Keith Busch
2022-05-24  6:02   ` Christoph Hellwig
2022-05-24  6:24   ` Johannes Thumshirn
2022-05-23 21:01 ` [PATCHv3 3/6] block: introduce bdev_dma_alignment helper Keith Busch
2022-05-24  6:02   ` Christoph Hellwig
2022-05-24  6:25   ` Johannes Thumshirn
2022-05-23 21:01 ` [PATCHv3 4/6] block/merge: count bytes instead of sectors Keith Busch
2022-05-24  6:07   ` Christoph Hellwig
2022-05-23 21:01 ` [PATCHv3 5/6] block/bounce: " Keith Busch
2022-05-24  6:09   ` Christoph Hellwig
2022-05-25 14:08     ` Keith Busch
2022-05-25 14:17       ` Keith Busch
2022-05-24 14:32   ` Pankaj Raghav
2022-05-23 21:01 ` [PATCHv3 6/6] block: relax direct io memory alignment Keith Busch
2022-05-24  6:12   ` Christoph Hellwig [this message]
2022-05-24 15:19   ` Pankaj Raghav

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220524061244.GF24737@lst.de \
    --to=hch@lst.de \
    --cc=Kernel-team@fb.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=damien.lemoal@opensource.wdc.com \
    --cc=ebiggers@kernel.org \
    --cc=kbusch@fb.com \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).