Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Ming Lei <ming.lei@redhat.com>
To:     Jens Axboe <axboe@fb.com>, Christoph Hellwig <hch@infradead.org>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Kent Overstreet <kent.overstreet@gmail.com>
Cc:     David Sterba <dsterba@suse.cz>, Huang Ying <ying.huang@intel.com>,
        linux-kernel@vger.kernel.org, linux-block@vger.kernel.org,
        linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
        Theodore Ts'o <tytso@mit.edu>,
        "Darrick J . Wong" <darrick.wong@oracle.com>,
        Coly Li <colyli@suse.de>, Filipe Manana <fdmanana@gmail.com>,
        Randy Dunlap <rdunlap@infradead.org>,
        Ming Lei <ming.lei@redhat.com>
Subject: [PATCH V6 07/30] block: use bio_for_each_chunk() to map sg
Date:   Sat,  9 Jun 2018 20:29:51 +0800
Message-Id: <20180609123014.8861-8-ming.lei@redhat.com>
In-Reply-To: <20180609123014.8861-1-ming.lei@redhat.com>
References: <20180609123014.8861-1-ming.lei@redhat.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

It is more efficient to use bio_for_each_chunk() to map sg, meantime
we have to consider splitting multipage bvec as done in blk_bio_segment_split().

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 2493fe027953..044db0fa2f89 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -424,6 +424,56 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	return 0;
 }
 
+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,
@@ -444,25 +494,7 @@ __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;
 }
@@ -484,7 +516,7 @@ 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_chunk(bvec, bio, iter)
 			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
 					     &nsegs, &cluster);
 
-- 
2.9.5