diff options
Diffstat (limited to 'drivers/md/raid10.c')
| -rw-r--r-- | drivers/md/raid10.c | 1486 |
1 files changed, 701 insertions, 785 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 16977e8e075d..84be4cc7e873 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -19,9 +19,12 @@ #include <linux/raid/md_p.h> #include <trace/events/block.h> #include "md.h" + +#define RAID_1_10_NAME "raid10" #include "raid10.h" #include "raid0.h" #include "md-bitmap.h" +#include "md-cluster.h" /* * RAID10 provides a combination of RAID0 and RAID1 functionality. @@ -74,11 +77,23 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio); static void end_reshape_write(struct bio *bio); static void end_reshape(struct r10conf *conf); -#define raid10_log(md, fmt, args...) \ - do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0) - #include "raid1-10.c" +#define NULL_CMD +#define cmd_before(conf, cmd) \ + do { \ + write_sequnlock_irq(&(conf)->resync_lock); \ + cmd; \ + } while (0) +#define cmd_after(conf) write_seqlock_irq(&(conf)->resync_lock) + +#define wait_event_barrier_cmd(conf, cond, cmd) \ + wait_event_cmd((conf)->wait_barrier, cond, cmd_before(conf, cmd), \ + cmd_after(conf)) + +#define wait_event_barrier(conf, cond) \ + wait_event_barrier_cmd(conf, cond, NULL_CMD) + /* * for resync bio, r10bio pointer can be retrieved from the per-bio * 'struct resync_pages'. @@ -145,15 +160,17 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) * Allocate bios. */ for (j = nalloc ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init_inline(bio, NULL, RESYNC_PAGES, 0); r10_bio->devs[j].bio = bio; if (!conf->have_replacement) continue; - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init_inline(bio, NULL, RESYNC_PAGES, 0); r10_bio->devs[j].repl_bio = bio; } /* @@ -197,9 +214,11 @@ out_free_pages: out_free_bio: for ( ; j < nalloc; j++) { if (r10_bio->devs[j].bio) - bio_put(r10_bio->devs[j].bio); + bio_uninit(r10_bio->devs[j].bio); + kfree(r10_bio->devs[j].bio); if (r10_bio->devs[j].repl_bio) - bio_put(r10_bio->devs[j].repl_bio); + bio_uninit(r10_bio->devs[j].repl_bio); + kfree(r10_bio->devs[j].repl_bio); } kfree(rps); out_free_r10bio: @@ -220,12 +239,15 @@ static void r10buf_pool_free(void *__r10_bio, void *data) if (bio) { rp = get_resync_pages(bio); resync_free_pages(rp); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } bio = r10bio->devs[j].repl_bio; - if (bio) - bio_put(bio); + if (bio) { + bio_uninit(bio); + kfree(bio); + } } /* resync pages array stored in the 1st bio's .bi_private */ @@ -267,6 +289,12 @@ static void put_buf(struct r10bio *r10_bio) lower_barrier(conf); } +static void wake_up_barrier(struct r10conf *conf) +{ + if (wq_has_sleeper(&conf->wait_barrier)) + wake_up(&conf->wait_barrier); +} + static void reschedule_retry(struct r10bio *r10_bio) { unsigned long flags; @@ -294,12 +322,12 @@ static void raid_end_bio_io(struct r10bio *r10_bio) struct bio *bio = r10_bio->master_bio; struct r10conf *conf = r10_bio->mddev->private; - if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) - bio->bi_status = BLK_STS_IOERR; + if (!test_and_set_bit(R10BIO_Returned, &r10_bio->state)) { + if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); + } - if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) - bio_end_io_acct(bio, r10_bio->start_time); - bio_endio(bio); /* * Wake up any possible resync thread that waits for the device * to go idle. @@ -373,6 +401,8 @@ 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 @@ -390,10 +420,9 @@ static void raid10_end_read_request(struct bio *bio) /* * oops, read error - keep the refcount on the rdev */ - char b[BDEVNAME_SIZE]; - pr_err_ratelimited("md/raid10:%s: %s: rescheduling sector %llu\n", + pr_err_ratelimited("md/raid10:%s: %pg: rescheduling sector %llu\n", mdname(conf->mddev), - bdevname(rdev->bdev, b), + rdev->bdev, (unsigned long long)r10_bio->sector); set_bit(R10BIO_ReadError, &r10_bio->state); reschedule_retry(r10_bio); @@ -402,12 +431,9 @@ static void raid10_end_read_request(struct bio *bio) static void close_write(struct r10bio *r10_bio) { - /* clear the bitmap if all writes complete successfully */ - md_bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector, - r10_bio->sectors, - !test_bit(R10BIO_Degraded, &r10_bio->state), - 0); - md_write_end(r10_bio->mddev); + struct mddev *mddev = r10_bio->mddev; + + md_write_end(mddev); } static void one_write_done(struct r10bio *r10_bio) @@ -434,9 +460,8 @@ 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); @@ -450,7 +475,7 @@ 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. @@ -471,12 +496,11 @@ static void raid10_end_write_request(struct bio *bio) /* * When the device is faulty, it is not necessary to * handle write error. - * For failfast, this is the only remaining device, - * We need to retry the write without FailFast. */ if (!test_bit(Faulty, &rdev->flags)) set_bit(R10BIO_WriteError, &r10_bio->state); else { + /* Fail the request */ r10_bio->devs[slot].bio = NULL; to_put = bio; dec_rdev = 1; @@ -491,11 +515,7 @@ static void raid10_end_write_request(struct bio *bio) * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. - */ - sector_t first_bad; - int bad_sectors; - - /* + * * Do not set R10BIO_Uptodate if the current device is * rebuilding or Faulty. This is because we cannot use * such device for properly reading the data back (we could @@ -508,10 +528,9 @@ static void raid10_end_write_request(struct bio *bio) set_bit(R10BIO_Uptodate, &r10_bio->state); /* Maybe we can clear some bad blocks. */ - if (is_badblock(rdev, - r10_bio->devs[slot].addr, - r10_bio->sectors, - &first_bad, &bad_sectors) && !discard_error) { + if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr, + r10_bio->sectors) && + !ignore_error) { bio_put(bio); if (repl) r10_bio->devs[slot].repl_bio = IO_MADE_GOOD; @@ -718,7 +737,6 @@ static struct md_rdev *read_balance(struct r10conf *conf, struct geom *geo = &conf->geo; raid10_find_phys(conf, r10_bio); - rcu_read_lock(); best_dist_slot = -1; min_pending = UINT_MAX; best_dist_rdev = NULL; @@ -727,22 +745,13 @@ static struct md_rdev *read_balance(struct r10conf *conf, best_good_sectors = 0; do_balance = 1; clear_bit(R10BIO_FailFast, &r10_bio->state); - /* - * Check if we can balance. We can balance on the whole - * device if no resync is going on (recovery is ok), or below - * the resync window. We take the first readable disk when - * above the resync window. - */ - if ((conf->mddev->recovery_cp < MaxSector - && (this_sector + sectors >= conf->next_resync)) || - (mddev_is_clustered(conf->mddev) && - md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector, - this_sector + sectors))) + + if (raid1_should_read_first(conf->mddev, this_sector, sectors)) do_balance = 0; for (slot = 0; slot < conf->copies ; slot++) { sector_t first_bad; - int bad_sectors; + sector_t bad_sectors; sector_t dev_sector; unsigned int pending; bool nonrot; @@ -750,10 +759,11 @@ static struct md_rdev *read_balance(struct r10conf *conf, if (r10_bio->devs[slot].bio == IO_BLOCKED) continue; disk = r10_bio->devs[slot].devnum; - rdev = rcu_dereference(conf->mirrors[disk].replacement); + rdev = conf->mirrors[disk].replacement; if (rdev == NULL || test_bit(Faulty, &rdev->flags) || - r10_bio->devs[slot].addr + sectors > rdev->recovery_offset) - rdev = rcu_dereference(conf->mirrors[disk].rdev); + r10_bio->devs[slot].addr + sectors > + rdev->recovery_offset) + rdev = conf->mirrors[disk].rdev; if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; @@ -796,7 +806,7 @@ static struct md_rdev *read_balance(struct r10conf *conf, if (!do_balance) break; - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); + nonrot = bdev_nonrot(rdev->bdev); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); if (min_pending > pending && nonrot) { @@ -843,7 +853,6 @@ static struct md_rdev *read_balance(struct r10conf *conf, r10_bio->read_slot = slot; } else rdev = NULL; - rcu_read_unlock(); *max_sectors = best_good_sectors; return rdev; @@ -861,7 +870,6 @@ static void flush_pending_writes(struct r10conf *conf) struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); - conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); /* @@ -876,25 +884,15 @@ static void flush_pending_writes(struct r10conf *conf) __set_current_state(TASK_RUNNING); blk_start_plug(&plug); - /* flush any pending bitmap writes to disk - * before proceeding w/ I/O */ - md_bitmap_unplug(conf->mddev->bitmap); + raid1_prepare_flush_writes(conf->mddev); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } blk_finish_plug(&plug); } else @@ -925,76 +923,118 @@ static void flush_pending_writes(struct r10conf *conf) static void raise_barrier(struct r10conf *conf, int force) { - BUG_ON(force && !conf->barrier); - spin_lock_irq(&conf->resync_lock); + write_seqlock_irq(&conf->resync_lock); + + if (WARN_ON_ONCE(force && !conf->barrier)) + force = false; /* Wait until no block IO is waiting (unless 'force') */ - wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting, - conf->resync_lock); + wait_event_barrier(conf, force || !conf->nr_waiting); /* block any new IO from starting */ - conf->barrier++; + WRITE_ONCE(conf->barrier, conf->barrier + 1); /* Now wait for all pending IO to complete */ - wait_event_lock_irq(conf->wait_barrier, - !