From b7c178d9e57c8fd4238ff77263b877f6f16182ba Mon Sep 17 00:00:00 2001 From: Meir Elisha Date: Tue, 8 Apr 2025 17:38:08 +0300 Subject: md/raid1: Add check for missing source disk in process_checks() During recovery/check operations, the process_checks function loops through available disks to find a 'primary' source with successfully read data. If no suitable source disk is found after checking all possibilities, the 'primary' index will reach conf->raid_disks * 2. Add an explicit check for this condition after the loop. If no source disk was found, print an error message and return early to prevent further processing without a valid primary source. Link: https://lore.kernel.org/linux-raid/20250408143808.1026534-1-meir.elisha@volumez.com Signed-off-by: Meir Elisha Suggested-and-reviewed-by: Yu Kuai Signed-off-by: Yu Kuai --- drivers/md/raid1.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0efc03cea24e..de9bccbe7337 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2200,14 +2200,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio) if (!rdev_set_badblocks(rdev, sect, s, 0)) abort = 1; } - if (abort) { - conf->recovery_disabled = - mddev->recovery_disabled; - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_done_sync(mddev, r1_bio->sectors, 0); - put_buf(r1_bio); + if (abort) return 0; - } + /* Try next page */ sectors -= s; sect += s; @@ -2346,10 +2341,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) int disks = conf->raid_disks * 2; struct bio *wbio; - if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - /* ouch - failed to read all of that. */ - if (!fix_sync_read_error(r1_bio)) + if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) { + /* + * ouch - failed to read all of that. + * No need to fix read error for check/repair + * because all member disks are read. + */ + if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) || + !fix_sync_read_error(r1_bio)) { + conf->recovery_disabled = mddev->recovery_disabled; + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_done_sync(mddev, r1_bio->sectors, 0); + put_buf(r1_bio); return; + } + } if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) process_checks(r1_bio); -- cgit v1.2.3 From 752d0464b78a5b28682256ed7a057106119e1d1a Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 6 May 2025 20:49:03 +0800 Subject: md: clean up accounting for issued sync IO It's no longer used and can be removed, also remove the field 'gendisk->sync_io'. Link: https://lore.kernel.org/linux-raid/20250506124903.2540268-10-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md.h | 11 ----------- drivers/md/raid1.c | 3 --- drivers/md/raid10.c | 9 --------- drivers/md/raid5.c | 8 -------- include/linux/blkdev.h | 1 - 5 files changed, 32 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/md.h b/drivers/md/md.h index 1982f1f18627..d45a9e6ead80 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -717,17 +717,6 @@ static inline int mddev_trylock(struct mddev *mddev) } extern void mddev_unlock(struct mddev *mddev); -static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) -{ - if (blk_queue_io_stat(bdev->bd_disk->queue)) - atomic_add(nr_sectors, &bdev->bd_disk->sync_io); -} - -static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors) -{ - md_sync_acct(bio->bi_bdev, nr_sectors); -} - struct md_personality { struct md_submodule_head head; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index de9bccbe7337..657d481525be 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2382,7 +2382,6 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) wbio->bi_end_io = end_sync_write; atomic_inc(&r1_bio->remaining); - md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio)); submit_bio_noacct(wbio); } @@ -3055,7 +3054,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r1_bio->bios[i]; if (bio->bi_end_io == end_sync_read) { read_targets--; - md_sync_acct_bio(bio, nr_sectors); if (read_targets == 1) bio->bi_opf &= ~MD_FAILFAST; submit_bio_noacct(bio); @@ -3064,7 +3062,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, } else { atomic_set(&r1_bio->remaining, 1); bio = r1_bio->bios[r1_bio->read_disk]; - md_sync_acct_bio(bio, nr_sectors); if (read_targets == 1) bio->bi_opf &= ~MD_FAILFAST; submit_bio_noacct(bio); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ba32bac975b8..dce06bf65016 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2426,7 +2426,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) atomic_inc(&conf->mirrors[d].rdev->nr_pending); atomic_inc(&r10_bio->remaining); - md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio)); if (test_bit(FailFast, &conf->mirrors[d].rdev->flags)) tbio->bi_opf |= MD_FAILFAST; @@ -2448,8 +2447,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) bio_copy_data(tbio, fbio); d = r10_bio->devs[i].devnum; atomic_inc(&r10_bio->remaining); - md_sync_acct(conf->mirrors[d].replacement->bdev, - bio_sectors(tbio)); submit_bio_noacct(tbio); } @@ -2583,13 +2580,10 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) d = r10_bio->devs[1].devnum; if (wbio->bi_end_io) { atomic_inc(&conf->mirrors[d].rdev->nr_pending); - md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio)); submit_bio_noacct(wbio); } if (wbio2) { atomic_inc(&conf->mirrors[d].replacement->nr_pending); - md_sync_acct(conf->mirrors[d].replacement->bdev, - bio_sectors(wbio2)); submit_bio_noacct(wbio2); } } @@ -3757,7 +3751,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->sectors = nr_sectors; if (bio->bi_end_io == end_sync_read) { - md_sync_acct_bio(bio, nr_sectors); bio->bi_status = 0; submit_bio_noacct(bio); } @@ -4880,7 +4873,6 @@ read_more: r10_bio->sectors = nr_sectors; /* Now submit the read */ - md_sync_acct_bio(read_bio, r10_bio->sectors); atomic_inc(&r10_bio->remaining); read_bio->bi_next = NULL; submit_bio_noacct(read_bio); @@ -4940,7 +4932,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio) continue; atomic_inc(&rdev->nr_pending); - md_sync_acct_bio(b, r10_bio->sectors); atomic_inc(&r10_bio->remaining); b->bi_next = NULL; submit_bio_noacct(b); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6389383166c0..ca5b0e8ba707 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1240,10 +1240,6 @@ again: } if (rdev) { - if (s->syncing || s->expanding || s->expanded - || s->replacing) - md_sync_acct(rdev->bdev, RAID5_STRIPE_SECTORS(conf)); - set_bit(STRIPE_IO_STARTED, &sh->state); bio_init(bi, rdev->bdev, &dev->vec, 1, op | op_flags); @@ -1300,10 +1296,6 @@ again: submit_bio_noacct(bi); } if (rrdev) { - if (s->syncing || s->expanding || s->expanded - || s->replacing) - md_sync_acct(rrdev->bdev, RAID5_STRIPE_SECTORS(conf)); - set_bit(STRIPE_IO_STARTED, &sh->state); bio_init(rbi, rrdev->bdev, &dev->rvec, 1, op | op_flags); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 52b7a27c46e8..ad75dee3b213 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -182,7 +182,6 @@ struct gendisk { struct list_head slave_bdevs; #endif struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_ZONED -- cgit v1.2.3 From 9f346f7d4ea73692b82f5102ca8698e4040469ea Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 27 May 2025 16:14:07 +0800 Subject: md/raid1,raid10: don't handle IO error for REQ_RAHEAD and REQ_NOWAIT IO with REQ_RAHEAD or REQ_NOWAIT can fail early, even if the storage medium is fine, hence record badblocks or remove the disk from array does not make sense. This problem if found by lvm2 test lvcreate-large-raid, where dm-zero will fail read ahead IO directly. Fixes: e879a0d9cb08 ("md/raid1,raid10: don't ignore IO flags") Reported-and-tested-by: Mikulas Patocka Closes: https://lore.kernel.org/all/34fa755d-62c8-4588-8ee1-33cb1249bdf2@redhat.com/ Link: https://lore.kernel.org/linux-raid/20250527081407.3004055-1-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/raid1-10.c | 10 ++++++++++ drivers/md/raid1.c | 19 ++++++++++--------- drivers/md/raid10.c | 11 ++++++----- 3 files changed, 26 insertions(+), 14 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index c7efd8aab675..b8b3a9069701 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -293,3 +293,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev, return false; } + +/* + * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is + * submitted to the underlying disks, hence don't record badblocks or retry + * in this case. + */ +static inline bool raid1_should_handle_error(struct bio *bio) +{ + return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)); +} diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 657d481525be..19c5a0ce5a40 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -373,14 +373,16 @@ static void raid1_end_read_request(struct bio *bio) */ update_head_pos(r1_bio->read_disk, r1_bio); - if (uptodate) + if (uptodate) { set_bit(R1BIO_Uptodate, &r1_bio->state); - else if (test_bit(FailFast, &rdev->flags) && - test_bit(R1BIO_FailFast, &r1_bio->state)) + } else if (test_bit(FailFast, &rdev->flags) && + test_bit(R1BIO_FailFast, &r1_bio->state)) { /* This was a fail-fast read so we definitely * want to retry */ ; - else { + } else if (!raid1_should_handle_error(bio)) { + uptodate = 1; + } else { /* If all other devices have failed, we want to return * the error upwards rather than fail the last device. * Here we redefine "uptodate" to mean "Don't want to retry" @@ -451,16 +453,15 @@ static void raid1_end_write_request(struct bio *bio) struct bio *to_put = NULL; int mirror = find_bio_disk(r1_bio, bio); struct md_rdev *rdev = conf->mirrors[mirror].rdev; - bool discard_error; sector_t lo = r1_bio->sector; sector_t hi = r1_bio->sector + r1_bio->sectors; - - discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD; + bool ignore_error = !raid1_should_handle_error(bio) || + (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD); /* * 'one mirror IO has finished' event handler: */ - if (bio->bi_status && !discard_error) { + if (bio->bi_status && !ignore_error) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -511,7 +512,7 @@ static void raid1_end_write_request(struct bio *bio) /* Maybe we can clear some bad blocks. */ if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) && - !discard_error) { + !ignore_error) { r1_bio->bios[mirror] = IO_MADE_GOOD; set_bit(R1BIO_MadeGood, &r1_bio->state); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index dce06bf65016..b74780af4c22 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -399,6 +399,8 @@ static void raid10_end_read_request(struct bio *bio) * wait for the 'master' bio. */ set_bit(R10BIO_Uptodate, &r10_bio->state); + } else if (!raid1_should_handle_error(bio)) { + uptodate = 1; } else { /* If all other devices that store this block have * failed, we want to return the error upwards rather @@ -456,9 +458,8 @@ static void raid10_end_write_request(struct bio *bio) int slot, repl; struct md_rdev *rdev = NULL; struct bio *to_put = NULL; - bool discard_error; - - discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD; + bool ignore_error = !raid1_should_handle_error(bio) || + (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD); dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); @@ -472,7 +473,7 @@ static void raid10_end_write_request(struct bio *bio) /* * this branch is our 'one mirror IO has finished' event handler: */ - if (bio->bi_status && !discard_error) { + if (bio->bi_status && !ignore_error) { if (repl) /* Never record new bad blocks to replacement, * just fail it. @@ -527,7 +528,7 @@ static void raid10_end_write_request(struct bio *bio) /* Maybe we can clear some bad blocks. */ if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr, r10_bio->sectors) && - !discard_error) { + !ignore_error) { bio_put(bio); if (repl) r10_bio->devs[slot].repl_bio = IO_MADE_GOOD; -- cgit v1.2.3