diff options
Diffstat (limited to 'drivers/md/raid5.c')
| -rw-r--r-- | drivers/md/raid5.c | 2254 |
1 files changed, 1678 insertions, 576 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 360f2b98f62..6234b2e8458 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -53,11 +53,18 @@ #include <linux/cpu.h> #include <linux/slab.h> #include <linux/ratelimit.h> +#include <linux/nodemask.h> +#include <trace/events/block.h> + #include "md.h" #include "raid5.h" #include "raid0.h" #include "bitmap.h" +#define cpu_to_group(cpu) cpu_to_node(cpu) +#define ANY_GROUP NUMA_NO_NODE + +static struct workqueue_struct *raid5_wq; /* * Stripe cache */ @@ -70,6 +77,7 @@ #define BYPASS_THRESHOLD 1 #define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) #define HASH_MASK (NR_HASH - 1) +#define MAX_STRIPE_BATCH 8 static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) { @@ -77,6 +85,42 @@ static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) return &conf->stripe_hashtbl[hash]; } +static inline int stripe_hash_locks_hash(sector_t sect) +{ + return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK; +} + +static inline void lock_device_hash_lock(struct r5conf *conf, int hash) +{ + spin_lock_irq(conf->hash_locks + hash); + spin_lock(&conf->device_lock); +} + +static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) +{ + spin_unlock(&conf->device_lock); + spin_unlock_irq(conf->hash_locks + hash); +} + +static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) +{ + int i; + local_irq_disable(); + spin_lock(conf->hash_locks); + for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) + spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks); + spin_lock(&conf->device_lock); +} + +static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) +{ + int i; + spin_unlock(&conf->device_lock); + for (i = NR_STRIPE_HASH_LOCKS; i; i--) + spin_unlock(conf->hash_locks + i - 1); + local_irq_enable(); +} + /* bio's attached to a stripe+device for I/O are linked together in bi_sector * order without overlap. There may be several bio's per stripe+device, and * a bio could span several devices. @@ -88,8 +132,8 @@ static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) */ static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector) { - int sectors = bio->bi_size >> 9; - if (bio->bi_sector + sectors < sector + STRIPE_SECTORS) + int sectors = bio_sectors(bio); + if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS) return bio->bi_next; else return NULL; @@ -99,34 +143,40 @@ static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector) * We maintain a biased count of active stripes in the bottom 16 bits of * bi_phys_segments, and a count of processed stripes in the upper 16 bits */ -static inline int raid5_bi_phys_segments(struct bio *bio) +static inline int raid5_bi_processed_stripes(struct bio *bio) { - return bio->bi_phys_segments & 0xffff; + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + return (atomic_read(segments) >> 16) & 0xffff; } -static inline int raid5_bi_hw_segments(struct bio *bio) +static inline int raid5_dec_bi_active_stripes(struct bio *bio) { - return (bio->bi_phys_segments >> 16) & 0xffff; + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + return atomic_sub_return(1, segments) & 0xffff; } -static inline int raid5_dec_bi_phys_segments(struct bio *bio) +static inline void raid5_inc_bi_active_stripes(struct bio *bio) { - --bio->bi_phys_segments; - return raid5_bi_phys_segments(bio); + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + atomic_inc(segments); } -static inline int raid5_dec_bi_hw_segments(struct bio *bio) +static inline void raid5_set_bi_processed_stripes(struct bio *bio, + unsigned int cnt) { - unsigned short val = raid5_bi_hw_segments(bio); + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + int old, new; - --val; - bio->bi_phys_segments = (val << 16) | raid5_bi_phys_segments(bio); - return val; + do { + old = atomic_read(segments); + new = (old & 0xffff) | (cnt << 16); + } while (atomic_cmpxchg(segments, old, new) != old); } -static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt) +static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt) { - bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16); + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + atomic_set(segments, cnt); } /* Find first data disk in a raid6 stripe */ @@ -175,7 +225,9 @@ static void return_io(struct bio *return_bi) return_bi = bi->bi_next; bi->bi_next = NULL; - bi->bi_size = 0; + bi->bi_iter.bi_size = 0; + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); bio_endio(bi, 0); bi = return_bi; } @@ -190,48 +242,203 @@ static int stripe_operations_active(struct stripe_head *sh) test_bit(STRIPE_COMPUTE_RUN, &sh->state); } -static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) +static void raid5_wakeup_stripe_thread(struct stripe_head *sh) { - if (atomic_dec_and_test(&sh->count)) { - BUG_ON(!list_empty(&sh->lru)); - BUG_ON(atomic_read(&conf->active_stripes)==0); - if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) - list_add_tail(&sh->lru, &conf->delayed_list); - else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && - sh->bm_seq - conf->seq_write > 0) - list_add_tail(&sh->lru, &conf->bitmap_list); - else { - clear_bit(STRIPE_BIT_DELAY, &sh->state); + struct r5conf *conf = sh->raid_conf; + struct r5worker_group *group; + int thread_cnt; + int i, cpu = sh->cpu; + + if (!cpu_online(cpu)) { + cpu = cpumask_any(cpu_online_mask); + sh->cpu = cpu; + } + + if (list_empty(&sh->lru)) { + struct r5worker_group *group; + group = conf->worker_groups + cpu_to_group(cpu); + list_add_tail(&sh->lru, &group->handle_list); + group->stripes_cnt++; + sh->group = group; + } + + if (conf->worker_cnt_per_group == 0) { + md_wakeup_thread(conf->mddev->thread); + return; + } + + group = conf->worker_groups + cpu_to_group(sh->cpu); + + group->workers[0].working = true; + /* at least one worker should run to avoid race */ + queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work); + + thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1; + /* wakeup more workers */ + for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) { + if (group->workers[i].working == false) { + group->workers[i].working = true; + queue_work_on(sh->cpu, raid5_wq, + &group->workers[i].work); + thread_cnt--; + } + } +} + +static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, + struct list_head *temp_inactive_list) +{ + BUG_ON(!list_empty(&sh->lru)); + BUG_ON(atomic_read(&conf->active_stripes)==0); + if (test_bit(STRIPE_HANDLE, &sh->state)) { + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + list_add_tail(&sh->lru, &conf->delayed_list); + if (atomic_read(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && + sh->bm_seq - conf->seq_write > 0) + list_add_tail(&sh->lru, &conf->bitmap_list); + else { + clear_bit(STRIPE_DELAYED, &sh->state); + clear_bit(STRIPE_BIT_DELAY, &sh->state); + if (conf->worker_cnt_per_group == 0) { list_add_tail(&sh->lru, &conf->handle_list); - } - md_wakeup_thread(conf->mddev->thread); - } else { - BUG_ON(stripe_operations_active(sh)); - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } - atomic_dec(&conf->active_stripes); - if (!test_bit(STRIPE_EXPANDING, &sh->state)) { - list_add_tail(&sh->lru, &conf->inactive_list); - wake_up(&conf->wait_for_stripe); - if (conf->retry_read_aligned) - md_wakeup_thread(conf->mddev->thread); + } else { + raid5_wakeup_stripe_thread(sh); + return; } } + md_wakeup_thread(conf->mddev->thread); + } else { + BUG_ON(stripe_operations_active(sh)); + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + if (atomic_dec_return(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + atomic_dec(&conf->active_stripes); + if (!test_bit(STRIPE_EXPANDING, &sh->state)) + list_add_tail(&sh->lru, temp_inactive_list); + } +} + +static void __release_stripe(struct r5conf *conf, struct stripe_head *sh, + struct list_head *temp_inactive_list) +{ + if (atomic_dec_and_test(&sh->count)) + do_release_stripe(conf, sh, temp_inactive_list); +} + +/* + * @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list + * + * Be careful: Only one task can add/delete stripes from temp_inactive_list at + * given time. Adding stripes only takes device lock, while deleting stripes + * only takes hash lock. + */ +static void release_inactive_stripe_list(struct r5conf *conf, + struct list_head *temp_inactive_list, + int hash) +{ + int size; + bool do_wakeup = false; + unsigned long flags; + + if (hash == NR_STRIPE_HASH_LOCKS) { + size = NR_STRIPE_HASH_LOCKS; + hash = NR_STRIPE_HASH_LOCKS - 1; + } else + size = 1; + while (size) { + struct list_head *list = &temp_inactive_list[size - 1]; + + /* + * We don't hold any lock here yet, get_active_stripe() might + * remove stripes from the list + */ + if (!list_empty_careful(list)) { + spin_lock_irqsave(conf->hash_locks + hash, flags); + if (list_empty(conf->inactive_list + hash) && + !list_empty(list)) + atomic_dec(&conf->empty_inactive_list_nr); + list_splice_tail_init(list, conf->inactive_list + hash); + do_wakeup = true; + spin_unlock_irqrestore(conf->hash_locks + hash, flags); + } + size--; + hash--; + } + + if (do_wakeup) { + wake_up(&conf->wait_for_stripe); + if (conf->retry_read_aligned) + md_wakeup_thread(conf->mddev->thread); } } +/* should hold conf->device_lock already */ +static int release_stripe_list(struct r5conf *conf, + struct list_head *temp_inactive_list) +{ + struct stripe_head *sh; + int count = 0; + struct llist_node *head; + + head = llist_del_all(&conf->released_stripes); + head = llist_reverse_order(head); + while (head) { + int hash; + + sh = llist_entry(head, struct stripe_head, release_list); + head = llist_next(head); + /* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */ + smp_mb(); + clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state); + /* + * Don't worry the bit is set here, because if the bit is set + * again, the count is always > 1. This is true for + * STRIPE_ON_UNPLUG_LIST bit too. + */ + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &temp_inactive_list[hash]); + count++; + } + + return count; +} + static void release_stripe(struct stripe_head *sh) { struct r5conf *conf = sh->raid_conf; unsigned long flags; + struct list_head list; + int hash; + bool wakeup; - spin_lock_irqsave(&conf->device_lock, flags); - __release_stripe(conf, sh); - spin_unlock_irqrestore(&conf->device_lock, flags); + /* Avoid release_list until the last reference. + */ + if (atomic_add_unless(&sh->count, -1, 1)) + return; + + if (unlikely(!conf->mddev->thread) || + test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state)) + goto slow_path; + wakeup = llist_add(&sh->release_list, &conf->released_stripes); + if (wakeup) + md_wakeup_thread(conf->mddev->thread); + return; +slow_path: + local_irq_save(flags); + /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */ + if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) { + INIT_LIST_HEAD(&list); + hash = sh->hash_lock_index; + do_release_stripe(conf, sh, &list); + spin_unlock(&conf->device_lock); + release_inactive_stripe_list(conf, &list, hash); + } + local_irq_restore(flags); } static inline void remove_hash(struct stripe_head *sh) @@ -254,18 +461,21 @@ static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh) /* find an idle stripe, make sure it is unhashed, and return it. */ -static struct stripe_head *get_free_stripe(struct r5conf *conf) +static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash) { struct stripe_head *sh = NULL; struct list_head *first; - if (list_empty(&conf->inactive_list)) + if (list_empty(conf->inactive_list + hash)) goto out; - first = conf->inactive_list.next; + first = (conf->inactive_list + hash)->next; sh = list_entry(first, struct stripe_head, lru); list_del_init(first); remove_hash(sh); atomic_inc(&conf->active_stripes); + BUG_ON(hash != sh->hash_lock_index); + if (list_empty(conf->inactive_list + hash)) + atomic_inc(&conf->empty_inactive_list_nr); out: return sh; } @@ -277,6 +487,7 @@ static void shrink_buffers(struct stripe_head *sh) int num = sh->raid_conf->pool_size; for (i = 0; i < num ; i++) { + WARN_ON(sh->dev[i].page != sh->dev[i].orig_page); p = sh->dev[i].page; if (!p) continue; @@ -297,6 +508,7 @@ static int grow_buffers(struct stripe_head *sh) return 1; } sh->dev[i].page = page; + sh->dev[i].orig_page = page; } return 0; } @@ -308,7 +520,7 @@ static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous, static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) { struct r5conf *conf = sh->raid_conf; - int i; + int i, seq; BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); @@ -318,7 +530,8 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) (unsigned long long)sh->sector); remove_hash(sh); - +retry: + seq = read_seqcount_begin(&conf->gen_lock); sh->generation = conf->generation - previous; sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks; sh->sector = sector; @@ -340,17 +553,19 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) dev->flags = 0; raid5_build_block(sh, i, previous); } + if (read_seqcount_retry(&conf->gen_lock, seq)) + goto retry; insert_hash(conf, sh); + sh->cpu = smp_processor_id(); } static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, short generation) { struct stripe_head *sh; - struct hlist_node *hn; pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector); - hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash) + hlist_for_each_entry(sh, stripe_hash(conf, sector), hash) if (sh->sector == sector && sh->generation == generation) return sh; pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector); @@ -379,6 +594,8 @@ static int calc_degraded(struct r5conf *conf) degraded = 0; for (i = 0; i < conf->previous_raid_disks; i++) { struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded++; else if (test_bit(In_sync, &rdev->flags)) @@ -403,6 +620,8 @@ static int calc_degraded(struct r5conf *conf) degraded2 = 0; for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded2++; else if (test_bit(In_sync, &rdev->flags)) @@ -440,55 +659,79 @@ get_active_stripe(struct r5conf *conf, sector_t sector, int previous, int noblock, int noquiesce) { struct stripe_head *sh; + int hash = stripe_hash_locks_hash(sector); pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); - spin_lock_irq(&conf->device_lock); + spin_lock_irq(conf->hash_locks + hash); do { wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0 || noquiesce, - conf->device_lock, /* nothing */); + *(conf->hash_locks + hash)); sh = __find_stripe(conf, sector, conf->generation - previous); if (!sh) { if (!conf->inactive_blocked) - sh = get_free_stripe(conf); + sh = get_free_stripe(conf, hash); if (noblock && sh == NULL) break; if (!sh) { conf->inactive_blocked = 1; - wait_event_lock_irq(conf->wait_for_stripe, - !list_empty(&conf->inactive_list) && - (atomic_read(&conf->active_stripes) - < (conf->max_nr_stripes *3/4) - || !conf->inactive_blocked), - conf->device_lock, - ); + 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) + || !conf->inactive_blocked), + *(conf->hash_locks + hash)); conf->inactive_blocked = 0; - } else - init_stripe(sh, sector, previous); - } else { - if (atomic_read(&sh->count)) { - BUG_ON(!list_empty(&sh->lru) - && !test_bit(STRIPE_EXPANDING, &sh->state)); } else { + init_stripe(sh, sector, previous); + atomic_inc(&sh->count); + } + } else if (!atomic_inc_not_zero(&sh->count)) { + spin_lock(&conf->device_lock); + if (!atomic_read(&sh->count)) { if (!test_bit(STRIPE_HANDLE, &sh->state)) atomic_inc(&conf->active_stripes); - if (list_empty(&sh->lru) && - !test_bit(STRIPE_EXPANDING, &sh->state)) - BUG(); + BUG_ON(list_empty(&sh->lru) && + !test_bit(STRIPE_EXPANDING, &sh->state)); list_del_init(&sh->lru); + if (sh->group) { + sh->group->stripes_cnt--; + sh->group = NULL; + } } + atomic_inc(&sh->count); + spin_unlock(&conf->device_lock); } } while (sh == NULL); - if (sh) - atomic_inc(&sh->count); - - spin_unlock_irq(&conf->device_lock); + spin_unlock_irq(conf->hash_locks + hash); return sh; } +/* Determine if 'data_offset' or 'new_data_offset' should be used + * in this stripe_head. + */ +static int use_new_offset(struct r5conf *conf, struct stripe_head *sh) +{ + sector_t progress = conf->reshape_progress; + /* Need a memory barrier to make sure we see the value + * of conf->generation, or ->data_offset that was set before + * reshape_progress was updated. + */ + smp_rmb(); + if (progress == MaxSector) + return 0; + if (sh->generation == conf->generation - 1) + return 0; + /* We are in a reshape, and this is a new-generation stripe, + * so use new_data_offset. + */ + return 1; +} + static void raid5_end_read_request(struct bio *bi, int error); static void @@ -511,6 +754,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) rw = WRITE_FUA; else rw = WRITE; + if (test_bit(R5_Discard, &sh->dev[i].flags)) + rw |= REQ_DISCARD; } else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) rw = READ; else if (test_and_clear_bit(R5_WantReplace, @@ -519,18 +764,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) replace_only = 1; } else continue; + if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags)) + rw |= REQ_SYNC; bi = &sh->dev[i].req; rbi = &sh->dev[i].rreq; /* For writing to replacement */ - bi->bi_rw = rw; - rbi->bi_rw = rw; - if (rw & WRITE) { - bi->bi_end_io = raid5_end_write_request; - rbi->bi_end_io = raid5_end_write_request; - } else - bi->bi_end_io = raid5_end_read_request; - rcu_read_lock(); rrdev = rcu_dereference(conf->disks[i].replacement); smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */ @@ -584,6 +823,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) * a chance*/ md_check_recovery(conf->mddev); } + /* + * Because md_wait_for_blocked_rdev + * will dec nr_pending, we must + * increment it first. + */ + atomic_inc(&rdev->nr_pending); md_wait_for_blocked_rdev(rdev, conf->mddev); } else { /* Acknowledged bad block - skip the write */ @@ -599,20 +844,47 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) set_bit(STRIPE_IO_STARTED, &sh->state); + bio_reset(bi); bi->bi_bdev = rdev->bdev; + bi->bi_rw = rw; + bi->bi_end_io = (rw & WRITE) + ? raid5_end_write_request + : raid5_end_read_request; + bi->bi_private = sh; + pr_debug("%s: for %llu schedule op %ld on disc %d\n", __func__, (unsigned long long)sh->sector, bi->bi_rw, i); atomic_inc(&sh->count); - bi->bi_sector = sh->sector + rdev->data_offset; - bi->bi_flags = 1 << BIO_UPTODATE; - bi->bi_idx = 0; + if (use_new_offset(conf, sh)) + bi->bi_iter.bi_sector = (sh->sector + + rdev->new_data_offset); + else + bi->bi_iter.bi_sector = (sh->sector + + rdev->data_offset); + if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + bi->bi_rw |= REQ_NOMERGE; + + if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].vec.bv_page = sh->dev[i].page; + bi->bi_vcnt = 1; bi->bi_io_vec[0].bv_len = STRIPE_SIZE; bi->bi_io_vec[0].bv_offset = 0; - bi->bi_size = STRIPE_SIZE; - bi->bi_next = NULL; + bi->bi_iter.bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + bi->bi_vcnt = 0; if (rrdev) set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); + + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(bi->bi_bdev), + bi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); generic_make_request(bi); } if (rrdev) { @@ -622,19 +894,41 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) set_bit(STRIPE_IO_STARTED, &sh->state); + bio_reset(rbi); rbi->bi_bdev = rrdev->bdev; + rbi->bi_rw = rw; + BUG_ON(!(rw & WRITE)); + rbi->bi_end_io = raid5_end_write_request; + rbi->bi_private = sh; + pr_debug("%s: for %llu schedule op %ld on " "replacement disc %d\n", __func__, (unsigned long long)sh->sector, rbi->bi_rw, i); atomic_inc(&sh->count); - rbi->bi_sector = sh->sector + rrdev->data_offset; - rbi->bi_flags = 1 << BIO_UPTODATE; - rbi->bi_idx = 0; + if (use_new_offset(conf, sh)) + rbi->bi_iter.bi_sector = (sh->sector + + rrdev->new_data_offset); + else + rbi->bi_iter.bi_sector = (sh->sector + + rrdev->data_offset); + if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].rvec.bv_page = sh->dev[i].page; + rbi->bi_vcnt = 1; rbi->bi_io_vec[0].bv_len = STRIPE_SIZE; rbi->bi_io_vec[0].bv_offset = 0; - rbi->bi_size = STRIPE_SIZE; - rbi->bi_next = NULL; + rbi->bi_iter.bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + rbi->bi_vcnt = 0; + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), + rbi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); generic_make_request(rbi); } if (!rdev && !rrdev) { @@ -649,27 +943,28 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) } static struct dma_async_tx_descriptor * -async_copy_data(int frombio, struct bio *bio, struct page *page, - sector_t sector, struct dma_async_tx_descriptor *tx) +async_copy_data(int frombio, struct bio *bio, struct page **page, + sector_t sector, struct dma_async_tx_descriptor *tx, + struct stripe_head *sh) { - struct bio_vec *bvl; + struct bio_vec bvl; + struct bvec_iter iter; struct page *bio_page; - int i; int page_offset; struct async_submit_ctl submit; enum async_tx_flags flags = 0; - if (bio->bi_sector >= sector) - page_offset = (signed)(bio->bi_sector - sector) * 512; + if (bio->bi_iter.bi_sector >= sector) + page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512; else - page_offset = (signed)(sector - bio->bi_sector) * -512; + page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512; if (frombio) flags |= ASYNC_TX_FENCE; init_async_submit(&submit, flags, tx, NULL, NULL, NULL); - bio_for_each_segment(bvl, bio, i) { - int len = bvl->bv_len; + bio_for_each_segment(bvl, bio, iter) { + int len = bvl.bv_len; int clen; int b_offset = 0; @@ -685,13 +980,18 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, clen = len; if (clen > 0) { - b_offset += bvl->bv_offset; - bio_page = bvl->bv_page; - if (frombio) - tx = async_memcpy(page, bio_page, page_offset, + b_offset += bvl.bv_offset; + bio_page = bvl.bv_page; + if (frombio) { + if (sh->raid_conf->skip_copy && + b_offset == 0 && page_offset == 0 && + clen == STRIPE_SIZE) + *page = bio_page; + else + tx = async_memcpy(*page, bio_page, page_offset, b_offset, clen, &submit); - else - tx = async_memcpy(bio_page, page, b_offset, + } else + tx = async_memcpy(bio_page, *page, b_offset, page_offset, clen, &submit); } /* chain the operations */ @@ -709,14 +1009,12 @@ static void ops_complete_biofill(void *stripe_head_ref) { struct stripe_head *sh = stripe_head_ref; struct bio *return_bi = NULL; - struct r5conf *conf = sh->raid_conf; int i; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); /* clear completed biofills */ - spin_lock_irq(&conf->device_lock); for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -731,10 +1029,10 @@ static void ops_complete_biofill(void *stripe_head_ref) BUG_ON(!dev->read); rbi = dev->read; dev->read = NULL; - while (rbi && rbi->bi_sector < + while (rbi && rbi->bi_iter.bi_sector < dev->sector + STRIPE_SECTORS) { rbi2 = r5_next_bio(rbi, dev->sector); - if (!raid5_dec_bi_phys_segments(rbi)) { + if (!raid5_dec_bi_active_stripes(rbi)) { rbi->bi_next = return_bi; return_bi = rbi; } @@ -742,7 +1040,6 @@ static void ops_complete_biofill(void *stripe_head_ref) } } } - spin_unlock_irq(&conf->device_lock); clear_bit(STRIPE_BIOFILL_RUN, &sh->state); return_io(return_bi); @@ -754,7 +1051,6 @@ static void ops_complete_biofill(void *stripe_head_ref) static void ops_run_biofill(struct stripe_head *sh) { struct dma_async_tx_descriptor *tx = NULL; - struct r5conf *conf = sh->raid_conf; struct async_submit_ctl submit; int i; @@ -765,14 +1061,14 @@ static void ops_run_biofill(struct stripe_head *sh) struct r5dev *dev = &sh->dev[i]; if (test_bit(R5_Wantfill, &dev->flags)) { struct bio *rbi; - spin_lock_irq(&conf->device_lock); + spin_lock_irq(&sh->stripe_lock); dev->read = rbi = dev->toread; dev->toread = NULL; - spin_unlock_irq(&conf->device_lock); - while (rbi && rbi->bi_sector < + spin_unlock_irq(&sh->stripe_lock); + while (rbi && rbi->bi_iter.bi_sector < dev->sector + STRIPE_SECTORS) { - tx = async_copy_data(0, rbi, dev->page, - dev->sector, tx); + tx = async_copy_data(0, rbi, &dev->page, + dev->sector, tx, sh); rbi = r5_next_bio(rbi, dev->sector); } } @@ -1104,19 +1400,31 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { struct bio *wbi; - spin_lock_irq(&sh->raid_conf->device_lock); + spin_lock_irq(&sh->stripe_lock); chosen = dev->towrite; dev->towrite = NULL; BUG_ON(dev->written); wbi = dev->written = chosen; - spin_unlock_irq(&sh->raid_conf->device_lock); + spin_unlock_irq(&sh->stripe_lock); + WARN_ON(dev->page != dev->orig_page); - while (wbi && wbi->bi_sector < + while (wbi && wbi->bi_iter.bi_sector < dev->sector + STRIPE_SECTORS) { if (wbi->bi_rw & REQ_FUA) set_bit(R5_WantFUA, &dev->flags); - tx = async_copy_data(1, wbi, dev->page, - dev->sector, tx); + if (wbi->bi_rw & REQ_SYNC) + set_bit(R5_SyncIO, &dev->flags); + if (wbi->bi_rw & REQ_DISCARD) + set_bit(R5_Discard, &dev->flags); + else { + tx = async_copy_data(1, wbi, &dev->page, + dev->sector, tx, sh); + if (dev->page != dev->orig_page) { + set_bit(R5_SkipCopy, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + clear_bit(R5_OVERWRITE, &dev->flags); + } + } wbi = r5_next_bio(wbi, dev->sector); } } @@ -1132,21 +1440,27 @@ static void ops_complete_reconstruct(void *stripe_head_ref) int pd_idx = sh->pd_idx; int qd_idx = sh->qd_idx; int i; - bool fua = false; + bool fua = false, sync = false, discard = false; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); - for (i = disks; i--; ) + for (i = disks; i--; ) { fua |= test_bit(R5_WantFUA, &sh->dev[i].flags); + sync |= test_bit(R5_SyncIO, &sh->dev[i].flags); + discard |= test_bit(R5_Discard, &sh->dev[i].flags); + } for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (dev->written || i == pd_idx || i == qd_idx) { - set_bit(R5_UPTODATE, &dev->flags); + if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) + set_bit(R5_UPTODATE, &dev->flags); if (fua) set_bit(R5_WantFUA, &dev->flags); + if (sync) + set_bit(R5_SyncIO, &dev->flags); } } @@ -1178,6 +1492,18 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); + for (i = 0; i < sh->disks; i++) { + if (pd_idx == i) + continue; + if (!test_bit(R5_Discard, &sh->dev[i].flags)) + break; + } + if (i >= sh->disks) { + atomic_inc(&sh->count); + set_bit(R5_Discard, &sh->dev[pd_idx].flags); + ops_complete_reconstruct(sh); + return; + } /* check if prexor is active which means only process blocks * that are part of a read-modify-write (written) */ @@ -1222,10 +1548,24 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, { struct async_submit_ctl submit; struct page **blocks = percpu->scribble; - int count; + int count, i; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); + for (i = 0; i < sh->disks; i++) { + if (sh->pd_idx == i || sh->qd_idx == i) + continue; + if (!test_bit(R5_Discard, &sh->dev[i].flags)) + break; + } + if (i >= sh->disks) { + atomic_inc(&sh->count); + set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); + set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags); + ops_complete_reconstruct(sh); + return; + } + count = set_syndrome_sources(blocks, sh); atomic_inc(&sh->count); @@ -1301,7 +1641,7 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu &sh->ops.zero_sum_result, percpu->spare_page, &submit); } -static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request) +static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) { int overlap_clear = 0, i, disks = sh->disks; struct dma_async_tx_descriptor *tx = NULL; @@ -1366,37 +1706,7 @@ static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request) put_cpu(); } -#ifdef CONFIG_MULTICORE_RAID456 -static void async_run_ops(void *param, async_cookie_t cookie) -{ - struct stripe_head *sh = param; - unsigned long ops_request = sh->ops.request; - - clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state); - wake_up(&sh->ops.wait_for_ops); - - __raid_run_ops(sh, ops_request); - release_stripe(sh); -} - -static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) -{ - /* since handle_stripe can be called outside of raid5d context - * we need to ensure sh->ops.request is de-staged before another - * request arrives - */ - wait_event(sh->ops.wait_for_ops, - !test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state)); - sh->ops.request = ops_request; - - atomic_inc(&sh->count); - async_schedule(async_run_ops, sh); -} -#else -#define raid_run_ops __raid_run_ops -#endif - -static int grow_one_stripe(struct r5conf *conf) +static int grow_one_stripe(struct r5conf *conf, int