From 770b1d216d7371c94c88713824da4be4bc39a4e0 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 15 Nov 2021 17:23:17 -0800 Subject: md/raid5: play nice with PREEMPT_RT raid_run_ops() relies on the implicitly disabled preemption for its percpu ops, although this is really about CPU locality. This breaks RT semantics as it can take regular (and thus sleeping) spinlocks, such as stripe_lock. Add a local_lock such that non-RT does not change and continues to be just map to preempt_disable/enable, but makes RT happy as the region will use a per-CPU spinlock and thus be preemptible and still guarantee CPU locality. Signed-off-by: Davidlohr Bueso Signed-off-by: Song Liu --- drivers/md/raid5.c | 11 ++++++----- drivers/md/raid5.h | 4 +++- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9c1a5877cf9f..1240a5c16af8 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2215,10 +2215,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) struct r5conf *conf = sh->raid_conf; int level = conf->level; struct raid5_percpu *percpu; - unsigned long cpu; - cpu = get_cpu(); - percpu = per_cpu_ptr(conf->percpu, cpu); + local_lock(&conf->percpu->lock); + percpu = this_cpu_ptr(conf->percpu); if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; @@ -2271,13 +2270,14 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) BUG(); } - if (overlap_clear && !sh->batch_head) + if (overlap_clear && !sh->batch_head) { for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_Overlap, &dev->flags)) wake_up(&sh->raid_conf->wait_for_overlap); } - put_cpu(); + } + local_unlock(&conf->percpu->lock); } static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) @@ -7052,6 +7052,7 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu return -ENOMEM; } + local_lock_init(&percpu->lock); return 0; } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 5c05acf20e1f..9e8486a9e445 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -4,6 +4,7 @@ #include #include +#include /* * @@ -640,7 +641,8 @@ struct r5conf { * lists and performing address * conversions */ - int scribble_obj_size; + int scribble_obj_size; + local_lock_t lock; } __percpu *percpu; int scribble_disks; int scribble_sectors; -- cgit From a92ce0feffeed8b91f02dac85246d1205e4a64b6 Mon Sep 17 00:00:00 2001 From: Mariusz Tkaczyk Date: Fri, 17 Dec 2021 10:29:55 +0100 Subject: md: drop queue limitation for RAID1 and RAID10 As suggested by Neil Brown[1], this limitation seems to be deprecated. With plugging in use, writes are processed behind the raid thread and conf->pending_count is not increased. This limitation occurs only if caller doesn't use plugs. It can be avoided and often it is (with plugging). There are no reports that queue is growing to enormous size so remove queue limitation for non-plugged IOs too. [1] https://lore.kernel.org/linux-raid/162496301481.7211.18031090130574610495@noble.neil.brown.name Signed-off-by: Mariusz Tkaczyk Signed-off-by: Song Liu --- drivers/md/raid1-10.c | 6 ------ drivers/md/raid1.c | 7 ------- drivers/md/raid10.c | 7 ------- 3 files changed, 20 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 54db34163968..83f9a4f3d82e 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -22,12 +22,6 @@ #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) -/* When there are this many requests queue to be written by - * the raid thread, we become 'congested' to provide back-pressure - * for writeback. - */ -static int max_queued_requests = 1024; - /* for managing resync I/O pages */ struct resync_pages { void *raid_bio; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7dc8026cf6ee..eeaedd6e0ce1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1358,12 +1358,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio = alloc_r1bio(mddev, bio); r1_bio->sectors = max_write_sectors; - if (conf->pending_count >= max_queued_requests) { - md_wakeup_thread(mddev->thread); - raid1_log(mddev, "wait queued"); - wait_event(conf->wait_barrier, - conf->pending_count < max_queued_requests); - } /* first select target devices under rcu_lock and * inc refcount on their rdev. Record them by setting * bios[x] to bio @@ -3410,4 +3404,3 @@ MODULE_ALIAS("md-personality-3"); /* RAID1 */ MODULE_ALIAS("md-raid1"); MODULE_ALIAS("md-level-1"); -module_param(max_queued_requests, int, S_IRUGO|S_IWUSR); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index dde98f65bd04..c683ba138b58 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1387,12 +1387,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, conf->reshape_safe = mddev->reshape_position; } - if (conf->pending_count >= max_queued_requests) { - md_wakeup_thread(mddev->thread); - raid10_log(mddev, "wait queued"); - wait_event(conf->wait_barrier, - conf->pending_count < max_queued_requests); - } /* first select target devices under rcu_lock and * inc refcount on their rdev. Record them by setting * bios[x] to bio @@ -5243,4 +5237,3 @@ MODULE_ALIAS("md-personality-9"); /* RAID10 */ MODULE_ALIAS("md-raid10"); MODULE_ALIAS("md-level-10"); -module_param(max_queued_requests, int, S_IRUGO|S_IWUSR); -- cgit From f51d46d0e7cb5b8494aa534d276a9d8915a2443d Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Tue, 21 Dec 2021 20:06:19 +0000 Subject: md: add support for REQ_NOWAIT commit 021a24460dc2 ("block: add QUEUE_FLAG_NOWAIT") added support for checking whether a given bdev supports handling of REQ_NOWAIT or not. Since then commit 6abc49468eea ("dm: add support for REQ_NOWAIT and enable it for linear target") added support for REQ_NOWAIT for dm. This uses a similar approach to incorporate REQ_NOWAIT for md based bios. This patch was tested using t/io_uring tool within FIO. A nvme drive was partitioned into 2 partitions and a simple raid 0 configuration /dev/md0 was created. md0 : active raid0 nvme4n1p1[1] nvme4n1p2[0] 937423872 blocks super 1.2 512k chunks Before patch: $ ./t/io_uring /dev/md0 -p 0 -a 0 -d 1 -r 100 Running top while the above runs: $ ps -eL | grep $(pidof io_uring) 38396 38396 pts/2 00:00:00 io_uring 38396 38397 pts/2 00:00:15 io_uring 38396 38398 pts/2 00:00:13 iou-wrk-38397 We can see iou-wrk-38397 io worker thread created which gets created when io_uring sees that the underlying device (/dev/md0 in this case) doesn't support nowait. After patch: $ ./t/io_uring /dev/md0 -p 0 -a 0 -d 1 -r 100 Running top while the above runs: $ ps -eL | grep $(pidof io_uring) 38341 38341 pts/2 00:10:22 io_uring 38341 38342 pts/2 00:10:37 io_uring After running this patch, we don't see any io worker thread being created which indicated that io_uring saw that the underlying device does support nowait. This is the exact behaviour noticed on a dm device which also supports nowait. For all the other raid personalities except raid0, we would need to train pieces which involves make_request fn in order for them to correctly handle REQ_NOWAIT. Reviewed-by: Jens Axboe Signed-off-by: Vishal Verma Signed-off-by: Song Liu --- drivers/md/md.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 7fbf6f0ac01b..c6de7d4bfe4d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -418,6 +418,12 @@ check_suspended: rcu_read_lock(); if (is_suspended(mddev, bio)) { DEFINE_WAIT(__wait); + /* Bail out if REQ_NOWAIT is set for the bio */ + if (bio->bi_opf & REQ_NOWAIT) { + rcu_read_unlock(); + bio_wouldblock_error(bio); + return; + } for (;;) { prepare_to_wait(&mddev->sb_wait, &__wait, TASK_UNINTERRUPTIBLE); @@ -5787,6 +5793,7 @@ int md_run(struct mddev *mddev) int err; struct md_rdev *rdev; struct md_personality *pers; + bool nowait = true; if (list_empty(&mddev->disks)) /* cannot run an array with no devices.. */ @@ -5857,8 +5864,13 @@ int md_run(struct mddev *mddev) } } sysfs_notify_dirent_safe(rdev->sysfs_state); + nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev)); } + /* Set the NOWAIT flags if all underlying devices support it */ + if (nowait) + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue); + if (!bioset_initialized(&mddev->bio_set)) { err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) @@ -7002,6 +7014,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) md_update_sb(mddev, 1); + /* + * If the new disk does not support REQ_NOWAIT, + * disable on the whole MD. + */ + if (!blk_queue_nowait(bdev_get_queue(rdev->bdev))) { + pr_info("%s: Disabling nowait because %s does not support nowait\n", + mdname(mddev), bdevname(rdev->bdev, b)); + blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue); + } /* * Kick recovery, maybe this spare has to be added to the * array immediately. -- cgit From 5aa705039c4fca84575539bfa2b8a28454a3d2ca Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Tue, 21 Dec 2021 20:06:20 +0000 Subject: md: raid1 add nowait support This adds nowait support to the RAID1 driver. It makes RAID1 driver return with EAGAIN for situations where it could wait for eg: - Waiting for the barrier, wait_barrier() fn is modified to return bool to support error for wait barriers. It returns true in case of wait or if wait is not required and returns false if wait was required but not