All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	Bart Van Assche <bvanassche@acm.org>,
	Ming Lei <ming.lei@redhat.com>, Keith Busch <kbusch@kernel.org>
Subject: [PATCH 06/10] block: Fix the number of segment calculations
Date: Wed, 19 Oct 2022 15:23:20 -0700	[thread overview]
Message-ID: <20221019222324.362705-7-bvanassche@acm.org> (raw)
In-Reply-To: <20221019222324.362705-1-bvanassche@acm.org>

Since multi-page bvecs are supported there can be multiple segments per
bvec (see also bvec_split_segs()). Hence this patch that calculates the
number of segments per bvec instead of assuming that there is only one
segment per bvec.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 block/blk-map.c | 14 +++++++++++++-
 block/blk-mq.c  |  2 ++
 block/blk.h     |  3 +++
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 4505307d758e..2976a8d68992 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -529,6 +529,18 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data,
 	return ERR_PTR(-ENOMEM);
 }
 
+/* Number of DMA segments required to transfer @bytes data. */
+unsigned int blk_segments(const struct queue_limits *limits, unsigned int bytes)
+{
+	const unsigned int mss = limits->max_segment_size;
+
+	if (bytes <= mss)
+		return 1;
+	if (is_power_of_2(mss))
+		return round_up(bytes, mss) >> ilog2(mss);
+	return (bytes + mss - 1) / mss;
+}
+
 /*
  * Append a bio to a passthrough request.  Only works if the bio can be merged
  * into the request based on the driver constraints.
@@ -540,7 +552,7 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio)
 	unsigned int nr_segs = 0;
 
 	bio_for_each_bvec(bv, bio, iter)
-		nr_segs++;
+		nr_segs += blk_segments(&rq->q->limits, bv.bv_len);
 
 	if (!rq->bio) {
 		blk_rq_bio_prep(rq, bio, nr_segs);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8070b6c10e8d..82ae8099afdd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2883,6 +2883,8 @@ void blk_mq_submit_bio(struct bio *bio)
 	bio = blk_queue_bounce(bio, q);
 	if (bio_may_exceed_limits(bio, &q->limits))
 		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+	else if (bio->bi_vcnt == 1)
+		nr_segs = blk_segments(&q->limits, bio->bi_io_vec[0].bv_len);
 
 	if (!bio_integrity_prep(bio))
 		return;
diff --git a/block/blk.h b/block/blk.h
index 7f9e089ab1f7..342ba7d86e87 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -81,6 +81,9 @@ struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs);
 
+unsigned int blk_segments(const struct queue_limits *limits,
+			  unsigned int bytes);
+
 static inline bool biovec_phys_mergeable(struct request_queue *q,
 		struct bio_vec *vec1, struct bio_vec *vec2)
 {

  parent reply	other threads:[~2022-10-19 22:23 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-19 22:23 [PATCH 00/10] Support DMA segments smaller than the page size Bart Van Assche
2022-10-19 22:23 ` [PATCH 01/10] block: Remove request.write_hint Bart Van Assche
2022-10-21  1:59   ` Ming Lei
2022-10-19 22:23 ` [PATCH 02/10] block: Constify most queue limits pointers Bart Van Assche
2022-10-21  2:01   ` Ming Lei
2022-10-19 22:23 ` [PATCH 03/10] block: Micro-optimize get_max_segment_size() Bart Van Assche
2022-10-21  2:17   ` Ming Lei
2022-10-19 22:23 ` [PATCH 04/10] block: Add support for small segments in blk_rq_map_user_iov() Bart Van Assche
2022-10-19 22:23 ` [PATCH 05/10] block: Introduce QUEUE_FLAG_SUB_PAGE_SEGMENTS Bart Van Assche
2022-10-19 22:23 ` Bart Van Assche [this message]
2022-11-01 17:23   ` [PATCH 06/10] block: Fix the number of segment calculations Bart Van Assche
2022-11-02  1:22     ` Ming Lei
2022-11-03 19:32       ` Bart Van Assche
2022-10-19 22:23 ` [PATCH 07/10] block: Add support for segments smaller than the page size Bart Van Assche
2022-10-19 22:23 ` [PATCH 08/10] scsi: core: Set the SUB_PAGE_SEGMENTS request queue flag Bart Van Assche
2022-10-19 22:23 ` [PATCH 09/10] scsi_debug: Support configuring the maximum segment size Bart Van Assche
2022-10-19 22:23 ` [PATCH 10/10] null_blk: " Bart Van Assche
2022-10-20 23:13   ` Damien Le Moal
2022-10-20 23:34     ` Bart Van Assche
2022-10-20 23:39       ` Damien Le Moal
2022-10-21  0:39         ` Bart Van Assche

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=20221019222324.362705-7-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=ming.lei@redhat.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.