[V10,04/19] block: use bio_for_each_bvec() to map sg
diff mbox series

Message ID 20181115085306.9910-5-ming.lei@redhat.com
State New
Headers show
Series
  • block: support multi-page bvec
Related show

Commit Message

Ming Lei Nov. 15, 2018, 8:52 a.m. UTC
It is more efficient to use bio_for_each_bvec() to map sg, meantime
we have to consider splitting multipage bvec as done in blk_bio_segment_split().

Cc: Dave Chinner <dchinner@redhat.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: Shaohua Li <shli@kernel.org>
Cc: linux-raid@vger.kernel.org
Cc: linux-erofs@lists.ozlabs.org
Cc: David Sterba <dsterba@suse.com>
Cc: linux-btrfs@vger.kernel.org
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: linux-xfs@vger.kernel.org
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: linux-ext4@vger.kernel.org
Cc: Coly Li <colyli@suse.de>
Cc: linux-bcache@vger.kernel.org
Cc: Boaz Harrosh <ooo@electrozaur.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: cluster-devel@redhat.com
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-merge.c | 72 +++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 52 insertions(+), 20 deletions(-)

Comments

Omar Sandoval Nov. 15, 2018, 10:33 p.m. UTC | #1
On Thu, Nov 15, 2018 at 04:52:51PM +0800, Ming Lei wrote:
> It is more efficient to use bio_for_each_bvec() to map sg, meantime
> we have to consider splitting multipage bvec as done in blk_bio_segment_split().
> 
> Cc: Dave Chinner <dchinner@redhat.com>
> Cc: Kent Overstreet <kent.overstreet@gmail.com>
> Cc: Mike Snitzer <snitzer@redhat.com>
> Cc: dm-devel@redhat.com
> Cc: Alexander Viro <viro@zeniv.linux.org.uk>
> Cc: linux-fsdevel@vger.kernel.org
> Cc: Shaohua Li <shli@kernel.org>
> Cc: linux-raid@vger.kernel.org
> Cc: linux-erofs@lists.ozlabs.org
> Cc: David Sterba <dsterba@suse.com>
> Cc: linux-btrfs@vger.kernel.org
> Cc: Darrick J. Wong <darrick.wong@oracle.com>
> Cc: linux-xfs@vger.kernel.org
> Cc: Gao Xiang <gaoxiang25@huawei.com>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Theodore Ts'o <tytso@mit.edu>
> Cc: linux-ext4@vger.kernel.org
> Cc: Coly Li <colyli@suse.de>
> Cc: linux-bcache@vger.kernel.org
> Cc: Boaz Harrosh <ooo@electrozaur.com>
> Cc: Bob Peterson <rpeterso@redhat.com>
> Cc: cluster-devel@redhat.com

Reviewed-by: Omar Sandoval <osandov@fb.com>

> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
>  block/blk-merge.c | 72 +++++++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 52 insertions(+), 20 deletions(-)
> 
> diff --git a/block/blk-merge.c b/block/blk-merge.c
> index 6f7deb94a23f..cb9f49bcfd36 100644
> --- a/block/blk-merge.c
> +++ b/block/blk-merge.c
> @@ -473,6 +473,56 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
>  	return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
>  }
>  
> +static struct scatterlist *blk_next_sg(struct scatterlist **sg,
> +		struct scatterlist *sglist)
> +{
> +	if (!*sg)
> +		return sglist;
> +	else {
> +		/*
> +		 * If the driver previously mapped a shorter
> +		 * list, we could see a termination bit
> +		 * prematurely unless it fully inits the sg
> +		 * table on each mapping. We KNOW that there
> +		 * must be more entries here or the driver
> +		 * would be buggy, so force clear the
> +		 * termination bit to avoid doing a full
> +		 * sg_init_table() in drivers for each command.
> +		 */
> +		sg_unmark_end(*sg);
> +		return sg_next(*sg);
> +	}
> +}
> +
> +static unsigned blk_bvec_map_sg(struct request_queue *q,
> +		struct bio_vec *bvec, struct scatterlist *sglist,
> +		struct scatterlist **sg)
> +{
> +	unsigned nbytes = bvec->bv_len;
> +	unsigned nsegs = 0, total = 0;
> +
> +	while (nbytes > 0) {
> +		unsigned seg_size;
> +		struct page *pg;
> +		unsigned offset, idx;
> +
> +		*sg = blk_next_sg(sg, sglist);
> +
> +		seg_size = min(nbytes, queue_max_segment_size(q));
> +		offset = (total + bvec->bv_offset) % PAGE_SIZE;
> +		idx = (total + bvec->bv_offset) / PAGE_SIZE;
> +		pg = nth_page(bvec->bv_page, idx);
> +
> +		sg_set_page(*sg, pg, seg_size, offset);
> +
> +		total += seg_size;
> +		nbytes -= seg_size;
> +		nsegs++;
> +	}
> +
> +	return nsegs;
> +}
> +
>  static inline void
>  __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
>  		     struct scatterlist *sglist, struct bio_vec *bvprv,
> @@ -490,25 +540,7 @@ __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
>  		(*sg)->length += nbytes;
>  	} else {
>  new_segment:
> -		if (!*sg)
> -			*sg = sglist;
> -		else {
> -			/*
> -			 * If the driver previously mapped a shorter
> -			 * list, we could see a termination bit
> -			 * prematurely unless it fully inits the sg
> -			 * table on each mapping. We KNOW that there
> -			 * must be more entries here or the driver
> -			 * would be buggy, so force clear the
> -			 * termination bit to avoid doing a full
> -			 * sg_init_table() in drivers for each command.
> -			 */
> -			sg_unmark_end(*sg);
> -			*sg = sg_next(*sg);
> -		}
> -
> -		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
> -		(*nsegs)++;
> +		(*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg);
>  	}
>  	*bvprv = *bvec;
>  }
> @@ -530,7 +562,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
>  	int cluster = blk_queue_cluster(q), nsegs = 0;
>  
>  	for_each_bio(bio)
> -		bio_for_each_segment(bvec, bio, iter)
> +		bio_for_each_bvec(bvec, bio, iter)
>  			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
>  					     &nsegs, &cluster);
>  
> -- 
> 2.9.5
>
Christoph Hellwig Nov. 16, 2018, 1:33 p.m. UTC | #2
> +	if (!*sg)
> +		return sglist;
> +	else {