performed to support nowait. Reviewed-by: Jens Axboe Signed-off-by: Vishal Verma Signed-off-by: Song Liu --- drivers/md/raid1.c | 76 ++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 56 insertions(+), 20 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index eeaedd6e0ce1..02db187090fa 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -929,8 +929,10 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr) wake_up(&conf->wait_barrier); } -static void _wait_barrier(struct r1conf *conf, int idx) +static bool _wait_barrier(struct r1conf *conf, int idx, bool nowait) { + bool ret = true; + /* * We need to increase conf->nr_pending[idx] very early here, * then raise_barrier() can be blocked when it waits for @@ -961,7 +963,7 @@ static void _wait_barrier(struct r1conf *conf, int idx) */ if (!READ_ONCE(conf->array_frozen) && !atomic_read(&conf->barrier[idx])) - return; + return ret; /* * After holding conf->resync_lock, conf->nr_pending[idx] @@ -979,18 +981,27 @@ static void _wait_barrier(struct r1conf *conf, int idx) */ wake_up(&conf->wait_barrier); /* Wait for the barrier in same barrier unit bucket to drop. */ - wait_event_lock_irq(conf->wait_barrier, - !conf->array_frozen && - !atomic_read(&conf->barrier[idx]), - conf->resync_lock); - atomic_inc(&conf->nr_pending[idx]); + + /* Return false when nowait flag is set */ + if (nowait) { + ret = false; + } else { + wait_event_lock_irq(conf->wait_barrier, + !conf->array_frozen && + !atomic_read(&conf->barrier[idx]), + conf->resync_lock); + atomic_inc(&conf->nr_pending[idx]); + } + atomic_dec(&conf->nr_waiting[idx]); spin_unlock_irq(&conf->resync_lock); + return ret; } -static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr) +static bool wait_read_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait) { int idx = sector_to_idx(sector_nr); + bool ret = true; /* * Very similar to _wait_barrier(). The difference is, for read @@ -1002,7 +1013,7 @@ static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr) atomic_inc(&conf->nr_pending[idx]); if (!READ_ONCE(conf->array_frozen)) - return; + return ret; spin_lock_irq(&conf->resync_lock); atomic_inc(&conf->nr_waiting[idx]); @@ -1013,19 +1024,28 @@ static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr) */ wake_up(&conf->wait_barrier); /* Wait for array to be unfrozen */ - wait_event_lock_irq(conf->wait_barrier, - !conf->array_frozen, - conf->resync_lock); - atomic_inc(&conf->nr_pending[idx]); + + /* Return false when nowait flag is set */ + if (nowait) { + /* Return false when nowait flag is set */ + ret = false; + } else { + wait_event_lock_irq(conf->wait_barrier, + !conf->array_frozen, + conf->resync_lock); + atomic_inc(&conf->nr_pending[idx]); + } + atomic_dec(&conf->nr_waiting[idx]); spin_unlock_irq(&conf->resync_lock); + return ret; } -static void wait_barrier(struct r1conf *conf, sector_t sector_nr) +static bool wait_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait) { int idx = sector_to_idx(sector_nr); - _wait_barrier(conf, idx); + return _wait_barrier(conf, idx, nowait); } static void _allow_barrier(struct r1conf *conf, int idx) @@ -1236,7 +1256,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, * Still need barrier for READ in case that whole * array is frozen. */ - wait_read_barrier(conf, bio->bi_iter.bi_sector); + if (!wait_read_barrier(conf, bio->bi_iter.bi_sector, + bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return; + } if (!r1_bio) r1_bio = alloc_r1bio(mddev, bio); @@ -1336,6 +1360,10 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, bio->bi_iter.bi_sector, bio_end_sector(bio))) { DEFINE_WAIT(w); + if (bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return; + } for (;;) { prepare_to_wait(&conf->wait_barrier, &w, TASK_IDLE); @@ -1353,7 +1381,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, * thread has put up a bar for new requests. * Continue immediately if no resync is active currently. */ - wait_barrier(conf, bio->bi_iter.bi_sector); + if (!wait_barrier(conf, bio->bi_iter.bi_sector, + bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return; + } r1_bio = alloc_r1bio(mddev, bio); r1_bio->sectors = max_write_sectors; @@ -1452,9 +1484,14 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, rdev_dec_pending(conf->mirrors[j].rdev, mddev); r1_bio->state = 0; allow_barrier(conf, bio->bi_iter.bi_sector); + + if (bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return; + } raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk); md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf, bio->bi_iter.bi_sector); + wait_barrier(conf, bio->bi_iter.bi_sector, false); goto