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH, - conf->resync_lock); + wait_event_barrier(conf, !atomic_read(&conf->nr_pending) && + conf->barrier < RESYNC_DEPTH); - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static void lower_barrier(struct r10conf *conf) { unsigned long flags; - spin_lock_irqsave(&conf->resync_lock, flags); - conf->barrier--; - spin_unlock_irqrestore(&conf->resync_lock, flags); + + write_seqlock_irqsave(&conf->resync_lock, flags); + WRITE_ONCE(conf->barrier, conf->barrier - 1); + write_sequnlock_irqrestore(&conf->resync_lock, flags); wake_up(&conf->wait_barrier); } -static void wait_barrier(struct r10conf *conf) +static bool stop_waiting_barrier(struct r10conf *conf) { - spin_lock_irq(&conf->resync_lock); + struct bio_list *bio_list = current->bio_list; + struct md_thread *thread; + + /* barrier is dropped */ + if (!conf->barrier) + return true; + + /* + * If there are already pending requests (preventing the barrier from + * rising completely), and the pre-process bio queue isn't empty, then + * don't wait, as we need to empty that queue to get the nr_pending + * count down. + */ + if (atomic_read(&conf->nr_pending) && bio_list && + (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1]))) + return true; + + /* daemon thread must exist while handling io */ + thread = rcu_dereference_protected(conf->mddev->thread, true); + /* + * move on if io is issued from raid10d(), nr_pending is not released + * from original io(see handle_read_error()). All raise barrier is + * blocked until this io is done. + */ + if (thread->tsk == current) { + WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0); + return true; + } + + return false; +} + +static bool wait_barrier_nolock(struct r10conf *conf) +{ + unsigned int seq = read_seqbegin(&conf->resync_lock); + + if (READ_ONCE(conf->barrier)) + return false; + + atomic_inc(&conf->nr_pending); + if (!read_seqretry(&conf->resync_lock, seq)) + return true; + + if (atomic_dec_and_test(&conf->nr_pending)) + wake_up_barrier(conf); + + return false; +} + +static bool wait_barrier(struct r10conf *conf, bool nowait) +{ + bool ret = true; + + if (wait_barrier_nolock(conf)) + return true; + + write_seqlock_irq(&conf->resync_lock); if (conf->barrier) { - struct bio_list *bio_list = current->bio_list; - conf->nr_waiting++; - /* Wait for the barrier to drop. - * However if there are already pending - * requests (preventing the barrier from - * rising completely), and the - * pre-process bio queue isn't empty, - * then don't wait, as we need to empty - * 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); - conf->nr_waiting--; + /* Return false when nowait flag is set */ + if (nowait) { + ret = false; + } else { + conf->nr_waiting++; + mddev_add_trace_msg(conf->mddev, "raid10 wait barrier"); + wait_event_barrier(conf, stop_waiting_barrier(conf)); + conf->nr_waiting--; + } if (!conf->nr_waiting) wake_up(&conf->wait_barrier); } - atomic_inc(&conf->nr_pending); - spin_unlock_irq(&conf->resync_lock); + /* Only increment nr_pending when we wait */ + if (ret) + atomic_inc(&conf->nr_pending); + write_sequnlock_irq(&conf->resync_lock); + return ret; } static void allow_barrier(struct r10conf *conf) { if ((atomic_dec_and_test(&conf->nr_pending)) || (conf->array_freeze_pending)) - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); } static void freeze_array(struct r10conf *conf, int extra) @@ -1011,27 +1051,24 @@ static void freeze_array(struct r10conf *conf, int extra) * must match the number of pending IOs (nr_pending) before * we continue. */ - spin_lock_irq(&conf->resync_lock); + write_seqlock_irq(&conf->resync_lock); conf->array_freeze_pending++; - conf->barrier++; + WRITE_ONCE(conf->barrier, conf->barrier + 1); conf->nr_waiting++; - wait_event_lock_irq_cmd(conf->wait_barrier, - atomic_read(&conf->nr_pending) == conf->nr_queued+extra, - conf->resync_lock, - flush_pending_writes(conf)); - + wait_event_barrier_cmd(conf, atomic_read(&conf->nr_pending) == + conf->nr_queued + extra, flush_pending_writes(conf)); conf->array_freeze_pending--; - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static void unfreeze_array(struct r10conf *conf) { /* reverse the effect of the freeze */ - spin_lock_irq(&conf->resync_lock); - conf->barrier--; + write_seqlock_irq(&conf->resync_lock); + WRITE_ONCE(conf->barrier, conf->barrier - 1); conf->nr_waiting--; wake_up(&conf->wait_barrier); - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static sector_t choose_data_offset(struct r10bio *r10_bio, @@ -1044,26 +1081,18 @@ static sector_t choose_data_offset(struct r10bio *r10_bio, return rdev->new_data_offset; } -struct raid10_plug_cb { - struct blk_plug_cb cb; - struct bio_list pending; - int pending_cnt; -}; - static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) { - struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb, - cb); + struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb, cb); struct mddev *mddev = plug->cb.data; struct r10conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); - conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); md_wakeup_thread(mddev->thread); kfree(plug); return; @@ -1071,23 +1100,15 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) /* we aren't scheduling, so we can do the write-out directly. */ bio = bio_list_get(&plug->pending); - md_bitmap_unplug(mddev->bitmap); - wake_up(&conf->wait_barrier); + raid1_prepare_flush_writes(mddev); + wake_up_barrier(conf); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } kfree(plug); } @@ -1098,30 +1119,37 @@ 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; + } + mddev_add_trace_msg(conf->mddev, "raid10 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, - struct r10bio *r10_bio) + struct r10bio *r10_bio, bool io_accounting) { struct r10conf *conf = mddev->private; struct bio *read_bio; - const int op = bio_op(bio); - const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); int max_sectors; struct md_rdev *rdev; char b[BDEVNAME_SIZE]; @@ -1144,20 +1172,22 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, */ gfp = GFP_NOIO | __GFP_HIGH; - rcu_read_lock(); disk = r10_bio->devs[slot].devnum; - err_rdev = rcu_dereference(conf->mirrors[disk].rdev); + err_rdev = conf->mirrors[disk].rdev; if (err_rdev) - bdevname(err_rdev->bdev, b); + snprintf(b, sizeof(b), "%pg", err_rdev->bdev); else { strcpy(b, "???"); /* This never gets dereferenced */ err_rdev = r10_bio->devs[slot].rdev; } - rcu_read_unlock(); } - regular_request_wait(mddev, conf, bio, r10_bio->sectors); + if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) { + raid_end_bio_io(r10_bio); + return; + } + rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1169,73 +1199,65 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, return; } if (err_rdev) - pr_err_ratelimited("md/raid10:%s: %s: redirecting sector %llu to another mirror\n", + pr_err_ratelimited("md/raid10:%s: %pg: redirecting sector %llu to another mirror\n", mdname(mddev), - bdevname(rdev->bdev, b), + rdev->bdev, (unsigned long long)r10_bio->sector); if (max_sectors < bio_sectors(bio)) { - struct bio *split = bio_split(bio, max_sectors, - gfp, &conf->bio_split); - bio_chain(split, bio); allow_barrier(conf); - submit_bio_noacct(bio); - wait_barrier(conf); - bio = split; + bio = bio_submit_split_bioset(bio, max_sectors, + &conf->bio_split); + wait_barrier(conf, false); + if (!bio) { + set_bit(R10BIO_Returned, &r10_bio->state); + goto err_handle; + } + r10_bio->master_bio = bio; r10_bio->sectors = max_sectors; } slot = r10_bio->read_slot; - if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) - r10_bio->start_time = bio_start_io_acct(bio); - read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set); + if (io_accounting) { + md_account_bio(mddev, &bio); + r10_bio->master_bio = bio; + } + read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set); + read_bio->bi_opf &= ~REQ_NOWAIT; r10_bio->devs[slot].bio = read_bio; r10_bio->devs[slot].rdev = rdev; read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr + choose_data_offset(r10_bio, rdev); - bio_set_dev(read_bio, rdev->bdev); read_bio->bi_end_io = raid10_end_read_request; - bio_set_op_attrs(read_bio, op, do_sync); if (test_bit(FailFast, &rdev->flags) && test_bit(R10BIO_FailFast, &r10_bio->state)) read_bio->bi_opf |= MD_FAILFAST; read_bio->bi_private = r10_bio; - - if (mddev->gendisk) - trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), - r10_bio->sector); + mddev_trace_remap(mddev, read_bio, r10_bio->sector); submit_bio_noacct(read_bio); return; +err_handle: + atomic_dec(&rdev->nr_pending); + raid_end_bio_io(r10_bio); } static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, struct bio *bio, bool replacement, int n_copy) { - const int op = bio_op(bio); - const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); - const unsigned long do_fua = (bio->bi_opf & REQ_FUA); unsigned long flags; - struct blk_plug_cb *cb; - struct raid10_plug_cb *plug = NULL; struct r10conf *conf = mddev->private; struct md_rdev *rdev; int devnum = r10_bio->devs[n_copy].devnum; struct bio *mbio; - if (replacement) { - rdev = conf->mirrors[devnum].replacement; - if (rdev == NULL) { - /* Replacement just got moved to main 'rdev' */ - smp_mb(); - rdev = conf->mirrors[devnum].rdev; - } - } else - rdev = conf->mirrors[devnum].rdev; + rdev = replacement ? conf->mirrors[devnum].replacement : + conf->mirrors[devnum].rdev; - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set); + mbio->bi_opf &= ~REQ_NOWAIT; if (replacement) r10_bio->devs[n_copy].repl_bio = mbio; else @@ -1243,35 +1265,21 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr + choose_data_offset(r10_bio, rdev)); - bio_set_dev(mbio, rdev->bdev); mbio->bi_end_io = raid10_end_write_request; - bio_set_op_attrs(mbio, op, do_sync | do_fua); if (!replacement && test_bit(FailFast, &conf->mirrors[devnum].rdev->flags) && enough(conf, devnum)) mbio->bi_opf |= MD_FAILFAST; mbio->bi_private = r10_bio; - - if (conf->mddev->gendisk) - trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk), - r10_bio->sector); + mddev_trace_remap(mddev, mbio, r10_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; atomic_inc(&r10_bio->remaining); - cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid10_plug_cb, cb); - else - plug = NULL; - if (plug) { - bio_list_add(&plug->pending, mbio); - plug->pending_cnt++; - } else { + if (!raid1_add_bio_to_plug(mddev, mbio, raid10_unplug, conf->copies)) { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); } @@ -1279,66 +1287,56 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) { - int i; struct r10conf *conf = mddev->private; struct md_rdev *blocked_rdev; + int i; retry_wait: blocked_rdev = NULL; - rcu_read_lock(); for (i = 0; i < conf->copies; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[i].replacement); - if (rdev == rrdev) - rrdev = NULL; - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } - if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { - atomic_inc(&rrdev->nr_pending); - blocked_rdev = rrdev; - break; - } + struct md_rdev *rdev, *rrdev; - if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { - sector_t first_bad; + rdev = conf->mirrors[i].rdev; + if (rdev) { sector_t dev_sector = r10_bio->devs[i].addr; - int bad_sectors; - int is_bad; /* * Discard request doesn't care the write result * so it doesn't need to wait blocked disk here. */ - if (!r10_bio->sectors) - continue; - - is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors, - &first_bad, &bad_sectors); - if (is_bad < 0) { + if (test_bit(WriteErrorSeen, &rdev->flags) && + r10_bio->sectors && + rdev_has_badblock(rdev, dev_sector, + r10_bio->sectors) < 0) /* - * Mustn't write here until the bad block - * is acknowledged + * Mustn't write here until the bad + * block is acknowledged */ - atomic_inc(&rdev->nr_pending); set_bit(BlockedBadBlocks, &rdev->flags); + + if (rdev_blocked(rdev)) { blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); break; } } + + rrdev = conf->mirrors[i].replacement; + if (rrdev && rdev_blocked(rrdev)) { + atomic_inc(&rrdev->nr_pending); + blocked_rdev = rrdev; + break; + } } - rcu_read_unlock(); if (unlikely(blocked_rdev)) { /* Have to wait for this device to get unblocked, then retry */ allow_barrier(conf); - raid10_log(conf->mddev, "%s wait rdev %d blocked", - __func__, blocked_rdev->raid_disk); + mddev_add_trace_msg(conf->mddev, + "raid10 %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; } } @@ -1347,19 +1345,24 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; - int i; + int i, k; sector_t sectors; int max_sectors; if ((mddev_is_clustered(mddev) && - md_cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, - bio_end_sector(bio)))) { + mddev->cluster_ops->area_resyncing(mddev, WRITE, + 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); - if (!md_cluster_ops->area_resyncing(mddev, WRITE, + if (!mddev->cluster_ops->area_resyncing(mddev, WRITE, bio->bi_iter.bi_sector, bio_end_sector(bio))) break; schedule(); @@ -1368,7 +1371,11 @@ 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)) { + raid_end_bio_io(r10_bio); + return; + } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && @@ -1380,19 +1387,19 @@ 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); - raid10_log(conf->mddev, "wait reshape metadata"); + if (bio->bi_opf & REQ_NOWAIT) { + allow_barrier(conf); + bio_wouldblock_error(bio); + return; + } + mddev_add_trace_msg(conf->mddev, + "raid10 wait reshape metadata"); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); 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 @@ -1408,16 +1415,14 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, wait_blocked_dev(mddev, r10_bio); - rcu_read_lock(); max_sectors = r10_bio->sectors; for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[d].replacement); - if (rdev == rrdev) - rrdev = NULL; + struct md_rdev *rdev, *rrdev; + + rdev = conf->mirrors[d].rdev; + rrdev = conf->mirrors[d].replacement; if (rdev && (test_bit(Faulty, &rdev->flags))) rdev = NULL; if (rrdev && (test_bit(Faulty, &rrdev->flags))) @@ -1426,14 +1431,12 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->devs[i].bio = NULL; r10_bio->devs[i].repl_bio = NULL; - if (!rdev && !rrdev) { - set_bit(R10BIO_Degraded, &r10_bio->state); + if (!rdev && !rrdev) continue; - } if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { sector_t first_bad; sector_t dev_sector = r10_bio->devs[i].addr; - int bad_sectors; + sector_t bad_sectors; int is_bad; is_bad = is_badblock(rdev, dev_sector, max_sectors, @@ -1446,18 +1449,22 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, * to other devices yet */ max_sectors = bad_sectors; - /* We don't set R10BIO_Degraded as that - * only applies if the disk is missing, - * so it might be re-added, and we want to - * know to recover this chunk. - * In this case the device is here, and the - * fact that this chunk is not in-sync is - * recorded in the bad block log. - */ continue; } if (is_bad) { - int good_sectors = first_bad - dev_sector; + int good_sectors; + + /* + * We cannot atomically write this, so just + * error in that case. It could be possible to + * atomically write other mirrors, but the + * complexity of supporting that is not worth + * the benefit. + */ + if (bio->bi_opf & REQ_ATOMIC) + goto err_handle; + + good_sectors = first_bad - dev_sector; if (good_sectors < max_sectors) max_sectors = good_sectors; } @@ -1471,26 +1478,26 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, atomic_inc(&rrdev->nr_pending); } } - rcu_read_unlock(); if (max_sectors < r10_bio->sectors) r10_bio->sectors = max_sectors; if (r10_bio->sectors < bio_sectors(bio)) { - struct bio *split = bio_split(bio, r10_bio->sectors, - GFP_NOIO, &conf->bio_split); - bio_chain(split, bio); allow_barrier(conf); - submit_bio_noacct(bio); - wait_barrier(conf); - bio = split; + bio = bio_submit_split_bioset(bio, r10_bio->sectors, + &conf->bio_split); + wait_barrier(conf, false); + if (!bio) { + set_bit(R10BIO_Returned, &r10_bio->state); + goto err_handle; + } + r10_bio->master_bio = bio; } - if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) - r10_bio->start_time = bio_start_io_acct(bio); + md_account_bio(mddev, &bio); + r10_bio->master_bio = bio; atomic_set(&r10_bio->remaining, 1); - md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0); for (i = 0; i < conf->copies; i++) { if (r10_bio->devs[i].bio) @@ -1499,6 +1506,24 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, raid10_write_one_disk(mddev, r10_bio, bio, true, i); } one_write_done(r10_bio); + return; +err_handle: + for (k = 0; k < i; k++) { + int d = r10_bio->devs[k].devnum; + struct md_rdev *rdev = conf->mirrors[d].rdev; + struct md_rdev *rrdev = conf->mirrors[d].replacement; + + if (r10_bio->devs[k].bio) { + rdev_dec_pending(rdev, mddev); + r10_bio->devs[k].bio = NULL; + } + if (r10_bio->devs[k].repl_bio) { + rdev_dec_pending(rrdev, mddev); + r10_bio->devs[k].repl_bio = NULL; + } + } + + raid_end_bio_io(r10_bio); } static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) @@ -1519,7 +1544,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) conf->geo.raid_disks); if (bio_data_dir(bio) == READ) - raid10_read_request(mddev, bio, r10_bio); + raid10_read_request(mddev, bio, r10_bio, true); else raid10_write_request(mddev, bio, r10_bio); } @@ -1561,17 +1586,8 @@ static void raid10_end_discard_request(struct bio *bio) set_bit(R10BIO_Uptodate, &r10_bio->state); dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); - if (repl) - rdev = conf->mirrors[dev].replacement; - if (!rdev) { - /* - * raid10_remove_disk uses smp_mb to make sure rdev is set to - * replacement before setting replacement to NULL. It can read - * rdev first without barrier protect even replacment is NULL - */ - smp_rmb(); - rdev = conf->mirrors[dev].rdev; - } + rdev = repl ? conf->mirrors[dev].replacement : + conf->mirrors[dev].rdev; raid_end_discard_bio(r10_bio); rdev_dec_pending(rdev, conf->mddev); @@ -1607,7 +1623,10 @@ 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 (!wait_barrier(conf, bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return 0; + } /* * Check reshape again to avoid reshape happens after checking @@ -1645,22 +1664,36 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) if (remainder) { split_size = stripe_size - remainder; split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split); + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return 0; + } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); 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) { split_size = bio_sectors(bio) - remainder; split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split); + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return 0; + } + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); allow_barrier(conf); /* 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; @@ -1705,6 +1738,7 @@ retry_discard: * The discard bio returns only first r10bio finishes */ if (first_copy) { + md_account_bio(mddev, &bio); r10_bio->master_bio = bio; set_bit(R10BIO_Discard, &r10_bio->state); first_copy = false; @@ -1712,12 +1746,16 @@ retry_discard: } else r10_bio->master_bio = (struct bio *)first_r10bio; - rcu_read_lock(); + /* + * first select target devices under rcu_lock and + * inc refcount on their rdev. Record them by setting + * bios[x] to bio + */ for (disk = 0; disk < geo->raid_disks; disk++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); + struct md_rdev *rdev, *rrdev; + rdev = conf->mirrors[disk].rdev; + rrdev = conf->mirrors[disk].replacement; r10_bio->devs[disk].bio = NULL; r10_bio->devs[disk].repl_bio = NULL; @@ -1737,15 +1775,11 @@ retry_discard: atomic_inc(&rrdev->nr_pending); } } - rcu_read_unlock(); atomic_set(&r10_bio->remaining, 1); for (disk = 0; disk < geo->raid_disks; disk++) { sector_t dev_start, dev_end; struct bio *mbio, *rbio = NULL; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); /* * Now start to calculate