[PATCH RFC v3 3/3] nvme-multipath: fix diskstats for partitions

From: John Garry <[email protected]>

Currently diskstats for partitions are never updated:
$ ./fio_read nvme1n1p1 # run traffic on /dev/nvme1n1p1
...
$ more /proc/diskstats | grep nvme1
259       2 nvme1c1n1 49857 0 400344 768565 0 0 0 0 0 2334 768565 0 0 0 0 0 0
259       3 nvme1n1 99710 0 800680 1599285 0 0 0 0 0 2346 1599285 0 0 0 0 0 0
259       5 nvme1n1p1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
259       4 nvme1c2n1 49853 0 400336 831472 0 0 0 0 0 2315 831472 0 0 0 0 0 0

This is because we only ever update the diskstats for the multipath disk in
nvme_mpath_end_request(), and we never take into account that the original
bi_bdev may been a partition of this disk.

Functions bdev_start_io_acct() and bdev_start_io_acct() do handle
updating diskstats for a partition, in that they also update the whole
disk also (if a partition), so use the partition (if applicable) when
calling those functions.

Change any functionality which used to lookup the gendisk part0 to now
lookup the specific gendisk partition.

Signed-off-by: John Garry <[email protected]>
---
 drivers/nvme/host/core.c      |  1 +
 drivers/nvme/host/multipath.c | 51 ++++++++++++++++++++++++++++-------
 2 files changed, 42 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1322c678f4eb8..b94b9a3bceb28 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4273,6 +4273,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		sprintf(disk->disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
 			ctrl->instance, ns->head->instance);
 		disk->flags |= GENHD_FL_HIDDEN;
+		disk_add_mirror(ns->head->disk, ns->disk);
 	} else if (multipath) {
 		sprintf(disk->disk_name, "nvme%dn%d", ctrl->subsys->instance,
 			ns->head->instance);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 75dbb58286a32..bd4056f1a9f28 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -144,6 +144,23 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 			blk_freeze_queue_start(h->disk->queue);
 }
 
+static struct block_device *nvme_disk_to_part(struct gendisk *disk,
+						u8 partno)
+{
+	/* Quick lookup for whole disk */
+	if (!partno)
+		return disk->part0;
+	return xa_load(&disk->part_tbl, partno);
+}
+
+static struct block_device *nvme_to_disk_part(struct gendisk *disk,
+					struct block_device *bdev)
+{
+	if (!bdev)
+		return disk->part0;
+	return nvme_disk_to_part(disk, bdev_partno(bdev));
+}
+
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
@@ -165,8 +182,10 @@ void nvme_failover_req(struct request *req)
 	}
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
-	for (bio = req->bio; bio; bio = bio->bi_next)
-		bio_set_dev(bio, ns->head->disk->part0);
+	for (bio = req->bio; bio; bio = bio->bi_next) {
+		bio_set_dev(bio, nvme_to_disk_part(ns->head->disk,
+				bio->bi_bdev));
+	}
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 
@@ -194,8 +213,9 @@ void nvme_mpath_start_request(struct request *rq)
 		return;
 
 	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
-	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),
-						      jiffies);
+	nvme_req(rq)->start_time = bdev_start_io_acct(
+			nvme_to_disk_part(disk, rq->part),
+			req_op(rq), jiffies);
 }
 EXPORT_SYMBOL_GPL(nvme_mpath_start_request);
 
@@ -208,7 +228,8 @@ void nvme_mpath_end_request(struct request *rq)
 
 	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
-	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
+	bdev_end_io_acct(nvme_to_disk_part(ns->head->disk,
+			 rq->part), req_op(rq),
 			 blk_rq_bytes(rq) >> SECTOR_SHIFT,
 			 nvme_req(rq)->start_time);
 }
@@ -530,11 +551,21 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	return nvme_mpath_queue_if_no_path(head);
 }
 
+static struct block_device *nvme_find_path_bdev(struct nvme_ns_head *head,
+						u8 partno)
+{
+	struct nvme_ns *ns = nvme_find_path(head);
+
+	if (!ns)
+		return NULL;
+	return nvme_disk_to_part(ns->disk, partno);
+}
+
 static void nvme_ns_head_submit_bio(struct bio *bio)
 {
 	struct nvme_ns_head *head = bio->bi_bdev->bd_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
-	struct nvme_ns *ns;
+	struct block_device *bdev;
 	int srcu_idx;
 
 	/*
@@ -547,9 +578,9 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 		return;
 
 	srcu_idx = srcu_read_lock(&head->srcu);
-	ns = nvme_find_path(head);
-	if (likely(ns)) {
-		bio_set_dev(bio, ns->disk->part0);
+	bdev = nvme_find_path_bdev(head, bdev_partno(bio->bi_bdev));
+	if (likely(bdev)) {
+		bio_set_dev(bio, bdev);
 		/*
 		 * Use BIO_REMAPPED to skip bio_check_eod() when this bio
 		 * enters submit_bio_noacct() for the per-path device. The EOD
@@ -557,7 +588,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 		 */
 		bio_set_flag(bio, BIO_REMAPPED);
 		bio->bi_opf |= REQ_NVME_MPATH;
-		trace_block_bio_remap(bio, disk_devt(ns->head->disk),
+		trace_block_bio_remap(bio, disk_devt(head->disk),
 				      bio->bi_iter.bi_sector);
 		submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
-- 
2.43.7