retry_write; } @@ -1681,7 +1718,7 @@ static void close_sync(struct r1conf *conf) int idx; for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) { - _wait_barrier(conf, idx); + _wait_barrier(conf, idx, false); _allow_barrier(conf, idx); } @@ -3403,4 +3440,3 @@ MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD"); MODULE_ALIAS("md-personality-3"); /* RAID1 */ MODULE_ALIAS("md-raid1"); MODULE_ALIAS("md-level-1"); - -- cgit From c9aa889b035fca4598ae985a0f0c76ebbb547ad2 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Tue, 21 Dec 2021 20:06:21 +0000 Subject: md: raid10 add nowait support This adds nowait support to the RAID10 driver. Very similar to raid1 driver changes. It makes RAID10 driver return with EAGAIN for situations where it could wait for eg: - Waiting for the barrier, - Reshape operation, - Discard operation. wait_barrier() and regular_request_wait() fn are modified to return bool to support error for wait barriers. They returns true in case of wait or if wait is not required and returns false if wait was required but not performed to support nowait. Reviewed-by: Jens Axboe Signed-off-by: Vishal Verma Signed-off-by: Song Liu --- drivers/md/raid10.c | 100 +++++++++++++++++++++++++++++++++++----------------- 1 file changed, 67 insertions(+), 33 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index c683ba138b58..2b969f70a31f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -952,8 +952,10 @@ static void lower_barrier(struct r10conf *conf) wake_up(&conf->wait_barrier); } -static void wait_barrier(struct r10conf *conf) +static bool wait_barrier(struct r10conf *conf, bool nowait) { + bool ret = true; + spin_lock_irq(&conf->resync_lock); if (conf->barrier) { struct bio_list *bio_list = current->bio_list; @@ -967,27 +969,35 @@ static void wait_barrier(struct r10conf *conf) * that queue to get the nr_pending * count down. */ - raid10_log(conf->mddev, "wait barrier"); - wait_event_lock_irq(conf->wait_barrier, - !conf->barrier || - (atomic_read(&conf->nr_pending) && - bio_list && - (!bio_list_empty(&bio_list[0]) || - !bio_list_empty(&bio_list[1]))) || - /* move on if recovery thread is - * blocked by us - */ - (conf->mddev->thread->tsk == current && - test_bit(MD_RECOVERY_RUNNING, - &conf->mddev->recovery) && - conf->nr_queued > 0), - conf->resync_lock); + /* Return false when nowait flag is set */ + if (nowait) { + ret = false; + } else { + raid10_log(conf->mddev, "wait barrier"); + wait_event_lock_irq(conf->wait_barrier, + !conf->barrier || + (atomic_read(&conf->nr_pending) && + bio_list && + (!bio_list_empty(&bio_list[0]) || + !bio_list_empty(&bio_list[1]))) || + /* move on if recovery thread is + * blocked by us + */ + (conf->mddev->thread->tsk == current && + test_bit(MD_RECOVERY_RUNNING, + &conf->mddev->recovery) && + conf->nr_queued > 0), + conf->resync_lock); + } conf->nr_waiting--; if (!conf->nr_waiting) wake_up(&conf->wait_barrier); } - atomic_inc(&conf->nr_pending); + /* Only increment nr_pending when we wait */ + if (ret) + atomic_inc(&conf->nr_pending); spin_unlock_irq(&conf->resync_lock); + return ret; } static void allow_barrier(struct r10conf *conf) @@ -1098,21 +1108,30 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) * currently. * 2. If IO spans the reshape position. Need to wait for reshape to pass. */ -static void regular_request_wait(struct mddev *mddev, struct r10conf *conf, +static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf, struct bio *bio, sector_t sectors) { - wait_barrier(conf); + /* Bail out if REQ_NOWAIT is set for the bio */ + if (!wait_barrier(conf, bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return false; + } while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && bio->bi_iter.bi_sector < conf->reshape_progress && bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { - raid10_log(conf->mddev, "wait reshape"); allow_barrier(conf); + if (bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return false; + } + raid10_log(conf->mddev, "wait reshape"); wait_event(conf->wait_barrier, conf->reshape_progress <= bio->bi_iter.bi_sector || conf->reshape_progress >= bio->bi_iter.bi_sector + sectors); - wait_barrier(conf); + wait_barrier(conf, false); } + return true; } static void raid10_read_request(struct mddev *mddev, struct bio *bio, @@ -1157,7 +1176,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, rcu_read_unlock(); } - regular_request_wait(mddev, conf, bio, r10_bio->sectors); + if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) + return; rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1179,7 +1199,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, bio_chain(split, bio); allow_barrier(conf); submit_bio_noacct(bio); - wait_barrier(conf); + wait_barrier(conf, false); bio = split; r10_bio->master_bio = bio; r10_bio->sectors = max_sectors; @@ -1338,7 +1358,7 @@ retry_wait: raid10_log(conf->mddev, "%s wait rdev %d blocked", __func__, blocked_rdev->raid_disk); md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf); + wait_barrier(conf, false); goto retry_wait; } } @@ -1356,6 +1376,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, bio->bi_iter.bi_sector, bio_end_sector(bio)))) { DEFINE_WAIT(w); + /* Bail out if REQ_NOWAIT is set for the bio */ + if (bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return; + } for (;;) { prepare_to_wait(&conf->wait_barrier, &w, TASK_IDLE); @@ -1368,7 +1393,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } sectors = r10_bio->sectors; - regular_request_wait(mddev, conf, bio, sectors); + if (!regular_request_wait(mddev, conf, bio, sectors)) + return; if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && @@ -1380,6 +1406,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); md_wakeup_thread(mddev->thread); + if (bio->bi_opf & REQ_NOWAIT) { + allow_barrier(conf); + bio_wouldblock_error(bio); + return; + } raid10_log(conf->mddev, "wait reshape metadata"); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); @@ -1476,7 +1507,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, bio_chain(split, bio); allow_barrier(conf); submit_bio_noacct(bio); - wait_barrier(conf); + wait_barrier(conf, false); bio = split; r10_bio->master_bio = bio; } @@ -1601,7 +1632,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) return -EAGAIN; - wait_barrier(conf); + if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return 0; + } + wait_barrier(conf, false); /* * Check reshape again to avoid reshape happens after checking @@ -1643,7 +1678,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) allow_barrier(conf); /* Resend the fist split part */ submit_bio_noacct(split); - wait_barrier(conf); + wait_barrier(conf, false); } div_u64_rem(bio_end, stripe_size, &remainder); if (remainder) { @@ -1654,7 +1689,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) /* Resend the second split part */ submit_bio_noacct(bio); bio = split; - wait_barrier(conf); + wait_barrier(conf, false); } bio_start = bio->bi_iter.bi_sector; @@ -1810,7 +1845,7 @@ retry_discard: end_disk_offset += geo->stride; atomic_inc(&first_r10bio->remaining); raid_end_discard_bio(r10_bio); - wait_barrier(conf); + wait_barrier(conf, false); goto retry_discard; } @@ -2005,7 +2040,7 @@ static void print_conf(struct r10conf *conf) static void close_sync(struct r10conf *conf) { - wait_barrier(conf); + wait_barrier(conf, false); allow_barrier(conf); mempool_exit(&conf->r10buf_pool); @@ -4813,7 +4848,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, if (need_flush || time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) { /* Need to update reshape_position in metadata */ - wait_barrier(conf); + wait_barrier(conf, false); mddev->reshape_position = conf->reshape_progress; if (mddev->reshape_backwards) mddev->curr_resync_completed = raid10_size(mddev, 0, 0) @@ -5236,4 +5271,3 @@ MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD"); MODULE_ALIAS("md-personality-9"); /* RAID10 */ MODULE_ALIAS("md-raid10"); MODULE_ALIAS("md-level-10"); - -- cgit From bf2c411bb1cfc45f73eb6c55b5755bcb990063ae Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Tue, 21 Dec 2021 20:06:22 +0000 Subject: md: raid456 add nowait support Returns EAGAIN in case the raid456 driver would block waiting for reshape. Reviewed-by: Jens Axboe Signed-off-by: Vishal Verma Signed-off-by: Song Liu --- drivers/md/raid5.