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

[John Garry]

From: John Garry <john.garry at linux.dev>

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.

Signed-off-by: John Garry <john.g.garry at oracle.com>
---
Setting as an RFC as adding this extra bio field is not acceptable, but I
can't see how to lookup the original partition.

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index c850a4bf73801..14d48cdc640c8 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -194,8 +194,12 @@ 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);
+	if (bdev_is_partition(rq->bio->bi_orig))
+		nvme_req(rq)->start_time = bdev_start_io_acct(rq->bio->bi_orig, req_op(rq),
+							      jiffies);
+	else
+		nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),
+							      jiffies);
 }
 EXPORT_SYMBOL_GPL(nvme_mpath_start_request);
 
@@ -208,7 +212,12 @@ 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),
+	if (bdev_is_partition(rq->bio->bi_orig))
+		bdev_end_io_acct(rq->bio->bi_orig, req_op(rq),
+				 blk_rq_bytes(rq) >> SECTOR_SHIFT,
+				 nvme_req(rq)->start_time);
+	else
+		bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
 			 blk_rq_bytes(rq) >> SECTOR_SHIFT,
 			 nvme_req(rq)->start_time);
 }
@@ -543,6 +552,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
 	if (likely(ns)) {
+		bio->bi_orig = bio->bi_bdev;
 		bio_set_dev(bio, ns->disk->part0);
 		/*
 		 * Use BIO_REMAPPED to skip bio_check_eod() when this bio
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 8808ee76e73c0..496005aff59b3 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -210,6 +210,7 @@ typedef unsigned int blk_qc_t;
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
+	struct block_device	*bi_orig;
 	blk_opf_t		bi_opf;		/* bottom bits REQ_OP, top bits
 						 * req_flags.
 						 */
-- 
2.43.7