the start and end address for each disk. @@ -1775,10 +1809,14 @@ retry_discard: /* * It only handles discard bio which size is >= stripe size, so - * dev_end > dev_start all the time + * dev_end > dev_start all the time. + * It doesn't need to use rcu lock to get rdev here. We already + * add rdev->nr_pending in the first loop. */ if (r10_bio->devs[disk].bio) { - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + struct md_rdev *rdev = conf->mirrors[disk].rdev; + mbio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, + &mddev->bio_set); mbio->bi_end_io = raid10_end_discard_request; mbio->bi_private = r10_bio; r10_bio->devs[disk].bio = mbio; @@ -1790,7 +1828,9 @@ retry_discard: bio_endio(mbio); } if (r10_bio->devs[disk].repl_bio) { - rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + struct md_rdev *rrdev = conf->mirrors[disk].replacement; + rbio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, + &mddev->bio_set); rbio->bi_end_io = raid10_end_discard_request; rbio->bi_private = r10_bio; r10_bio->devs[disk].repl_bio = rbio; @@ -1810,7 +1850,7 @@ 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; } @@ -1833,8 +1873,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) && md_flush_request(mddev, bio)) return true; - if (!md_write_start(mddev, bio)) - return false; + md_write_start(mddev, bio); if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) if (!raid10_handle_discard(mddev, bio)) @@ -1855,7 +1894,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) __make_request(mddev, bio, sectors); /* In case raid10d snuck in to freeze_array */ - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); return true; } @@ -1864,6 +1903,8 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev) struct r10conf *conf = mddev->private; int i; + lockdep_assert_held(&mddev->lock); + if (conf->geo.near_copies < conf->geo.raid_disks) seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2); if (conf->geo.near_copies > 1) @@ -1878,12 +1919,11 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev) } seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks, conf->geo.raid_disks - mddev->degraded); - rcu_read_lock(); for (i = 0; i < conf->geo.raid_disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = READ_ONCE(conf->mirrors[i].rdev); + seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); } - rcu_read_unlock(); seq_printf(seq, "]"); } @@ -1905,7 +1945,6 @@ static int _enough(struct r10conf *conf, int previous, int ignore) ncopies = conf->geo.near_copies; } - rcu_read_lock(); do { int n = conf->copies; int cnt = 0; @@ -1913,7 +1952,7 @@ static int _enough(struct r10conf *conf, int previous, int ignore) while (n--) { struct md_rdev *rdev; if (this != ignore && - (rdev = rcu_dereference(conf->mirrors[this].rdev)) && + (rdev = conf->mirrors[this].rdev) && test_bit(In_sync, &rdev->flags)) cnt++; this = (this+1) % disks; @@ -1924,7 +1963,6 @@ static int _enough(struct r10conf *conf, int previous, int ignore) } while (first != 0); has_enough = 1; out: - rcu_read_unlock(); return has_enough; } @@ -1939,41 +1977,48 @@ static int enough(struct r10conf *conf, int ignore) _enough(conf, 1, ignore); } +/** + * raid10_error() - RAID10 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + * + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev) { - char b[BDEVNAME_SIZE]; struct r10conf *conf = mddev->private; unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks with "fail_last_dev == false", - * ignore the error, let the next level up know. - * else mark the drive as failed - */ spin_lock_irqsave(&conf->device_lock, flags); - if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev - && !enough(conf, rdev->raid_disk)) { - /* - * Don't fail the drive, just return an IO error. - */ - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * If recovery is running, make sure it aborts. - */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); spin_unlock_irqrestore(&conf->device_lock, flags); - pr_crit("md/raid10:%s: Disk failure on %s, disabling device.\n" + pr_crit("md/raid10:%s: Disk failure on %pg, disabling device.\n" "md/raid10:%s: Operation continuing on %d devices.\n", - mdname(mddev), bdevname(rdev->bdev, b), + mdname(mddev), rdev->bdev, mdname(mddev), conf->geo.raid_disks - mddev->degraded); } @@ -1990,22 +2035,20 @@ static void print_conf(struct r10conf *conf) pr_debug(" --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded, conf->geo.raid_disks); - /* This is only called with ->reconfix_mutex held, so - * rcu protection of rdev is not needed */ + lockdep_assert_held(&conf->mddev->reconfig_mutex); for (i = 0; i < conf->geo.raid_disks; i++) { - char b[BDEVNAME_SIZE]; rdev = conf->mirrors[i].rdev; if (rdev) - pr_debug(" disk %d, wo:%d, o:%d, dev:%s\n", + pr_debug(" disk %d, wo:%d, o:%d, dev:%pg\n", i, !test_bit(In_sync, &rdev->flags), !test_bit(Faulty, &rdev->flags), - bdevname(rdev->bdev,b)); + rdev->bdev); } } static void close_sync(struct r10conf *conf) { - wait_barrier(conf); + wait_barrier(conf, false); allow_barrier(conf); mempool_exit(&conf->r10buf_pool); @@ -2063,11 +2106,12 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r10conf *conf = mddev->private; int err = -EEXIST; - int mirror; + int mirror, repl_slot = -1; int first = 0; int last = conf->geo.raid_disks - 1; + struct raid10_info *p; - if (mddev->recovery_cp < MaxSector) + if (mddev->resync_offset < MaxSector) /* only hot-add to in-sync arrays, as recovery is * very different from resync */ @@ -2075,9 +2119,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1)) return -EINVAL; - if (md_integrity_add_rdev(rdev, mddev)) - return -ENXIO; - if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -2088,40 +2129,40 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) else mirror = first; for ( ; mirror <= last ; mirror++) { - struct raid10_info *p = &conf->mirrors[mirror]; + p = &conf->mirrors[mirror]; if (p->recovery_disabled == mddev->recovery_disabled) continue; if (p->rdev) { - if (!test_bit(WantReplacement, &p->rdev->flags) || - p->replacement != NULL) - continue; - clear_bit(In_sync, &rdev->flags); - set_bit(Replacement, &rdev->flags); - rdev->raid_disk = mirror; - err = 0; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - conf->fullsync = 1; - rcu_assign_pointer(p->replacement, rdev); - break; + if (test_bit(WantReplacement, &p->rdev->flags) && + p->replacement == NULL && repl_slot < 0) + repl_slot = mirror; + continue; } - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; p->head_position = 0; p->recovery_disabled = mddev->recovery_disabled - 1; rdev->raid_disk = mirror; err = 0; if (rdev->saved_raid_disk != mirror) conf->fullsync = 1; - rcu_assign_pointer(p->rdev, rdev); + WRITE_ONCE(p->rdev, rdev); break; } - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); + + if (err && repl_slot >= 0) { + p = &conf->mirrors[repl_slot]; + clear_bit(In_sync, &rdev->flags); + set_bit(Replacement, &rdev->flags); + rdev->raid_disk = repl_slot; + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; + conf->fullsync = 1; + WRITE_ONCE(p->replacement, rdev); + } print_conf(conf); return err; @@ -2133,9 +2174,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) int err = 0; int number = rdev->raid_disk; struct md_rdev **rdevp; - struct raid10_info *p = conf->mirrors + number; + struct raid10_info *p; print_conf(conf); + if (unlikely(number >= mddev->raid_disks)) + return 0; + p = conf->mirrors + number; if (rdev == p->rdev) rdevp = &p->rdev; else if (rdev == p->replacement) @@ -2159,24 +2203,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) err = -EBUSY; goto abort; } - *rdevp = NULL; - if (!test_bit(RemoveSynchronized, &rdev->flags)) { - synchronize_rcu(); - if (atomic_read(&rdev->nr_pending)) { - /* lost the race, try later */ - err = -EBUSY; - *rdevp = rdev; - goto abort; - } - } + WRITE_ONCE(*rdevp, NULL); if (p->replacement) { /* We must have just cleared 'rdev' */ - p->rdev = p->replacement; + WRITE_ONCE(p->rdev, p->replacement); clear_bit(Replacement, &p->replacement->flags); - smp_mb(); /* Make sure other CPUs may see both as identical - * but will never see neither -- if they are careful. - */ - p->replacement = NULL; + WRITE_ONCE(p->replacement, NULL); } clear_bit(WantReplacement, &rdev->flags); @@ -2264,8 +2296,6 @@ static void end_sync_write(struct bio *bio) struct mddev *mddev = r10_bio->mddev; struct r10conf *conf = mddev->private; int d; - sector_t first_bad; - int bad_sectors; int slot; int repl; struct md_rdev *rdev = NULL; @@ -2286,11 +2316,10 @@ static void end_sync_write(struct bio *bio) &rdev->mddev->recovery); set_bit(R10BIO_WriteError, &r10_bio->state); } - } else if (is_badblock(rdev, - r10_bio->devs[slot].addr, - r10_bio->sectors, - &first_bad, &bad_sectors)) + } else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr, + r10_bio->sectors)) { set_bit(R10BIO_MadeGood, &r10_bio->state); + } rdev_dec_pending(rdev, mddev); @@ -2387,7 +2416,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) * bi_vecs, as the read request might have corrupted these */ rp = get_resync_pages(tbio); - bio_reset(tbio); + bio_reset(tbio, conf->mirrors[d].rdev->bdev, REQ_OP_WRITE); md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size); @@ -2395,18 +2424,15 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) tbio->bi_private = rp; tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; tbio->bi_end_io = end_sync_write; - bio_set_op_attrs(tbio, REQ_OP_WRITE, 0); bio_copy_data(tbio, fbio); 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; tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset; - bio_set_dev(tbio, conf->mirrors[d].rdev->bdev); submit_bio_noacct(tbio); } @@ -2414,18 +2440,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) * that are