diff options
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r-- | drivers/md/raid5.c | 108 |
1 files changed, 60 insertions, 48 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index a086014dcd49..8ab8b65e1741 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -340,8 +340,7 @@ static void release_inactive_stripe_list(struct r5conf *conf, int hash) { int size; - unsigned long do_wakeup = 0; - int i = 0; + bool do_wakeup = false; unsigned long flags; if (hash == NR_STRIPE_HASH_LOCKS) { @@ -362,19 +361,15 @@ static void release_inactive_stripe_list(struct r5conf *conf, !list_empty(list)) atomic_dec(&conf->empty_inactive_list_nr); list_splice_tail_init(list, conf->inactive_list + hash); - do_wakeup |= 1 << hash; + do_wakeup = true; spin_unlock_irqrestore(conf->hash_locks + hash, flags); } size--; hash--; } - for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) { - if (do_wakeup & (1 << i)) - wake_up(&conf->wait_for_stripe[i]); - } - if (do_wakeup) { + wake_up(&conf->wait_for_stripe); if (atomic_read(&conf->active_stripes) == 0) wake_up(&conf->wait_for_quiescent); if (conf->retry_read_aligned) @@ -687,15 +682,14 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, if (!sh) { set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); - wait_event_exclusive_cmd( - conf->wait_for_stripe[hash], + wait_event_lock_irq( + conf->wait_for_stripe, !list_empty(conf->inactive_list + hash) && (atomic_read(&conf->active_stripes) < (conf->max_nr_stripes * 3 / 4) || !test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)), - spin_unlock_irq(conf->hash_locks + hash), - spin_lock_irq(conf->hash_locks + hash)); + *(conf->hash_locks + hash)); clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); } else { @@ -720,9 +714,6 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, } } while (sh == NULL); - if (!list_empty(conf->inactive_list + hash)) - wake_up(&conf->wait_for_stripe[hash]); - spin_unlock_irq(conf->hash_locks + hash); return sh; } @@ -2089,6 +2080,14 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors) unsigned long cpu; int err = 0; + /* + * Never shrink. And mddev_suspend() could deadlock if this is called + * from raid5d. In that case, scribble_disks and scribble_sectors + * should equal to new_disks and new_sectors + */ + if (conf->scribble_disks >= new_disks && + conf->scribble_sectors >= new_sectors) + return 0; mddev_suspend(conf->mddev); get_online_cpus(); for_each_present_cpu(cpu) { @@ -2110,6 +2109,10 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors) } put_online_cpus(); mddev_resume(conf->mddev); + if (!err) { + conf->scribble_disks = new_disks; + conf->scribble_sectors = new_sectors; + } return err; } @@ -2190,7 +2193,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) cnt = 0; list_for_each_entry(nsh, &newstripes, lru) { lock_device_hash_lock(conf, hash); - wait_event_exclusive_cmd(conf->wait_for_stripe[hash], + wait_event_cmd(conf->wait_for_stripe, !list_empty(conf->inactive_list + hash), unlock_device_hash_lock(conf, hash), lock_device_hash_lock(conf, hash)); @@ -2496,7 +2499,7 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous) dev->sector = raid5_compute_blocknr(sh, i, previous); } -static void error(struct mddev *mddev, struct md_rdev *rdev) +static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r5conf *conf = mddev->private; @@ -2958,7 +2961,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, * If several bio share a stripe. The bio bi_phys_segments acts as a * reference count to avoid race. The reference count should already be * increased before this function is called (for example, in - * make_request()), so other bio sharing this stripe will not free the + * raid5_make_request()), so other bio sharing this stripe will not free the * stripe. If a stripe is owned by one stripe, the stripe lock will * protect it. */ @@ -4233,10 +4236,9 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, list_del_init(&sh->batch_list); - WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) | + WARN_ONCE(sh->state & ((1 << STRIPE_ACTIVE) | (1 << STRIPE_SYNCING) | (1 << STRIPE_REPLACED) | - (1 << STRIPE_PREREAD_ACTIVE) | (1 << STRIPE_DELAYED) | (1 << STRIPE_BIT_DELAY) | (1 << STRIPE_FULL_WRITE) | @@ -4246,11 +4248,14 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, (1 << STRIPE_DISCARD) | (1 << STRIPE_BATCH_READY) | (1 << STRIPE_BATCH_ERR) | - (1 << STRIPE_BITMAP_PENDING))); - WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | - (1 << STRIPE_REPLACED))); + (1 << STRIPE_BITMAP_PENDING)), + "stripe state: %lx\n", sh->state); + WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | + (1 << STRIPE_REPLACED)), + "head stripe