block: optimize blk_bio_segment_split for single-page bvec

Introduce a fast path for single-page bvec IO, then we can avoid
to call bvec_split_segs() unnecessarily.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-merge.c

@@ -286,10 +286,16 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		bvprv = bv;
 		bvprvp = &bvprv;
 
-		if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
-				    &front_seg_size, &sectors))
+		if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+			nsegs++;
+			seg_size = bv.bv_len;
+			sectors += bv.bv_len >> 9;
+			if (nsegs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
+		} else if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
+				    &front_seg_size, &sectors)) {
 			goto split;
-
+		}
 	}
 
 	do_split = false;