block: handle fast path of bio splitting inline

The fast path is no splitting needed. Separate the handling into a
check part we can inline, and an out-of-line handling path if we do
need to split.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-merge.c

@@ -324,6 +324,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
 /**
  * __blk_queue_split - split a bio and submit the second half
+ * @q:       [in] request_queue new bio is being queued at
  * @bio:     [in, out] bio to be split
  * @nr_segs: [out] number of segments in the first bio
  *
@@ -334,9 +335,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
  * of the caller to ensure that q->bio_split is only released after processing
  * of the split bio has finished.
  */
-void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
+void __blk_queue_split(struct request_queue *q, struct bio **bio,
+		       unsigned int *nr_segs)
 {
-	struct request_queue *q = (*bio)->bi_bdev->bd_disk->queue;
 	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
@@ -353,21 +354,6 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
 				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 +
-		     (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) {
-			*nr_segs = 1;
-			break;
-		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}
@@ -397,9 +383,11 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
  */
 void blk_queue_split(struct bio **bio)
 {
+	struct request_queue *q = (*bio)->bi_bdev->bd_disk->queue;
 	unsigned int nr_segs;
 
-	__blk_queue_split(bio, &nr_segs);
+	if (blk_may_split(q, *bio))
+		__blk_queue_split(q, bio, &nr_segs);
 }
 EXPORT_SYMBOL(blk_queue_split);
 

block/blk-mq.c

@@ -2259,11 +2259,12 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct request *rq;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
-	unsigned int nr_segs;
+	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
 	blk_queue_bounce(q, &bio);
-	__blk_queue_split(&bio, &nr_segs);
+	if (blk_may_split(q, bio))
+		__blk_queue_split(q, &bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
 		goto queue_exit;

block/blk.h

@@ -266,7 +266,32 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
 
-void __blk_queue_split(struct bio **bio, unsigned int *nr_segs);
+static inline bool blk_may_split(struct request_queue *q, struct bio *bio)
+{
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+		return true; /* non-trivial splitting decisions */
+	default:
+		break;
+	}
+
+	/*
+	 * 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.
+	 */
+	return q->limits.chunk_sectors || bio->bi_vcnt != 1 ||
+		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
+}
+
+void __blk_queue_split(struct request_queue *q, struct bio **bio,
+			unsigned int *nr_segs);
 int ll_back_merge_fn(struct request *req, struct bio *bio,
 		unsigned int nr_segs);
 bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,