hash) { struct stripe_head *sh; sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL); @@ -1404,15 +1714,15 @@ static int grow_one_stripe(struct r5conf *conf) return 0; sh->raid_conf = conf; - #ifdef CONFIG_MULTICORE_RAID456 - init_waitqueue_head(&sh->ops.wait_for_ops); - #endif + + spin_lock_init(&sh->stripe_lock); if (grow_buffers(sh)) { shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); return 0; } + sh->hash_lock_index = hash; /* we just created an active stripe so... */ atomic_set(&sh->count, 1); atomic_inc(&conf->active_stripes); @@ -1425,6 +1735,7 @@ static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; int devs = max(conf->raid_disks, conf->previous_raid_disks); + int hash; if (conf->mddev->gendisk) sprintf(conf->cache_name[0], @@ -1442,9 +1753,13 @@ static int grow_stripes(struct r5conf *conf, int num) return 1; conf->slab_cache = sc; conf->pool_size = devs; - while (num--) - if (!grow_one_stripe(conf)) + hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; + while (num--) { + if (!grow_one_stripe(conf, hash)) return 1; + conf->max_nr_stripes++; + hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; + } return 0; } @@ -1478,7 +1793,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) * This happens in stages: * 1/ create a new kmem_cache and allocate the required number of * stripe_heads. - * 2/ gather all the old stripe_heads and tranfer the pages across + * 2/ gather all the old stripe_heads and transfer the pages across * to the new stripe_heads. This will have the side effect of * freezing the array as once all stripe_heads have been collected, * no IO will be possible. Old stripe heads are freed once their @@ -1502,6 +1817,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) int err; struct kmem_cache *sc; int i; + int hash, cnt; if (newsize <= conf->pool_size) return 0; /* never bother to shrink */ @@ -1523,9 +1839,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) break; nsh->raid_conf = conf; - #ifdef CONFIG_MULTICORE_RAID456 - init_waitqueue_head(&nsh->ops.wait_for_ops); - #endif + spin_lock_init(&nsh->stripe_lock); list_add(&nsh->lru, &newstripes); } @@ -1543,20 +1857,31 @@ static int resize_stripes(struct r5conf *conf, int newsize) * OK, we have enough stripes, start collecting inactive * stripes and copying them over */ + hash = 0; + cnt = 0; list_for_each_entry(nsh, &newstripes, lru) { - spin_lock_irq(&conf->device_lock); - wait_event_lock_irq(conf->wait_for_stripe, - !list_empty(&conf->inactive_list), - conf->device_lock, - ); - osh = get_free_stripe(conf); - spin_unlock_irq(&conf->device_lock); + lock_device_hash_lock(conf, 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)); + osh = get_free_stripe(conf, hash); + unlock_device_hash_lock(conf, hash); atomic_set(&nsh->count, 1); - for(i=0; i<conf->pool_size; i++) + for(i=0; i<conf->pool_size; i++) { nsh->dev[i].page = osh->dev[i].page; + nsh->dev[i].orig_page = osh->dev[i].page; + } for( ; i<newsize; i++) nsh->dev[i].page = NULL; + nsh->hash_lock_index = hash; kmem_cache_free(conf->slab_cache, osh); + cnt++; + if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS + + !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) { + hash++; + cnt = 0; + } } kmem_cache_destroy(conf->slab_cache); @@ -1602,6 +1927,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) if (nsh->dev[i].page == NULL) { struct page *p = alloc_page(GFP_NOIO); nsh->dev[i].page = p; + nsh->dev[i].orig_page = p; if (!p) err = -ENOMEM; } @@ -1615,13 +1941,13 @@ static int resize_stripes(struct r5conf *conf, int newsize) return err; } -static int drop_one_stripe(struct r5conf *conf) +static int drop_one_stripe(struct r5conf *conf, int hash) { struct stripe_head *sh; - spin_lock_irq(&conf->device_lock); - sh = get_free_stripe(conf); - spin_unlock_irq(&conf->device_lock); + spin_lock_irq(conf->hash_locks + hash); + sh = get_free_stripe(conf, hash); + spin_unlock_irq(conf->hash_locks + hash); if (!sh) return 0; BUG_ON(atomic_read(&sh->count)); @@ -1633,8 +1959,10 @@ static int drop_one_stripe(struct r5conf *conf) static void shrink_stripes(struct r5conf *conf) { - while (drop_one_stripe(conf)) - ; + int hash; + for (hash = 0; hash < NR_STRIPE_HASH_LOCKS; hash++) + while (drop_one_stripe(conf, hash)) + ; if (conf->slab_cache) kmem_cache_destroy(conf->slab_cache); @@ -1649,7 +1977,7 @@ static void raid5_end_read_request(struct bio * bi, int error) int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); char b[BDEVNAME_SIZE]; struct md_rdev *rdev = NULL; - + sector_t s; for (i=0 ; i<disks; i++) if (bi == &sh->dev[i].req) @@ -1672,6 +2000,10 @@ static void raid5_end_read_request(struct bio * bi, int error) if (!rdev) rdev = conf->disks[i].rdev; + if (use_new_offset(conf, sh)) + s = sh->sector + rdev->new_data_offset; + else + s = sh->sector + rdev->data_offset; if (uptodate) { set_bit(R5_UPTODATE, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) { @@ -1684,18 +2016,20 @@ static void raid5_end_read_request(struct bio * bi, int error) "md/raid:%s: read error corrected" " (%lu sectors at %llu on %s)\n", mdname(conf->mddev), STRIPE_SECTORS, - (unsigned long long)(sh->sector - + rdev->data_offset), + (unsigned long long)s, bdevname(rdev->bdev, b)); atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); - } + } else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); + if (atomic_read(&rdev->read_errors)) atomic_set(&rdev->read_errors, 0); } else { const char *bdn = bdevname(rdev->bdev, b); int retry = 0; + int set_bad = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); @@ -1705,41 +2039,51 @@ static void raid5_end_read_request(struct bio * bi, int error) "md/raid:%s: read error on replacement device " "(sector %llu on %s).\n", mdname(conf->mddev), - (unsigned long long)(sh->sector - + rdev->data_offset), + (unsigned long long)s, bdn); - else if (conf->mddev->degraded >= conf->max_degraded) + else if (conf->mddev->degraded >= conf->max_degraded) { + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error not correctable " "(sector %llu on %s).\n", mdname(conf->mddev), - (unsigned long long)(sh->sector - + rdev->data_offset), + (unsigned long long)s, bdn); - else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) + } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { /* Oh, no!!! */ + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error NOT corrected!! " "(sector %llu on %s).\n", mdname(conf->mddev), - (unsigned long long)(sh->sector - + rdev->data_offset), + (unsigned long long)s, bdn); - else if (atomic_read(&rdev->read_errors) + } else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING "md/raid:%s: Too many read errors, failing device %s.\n", mdname(conf->mddev), bdn); else retry = 1; + if (set_bad && test_bit(In_sync, &rdev->flags) + && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + retry = 1; if (retry) - set_bit(R5_ReadError, &sh->dev[i].flags); + if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) { + set_bit(R5_ReadError, &sh->dev[i].flags); + clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); + } else + set_bit(R5_ReadNoMerge, &sh->dev[i].flags); else { clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, rdev); + if (!