No need for an else after an early return.
Ming Lei Nov. 19, 2018, 7:51 a.m. UTC | #3
On Fri, Nov 16, 2018 at 02:33:14PM +0100, Christoph Hellwig wrote:
> > +	if (!*sg)
> > +		return sglist;
> > +	else {
> 
> No need for an else after an early return.

OK, good catch!

Thanks,
Ming

Patch
diff mbox series

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 6f7deb94a23f..cb9f49bcfd36 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -473,6 +473,56 @@  static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
 }
 
+static struct scatterlist *blk_next_sg(struct scatterlist **sg,
+		struct scatterlist *sglist)
+{
+	if (!*sg)
+		return sglist;
+	else {
+		/*
+		 * If the driver previously mapped a shorter
+		 * list, we could see a termination bit
+		 * prematurely unless it fully inits the sg
+		 * table on each mapping. We KNOW that there
+		 * must be more entries here or the driver
+		 * would be buggy, so force clear the
+		 * termination bit to avoid doing a full
+		 * sg_init_table() in drivers for each command.
+		 */
+		sg_unmark_end(*sg);
+		return sg_next(*sg);
+	}
+}
+
+static unsigned blk_bvec_map_sg(struct request_queue *q,
+		struct bio_vec *bvec, struct scatterlist *sglist,
+		struct scatterlist **sg)
+{
+	unsigned nbytes = bvec->bv_len;
+	unsigned nsegs = 0, total = 0;
+
+	while (nbytes > 0) {
+		unsigned seg_size;
+		struct page *pg;
+		unsigned offset, idx;
+
+		*sg = blk_next_sg(sg, sglist);
+
+		seg_size = min(nbytes, queue_max_segment_size(q));
+		offset = (total + bvec->bv_offset) % PAGE_SIZE;
+		idx = (total + bvec->bv_offset) / PAGE_SIZE;
+		pg = nth_page(bvec->bv_page, idx);
+
+		sg_set_page(*sg, pg, seg_size, offset);
+
+		total += seg_size;
+		nbytes -= seg_size;
+		nsegs++;
+	}
+
+	return nsegs;
+}
+
 static inline void
 __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 		     struct scatterlist *sglist, struct bio_vec *bvprv,
@@ -490,25 +540,7 @@  __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 		(*sg)->length += nbytes;
 	} else {
 new_segment:
-		if (!*sg)
-			*sg = sglist;
-		else {
-			/*
-			 * If the driver previously mapped a shorter
-			 * list, we could see a termination bit
-			 * prematurely unless it fully inits the sg
-			 * table on each mapping. We KNOW that there
-			 * must be more entries here or the driver
-			 * would be buggy, so force clear the
-			 * termination bit to avoid doing a full
-			 * sg_init_table() in drivers for each command.
-			 */
-			sg_unmark_end(*sg);
-			*sg = sg_next(*sg);
-		}
-
-		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
-		(*nsegs)++;
+		(*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg);
 	}
 	*bvprv = *bvec;
 }
@@ -530,7 +562,7 @@  static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	int cluster = blk_queue_cluster(q), nsegs = 0;
 
 	for_each_bio(bio)
-		bio_for_each_segment(bvec, bio, iter)
+		bio_for_each_bvec(bvec, bio, iter)
 			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
 					     &nsegs, &cluster);