md/raid5: account discard IO

Raid5 handles discard bios internally through make_discard_request() and
never passes them through md_account_bio(). As a result, discard IO is
missing the md-device iostat accounting that normal raid5 IO and discard
IO in other raid levels get from md_account_bio().

Before accounting the bio, trim the request to the full data stripes that
raid5 will actually discard. The first full stripe is the ceiling of the
bio start divided by data-stripe sectors, and the last full stripe is the
floor of the bio end divided by data-stripe sectors. Account that exact
MD logical full-stripe range, then restore the original iterator so bio
completion and iostat still cover the original request.

Link: https://patch.msgid.link/20260605072639.2434847-2-yukuai@kernel.org
Signed-off-by: Yu Kuai <yukuai@fygo.io>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 65ae7d8930fcaa32366b5c573173d61c695b91cf..debf35342ae0a9ca4c88f7cc12d8ad18b0004663 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5690,7 +5690,10 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 {
        struct r5conf *conf = mddev->private;
        sector_t logical_sector, last_sector;
+       sector_t first_stripe, last_stripe;
        struct stripe_head *sh;
+       struct bvec_iter bi_iter;
+       struct bio *orig_bi = bi;
        int stripe_sectors;
 
        /* We need to handle this when io_uring supports discard/trim */
@@ -5701,19 +5704,29 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
                /* Skip discard while reshape is happening */
                return;
 
-       logical_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1);
-       last_sector = bio_end_sector(bi);
-
-       bi->bi_next = NULL;
-
        stripe_sectors = conf->chunk_sectors *
                (conf->raid_disks - conf->max_degraded);
-       logical_sector = DIV_ROUND_UP_SECTOR_T(logical_sector,
-                                              stripe_sectors);
-       sector_div(last_sector, stripe_sectors);
+       first_stripe = DIV_ROUND_UP_SECTOR_T(bi->bi_iter.bi_sector,
+                                            stripe_sectors);
+       last_stripe = bio_end_sector(bi);
+       sector_div(last_stripe, stripe_sectors);
+
+       if (first_stripe >= last_stripe) {
+               bio_endio(bi);
+               return;
+       }
+
+       bi_iter = bi->bi_iter;
+       bi->bi_iter.bi_sector = first_stripe * stripe_sectors;
+       bi->bi_iter.bi_size = ((last_stripe - first_stripe) *
+                              stripe_sectors) << 9;
+       md_account_bio(mddev, &bi);
+       orig_bi->bi_iter = bi_iter;
+       bi->bi_iter = bi_iter;
+       bi->bi_next = NULL;
 
-       logical_sector *= conf->chunk_sectors;
-       last_sector *= conf->chunk_sectors;
+       logical_sector = first_stripe * conf->chunk_sectors;
+       last_sector = last_stripe * conf->chunk_sectors;
 
        for (; logical_sector < last_sector;
             logical_sector += RAID5_STRIPE_SECTORS(conf)) {