(set_bad + && test_bit(In_sync, &rdev->flags) + && rdev_set_badblocks( + rdev, sh->sector, STRIPE_SECTORS, 0))) + md_error(conf->mddev, rdev); } } rdev_dec_pending(rdev, conf->mddev); @@ -1794,6 +2138,7 @@ static void raid5_end_write_request(struct bio *bi, int error) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { if (!uptodate) { + set_bit(STRIPE_DEGRADED, &sh->state); set_bit(WriteErrorSeen, &rdev->flags); set_bit(R5_WriteError, &sh->dev[i].flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -1801,8 +2146,15 @@ static void raid5_end_write_request(struct bio *bi, int error) &rdev->mddev->recovery); } else if (is_badblock(rdev, sh->sector, STRIPE_SECTORS, - &first_bad, &bad_sectors)) + &first_bad, &bad_sectors)) { set_bit(R5_MadeGood, &sh->dev[i].flags); + if (test_bit(R5_ReadError, &sh->dev[i].flags)) + /* That was a successful write so make + * sure it looks like we already did + * a re-write. + */ + set_bit(R5_ReWrite, &sh->dev[i].flags); + } } rdev_dec_pending(rdev, conf->mddev); @@ -1813,24 +2165,20 @@ static void raid5_end_write_request(struct bio *bi, int error) } static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); - + static void raid5_build_block(struct stripe_head *sh, int i, int previous) { struct r5dev *dev = &sh->dev[i]; bio_init(&dev->req); dev->req.bi_io_vec = &dev->vec; - dev->req.bi_vcnt++; - dev->req.bi_max_vecs++; + dev->req.bi_max_vecs = 1; dev->req.bi_private = sh; - dev->vec.bv_page = dev->page; bio_init(&dev->rreq); dev->rreq.bi_io_vec = &dev->rvec; - dev->rreq.bi_vcnt++; - dev->rreq.bi_max_vecs++; + dev->rreq.bi_max_vecs = 1; dev->rreq.bi_private = sh; - dev->rvec.bv_page = dev->page; dev->flags = 0; dev->sector = compute_blocknr(sh, i, previous); @@ -2199,17 +2547,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int level = conf->level; if (rcw) { - /* if we are not expanding this is a proper write request, and - * there will be bios with new data to be drained into the - * stripe cache - */ - if (!expand) { - sh->reconstruct_state = reconstruct_state_drain_run; - set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); - } else - sh->reconstruct_state = reconstruct_state_run; - - set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -2222,6 +2559,21 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, s->locked++; } } + /* if we are not expanding this is a proper write request, and + * there will be bios with new data to be drained into the + * stripe cache + */ + if (!expand) { + if (!s->locked) + /* False alarm, nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_drain_run; + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + } else + sh->reconstruct_state = reconstruct_state_run; + + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); + if (s->locked + conf->max_degraded == disks) if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) atomic_inc(&conf->pending_full_writes); @@ -2230,11 +2582,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); - sh->reconstruct_state = reconstruct_state_prexor_drain_run; - set_bit(STRIPE_OP_PREXOR, &s->ops_request); - set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); - set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); - for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (i == pd_idx) @@ -2249,6 +2596,13 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, s->locked++; } } + if (!s->locked) + /* False alarm - nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_prexor_drain_run; + set_bit(STRIPE_OP_PREXOR, &s->ops_request); + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); } /* keep the parity disk(s) locked while asynchronous operations @@ -2284,49 +2638,56 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in int firstwrite=0; pr_debug("adding bi b#%llu to stripe s#%llu\n", - (unsigned long long)bi->bi_sector, + (unsigned long long)bi->bi_iter.bi_sector, (unsigned long long)sh->sector); - - spin_lock_irq(&conf->device_lock); + /* + * 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 + * stripe. If a stripe is owned by one stripe, the stripe lock will + * protect it. + */ + spin_lock_irq(&sh->stripe_lock); if (forwrite) { bip = &sh->dev[dd_idx].towrite; - if (*bip == NULL && sh->dev[dd_idx].written == NULL) + if (*bip == NULL) firstwrite = 1; } else bip = &sh->dev[dd_idx].toread; - while (*bip && (*bip)->bi_sector < bi->bi_sector) { - if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector) + while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) { + if (bio_end_sector(*bip) > bi->bi_iter.bi_sector) goto overlap; bip = & (*bip)->bi_next; } - if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9)) + if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi)) goto overlap; BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next); if (*bip) bi->bi_next = *bip; *bip = bi; - bi->bi_phys_segments++; + raid5_inc_bi_active_stripes(bi); if (forwrite) { /* check if page is covered */ sector_t sector = sh->dev[dd_idx].sector; for (bi=sh->dev[dd_idx].towrite; sector < sh->dev[dd_idx].sector + STRIPE_SECTORS && - bi && bi->bi_sector <= sector; + bi && bi->bi_iter.bi_sector <= sector; bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) { - if (bi->bi_sector + (bi->bi_size>>9) >= sector) - sector = bi->bi_sector + (bi->bi_size>>9); + if (bio_end_sector(bi) >= sector) + sector = bio_end_sector(bi); } if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); } - spin_unlock_irq(&conf->device_lock); pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", - (unsigned long long)(*bip)->bi_sector, + (unsigned long long)(*bip)->bi_iter.bi_sector, (unsigned long long)sh->sector, dd_idx); + spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap && firstwrite) { bitmap_startwrite(conf->mddev->bitmap, sh->sector, @@ -2338,7 +2699,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in overlap: set_bit(R5_Overlap, &sh->dev[dd_idx].flags); - spin_unlock_irq(&conf->device_lock); + spin_unlock_irq(&sh->stripe_lock); return 0; } @@ -2388,38 +2749,46 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, rdev_dec_pending(rdev, conf->mddev); } } - spin_lock_irq(&conf->device_lock); + spin_lock_irq(&sh->stripe_lock); /* fail all writes first */ bi = sh->dev[i].towrite; sh->dev[i].towrite = NULL; - if (bi) { - s->to_write--; + spin_unlock_irq(&sh->stripe_lock); + if (bi) bitmap_end = 1; - } if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) wake_up(&conf->wait_for_overlap); - while (bi && bi->bi_sector < + while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (!raid5_dec_bi_phys_segments(bi)) { + if (!raid5_dec_bi_active_stripes(bi)) { md_write_end(conf->mddev); bi->bi_next = *return_bi; *return_bi = bi; } bi = nextbi; } + if (bitmap_end) + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, 0, 0); + bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; sh->dev[i].written = NULL; + if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) { + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].page = sh->dev[i].orig_page; + } + if (bi) bitmap_end = 1; - while (bi && bi->bi_sector < + while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (!raid5_dec_bi_phys_segments(bi)) { + if (!raid5_dec_bi_active_stripes(bi)) { md_write_end(conf->mddev); bi->bi_next = *return_bi; *return_bi = bi; @@ -2433,24 +2802,24 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, if (!test_bit(R5_Wantfill, &sh->dev[i].flags) && (!test_bit(R5_Insync, &sh->dev[i].flags) || test_bit(R5_ReadError, &sh->dev[i].flags))) { + spin_lock_irq(&sh->stripe_lock); bi = sh->dev[i].toread; sh->dev[i].toread = NULL; + spin_unlock_irq(&sh->stripe_lock); if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) wake_up(&conf->wait_for_overlap); - if (bi) s->to_read--; - while (bi && bi->bi_sector < + while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (!raid5_dec_bi_phys_segments(bi)) { + if (!raid5_dec_bi_active_stripes(bi)) { bi->bi_next = *return_bi; *return_bi = bi; } bi = nextbi; } } - spin_unlock_irq(&conf->device_lock); if (bitmap_end) bitmap_endwrite(conf->mddev->bitmap, sh->sector, STRIPE_SECTORS, 0, 0); @@ -2472,39 +2841,43 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, int abort = 0; int i; - md_done_sync(conf->mddev, STRIPE_SECTORS, 0); clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); s->syncing = 0; s->replacing = 0; /* There is nothing more to do for sync/check/repair. + * Don't even need to abort as that is handled elsewhere + * if needed, and not always wanted e.g. if there is a known + * bad block here. * For recover/replace we need to record a bad block on all * non-sync devices, or abort the recovery */ - if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) - return; - /* During recovery devices cannot be removed, so locking and - * refcounting of rdevs is not needed - */ - for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = conf->disks[i].rdev; - if (rdev - && !test_bit(Faulty, &rdev->flags) - && !test_bit(In_sync, &rdev->flags) - && !rdev_set_badblocks(rdev, sh->sector, - STRIPE_SECTORS, 0)) - abort = 1; - rdev = conf->disks[i].replacement; - if (rdev - && !test_bit(Faulty, &rdev->flags) - && !test_bit(In_sync, &rdev->flags) - && !rdev_set_badblocks(rdev, sh->sector, - STRIPE_SECTORS, 0)) - abort = 1; - } - if (abort) { - conf->recovery_disabled = conf->mddev->recovery_disabled; - set_bit(MD_RECOVERY_INTR, &conf->mddev->recovery); + if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) { + /* During recovery devices cannot be removed, so + * locking and refcounting of rdevs is not needed + */ + for (i = 0; i < conf->raid_disks; i++) { + struct md_rdev *rdev = conf->disks[i].rdev; + if (rdev + && !test_bit(Faulty, &rdev->flags) + && !test_bit(In_sync, &rdev->flags) + && !rdev_set_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0)) + abort = 1; + rdev = conf->disks[i].replacement; + if (rdev + && !test_bit(Faulty, &rdev->flags) + && !test_bit(In_sync, &rdev->flags) + && !rdev_set_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0)) + abort = 1; + } + if (abort) + conf->recovery_disabled = + conf->mddev->recovery_disabled; } + md_done_sync(conf->mddev, STRIPE_SECTORS, !abort); } static int want_replace(struct stripe_head *sh, int disk_idx) @@ -2546,8 +2919,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, (s->failed >= 1 && fdev[0]->toread) || (s->failed >= 2 && fdev[1]->toread) || (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite && + (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) && !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || - (sh->raid_conf->level == 6 && s->failed && s->to_write))) { + (sh->raid_conf->level == 6 && s->failed && s->to_write && + s->to_write < sh->raid_conf->raid_disks - 2 && + (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) { /* we would like to get this block, possibly by computing it, * otherwise read it if the backing disk is insync */ @@ -2644,40 +3020,67 @@ static void handle_stripe_clean_event(struct r5conf *conf, { int i; struct r5dev *dev; + int discard_pending = 0; for (i = disks; i--; ) if (sh->dev[i].written) { dev = &sh->dev[i]; if (!test_bit(R5_LOCKED, &dev->flags) && - test_bit(R5_UPTODATE, &dev->flags)) { + (test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Discard, &dev->flags) || + test_bit(R5_SkipCopy, &dev->flags))) { /* We can return any write requests */ struct bio *wbi, *wbi2; - int bitmap_end = 0; pr_debug("Return write for disc %d\n", i); - spin_lock_irq(&conf->device_lock); + if (test_and_clear_bit(R5_Discard, &dev->flags)) + clear_bit(R5_UPTODATE, &dev->flags); + if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) { + WARN_ON(test_bit(R5_UPTODATE, &dev->flags)); + dev->page = dev->orig_page; + } wbi = dev->written; dev->written = NULL; - while (wbi && wbi->bi_sector < + while (wbi && wbi->bi_iter.bi_sector < dev->sector + STRIPE_SECTORS) { wbi2 = r5_next_bio(wbi, dev->sector); - if (!raid5_dec_bi_phys_segments(wbi)) { + if (!raid5_dec_bi_active_stripes(wbi)) { md_write_end(conf->mddev); wbi->bi_next = *return_bi; *return_bi = wbi; } wbi = wbi2; } - if (dev->towrite == NULL) - bitmap_end = 1; - spin_unlock_irq(&conf->device_lock); - if (bitmap_end) - bitmap_endwrite(conf->mddev->bitmap, - sh->sector, - STRIPE_SECTORS, + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, !test_bit(STRIPE_DEGRADED, &sh->state), - 0); - } + 0); + } else if (test_bit(R5_Discard, &dev->flags)) + discard_pending = 1; + WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); + WARN_ON(dev->page != dev->orig_page); } + if (!discard_pending && + test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); + if (sh->qd_idx >= 0) { + clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags); + } + /* now that discard is done we can proceed with any sync */ + clear_bit(STRIPE_DISCARD, &sh->state); + /* + * SCSI discard will change some bio fields and the stripe has + * no updated data, so remove it from hash list and the stripe + * will be reinitialized + */ + spin_lock_irq(&conf->device_lock); + remove_hash(sh); + spin_unlock_irq(&conf->device_lock); + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) + set_bit(STRIPE_HANDLE, &sh->state); + + } if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) if (atomic_dec_and_test(&conf->pending_full_writes)) @@ -2690,12 +3093,25 @@ static void handle_stripe_dirtying(struct r5conf *conf, int disks) { int rmw = 0, rcw = 0, i; - if (conf->max_degraded == 2) { - /* RAID6 requires 'rcw' in current implementation - * Calculate the real rcw later - for now fake it + sector_t recovery_cp = conf->mddev->recovery_cp; + + /* RAID6 requires 'rcw' in current implementation. + * Otherwise, check whether resync is now happening or should start. + * If yes, then the array is dirty (after unclean shutdown or + * initial creation), so parity in some stripes might be inconsistent. + * In this case, we need to always do reconstruct-write, to ensure + * that in case of drive failure or read-error correction, we + * generate correct data from the parity. + */ + if (conf->max_degraded == 2 || + (recovery_cp < MaxSector && sh->sector >= recovery_cp)) { + /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ rcw = 1; rmw = 2; + pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n", + conf->max_degraded, (unsigned long long)recovery_cp, + (unsigned long long)sh->sector); } else for (i = disks; i--; ) { /* would I have to read this buffer for read_modify_write */ struct r5dev *dev = &sh->dev[i]; @@ -2713,7 +3129,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { - if (test_bit(R5_Insync, &dev->flags)) rcw++; + if (test_bit(R5_Insync, &dev->flags)) + rcw++; else rcw += 2*disks; } @@ -2721,8 +3138,12 @@ static void handle_stripe_dirtying(struct r5conf *conf, pr_debug("for sector %llu, rmw=%d rcw=%d\n", (unsigned long long)sh->sector, rmw, rcw); set_bit(STRIPE_HANDLE, &sh->state); - if (rmw < rcw && rmw > 0) + if (rmw < rcw && rmw > 0) { /* prefer read-modify-write, but need to get some data */ + if (conf->mddev->queue) + blk_add_trace_msg(conf->mddev->queue, + "raid5 rmw %llu %d", + (unsigned long long)sh->sector, rmw); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if ((dev->towrite || i == sh->pd_idx) && @@ -2730,10 +3151,10 @@ static void handle_stripe_dirtying(struct r5conf *conf, !