diff --git a/block/blk-merge.c b/block/blk-merge.c
index f85d878f313d25deaf4851159dd05aa834f55d7f..4ef56b2d2aa563bfebc24f398bfeca8e46d3b776 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -161,6 +161,73 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return sectors;
 }
 
+static unsigned get_max_segment_size(struct request_queue *q,
+				     unsigned offset)
+{
+	unsigned long mask = queue_segment_boundary(q);
+
+	/* default segment boundary mask means no boundary limit */
+	if (mask == BLK_SEG_BOUNDARY_MASK)
+		return queue_max_segment_size(q);
+
+	return min_t(unsigned long, mask - (mask & offset) + 1,
+		     queue_max_segment_size(q));
+}
+
+/*
+ * 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;
+
+	/*
+	 * Multi-page 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 = get_max_segment_size(q, bv->bv_offset + total_len);
+		seg_size = min(seg_size, len);
+
+		new_nsegs++;
+		total_len += seg_size;
+		len -= seg_size;
+
+		if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
+			break;
+	}
+
+	if (!new_nsegs)
+		return !!len;
+
+	/* update front segment size */
+	if (!*nsegs) {
+		unsigned first_seg_size;
+
+		if (new_nsegs == 1)
+			first_seg_size = get_max_segment_size(q, bv->bv_offset);
+		else
+			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 +241,7 @@ 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 +256,12 @@ 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 +283,12 @@ 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 +302,6 @@ 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 +364,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	struct bio_vec bv, bvprv = { NULL };
 	int 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 +384,7 @@ 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 +404,15 @@ 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;
-
-			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;
+	fbio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bbio->bi_seg_back_size)
 		bbio->bi_seg_back_size = seg_size;