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 1240a5c16af8..beb544be9058 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5686,6 +5686,10 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) struct stripe_head *sh; int stripe_sectors; + /* We need to handle this when io_uring supports discard/trim */ + if (WARN_ON_ONCE(bi->bi_opf & REQ_NOWAIT)) + return; + if (mddev->reshape_position != MaxSector) /* Skip discard while reshape is happening */ return; @@ -5819,6 +5823,17 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) last_sector = bio_end_sector(bi); bi->bi_next = NULL; + /* Bail out if conflicts with reshape and REQ_NOWAIT is set */ + if ((bi->bi_opf & REQ_NOWAIT) && + (conf->reshape_progress != MaxSector) && + (mddev->reshape_backwards + ? (logical_sector > conf->reshape_progress && logical_sector <= conf->reshape_safe) + : (logical_sector >= conf->reshape_safe && logical_sector < conf->reshape_progress))) { + bio_wouldblock_error(bi); + if (rw == WRITE) + md_write_end(mddev); + return true; + } md_account_bio(mddev, &bi); prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) { -- cgit From dd3dc5f416b7247a4b5d7bac6698be623c180572 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Dec 2021 18:24:11 -0800 Subject: md: fix spelling of "its" Use the possessive "its" instead of the contraction "it's" in printed messages. Signed-off-by: Randy Dunlap Cc: Song Liu Cc: linux-raid@vger.kernel.org Signed-off-by: Song Liu --- drivers/md/md-cluster.c | 2 +- drivers/md/md.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 7fbd41e156c9..1c8a06b77c85 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -574,7 +574,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) int ret = 0; if (WARN(mddev->cluster_info->slot_number - 1 == le32_to_cpu(msg->slot), - "node %d received it's own msg\n", le32_to_cpu(msg->slot))) + "node %d received its own msg\n", le32_to_cpu(msg->slot))) return -1; switch (le32_to_cpu(msg->type)) { case METADATA_UPDATED: diff --git a/drivers/md/md.c b/drivers/md/md.c index c6de7d4bfe4d..3f75c5896b92 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8421,7 +8421,7 @@ int md_setup_cluster(struct mddev *mddev, int nodes) spin_lock(&pers_lock); /* ensure module won't be unloaded */ if (!md_cluster_ops || !try_module_get(md_cluster_mod)) { - pr_warn("can't find md-cluster module or get it's reference.\n"); + pr_warn("can't find md-cluster module or get its reference.\n"); spin_unlock(&pers_lock); return -ENOENT; } -- cgit From 0c031fd37f69deb0cd8c43bbfcfccd62ebd7e952 Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Fri, 10 Dec 2021 17:31:15 +0800 Subject: md: Move alloc/free acct bioset in to personality bioset acct is only needed for raid0 and raid5. Therefore, md_run only allocates it for raid0 and raid5. However, this does not cover personality takeover, which may cause uninitialized bioset. For example, the following repro steps: mdadm -CR /dev/md0 -l1 -n2 /dev/loop0 /dev/loop1 mdadm --wait /dev/md0 mkfs.xfs /dev/md0 mdadm /dev/md0 --grow -l5 mount /dev/md0 /mnt causes panic like: [ 225.933939] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 225.934903] #PF: supervisor instruction fetch in kernel mode [ 225.935639] #PF: error_code(0x0010) - not-present page [ 225.936361] PGD 0 P4D 0 [ 225.936677] Oops: 0010 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN PTI [ 225.937525] CPU: 27 PID: 1133 Comm: mount Not tainted 5.16.0-rc3+ #706 [ 225.938416] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.module_el8.4.0+547+a85d02ba 04/01/2014 [ 225.939922] RIP: 0010:0x0 [ 225.940289] Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6. [ 225.941196] RSP: 0018:ffff88815897eff0 EFLAGS: 00010246 [ 225.941897] RAX: 0000000000000000 RBX: 0000000000092800 RCX: ffffffff81370a39 [ 225.942813] RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000092800 [ 225.943772] RBP: 1ffff1102b12fe04 R08: fffffbfff0b43c01 R09: fffffbfff0b43c01 [ 225.944807] R10: ffffffff85a1e007 R11: fffffbfff0b43c00 R12: ffff88810eaaaf58 [ 225.945757] R13: 0000000000000000 R14: ffff88810eaaafb8 R15: ffff88815897f040 [ 225.946709] FS: 00007ff3f2505080(0000) GS:ffff888fb5e00000(0000) knlGS:0000000000000000 [ 225.947814] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 225.948556] CR2: ffffffffffffffd6 CR3: 000000015aa5a006 CR4: 0000000000370ee0 [ 225.949537] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 225.950455] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 225.951414] Call Trace: [ 225.951787] [ 225.952120] mempool_alloc+0xe5/0x250 [ 225.952625] ? mempool_resize+0x370/0x370 [ 225.953187] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 225.953862] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 225.954464] ? sched_clock_cpu+0x15/0x120 [ 225.955019] ? find_held_lock+0xac/0xd0 [ 225.955564] bio_alloc_bioset+0x1ed/0x2a0 [ 225.956080] ? lock_downgrade+0x3a0/0x3a0 [ 225.956644] ? bvec_alloc+0xc0/0xc0 [ 225.957135] bio_clone_fast+0x19/0x80 [ 225.957651] raid5_make_request+0x1370/0x1b70 [ 225.958286] ? sched_clock_cpu+0x15/0x120 [ 225.958797] ? __lock_acquire+0x8b2/0x3510 [ 225.959339] ? raid5_get_active_stripe+0xce0/0xce0 [ 225.959986] ? lock_is_held_type+0xd8/0x130 [ 225.960528] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 225.961135] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 225.961703] ? sched_clock_cpu+0x15/0x120 [ 225.962232] ? lock_release+0x27a/0x6c0 [ 225.962746] ? do_wait_intr_irq+0x130/0x130 [ 225.963302] ? lock_downgrade+0x3a0/0x3a0 [ 225.963815] ? lock_release+0x6c0/0x6c0 [ 225.964348] md_handle_request+0x342/0x530 [ 225.964888] ? set_in_sync+0x170/0x170 [ 225.965397] ? blk_queue_split+0x133/0x150 [ 225.965988] ? __blk_queue_split+0x8b0/0x8b0 [ 225.966524] ? submit_bio_checks+0x3b2/0x9d0 [ 225.967069] md_submit_bio+0x127/0x1c0 [...] Fix this by moving alloc/free of acct bioset to pers->run and pers->free. While we are on this, properly handle md_integrity_register() error in raid0_run(). Fixes: daee2024715d (md: check level before create and exit io_acct_set) Cc: stable@vger.kernel.org Acked-by: Guoqing Jiang Signed-off-by: Xiao Ni Signed-off-by: Song Liu --- drivers/md/md.c | 27 +++++++++++++++++---------- drivers/md/md.h | 2 ++ drivers/md/raid0.c | 38 ++++++++++++++++++++++++++++---------- drivers/md/raid5.c | 41 ++++++++++++++++++++++++++++++----------- 4 files changed, 77 insertions(+), 31 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 3f75c5896b92..3f57843918ec 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5881,13 +5881,6 @@ int md_run(struct mddev *mddev) if (err) goto exit_bio_set; } - if (mddev->level != 1 && mddev->level != 10 && - !bioset_initialized(&mddev->io_acct_set)) { - err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE, - offsetof(struct md_io_acct, bio_clone), 0); - if (err) - goto exit_sync_set; - } spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -6064,9 +6057,6 @@ bitmap_abort: module_put(pers->owner); md_bitmap_destroy(mddev); abort: - if (mddev->level != 1 && mddev->level != 10) - bioset_exit(&mddev->io_acct_set); -exit_sync_set: bioset_exit(&mddev->sync_set); exit_bio_set: bioset_exit(&mddev->bio_set); @@ -8608,6 +8598,23 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, } EXPORT_SYMBOL_GPL(md_submit_discard_bio); +int acct_bioset_init(struct mddev *mddev) +{ + int err = 0; + + if (!bioset_initialized(&mddev->io_acct_set)) + err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE, + offsetof(struct md_io_acct, bio_clone), 0); + return err; +} +EXPORT_SYMBOL_GPL(acct_bioset_init); + +void acct_bioset_exit(struct mddev *mddev) +{ + bioset_exit(&mddev->io_acct_set); +} +EXPORT_SYMBOL_GPL(acct_bioset_exit); + static void md_end_io_acct(struct bio *bio) { struct md_io_acct *md_io_acct = bio->bi_private; diff --git a/drivers/md/md.h b/drivers/md/md.h index 53ea7a6961de..f1bf3625ef4c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -721,6 +721,8 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); +int acct_bioset_init(struct mddev *mddev); +void acct_bioset_exit(struct mddev *mddev); void md_account_bio(struct mddev *mddev, struct bio **bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 62c8b6adac70..b59a77b31b90 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -356,7 +356,21 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks return array_sectors; } -static void raid0_free(struct mddev *mddev, void *priv); +static void free_conf(struct mddev *mddev, struct r0conf *conf) +{ + kfree(conf->strip_zone); + kfree(conf->devlist); + kfree(conf); + mddev->private = NULL; +} + +static void raid0_free(struct mddev *mddev, void *priv) +{ + struct r0conf *conf = priv; + + free_conf(mddev, conf); + acct_bioset_exit(mddev); +} static int raid0_run(struct mddev *mddev) { @@ -370,11 +384,16 @@ static int raid0_run(struct mddev *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; + if (acct_bioset_init(mddev)) { + pr_err("md/raid0:%s: alloc acct bioset failed.\n", mdname(mddev)); + return -ENOMEM; + } + /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { ret = create_strip_zones(mddev, &conf); if (ret < 0) - return ret; + goto exit_acct_set; mddev->private = conf; } conf = mddev->private; @@ -413,17 +432,16 @@ static int raid0_run(struct mddev *mddev) dump_zones(mddev); ret = md_integrity_register(mddev); + if (ret) + goto free; return ret; -} -static void raid0_free(struct mddev *mddev, void *priv) -{ - struct r0conf *conf = priv; - - kfree(conf->strip_zone); - kfree(conf->devlist); - kfree(conf); +free: + free_conf(mddev, conf); +exit_acct_set: + acct_bioset_exit(mddev); + return ret; } static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index beb544be9058..ffe720c73b0a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7462,12 +7462,19 @@ static int raid5_run(struct mddev *mddev) struct md_rdev *rdev; struct md_rdev *journal_dev = NULL; sector_t reshape_offset = 0; - int i; + int i, ret = 0; long long min_offset_diff = 0; int first = 1; - if (mddev_init_writes_pending(mddev) < 0) + if (acct_bioset_init(mddev)) { + pr_err("md/raid456:%s: alloc acct bioset failed.