diff --git a/block/blk-merge.c b/block/blk-merge.c
index cc7f6a4a255c..0f62c68b455c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -285,7 +285,8 @@ static struct bio *bio_split_rw(struct bio *bio, struct queue_limits *lim,
 		if (nsegs < lim->max_segments &&
 		    bytes + bv.bv_len <= max_bytes &&
 		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
-			nsegs++;
+			/* single-page bvec optimization */
+			nsegs += blk_segments(lim, bv.bv_len);
 			bytes += bv.bv_len;
 		} else {
 			if (bvec_split_segs(lim, &bv, &nsegs, &bytes,
@@ -533,7 +534,10 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 			    __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
 				goto next_bvec;
 
-			if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
+			if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE &&
+			    (!blk_queue_sub_page_limits(&q->limits) ||
+			     bvec.bv_len <= q->limits.max_segment_size))
+				/* single-segment bvec optimization */
 				nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
 			else
 				nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0e56e3e73019..276b0a6eaec5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2956,6 +2956,8 @@ void blk_mq_submit_bio(struct bio *bio)
 			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 			if (!bio)
 				return;
+		} else if (bio->bi_vcnt == 1) {
+			nr_segs = blk_segments(&q->limits, bio->bi_io_vec[0].bv_len);
 		}
 		if (!bio_integrity_prep(bio))
 			return;
@@ -2971,6 +2973,8 @@ void blk_mq_submit_bio(struct bio *bio)
 			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 			if (!bio)
 				goto fail;
+		} else if (bio->bi_vcnt == 1) {
+			nr_segs = blk_segments(&q->limits, bio->bi_io_vec[0].bv_len);
 		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
diff --git a/block/blk.h b/block/blk.h
index f6e59cd7cfa1..82143bf38064 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -337,13 +337,12 @@ static inline bool bio_may_exceed_limits(struct bio *bio,
 	}
 
 	/*
-	 * All drivers must accept single-segments bios that are <= PAGE_SIZE.
-	 * This is a quick and dirty check that relies on the fact that
-	 * bi_io_vec[0] is always valid if a bio has data.  The check might
-	 * lead to occasional false negatives when bios are cloned, but compared
-	 * to the performance impact of cloned bios themselves the loop below
-	 * doesn't matter anyway.
+	 * Check whether bio splitting should be performed. This check may
+	 * trigger the bio splitting code even if splitting is not necessary.
 	 */
+	if (blk_queue_sub_page_limits(lim) && bio->bi_io_vec &&
+	    bio->bi_io_vec->bv_len > lim->max_segment_size)
+		return true;
 	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
 		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
 }