active */ for (i = 0; i < conf->copies; i++) { - int d; - tbio = r10_bio->devs[i].repl_bio; if (!tbio || !tbio->bi_end_io) continue; if (r10_bio->devs[i].bio->bi_end_io != end_sync_write && r10_bio->devs[i].bio != fbio) 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); } @@ -2475,12 +2496,12 @@ static void fix_recovery_read_error(struct r10bio *r10_bio) s = PAGE_SIZE >> 9; rdev = conf->mirrors[dr].rdev; - addr = r10_bio->devs[0].addr + sect, + addr = r10_bio->devs[0].addr + sect; ok = sync_page_io(rdev, addr, s << 9, pages[idx], - REQ_OP_READ, 0, false); + REQ_OP_READ, false); if (ok) { rdev = conf->mirrors[dw].rdev; addr = r10_bio->devs[1].addr + sect; @@ -2488,7 +2509,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio) addr, s << 9, pages[idx], - REQ_OP_WRITE, 0, false); + REQ_OP_WRITE, false); if (!ok) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, @@ -2533,11 +2554,22 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; int d; - struct bio *wbio, *wbio2; + struct bio *wbio = r10_bio->devs[1].bio; + struct bio *wbio2 = r10_bio->devs[1].repl_bio; + + /* Need to test wbio2->bi_end_io before we call + * submit_bio_noacct as if the former is NULL, + * the latter is free to free wbio2. + */ + if (wbio2 && !wbio2->bi_end_io) + wbio2 = NULL; if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) { fix_recovery_read_error(r10_bio); - end_sync_request(r10_bio); + if (wbio->bi_end_io) + end_sync_request(r10_bio); + if (wbio2) + end_sync_request(r10_bio); return; } @@ -2546,76 +2578,26 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) * and submit the write request */ d = r10_bio->devs[1].devnum; - wbio = r10_bio->devs[1].bio; - wbio2 = r10_bio->devs[1].repl_bio; - /* Need to test wbio2->bi_end_io before we call - * submit_bio_noacct as if the former is NULL, - * the latter is free to free wbio2. - */ - if (wbio2 && !wbio2->bi_end_io) - wbio2 = NULL; 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); } } -/* - * Used by fix_read_error() to decay the per rdev read_errors. - * We halve the read error count for every hour that has elapsed - * since the last recorded read error. - * - */ -static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev) -{ - long cur_time_mon; - unsigned long hours_since_last; - unsigned int read_errors = atomic_read(&rdev->read_errors); - - cur_time_mon = ktime_get_seconds(); - - if (rdev->last_read_error == 0) { - /* first time we've seen a read error */ - rdev->last_read_error = cur_time_mon; - return; - } - - hours_since_last = (long)(cur_time_mon - - rdev->last_read_error) / 3600; - - rdev->last_read_error = cur_time_mon; - - /* - * if hours_since_last is > the number of bits in read_errors - * just set read errors to 0. We do this to avoid - * overflowing the shift of read_errors by hours_since_last. - */ - if (hours_since_last >= 8 * sizeof(read_errors)) - atomic_set(&rdev->read_errors, 0); - else - atomic_set(&rdev->read_errors, read_errors >> hours_since_last); -} - static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, enum req_op op) { - sector_t first_bad; - int bad_sectors; - - if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors) - && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags))) + if (rdev_has_badblock(rdev, sector, sectors) && + (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags))) return -1; - if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false)) + if (sync_page_io(rdev, sector, sectors << 9, page, op, false)) /* success */ return 1; - if (rw == WRITE) { + if (op == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, @@ -2638,10 +2620,9 @@ static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10bio *r10_bio) { int sect = 0; /* Offset from r10_bio->sector */ - int sectors = r10_bio->sectors; + int sectors = r10_bio->sectors, slot = r10_bio->read_slot; struct md_rdev *rdev; - int max_read_errors = atomic_read(&mddev->max_corr_read_errors); - int d = r10_bio->devs[r10_bio->read_slot].devnum; + int d = r10_bio->devs[slot].devnum; /* still own a reference to this rdev, so it cannot * have been cleared recently. @@ -2653,77 +2634,60 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 more fix_read_error() attempts */ return; - check_decay_read_errors(mddev, rdev); - atomic_inc(&rdev->read_errors); - if (atomic_read(&rdev->read_errors) > max_read_errors) { - char b[BDEVNAME_SIZE]; - bdevname(rdev->bdev, b); - - pr_notice("md/raid10:%s: %s: Raid device exceeded read_error threshold [cur %d:max %d]\n", - mdname(mddev), b, - atomic_read(&rdev->read_errors), max_read_errors); - pr_notice("md/raid10:%s: %s: Failing raid device\n", - mdname(mddev), b); - md_error(mddev, rdev); - r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED; + if (exceed_read_errors(mddev, rdev)) { + r10_bio->devs[slot].bio = IO_BLOCKED; return; } while(sectors) { int s = sectors; - int sl = r10_bio->read_slot; + int sl = slot; int success = 0; int start; if (s > (PAGE_SIZE>>9)) s = PAGE_SIZE >> 9; - rcu_read_lock(); do { - sector_t first_bad; - int bad_sectors; - d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); + rdev = conf->mirrors[d].rdev; if (rdev && test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags) && - is_badblock(rdev, r10_bio->devs[sl].addr + sect, s, - &first_bad, &bad_sectors) == 0) { + rdev_has_badblock(rdev, + r10_bio->devs[sl].addr + sect, + s) == 0) { atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); success = sync_page_io(rdev, r10_bio->devs[sl].addr + sect, s<<9, conf->tmppage, - REQ_OP_READ, 0, false); + REQ_OP_READ, false); rdev_dec_pending(rdev, mddev); - rcu_read_lock(); if (success) break; } sl++; if (sl == conf->copies) sl = 0; - } while (!success && sl != r10_bio->read_slot); - rcu_read_unlock(); + } while (sl != slot); if (!success) { /* Cannot read from anywhere, just mark the block * as bad on the first device to discourage future * reads. */ - int dn = r10_bio->devs[r10_bio->read_slot].devnum; + int dn = r10_bio->devs[slot].devnum; rdev = conf->mirrors[dn].rdev; if (!rdev_set_badblocks( rdev, - r10_bio->devs[r10_bio->read_slot].addr + r10_bio->devs[slot].addr + sect, s, 0)) { md_error(mddev, rdev); - r10_bio->devs[r10_bio->read_slot].bio + r10_bio->devs[slot].bio = IO_BLOCKED; } break; @@ -2731,96 +2695,85 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 start = sl; /* write it back and re-read */ - rcu_read_lock(); - while (sl != r10_bio->read_slot) { - char b[BDEVNAME_SIZE]; - + while (sl != slot) { if (sl==0) sl = conf->copies; sl--; d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); + rdev = conf->mirrors[d].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || !test_bit(In_sync, &rdev->flags)) continue; atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, WRITE) + s, conf->tmppage, REQ_OP_WRITE) == 0) { /* Well, this device is dead */ - pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %s)\n", + pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %pg)\n", mdname(mddev), s, (unsigned long long)( sect + choose_data_offset(r10_bio, rdev)), - bdevname(rdev->bdev, b)); - pr_notice("md/raid10:%s: %s: failing drive\n", + rdev->bdev); + pr_notice("md/raid10:%s: %pg: failing drive\n", mdname(mddev), - bdevname(rdev->bdev, b)); + rdev->bdev); } rdev_dec_pending(rdev, mddev); - rcu_read_lock(); } sl = start; - while (sl != r10_bio->read_slot) { - char b[BDEVNAME_SIZE]; - + while (sl != slot) { if (sl==0) sl = conf->copies; sl--; d = r10_bio->devs[sl].devnum; - rdev = rcu_dereference(conf->mirrors[d].rdev); + rdev = conf->mirrors[d].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || !test_bit(In_sync, &rdev->flags)) continue; atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, - READ)) { + s, conf->tmppage, REQ_OP_READ)) { case 0: /* Well, this device is dead */ - pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %s)\n", + pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %pg)\n", mdname(mddev), s, (unsigned long long)( sect + choose_data_offset(r10_bio, rdev)), - bdevname(rdev->bdev, b)); - pr_notice("md/raid10:%s: %s: failing drive\n", + rdev->bdev); + pr_notice("md/raid10:%s: %pg: failing drive\n", mdname(mddev), - bdevname(rdev->bdev, b)); + rdev->bdev); break; case 1: - pr_info("md/raid10:%s: read error corrected (%d sectors at %llu on %s)\n", + pr_info("md/raid10:%s: read error corrected (%d sectors at %llu on %pg)\n", mdname(mddev), s, (unsigned long long)( sect + choose_data_offset(r10_bio, rdev)), - bdevname(rdev->bdev, b)); + rdev->bdev); atomic_add(s, &rdev->corrected_errors); } rdev_dec_pending(rdev, mddev); - rcu_read_lock(); } - rcu_read_unlock(); sectors -= s; sect += s; } } -static int narrow_write_error(struct r10bio *r10_bio, int i) +static bool narrow_write_error(struct r10bio *r10_bio, int i) { struct bio *bio = r10_bio->master_bio; struct mddev *mddev = r10_bio->mddev; @@ -2841,10 +2794,10 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) sector_t sector; int sectors; int sect_to_write = r10_bio->sectors; - int ok = 1; + bool ok = true; if (rdev->badblocks.shift < 0) - return 0; + return false; block_sectors = roundup(1 << rdev->badblocks.shift, bdev_logical_block_size(rdev->bdev) >> 9); @@ -2859,13 +2812,13 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) if (sectors > sect_to_write) sectors = sect_to_write; /* Write at 'sector' for 'sectors' */ - wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + wbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, + &mddev->bio_set); bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors); wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector); wbio->bi_iter.bi_sector = wsector + choose_data_offset(r10_bio, rdev); - bio_set_dev(wbio, rdev->bdev); - bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); + wbio->bi_opf = REQ_OP_WRITE; if (submit_bio_wait(wbio) < 0) /* Failure! */ @@ -2910,9 +2863,13 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio) md_error(mddev, rdev); rdev_dec_pending(rdev, mddev); - allow_barrier(conf); r10_bio->state = 0; - raid10_read_request(mddev, r10_bio->master_bio, r10_bio); + raid10_read_request(mddev, r10_bio->master_bio, r10_bio, false); + /* + * allow_barrier after re-submit to ensure no sync io + * can be issued while regular io pending. + */ + allow_barrier(conf); } static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) @@ -2979,11 +2936,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } else if (bio != NULL && bio->bi_status) { fail = true; - if (!narrow_write_error(r10_bio, m)) { + if (!narrow_write_error(r10_bio, m)) md_error(conf->mddev, rdev); - set_bit(R10BIO_Degraded, - &r10_bio->state); - } rdev_dec_pending(rdev, conf->mddev); } bio = r10_bio->devs[m].repl_bio; @@ -3042,8 +2996,6 @@ static void raid10d(struct md_thread *thread) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list); list_del(&r10_bio->retry_list); - if (mddev->degraded) - set_bit(R10BIO_Degraded, &r10_bio->state); if (test_bit(R10BIO_WriteError, &r10_bio->state)) @@ -3125,12 +3077,12 @@ static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf) for (i = 0; i < nalloc; i++) { bio = r10bio->devs[i].bio; rp = bio->bi_private; - bio_reset(bio); + bio_reset(bio, NULL, 0); bio->bi_private = rp; bio = r10bio->devs[i].repl_bio; if (bio) { rp = bio->bi_private; - bio_reset(bio); + bio_reset(bio, NULL, 0); bio->bi_private = rp; } } @@ -3207,12 +3159,12 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf) */ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped) + sector_t max_sector, int *skipped) { struct r10conf *conf = mddev->private; struct r10bio *r10_bio; struct bio *biolist = NULL, *bio; - sector_t max_sector, nr_sectors; + sector_t nr_sectors; int i; int max_sync; sector_t sync_blocks; @@ -3220,17 +3172,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int chunks_skipped = 0; sector_t chunk_mask = conf->geo.chunk_mask; int page_idx = 0; - - if (!mempool_initialized(&conf->r10buf_pool)) - if (init_resync(conf)) - return 0; + int error_disk = -1; /* * Allow skipping a full rebuild for incremental assembly * of a clean array, like RAID1 does. */ if (mddev->bitmap == NULL && - mddev->recovery_cp == MaxSector && + mddev->resync_offset == MaxSector && mddev->reshape_position == MaxSector && !test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && @@ -3240,11 +3189,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return mddev->dev_sectors - sector_nr; } + if (!mempool_initialized(&conf->r10buf_pool)) + if (init_resync(conf)) + return 0; + skipped: - max_sector = mddev->dev_sectors; - if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || - test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - max_sector = mddev->resync_max_sectors; if (sector_nr >= max_sector) { conf->cluster_sync_low = 0; conf->cluster_sync_high = 0; @@ -3266,13 +3215,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (mddev->curr_resync < max_sector) { /* aborted */ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) - md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync, - &sync_blocks, 1); + md_bitmap_end_sync(mddev, mddev->curr_resync, + &sync_blocks); else for (i = 0; i < conf->geo.raid_disks; i++) { sector_t sect = raid10_find_virt(conf, mddev->curr_resync, i); - md_bitmap_end_sync(mddev->bitmap, sect, - &sync_blocks, 1); + + md_bitmap_end_sync(mddev, sect, &sync_blocks); } } else { /* completed sync */ @@ -3282,18 +3231,18 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* Completed a full sync so the replacements * are now fully recovered. */ - rcu_read_lock(); for (i = 0; i < conf->geo.raid_disks; i++) { struct md_rdev *rdev = - rcu_dereference(conf->mirrors[i].replacement); + conf->mirrors[i].replacement; + if (rdev) rdev->recovery_offset = MaxSector; } - rcu_read_unlock(); } conf->fullsync = 0; } - md_bitmap_close_sync(mddev->bitmap); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->close_sync(mddev); close_sync(conf); *skipped = 1; return sectors_skipped; @@ -3303,8 +3252,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return reshape_request(mddev, sector_nr, skipped); if (chunks_skipped >= conf->geo.raid_disks) { - /* if there has been nothing to do on any drive, - * then there is nothing to do at all.. + pr_err("md/raid10:%s: %s fails\n", mdname(mddev), + test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ? "resync" : "recovery"); + if (error_disk >= 0 && + !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { + /* + * recovery fails, set mirrors.recovery_disabled, + * device shouldn't be added to there. + */ + conf->mirrors[error_disk].recovery_disabled = + mddev->recovery_disabled; + return 0; + } + /* + * if there has been nothing to do on any drive, + * then there is nothing to do at all. */ *skipped = 1; return (max_sector - sector_nr) + sectors_skipped; @@ -3349,52 +3311,41 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio = NULL; for (i = 0 ; i < conf->geo.raid_disks; i++) { - int still_degraded; + bool still_degraded; struct r10bio *rb2; sector_t sect; - int must_sync; + bool must_sync; int any_working; - int need_recover = 0; - int need_replace = 0; struct raid10_info *mirror = &conf->mirrors[i]; struct md_rdev *mrdev, *mreplace; - rcu_read_lock(); - mrdev = rcu_dereference(mirror->rdev); - mreplace = rcu_dereference(mirror->replacement); + mrdev = mirror->rdev; + mreplace = mirror->replacement; - if (mrdev != NULL && - !test_bit(Faulty, &mrdev->flags) && - !test_bit(In_sync, &mrdev->flags)) - need_recover = 1; - if (mreplace != NULL && - !test_bit(Faulty, &mreplace->flags)) - need_replace = 1; + if (mrdev && (test_bit(Faulty, &mrdev->flags) || + test_bit(In_sync, &mrdev->flags))) + mrdev = NULL; + if (mreplace && test_bit(Faulty, &mreplace->flags)) + mreplace = NULL; - if (!need_recover && !need_replace) { - rcu_read_unlock(); + if (!mrdev && !mreplace) continue; - } - still_degraded = 0; + still_degraded = false; /* want to reconstruct this device */ rb2 = r10_bio; sect = raid10_find_virt(conf, sector_nr, i); - if (sect >= mddev->resync_max_sectors) { + if (sect >= mddev->resync_max_sectors) /* last stripe is not complete - don't * try to recover this sector. */ - rcu_read_unlock(); continue; - } - if (mreplace && test_bit(Faulty, &mreplace->flags)) - mreplace = NULL; /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap */ - must_sync = md_bitmap_start_sync(mddev->bitmap, sect, - &sync_blocks, 1); + must_sync = md_bitmap_start_sync(mddev, sect, + &sync_blocks, true); if (sync_blocks < max_sync) max_sync = sync_blocks; if (!must_sync && @@ -3404,13 +3355,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, * that there will never be anything to do here */ chunks_skipped = -1; - rcu_read_unlock(); continue; } - atomic_inc(&mrdev->nr_pending); + if (mrdev) + atomic_inc(&mrdev->nr_pending); if (mreplace) atomic_inc(&mreplace->nr_pending); - rcu_read_unlock(); r10_bio = raid10_alloc_init_r10buf(conf); r10_bio->state = 0; @@ -3429,28 +3379,25 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* Need to check if the array will still be * degraded */ - rcu_read_lock(); for (j = 0; j < conf->geo.raid_disks; j++) { - struct md_rdev *rdev = rcu_dereference( - conf->mirrors[j].rdev); + struct md_rdev *rdev = conf->mirrors[j].rdev; + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { - still_degraded = 1; + still_degraded = false; break; } } - must_sync = md_bitmap_start_sync(mddev->bitmap, sect, - &sync_blocks, still_degraded); - + md_bitmap_start_sync(mddev, sect, &sync_blocks, + still_degraded); any_working = 0; for (j=0; j<conf->copies;j++) { int k; int d = r10_bio->devs[j].devnum; sector_t from_addr, to_addr; - struct md_rdev *rdev = - rcu_dereference(conf->mirrors[d].rdev); + struct md_rdev *rdev = conf->mirrors[d].rdev; sector_t sector, first_bad; - int bad_sectors; + sector_t bad_sectors; if (!rdev || !test_bit(In_sync, &rdev->flags)) continue; @@ -3474,7 +3421,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_next = biolist; biolist = bio; bio->bi_end_io = end_sync_read; - bio_set_op_attrs(bio, REQ_OP_READ, 0); + bio->bi_opf = REQ_OP_READ; if (test_bit(FailFast, &rdev->flags)) bio->bi_opf |= MD_FAILFAST; from_addr = r10_bio->devs[j].addr; @@ -3494,12 +3441,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[1].devnum = i; r10_bio->devs[1].addr = to_addr; - if (need_recover) { + if (mrdev) { bio = r10_bio->devs[1].bio; bio->bi_next = biolist; biolist = bio; bio->bi_end_io = end_sync_write; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf = REQ_OP_WRITE; bio->bi_iter.bi_sector = to_addr + mrdev->data_offset; bio_set_dev(bio, mrdev->bdev); @@ -3511,23 +3458,22 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - /* Note: if need_replace, then bio + /* Note: if replace is not NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. */ - if (!need_replace) + if (!mreplace) break; bio->bi_next = biolist; biolist = bio; bio->bi_end_io = end_sync_write; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf = REQ_OP_WRITE; bio->bi_iter.bi_sector = to_addr + mreplace->data_offset; bio_set_dev(bio, mreplace->bdev); atomic_inc(&r10_bio->remaining); break; } - rcu_read_unlock(); if (j == conf->copies) { /* Cannot recover, so abort the recovery or * record a bad block */ @@ -3539,7 +3485,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (k = 0; k < conf->copies; k++) if (r10_bio->devs[k].devnum == i) break; - if (!test_bit(In_sync, + if (mrdev && !test_bit(In_sync, &mrdev->flags) && !rdev_set_badblocks( mrdev, @@ -3560,17 +3506,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mdname(mddev)); mirror->recovery_disabled = mddev->recovery_disabled; + } else { + error_disk = i; } put_buf(r10_bio); if (rb2) atomic_dec(&rb2->remaining); r10_bio = rb2; - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); break; } - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); if (r10_bio->devs[0].bio->bi_opf & MD_FAILFAST) { @@ -3611,12 +3561,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, * safety reason, which ensures curr_resync_completed is * updated in bitmap_cond_end_sync. */ - md_bitmap_cond_end_sync(mddev->bitmap, sector_nr, + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high)); - if (!md_bitmap_start_sync(mddev->bitmap, sector_nr, - &sync_blocks, mddev->degraded) && + if (!md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, + mddev->degraded) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* We can skip this block */ @@ -3642,7 +3593,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; sector_t first_bad, sector; - int bad_sectors; + sector_t bad_sectors; struct md_rdev *rdev; if (r10_bio->devs[i].repl_bio) @@ -3650,12 +3601,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[i].bio; bio->bi_status = BLK_STS_IOERR; - rcu_read_lock(); - rdev = rcu_dereference(conf->mirrors[d].rdev); - if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { - rcu_read_unlock(); + rdev = conf->mirrors[d].rdev; + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; - } + sector = r10_bio->devs[i].addr; if (is_badblock(rdev, sector, max_sync, &first_bad, &bad_sectors)) { @@ -3665,7 +3614,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bad_sectors -= (sector - first_bad); if (max_sync > bad_sectors) max_sync = bad_sectors; - rcu_read_unlock(); continue; } } @@ -3674,18 +3622,17 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_next = biolist; biolist = bio; bio->bi_end_io = end_sync_read; - bio_set_op_attrs(bio, REQ_OP_READ, 0); + bio->bi_opf = REQ_OP_READ; if (test_bit(FailFast, &rdev->flags)) bio->bi_opf |= MD_FAILFAST; bio->bi_iter.bi_sector = sector + rdev->data_offset; bio_set_dev(bio, rdev->bdev); count++; - rdev = rcu_dereference(conf->mirrors[d].replacement); - if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { - rcu_read_unlock(); + rdev = conf->mirrors[d].replacement; + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; - } + atomic_inc(&rdev->nr_pending); /* Need to set up for writing to the replacement */ @@ -3696,13 +3643,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_next = biolist; biolist = bio; bio->bi_end_io = end_sync_write; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf = REQ_OP_WRITE; if (test_bit(FailFast, &rdev->flags)) bio->bi_opf |= MD_FAILFAST; bio->bi_iter.bi_sector = sector + rdev->data_offset; bio_set_dev(bio, rdev->bdev); count++; - rcu_read_unlock(); } if (count < 2) { @@ -3736,11 +3682,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (bio= biolist ; bio ; bio=bio->bi_next) { struct resync_pages *rp = get_resync_pages(bio); page = resync_fetch_page(rp, page_idx); - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + goto giveup; + } } nr_sectors += len>>9; sector_nr += len>>9; @@ -3754,7 +3700,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, conf->cluster_sync_low = mddev->curr_resync_completed; raid10_set_cluster_sync_high(conf); /* Send resync message */ - md_cluster_ops->resync_info_update(mddev, + mddev->cluster_ops->resync_info_update(mddev, conf->cluster_sync_low, conf->cluster_sync_high); } @@ -3787,7 +3733,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, } if (broadcast_msg) { raid10_set_cluster_sync_high(conf); - md_cluster_ops->resync_info_update(mddev, + mddev->cluster_ops->resync_info_update(mddev, conf->cluster_sync_low, conf->cluster_sync_high); } @@ -3802,7 +3748,6 @@ 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); } @@ -3936,6 +3881,20 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) return nc*fc; } +static void raid10_free_conf(struct r10conf *conf) +{ + if (!conf) + return; + + mempool_exit(&conf->r10bio_pool); + kfree(conf->mirrors); + kfree(conf->mirrors_old); + kfree(conf->mirrors_new); + safe_put_page(conf->tmppage); + bioset_exit(&conf->bio_split); + kfree(conf); +} + static struct r10conf *setup_conf(struct mddev *mddev) { struct r10conf *conf = NULL; @@ -4005,12 +3964,13 @@ static struct r10conf *setup_conf(struct mddev *mddev) INIT_LIST_HEAD(&conf->retry_list); INIT_LIST_HEAD(&conf->bio_end_io_list); - spin_lock_init(&conf->resync_lock); + seqlock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); atomic_set(&conf->nr_pending, 0); err = -ENOMEM; - conf->thread = md_register_thread(raid10d, mddev, "raid10"); + rcu_assign_pointer(conf->thread, + md_register_thread(raid10d, mddev, "raid10")); if (!conf->thread) goto out; @@ -4018,24 +3978,37 @@ static struct r10conf *setup_conf(struct mddev *mddev) return conf; out: - if (conf) { - mempool_exit(&conf->r10bio_pool); - kfree(conf->mirrors); - safe_put_page(conf->tmppage); - bioset_exit(&conf->bio_split); - kfree(conf); - } + raid10_free_conf(conf); return ERR_PTR(err); } -static void raid10_set_io_opt(struct r10conf *conf) +static unsigned int raid10_nr_stripes(struct r10conf *conf) { - int raid_disks = conf->geo.raid_disks; + unsigned int raid_disks = conf->geo.raid_disks; - if (!(conf->geo.raid_disks % conf->geo.near_copies)) - raid_disks /= conf->geo.near_copies; - blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) * - raid_disks); + if (conf->geo.raid_disks % conf->geo.near_copies) + return raid_disks; + return raid_disks / conf->geo.near_copies; +} + +static int raid10_set_queue_limits(struct mddev *mddev) +{ + struct r10conf *conf = mddev->private; + struct queue_limits lim; + int err; + + md_init_stacking_limits(&lim); + lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; + lim.logical_block_size = mddev->logical_block_size; + lim.io_min = mddev->chunk_sectors << 9; + lim.chunk_sectors = mddev->chunk_sectors; + lim.io_opt = lim.io_min * raid10_nr_stripes(conf); + lim.features |= BLK_FEAT_ATOMIC_WRITES; + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) + return err; + return queue_limits_set(mddev->gendisk->queue, &lim); } static int raid10_run(struct mddev *mddev) @@ -4047,10 +4020,7 @@ static int raid10_run(struct mddev *mddev) sector_t size; sector_t min_offset_diff = 0; int first = 1; - bool discard_supported = false; - - if (mddev_init_writes_pending(mddev) < 0) - return -ENOMEM; + int ret = -EIO; if (mddev->private == NULL) { conf = setup_conf(mddev); @@ -4062,6 +4032,9 @@ static int raid10_run(struct mddev *mddev) if (!conf) goto out; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); + if (mddev_is_clustered(conf->mddev)) { int fc, fo; @@ -4074,18 +4047,6 @@ static int raid10_run(struct mddev *mddev) } } - mddev->thread = conf->thread; - conf->thread = NULL; - - if (mddev->queue) { - blk_queue_max_discard_sectors(mddev->queue, - UINT_MAX); - blk_queue_max_write_same_sectors(mddev->queue, 0); - blk_queue_max_write_zeroes_sectors(mddev->queue, 0); - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - raid10_set_io_opt(conf); - } - rdev_for_each(rdev, mddev) { long long diff; @@ -4114,25 +4075,19 @@ static int raid10_run(struct mddev *mddev) if (first || diff < min_offset_diff) min_offset_diff = diff; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - disk->head_position = 0; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; first = 0; } - if (mddev->queue) { - if (discard_supported) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); + if (!mddev_is_dm(conf->mddev)) { + int err = raid10_set_queue_limits(mddev); + + if (err) { + ret = err; + goto out_free_conf; + } } + /* need to check that every block has at least one working mirror */ if (!enough(conf, -1)) { pr_err("md/raid10:%s: not enough operational mirrors.\n", @@ -4183,7 +4138,7 @@ static int raid10_run(struct mddev *mddev) disk->recovery_disabled = mddev->recovery_disabled - 1; } - if (mddev->recovery_cp != MaxSector) + if (mddev->resync_offset != MaxSector) pr_notice("md/raid10:%s: not clean -- starting background reconstruction\n", mdname(mddev)); pr_info("md/raid10:%s: active with %d out of %d devices\n", @@ -4219,37 +4174,22 @@ static int raid10_run(struct mddev *mddev) clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); - if (!mddev->sync_thread) - goto out_free_conf; + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } return 0; out_free_conf: - md_unregister_thread(&mddev->thread); - mempool_exit(&conf->r10bio_pool); - safe_put_page(conf->tmppage); - kfree(conf->mirrors); - kfree(conf); + md_unregister_thread(mddev, &mddev->thread); + raid10_free_conf(conf); mddev->private = NULL; out: - return -EIO; + return ret; } static void raid10_free(struct mddev *mddev, void *priv) { - struct r10conf *conf = priv; - - mempool_exit(&conf->r10bio_pool); - safe_put_page(conf->tmppage); - kfree(conf->mirrors); - kfree(conf->mirrors_old); - kfree(conf->mirrors_new); - bioset_exit(&conf->bio_split); - kfree(conf); + raid10_free_conf(priv); } static void raid10_quiesce(struct mddev *mddev, int quiesce) @@ -4290,15 +4230,18 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors) if (mddev->external_size && mddev->array_sectors > size) return -EINVAL; - if (mddev->bitmap) { - int ret = md_bitmap_resize(mddev->bitmap, size, 0, 0); + + if (md_bitmap_enabled(mddev, false)) { + int ret = mddev->bitmap_ops->resize(mddev, size, 0); + if (ret) return ret; } + md_set_array_sectors(mddev, size); if (sectors > mddev->dev_sectors && - mddev->recovery_cp > oldsize) { - mddev->recovery_cp = oldsize; + mddev->resync_offset > oldsize) { + mddev->resync_offset = oldsize; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } calc_sectors(conf, sectors); @@ -4327,7 +4270,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs) mddev->delta_disks = mddev->raid_disks; mddev->raid_disks *= 2; /* make sure it will be not marked as dirty */ - mddev->recovery_cp = MaxSector; + mddev->resync_offset = MaxSector; mddev->dev_sectors = size; conf = setup_conf(mddev); @@ -4337,7 +4280,6 @@ static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs) rdev->new_raid_disk = rdev->raid_disk * 2; rdev->sectors = size; } - conf->barrier = 1; } return conf; @@ -4433,11 +4375,11 @@ static int calc_degraded(struct r10conf *conf) int degraded, degraded2; int i; - rcu_read_lock(); degraded = 0; /* 'prev' section first */ for (i = 0; i < conf->prev.raid_disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = conf->mirrors[i].