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@kernel.dk>
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        Ming Lei <ming.lei@redhat.com>, Christoph Hellwig <hch@lst.de>
Subject: [PATCH V9 03/19] block: use bio_for_each_bvec() to compute multi-page bvec count
Date:   Tue, 13 Nov 2018 23:14:49 +0800
Message-Id: <20181113151505.15498-4-ming.lei@redhat.com>
In-Reply-To: <20181113151505.15498-1-ming.lei@redhat.com>
References: <20181113151505.15498-1-ming.lei@redhat.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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.

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-merge.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 76 insertions(+), 14 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 91b2af332a84..6f7deb94a23f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -160,6 +160,62 @@ 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)
+{
+	bool need_split = false;
+	unsigned len = bv->bv_len;
+	unsigned total_len = 0;
+	unsigned new_nsegs = 0, seg_size = 0;
+
+	if ((*nsegs >= queue_max_segments(q)) || !len)
+		return need_split;
+
+	/*
+	 * Multipage bvec may be too big to hold in one segment,
+	 * so the current bvec has to be splitted as multiple
+	 * segments.
+	 */
+	while (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 ((queue_virt_boundary(q) && ((bv->bv_offset +
+		    total_len) & queue_virt_boundary(q))) || !len)
+			break;
+	}
+
+	/* split in the middle of the bvec */
+	if (len)
+		need_split = true;
+
+	/* 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;
+
+	return need_split;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -173,7 +229,7 @@ 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.
@@ -188,8 +244,12 @@ 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;
 		}
@@ -214,11 +274,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		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;
 
 	}
 
@@ -296,6 +357,7 @@ 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;
 
@@ -316,7 +378,7 @@ 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
@@ -336,20 +398,20 @@ 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