public inbox for [email protected]
 help / color / mirror / Atom feed
From: Anuj Gupta <[email protected]>
To: Christoph Hellwig <[email protected]>
Cc: Kanchan Joshi <[email protected]>,
	[email protected], [email protected], [email protected],
	[email protected], [email protected],
	[email protected]
Subject: Re: [PATCH for-next v10 6/7] block: extend functionality to map bvec iterator
Date: Thu, 29 Sep 2022 17:03:45 +0530	[thread overview]
Message-ID: <20220929113345.GC27633@test-zns> (raw)
In-Reply-To: <[email protected]>

[-- Attachment #1: Type: text/plain, Size: 4404 bytes --]

On Wed, Sep 28, 2022 at 07:40:39PM +0200, Christoph Hellwig wrote:
> On Tue, Sep 27, 2022 at 11:06:09PM +0530, Kanchan Joshi wrote:
> > Extend blk_rq_map_user_iov so that it can handle bvec iterator.
> > It  maps the pages from bvec iterator into a bio and place the bio into
> > request.
> > 
> > This helper will be used by nvme for uring-passthrough path when IO is
> > done using pre-mapped buffers.
> 
> Can we avoid duplicating some of the checks?  Something like the below
> incremental patch.  Note that this now also allows the copy path for
> all kinds of iov_iters, but as the copy from/to iter code is safe
> and the sanity check was just or the map path that should be fine.
> It's best split into a prep patch, though.

Right, this one looks way better. Will fold this in a separate prep patch.

> 
> ---
> diff --git a/block/blk-map.c b/block/blk-map.c
> index a1aa8dacb02bc..c51de30767403 100644
> --- a/block/blk-map.c
> +++ b/block/blk-map.c
> @@ -549,26 +549,16 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio)
>  EXPORT_SYMBOL(blk_rq_append_bio);
>  
>  /* Prepare bio for passthrough IO given ITER_BVEC iter */
> -static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter,
> -				bool *copy)
> +static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
>  {
>  	struct request_queue *q = rq->q;
> -	size_t nr_iter, nr_segs, i;
> -	struct bio *bio = NULL;
> -	struct bio_vec *bv, *bvecs, *bvprvp = NULL;
> +	size_t nr_iter = iov_iter_count(iter);
> +	size_t nr_segs = iter->nr_segs;
> +	struct bio_vec *bvecs, *bvprvp = NULL;
>  	struct queue_limits *lim = &q->limits;
>  	unsigned int nsegs = 0, bytes = 0;
> -	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
> -
> -	/* see if we need to copy pages due to any weird situation */
> -	if (blk_queue_may_bounce(q))
> -		goto out_copy;
> -	else if (iov_iter_alignment(iter) & align)
> -		goto out_copy;
> -	/* virt-alignment gap is checked anyway down, so avoid extra loop here */
> -
> -	nr_iter = iov_iter_count(iter);
> -	nr_segs = iter->nr_segs;
> +	struct bio *bio;
> +	size_t i;
>  
>  	if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q))
>  		return -EINVAL;
> @@ -586,14 +576,15 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter,
>  	/* loop to perform a bunch of sanity checks */
>  	bvecs = (struct bio_vec *)iter->bvec;
>  	for (i = 0; i < nr_segs; i++) {
> -		bv = &bvecs[i];
> +		struct bio_vec *bv = &bvecs[i];
> +
>  		/*
>  		 * If the queue doesn't support SG gaps and adding this
>  		 * offset would create a gap, fallback to copy.
>  		 */
>  		if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) {
>  			bio_map_put(bio);
> -			goto out_copy;
> +			return -EREMOTEIO;
>  		}
>  		/* check full condition */
>  		if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
> @@ -611,9 +602,6 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter,
>  put_bio:
>  	bio_map_put(bio);
>  	return -EINVAL;
> -out_copy:
> -	*copy = true;
> -	return 0;
>  }
>  
>  /**
> @@ -635,33 +623,35 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
>  			struct rq_map_data *map_data,
>  			const struct iov_iter *iter, gfp_t gfp_mask)
>  {
> -	bool copy = false;
> +	bool copy = false, map_bvec = false;
>  	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
>  	struct bio *bio = NULL;
>  	struct iov_iter i;
>  	int ret = -EINVAL;
>  
> -	if (iov_iter_is_bvec(iter)) {
> -		ret = blk_rq_map_user_bvec(rq, iter, &copy);
> -		if (ret != 0)
> -			goto fail;
> -		if (copy)
> -			goto do_copy;
> -		return ret;
> -	}
> -	if (!iter_is_iovec(iter))
> -		goto fail;
> -
>  	if (map_data)
>  		copy = true;
>  	else if (blk_queue_may_bounce(q))
>  		copy = true;
>  	else if (iov_iter_alignment(iter) & align)
>  		copy = true;
> +	else if (iov_iter_is_bvec(iter))
> +		map_bvec = true;
> +	else if (!iter_is_iovec(iter))
> +		copy = true;
>  	else if (queue_virt_boundary(q))
>  		copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter);
>  
> -do_copy:
> +	if (map_bvec) {
> +		ret = blk_rq_map_user_bvec(rq, iter);
> +		if (!ret)
> +			return 0;
> +		if (ret != -EREMOTEIO)
> +			goto fail;
> +		/* fall back to copying the data on limits mismatches */
> +		copy = true;
> +	}
> +
>  	i = *iter;
>  	do {
>  		if (copy)
> 

