block: return ELEVATOR_DISCARD_MERGE if possible

commit 866663b7b52d2da267b28e12eed89ee781b8fed1 upstream.

When merging one bio to request, if they are discard IO and the queue
supports multi-range discard, we need to return ELEVATOR_DISCARD_MERGE
because both block core and related drivers(nvme, virtio-blk) doesn't
handle mixed discard io merge(traditional IO merge together with
discard merge) well.

Fix the issue by returning ELEVATOR_DISCARD_MERGE in this situation,
so both blk-mq and drivers just need to handle multi-range discard.

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Fixes: 2705dfb20947 ("block: fix discard request merge")
Link: https://lore.kernel.org/r/20210729034226.1591070-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Gwendal Grignou <gwendal@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

5 files changed, 24 insertions, 15 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 1d443d17cf7c..d46806182b05 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2251,6 +2251,9 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
 	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
+
+		if (blk_discard_mergable(__rq))
+			return ELEVATOR_DISCARD_MERGE;
 		return ELEVATOR_FRONT_MERGE;
 	}
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index a62692d13566..5219064cd72b 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -721,21 +721,6 @@ static void blk_account_io_merge(struct request *req)
 		part_stat_unlock();
 	}
 }
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
-{
-	if (req_op(req) == REQ_OP_DISCARD &&
-	    queue_max_discard_segments(req->q) > 1)
-		return true;
-	return false;
-}
 
 static enum elv_merge blk_try_req_merge(struct request *req,
 					struct request *next)
diff --git a/block/elevator.c b/block/elevator.c
index 78805c74ea8a..3ba826230c57 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -337,6 +337,9 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req,
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
+
+		if (blk_discard_mergable(__rq))
+			return ELEVATOR_DISCARD_MERGE;
 		return ELEVATOR_BACK_MERGE;
 	}
 
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 19c6922e85f1..6d6dda5cfffa 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -452,6 +452,8 @@ static int dd_request_merge(struct request_queue *q, struct request **rq,
 
 		if (elv_bio_merge_ok(__rq, bio)) {
 			*rq = __rq;
+			if (blk_discard_mergable(__rq))
+				return ELEVATOR_DISCARD_MERGE;
 			return ELEVATOR_FRONT_MERGE;
 		}
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8cc766743270..308c2d8cdca1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1409,6 +1409,22 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	return offset << SECTOR_SHIFT;
 }
 
+/*
+ * Two cases of handling DISCARD merge:
+ * If max_discard_segments > 1, the driver takes every bio
+ * as a range and send them to controller together. The ranges
+ * needn't to be contiguous.
+ * Otherwise, the bios/requests will be handled as same as
+ * others which should be contiguous.
+ */
+static inline bool blk_discard_mergable(struct request *req)
+{
+	if (req_op(req) == REQ_OP_DISCARD &&
+	    queue_max_discard_segments(req->q) > 1)
+		return true;
+	return false;
+}
+
 static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);