\n", mdname(mddev)); return -ENOMEM; + } + + if (mddev_init_writes_pending(mddev) < 0) { + ret = -ENOMEM; + goto exit_acct_set; + } if (mddev->recovery_cp != MaxSector) pr_notice("md/raid:%s: not clean -- starting background reconstruction\n", @@ -7498,7 +7505,8 @@ static int raid5_run(struct mddev *mddev) (mddev->bitmap_info.offset || mddev->bitmap_info.file)) { pr_notice("md/raid:%s: array cannot have both journal and bitmap\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } if (mddev->reshape_position != MaxSector) { @@ -7523,13 +7531,15 @@ static int raid5_run(struct mddev *mddev) if (journal_dev) { pr_warn("md/raid:%s: don't support reshape with journal - aborting.\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } if (mddev->new_level != mddev->level) { pr_warn("md/raid:%s: unsupported reshape required - aborting.\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } old_disks = mddev->raid_disks - mddev->delta_disks; /* reshape_position must be on a new-stripe boundary, and one @@ -7545,7 +7555,8 @@ static int raid5_run(struct mddev *mddev) if (sector_div(here_new, chunk_sectors * new_data_disks)) { pr_warn("md/raid:%s: reshape_position not on a stripe boundary\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } reshape_offset = here_new * chunk_sectors; /* here_new is the stripe we will write to */ @@ -7567,7 +7578,8 @@ static int raid5_run(struct mddev *mddev) else if (mddev->ro == 0) { pr_warn("md/raid:%s: in-place reshape must be started in read-only mode - aborting\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } } else if (mddev->reshape_backwards ? (here_new * chunk_sectors + min_offset_diff <= @@ -7577,7 +7589,8 @@ static int raid5_run(struct mddev *mddev) /* Reading from the same stripe as writing to - bad */ pr_warn("md/raid:%s: reshape_position too early for auto-recovery - aborting.\n", mdname(mddev)); - return -EINVAL; + ret = -EINVAL; + goto exit_acct_set; } pr_debug("md/raid:%s: reshape will continue\n", mdname(mddev)); /* OK, we should be able to continue; */ @@ -7601,8 +7614,10 @@ static int raid5_run(struct mddev *mddev) else conf = mddev->private; - if (IS_ERR(conf)) - return PTR_ERR(conf); + if (IS_ERR(conf)) { + ret = PTR_ERR(conf); + goto exit_acct_set; + } if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) { if (!journal_dev) { @@ -7799,7 +7814,10 @@ abort: free_conf(conf); mddev->private = NULL; pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev)); - return -EIO; + ret = -EIO; +exit_acct_set: + acct_bioset_exit(mddev); + return ret; } static void raid5_free(struct mddev *mddev, void *priv) @@ -7807,6 +7825,7 @@ static void raid5_free(struct mddev *mddev, void *priv) struct r5conf *conf = priv; free_conf(conf); + acct_bioset_exit(mddev); mddev->to_remove = &raid5_attrs_group; } -- cgit From 1745e857e73a2e29379013438ee271e9aadab2e0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 6 Jan 2022 11:03:35 +0100 Subject: md: use default_groups in kobj_type There are currently 2 ways to create a set of sysfs files for a kobj_type, through the default_attrs field, and the default_groups field. Move the md rdev sysfs code to use default_groups field which has been the preferred way since commit aa30f47cf666 ("kobject: Add support for default attribute groups to kobj_type") so that we can soon get rid of the obsolete default_attrs field. Cc: Song Liu Cc: linux-raid@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Song Liu --- drivers/md/md.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 3f57843918ec..854cbf4234aa 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3608,6 +3608,7 @@ static struct attribute *rdev_default_attrs[] = { &rdev_ppl_size.attr, NULL, }; +ATTRIBUTE_GROUPS(rdev_default); static ssize_t rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { @@ -3657,7 +3658,7 @@ static const struct sysfs_ops rdev_sysfs_ops = { static struct kobj_type rdev_ktype = { .release = rdev_free, .sysfs_ops = &rdev_sysfs_ops, - .default_attrs = rdev_default_attrs, + .default_groups = rdev_default_groups, }; int md_rdev_init(struct md_rdev *rdev) -- cgit