--
Anuj Gupta


[-- Attachment #2: Type: text/plain, Size: 0 bytes --]



  reply	other threads:[~2022-09-29 11:50 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20220927174622epcas5p1685c0f97a7ee2ee13ba25f5fb58dff00@epcas5p1.samsung.com>
2022-09-27 17:36 ` [PATCH for-next v10 0/7] Fixed-buffer for uring-cmd/passthru Kanchan Joshi
     [not found]   ` <CGME20220927174626epcas5p4002acda6f0578ee314ee5e611b8d6662@epcas5p4.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 1/7] io_uring: add io_uring_cmd_import_fixed Kanchan Joshi
     [not found]   ` <CGME20220927174628epcas5p21beda845f26eedeb538cb67e286954d4@epcas5p2.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 2/7] io_uring: introduce fixed buffer support for io_uring_cmd Kanchan Joshi
     [not found]   ` <CGME20220927174631epcas5p12cd6ffbd7dad819b0af75733ce6cdd2c@epcas5p1.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 3/7] nvme: refactor nvme_add_user_metadata Kanchan Joshi
2022-09-28 17:18       ` Christoph Hellwig
2022-09-29 11:28         ` Anuj Gupta
     [not found]   ` <CGME20220927174633epcas5p4d492bdebde981e2c019e30c47cf00869@epcas5p4.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 4/7] nvme: refactor nvme_alloc_request Kanchan Joshi
2022-09-28 17:19       ` Christoph Hellwig
2022-09-29 11:30         ` Anuj Gupta
     [not found]   ` <CGME20220927174636epcas5p49008baa36dcbf2f61c25ba89c4707c0c@epcas5p4.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 5/7] block: factor out bio_map_get helper Kanchan Joshi
2022-09-28 17:31       ` Christoph Hellwig
2022-09-28 17:49         ` Jens Axboe
2022-09-28 17:53           ` Jens Axboe
2022-09-29 11:34         ` Anuj Gupta
     [not found]   ` <CGME20220927174639epcas5p22b46aed144d81d82b2a9b9de586808ac@epcas5p2.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 6/7] block: extend functionality to map bvec iterator Kanchan Joshi
2022-09-28 17:40       ` Christoph Hellwig
2022-09-29 11:33         ` Anuj Gupta [this message]
     [not found]   ` <CGME20220927174642epcas5p1dafa31776d4eb8180e18f149ed25640c@epcas5p1.samsung.com>
2022-09-27 17:36     ` [PATCH for-next v10 7/7] nvme: wire up fixed buffer support for nvme passthrough Kanchan Joshi
2022-09-28 17:59       ` Christoph Hellwig
2022-09-29 11:36         ` Anuj Gupta
2022-09-28 14:28   ` [PATCH for-next v10 0/7] Fixed-buffer for uring-cmd/passthru Jens Axboe
2022-09-28 17:12     ` Christoph Hellwig
2022-09-28 17:13       ` Jens Axboe

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=20220929113345.GC27633@test-zns \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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