From 862e5a5e6fa2c7fd514c179e9ceea27a49a3327f Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 15 Feb 2019 19:13:13 +0800
Subject: [PATCH] block: use bio_for_each_bvec() to map sg

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().

Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 70 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 50 insertions(+), 20 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4ef56b2d2aa5..1912499b08b7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -464,6 +464,54 @@ 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;
+
+	/*
+	 * 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, offset = 0;
+
+	while (nbytes > 0) {
+		unsigned seg_size;
+		struct page *pg;
+		unsigned idx;
+
+		*sg = blk_next_sg(sg, sglist);
+
+		seg_size = get_max_segment_size(q, bvec->bv_offset + total);
+		seg_size = min(nbytes, seg_size);
+
+		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,
@@ -481,25 +529,7 @@ __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;
 }
@@ -521,7 +551,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	int 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);