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags)) degraded++; else if (!test_bit(In_sync, &rdev->flags)) @@ -4447,13 +4389,12 @@ static int calc_degraded(struct r10conf *conf) */ degraded++; } - rcu_read_unlock(); if (conf->geo.raid_disks == conf->prev.raid_disks) return degraded; - rcu_read_lock(); degraded2 = 0; for (i = 0; i < conf->geo.raid_disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = conf->mirrors[i].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags)) degraded2++; else if (!test_bit(In_sync, &rdev->flags)) { @@ -4466,7 +4407,6 @@ static int calc_degraded(struct r10conf *conf) degraded2++; } } - rcu_read_unlock(); if (degraded2 > degraded) return degraded2; return degraded; @@ -4562,8 +4502,9 @@ static int raid10_start_reshape(struct mddev *mddev) oldsize = raid10_size(mddev, 0, 0); newsize = raid10_size(mddev, 0, conf->geo.raid_disks); - if (!mddev_is_clustered(mddev)) { - ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0); + if (!mddev_is_clustered(mddev) && + md_bitmap_enabled(mddev, false)) { + ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; else @@ -4578,20 +4519,21 @@ static int raid10_start_reshape(struct mddev *mddev) /* * some node is already performing reshape, and no need to - * call md_bitmap_resize again since it should be called when + * call bitmap_ops->resize again since it should be called when * receiving BITMAP_RESIZE msg */ if ((sb && (le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize)) goto out; - ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0); + /* cluster can't be setup without bitmap */ + ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; - ret = md_cluster_ops->resize_bitmaps(mddev, newsize, oldsize); + ret = mddev->cluster_ops->resize_bitmaps(mddev, newsize, oldsize); if (ret) { - md_bitmap_resize(mddev->bitmap, oldsize, 0, 0); + mddev->bitmap_ops->resize(mddev, oldsize, 0); goto abort; } } @@ -4631,17 +4573,9 @@ out: clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); - if (!mddev->sync_thread) { - ret = -EAGAIN; - goto abort; - } + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); conf->reshape_checkpoint = jiffies; - md_wakeup_thread(mddev->sync_thread); - md_new_event(mddev); + md_new_event(); return 0; abort: @@ -4813,7 +4747,7 @@ 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) @@ -4857,14 +4791,12 @@ read_more: return sectors_done; } - read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set); - - bio_set_dev(read_bio, rdev->bdev); + read_bio = bio_alloc_bioset(rdev->bdev, RESYNC_PAGES, REQ_OP_READ, + GFP_KERNEL, &mddev->bio_set); read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr + rdev->data_offset); read_bio->bi_private = r10_bio; read_bio->bi_end_io = end_reshape_read; - bio_set_op_attrs(read_bio, REQ_OP_READ, 0); r10_bio->master_bio = read_bio; r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum; @@ -4890,7 +4822,7 @@ read_more: conf->cluster_sync_low = sb_reshape_pos; } - md_cluster_ops->resync_info_update(mddev, conf->cluster_sync_low, + mddev->cluster_ops->resync_info_update(mddev, conf->cluster_sync_low, conf->cluster_sync_high); } @@ -4900,16 +4832,15 @@ read_more: blist = read_bio; read_bio->bi_next = NULL; - rcu_read_lock(); for (s = 0; s < conf->copies*2; s++) { struct bio *b; int d = r10_bio->devs[s/2].devnum; struct md_rdev *rdev2; if (s&1) { - rdev2 = rcu_dereference(conf->mirrors[d].replacement); + rdev2 = conf->mirrors[d].replacement; b = r10_bio->devs[s/2].repl_bio; } else { - rdev2 = rcu_dereference(conf->mirrors[d].rdev); + rdev2 = conf->mirrors[d].rdev; b = r10_bio->devs[s/2].bio; } if (!rdev2 || test_bit(Faulty, &rdev2->flags)) @@ -4919,7 +4850,7 @@ read_more: b->bi_iter.bi_sector = r10_bio->devs[s/2].addr + rdev2->new_data_offset; b->bi_end_io = end_reshape_write; - bio_set_op_attrs(b, REQ_OP_WRITE, 0); + b->bi_opf = REQ_OP_WRITE; b->bi_next = blist; blist = b; } @@ -4934,20 +4865,18 @@ read_more: if (len > PAGE_SIZE) len = PAGE_SIZE; for (bio = blist; bio ; bio = bio->bi_next) { - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return sectors_done; + } } sector_nr += len >> 9; nr_sectors += len >> 9; } - rcu_read_unlock(); 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); @@ -4996,21 +4925,17 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio) struct bio *b; int d = r10_bio->devs[s/2].devnum; struct md_rdev *rdev; - rcu_read_lock(); if (s&1) { - rdev = rcu_dereference(conf->mirrors[d].replacement); + rdev = conf->mirrors[d].replacement; b = r10_bio->devs[s/2].repl_bio; } else { - rdev = rcu_dereference(conf->mirrors[d].rdev); + rdev = conf->mirrors[d].rdev; b = r10_bio->devs[s/2].bio; } - if (!rdev || test_bit(Faulty, &rdev->flags)) { - rcu_read_unlock(); + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; - } + atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - md_sync_acct_bio(b, r10_bio->sectors); atomic_inc(&r10_bio->remaining); b->bi_next = NULL; submit_bio_noacct(b); @@ -5031,8 +4956,7 @@ static void end_reshape(struct r10conf *conf) conf->reshape_safe = MaxSector; spin_unlock_irq(&conf->device_lock); - if (conf->mddev->queue) - raid10_set_io_opt(conf); + mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf)); conf->fullsync = 0; } @@ -5041,7 +4965,7 @@ static void raid10_update_reshape_pos(struct mddev *mddev) struct r10conf *conf = mddev->private; sector_t lo, hi; - md_cluster_ops->resync_info_get(mddev, &lo, &hi); + mddev->cluster_ops->resync_info_get(mddev, &lo, &hi); if (((mddev->reshape_position <= hi) && (mddev->reshape_position >= lo)) || mddev->reshape_position == MaxSector) conf->reshape_progress = mddev->reshape_position; @@ -5080,10 +5004,9 @@ static int handle_reshape_read_error(struct mddev *mddev, if (s > (PAGE_SIZE >> 9)) s = PAGE_SIZE >> 9; - rcu_read_lock(); while (!success) { int d = r10b->devs[slot].devnum; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); + struct md_rdev *rdev = conf->mirrors[d].rdev; sector_t addr; if (rdev == NULL || test_bit(Faulty, &rdev->flags) || @@ -5092,14 +5015,12 @@ static int handle_reshape_read_error(struct mddev *mddev, addr = r10b->devs[slot].addr + idx * PAGE_SIZE; atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); success = sync_page_io(rdev, addr, s << 9, pages[idx], - REQ_OP_READ, 0, false); + REQ_OP_READ, false); rdev_dec_pending(rdev, mddev); - rcu_read_lock(); if (success) break; failed: @@ -5109,7 +5030,6 @@ static int handle_reshape_read_error(struct mddev *mddev, if (slot == first_slot) break; } - rcu_read_unlock(); if (!success) { /* couldn't read this block, must give up */ set_bit(MD_RECOVERY_INTR, @@ -5135,12 +5055,8 @@ static void end_reshape_write(struct bio *bio) struct md_rdev *rdev = NULL; d = find_bio_disk(conf, r10_bio, bio, &slot, &repl); - if (repl) - rdev = conf->mirrors[d].replacement; - if (!rdev) { - smp_mb(); - rdev = conf->mirrors[d].rdev; - } + rdev = repl ? conf->mirrors[d].replacement : + conf->mirrors[d].rdev; if (bio->bi_status) { /* FIXME should record badblock */ @@ -5168,25 +5084,23 @@ static void raid10_finish_reshape(struct mddev *mddev) return; if (mddev->delta_disks > 0) { - if (mddev->recovery_cp > mddev->resync_max_sectors) { - mddev->recovery_cp = mddev->resync_max_sectors; + if (mddev->resync_offset > mddev->resync_max_sectors) { + mddev->resync_offset = mddev->resync_max_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } mddev->resync_max_sectors = mddev->array_sectors; } else { int d; - rcu_read_lock(); for (d = conf->geo.raid_disks ; d < conf->geo.raid_disks - mddev->delta_disks; d++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); + struct md_rdev *rdev = conf->mirrors[d].rdev; if (rdev) clear_bit(In_sync, &rdev->flags); - rdev = rcu_dereference(conf->mirrors[d].replacement); + rdev = conf->mirrors[d].replacement; if (rdev) clear_bit(In_sync, &rdev->flags); } - rcu_read_unlock(); } mddev->layout = mddev->new_layout; mddev->chunk_sectors = 1 << conf->geo.chunk_shift; @@ -5197,9 +5111,13 @@ static void raid10_finish_reshape(struct mddev *mddev) static struct md_personality raid10_personality = { - .name = "raid10", - .level = 10, - .owner = THIS_MODULE, + .head = { + .type = MD_PERSONALITY, + .id = ID_RAID10, + .name = "raid10", + .owner = THIS_MODULE, + }, + .make_request = raid10_make_request, .run = raid10_run, .free = raid10_free, @@ -5219,22 +5137,20 @@ static struct md_personality raid10_personality = .update_reshape_pos = raid10_update_reshape_pos, }; -static int __init raid_init(void) +static int __init raid10_init(void) { - return register_md_personality(&raid10_personality); + return register_md_submodule(&raid10_personality.head); } -static void raid_exit(void) +static void __exit raid10_exit(void) { - unregister_md_personality(&raid10_personality); + unregister_md_submodule(&raid10_personality.head); } -module_init(raid_init); -module_exit(raid_exit); +module_init(raid10_init); +module_exit(raid10_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD"); 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); |