state: %lx\n", head_sh->state); set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | + (1 << STRIPE_PREREAD_ACTIVE) | (1 << STRIPE_DEGRADED)), head_sh->state & (1 << STRIPE_INSYNC)); @@ -5135,7 +5140,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } } -static void make_request(struct mddev *mddev, struct bio * bi) +static void raid5_make_request(struct mddev *mddev, struct bio * bi) { struct r5conf *conf = mddev->private; int dd_idx; @@ -5225,7 +5230,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) new_sector = raid5_compute_sector(conf, logical_sector, previous, &dd_idx, NULL); - pr_debug("raid456: make_request, sector %llu logical %llu\n", + pr_debug("raid456: raid5_make_request, sector %llu logical %llu\n", (unsigned long long)new_sector, (unsigned long long)logical_sector); @@ -5575,7 +5580,8 @@ ret: return retn; } -static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped) +static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr, + int *skipped) { struct r5conf *conf = mddev->private; struct stripe_head *sh; @@ -6375,6 +6381,8 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, break; case CPU_DEAD: case CPU_DEAD_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); break; default: @@ -6412,6 +6420,12 @@ static int raid5_alloc_percpu(struct r5conf *conf) } put_online_cpus(); + if (!err) { + conf->scribble_disks = max(conf->raid_disks, + conf->previous_raid_disks); + conf->scribble_sectors = max(conf->chunk_sectors, + conf->prev_chunk_sectors); + } return err; } @@ -6502,9 +6516,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) seqcount_init(&conf->gen_lock); mutex_init(&conf->cache_size_mutex); init_waitqueue_head(&conf->wait_for_quiescent); - for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) { - init_waitqueue_head(&conf->wait_for_stripe[i]); - } + init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); INIT_LIST_HEAD(&conf->handle_list); INIT_LIST_HEAD(&conf->hold_list); @@ -6674,7 +6686,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded return 0; } -static int run(struct mddev *mddev) +static int raid5_run(struct mddev *mddev) { struct r5conf *conf; int working_disks = 0; @@ -7013,8 +7025,8 @@ static int run(struct mddev *mddev) } if (discard_supported && - mddev->queue->limits.max_discard_sectors >= stripe && - mddev->queue->limits.discard_granularity >= stripe) + mddev->queue->limits.max_discard_sectors >= (stripe >> 9) && + mddev->queue->limits.discard_granularity >= stripe) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); else @@ -7048,7 +7060,7 @@ static void raid5_free(struct mddev *mddev, void *priv) mddev->to_remove = &raid5_attrs_group; } -static void status(struct seq_file *seq, struct mddev *mddev) +static void raid5_status(struct seq_file *seq, struct mddev *mddev) { struct r5conf *conf = mddev->private; int i; @@ -7864,15 +7876,15 @@ static struct md_personality raid6_personality = .name = "raid6", .level = 6, .owner = THIS_MODULE, - .make_request = make_request, - .run = run, + .make_request = raid5_make_request, + .run = raid5_run, .free = raid5_free, - .status = status, - .error_handler = error, + .status = raid5_status, + .error_handler = raid5_error, .hot_add_disk = raid5_add_disk, .hot_remove_disk= raid5_remove_disk, .spare_active = raid5_spare_active, - .sync_request = sync_request, + .sync_request = raid5_sync_request, .resize = raid5_resize, .size = raid5_size, .check_reshape = raid6_check_reshape, @@ -7887,15 +7899,15 @@ static struct md_personality raid5_personality = .name = "raid5", .level = 5, .owner = THIS_MODULE, - .make_request = make_request, - .run = run, + .make_request = raid5_make_request, + .run = raid5_run, .free = raid5_free, - .status = status, - .error_handler = error, + .status = raid5_status, + .error_handler = raid5_error, .hot_add_disk = raid5_add_disk, .hot_remove_disk= raid5_remove_disk, .spare_active = raid5_spare_active, - .sync_request = sync_request, + .sync_request = raid5_sync_request, .resize = raid5_resize, .size = raid5_size, .check_reshape = raid5_check_reshape, @@ -7911,15 +7923,15 @@ static struct md_personality raid4_personality = .name = "raid4", .level = 4, .owner = THIS_MODULE, - .make_request = make_request, - .run = run, + .make_request = raid5_make_request, + .run = raid5_run, .free = raid5_free, - .status = status, - .error_handler = error, + .status = raid5_status, + .error_handler = raid5_error, .hot_add_disk = raid5_add_disk, .hot_remove_disk= raid5_remove_disk, .spare_active = raid5_spare_active, - .sync_request = sync_request, + .sync_request = raid5_sync_request, .resize = raid5_resize, .size = raid5_size, .check_reshape = raid5_check_reshape, |