[PATCH V11 04/19] block: use bio_for_each_bvec() to compute multi-page bvec count

[Ming Lei <ming.lei@redhat.com>]

First it is more efficient to use bio_for_each_bvec() in both
blk_bio_segment_split() and __blk_recalc_rq_segments() to compute how
many multi-page bvecs there are in the bio.

Secondly once bio_for_each_bvec() is used, the bvec may need to be
splitted because its length can be very longer than max segment size,
so we have to split the big bvec into several segments.

Thirdly when splitting multi-page bvec into segments, the max segment
limit may be reached, so the bio split need to be considered under
this situation too.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-merge.c | 87 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 68 insertions(+), 19 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index f52400ce2187..ec0b93fa1ff8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -161,6 +161,54 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return sectors;
 }
 
+/*
+ * Split the bvec @bv into segments, and update all kinds of
+ * variables.
+ */
+static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
+		unsigned *nsegs, unsigned *last_seg_size,
+		unsigned *front_seg_size, unsigned *sectors)
+{
+	unsigned len = bv->bv_len;
+	unsigned total_len = 0;
+	unsigned new_nsegs = 0, seg_size = 0;
+
+	/*
+	 * Multipage bvec may be too big to hold in one segment,
+	 * so the current bvec has to be splitted as multiple
+	 * segments.
+	 */
+	while (len && new_nsegs + *nsegs < queue_max_segments(q)) {
+		seg_size = min(queue_max_segment_size(q), len);
+
+		new_nsegs++;
+		total_len += seg_size;
+		len -= seg_size;
+
+		if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
+			break;
+	}
+
+	/* update front segment size */
+	if (!*nsegs) {
+		unsigned first_seg_size = seg_size;
+
+		if (new_nsegs > 1)
+			first_seg_size = queue_max_segment_size(q);
+		if (*front_seg_size < first_seg_size)
+			*front_seg_size = first_seg_size;
+	}
+
+	/* update other varibles */
+	*last_seg_size = seg_size;
+	*nsegs += new_nsegs;
+	if (sectors)
+		*sectors += total_len >> 9;
+
+	/* split in the middle of the bvec if len != 0 */
+	return !!len;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -174,7 +222,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
 
-	bio_for_each_segment(bv, bio, iter) {
+	bio_for_each_bvec(bv, bio, iter) {
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -189,8 +237,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			 */
 			if (nsegs < queue_max_segments(q) &&
 			    sectors < max_sectors) {
-				nsegs++;
-				sectors = max_sectors;
+				/* split in the middle of bvec */
+				bv.bv_len = (max_sectors - sectors) << 9;
+				bvec_split_segs(q, &bv, &nsegs,
+						&seg_size,
+						&front_seg_size,
+						&sectors);
 			}
 			goto split;
 		}
@@ -212,14 +264,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (nsegs == queue_max_segments(q))
 			goto split;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
-
-		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
-		seg_size = bv.bv_len;
-		sectors += bv.bv_len >> 9;
+
+		if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
+				    &front_seg_size, &sectors))
+			goto split;
 
 	}
 
@@ -233,8 +283,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bio = new;
 	}
 
-	if (nsegs == 1 && seg_size > front_seg_size)
-		front_seg_size = seg_size;
 	bio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bio->bi_seg_back_size)
 		bio->bi_seg_back_size = seg_size;
@@ -297,6 +345,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	struct bio_vec bv, bvprv = { NULL };
 	int cluster, prev = 0;
 	unsigned int seg_size, nr_phys_segs;
+	unsigned front_seg_size = bio->bi_seg_front_size;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
 
@@ -317,7 +366,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, iter) {
+		bio_for_each_bvec(bv, bio, iter) {
 			/*
 			 * If SG merging is disabled, each bio vector is
 			 * a segment
@@ -337,20 +386,20 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 				continue;
 			}
 new_segment:
-			if (nr_phys_segs == 1 && seg_size >
-			    fbio->bi_seg_front_size)
-				fbio->bi_seg_front_size = seg_size;
+			if (nr_phys_segs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
 
-			nr_phys_segs++;
 			bvprv = bv;
 			prev = 1;
-			seg_size = bv.bv_len;
+			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
+					&front_seg_size, NULL);
 		}
 		bbio = bio;
 	}
 
-	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
-		fbio->bi_seg_front_size = seg_size;
+	if (nr_phys_segs == 1 && seg_size > front_seg_size)
+		front_seg_size = seg_size;
+	fbio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bbio->bi_seg_back_size)
 		bbio->bi_seg_back_size = seg_size;
 
-- 
2.9.5