block: avoid blk_bio_segment_split for small I/O operations

__blk_queue_split() adds significant overhead for small I/O operations.
Add a shortcut to avoid it for cases where we know we never need to
split.

Based on a patch from Ming Lei.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-merge.c

@@ -293,7 +293,7 @@ split:
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
-	struct bio *split;
+	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
@@ -309,6 +309,20 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 				nr_segs);
 		break;
 	default:
+		/*
+		 * 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.
+		 */
+		if (!q->limits.chunk_sectors &&
+		    (*bio)->bi_vcnt == 1 &&
+		    (*bio)->bi_io_vec[0].bv_len <= PAGE_SIZE) {
+			*nr_segs = 1;
+			break;
+		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}