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags)) && test_bit(R5_Insync, &dev->flags)) { - if ( - test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - pr_debug("Read_old block " - "%d for r-m-w\n", i); + if (test_bit(STRIPE_PREREAD_ACTIVE, + &sh->state)) { + pr_debug("Read_old block %d for r-m-w\n", + i); set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); s->locked++; @@ -2743,8 +3164,10 @@ static void handle_stripe_dirtying(struct r5conf *conf, } } } + } if (rcw <= rmw && rcw > 0) { /* want reconstruct write, but need to get some data */ + int qread =0; rcw = 0; for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -2754,21 +3177,25 @@ static void handle_stripe_dirtying(struct r5conf *conf, !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { rcw++; - if (!test_bit(R5_Insync, &dev->flags)) - continue; /* it's a failed drive */ - if ( - test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + if (test_bit(R5_Insync, &dev->flags) && + test_bit(STRIPE_PREREAD_ACTIVE, + &sh->state)) { pr_debug("Read_old block " "%d for Reconstruct\n", i); set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); s->locked++; + qread++; } else { set_bit(STRIPE_DELAYED, &sh->state); set_bit(STRIPE_HANDLE, &sh->state); } } } + if (rcw && conf->mddev->queue) + blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d", + (unsigned long long)sh->sector, + rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); } /* now if nothing is locked, and if we have enough data, * we can start a write request @@ -2847,7 +3274,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, */ set_bit(STRIPE_INSYNC, &sh->state); else { - conf->mddev->resync_mismatches += STRIPE_SECTORS; + atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) /* don't try to repair!! */ set_bit(STRIPE_INSYNC, &sh->state); @@ -2999,7 +3426,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, */ } } else { - conf->mddev->resync_mismatches += STRIPE_SECTORS; + atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) /* don't try to repair!! */ set_bit(STRIPE_INSYNC, &sh->state); @@ -3090,10 +3517,7 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) } /* done submitting copies, wait for them to complete */ - if (tx) { - async_tx_ack(tx); - dma_wait_for_async_tx(tx); - } + async_tx_quiesce(&tx); } /* @@ -3127,7 +3551,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) /* Now to look around and see what can be done */ rcu_read_lock(); - spin_lock_irq(&conf->device_lock); for (i=disks; i--; ) { struct md_rdev *rdev; sector_t first_bad; @@ -3204,7 +3627,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) /* Not in-sync */; else if (is_bad) { /* also not in-sync */ - if (!test_bit(WriteErrorSeen, &rdev->flags)) { + if (!test_bit(WriteErrorSeen, &rdev->flags) && + test_bit(R5_UPTODATE, &dev->flags)) { /* treat as in-sync, but with a read error * which we can now try to correct */ @@ -3224,7 +3648,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) */ set_bit(R5_Insync, &dev->flags); - if (rdev && test_bit(R5_WriteError, &dev->flags)) { + if (test_bit(R5_WriteError, &dev->flags)) { /* This flag does not apply to '.replacement' * only to .rdev, so make sure to check that*/ struct md_rdev *rdev2 = rcu_dereference( @@ -3237,7 +3661,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) } else clear_bit(R5_WriteError, &dev->flags); } - if (rdev && test_bit(R5_MadeGood, &dev->flags)) { + if (test_bit(R5_MadeGood, &dev->flags)) { /* This flag does not apply to '.replacement' * only to .rdev, so make sure to check that*/ struct md_rdev *rdev2 = rcu_dereference( @@ -3272,17 +3696,18 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) do_recovery = 1; } } - spin_unlock_irq(&conf->device_lock); if (test_bit(STRIPE_SYNCING, &sh->state)) { /* If there is a failed device being replaced, * we must be recovering. * else if we are after recovery_cp, we must be syncing + * else if MD_RECOVERY_REQUESTED is set, we also are syncing. * else we can only be replacing * sync and recovery both need to read all devices, and so * use the same flag. */ if (do_recovery || - sh->sector >= conf->mddev->recovery_cp) + sh->sector >= conf->mddev->recovery_cp || + test_bit(MD_RECOVERY_REQUESTED, &(conf->mddev->recovery))) s->syncing = 1; else s->replacing = 1; @@ -3307,9 +3732,16 @@ static void handle_stripe(struct stripe_head *sh) return; } - if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { - set_bit(STRIPE_SYNCING, &sh->state); - clear_bit(STRIPE_INSYNC, &sh->state); + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + spin_lock(&sh->stripe_lock); + /* Cannot process 'sync' concurrently with 'discard' */ + if (!test_bit(STRIPE_DISCARD, &sh->state) && + test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + set_bit(STRIPE_SYNCING, &sh->state); + clear_bit(STRIPE_INSYNC, &sh->state); + clear_bit(STRIPE_REPLACED, &sh->state); + } + spin_unlock(&sh->stripe_lock); } clear_bit(STRIPE_DELAYED, &sh->state); @@ -3358,38 +3790,6 @@ static void handle_stripe(struct stripe_head *sh) handle_failed_sync(conf, sh, &s); } - /* - * might be able to return some write requests if the parity blocks - * are safe, or on a failed drive - */ - pdev = &sh->dev[sh->pd_idx]; - s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx) - || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx); - qdev = &sh->dev[sh->qd_idx]; - s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx) - || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx) - || conf->level < 6; - - if (s.written && - (s.p_failed || ((test_bit(R5_Insync, &pdev->flags) - && !test_bit(R5_LOCKED, &pdev->flags) - && test_bit(R5_UPTODATE, &pdev->flags)))) && - (s.q_failed || ((test_bit(R5_Insync, &qdev->flags) - && !test_bit(R5_LOCKED, &qdev->flags) - && test_bit(R5_UPTODATE, &qdev->flags))))) - handle_stripe_clean_event(conf, sh, disks, &s.return_bi); - - /* Now we might consider reading some blocks, either to check/generate - * parity, or to satisfy requests - * or to load a block that is being partially written. - */ - if (s.to_read || s.non_overwrite - || (conf->level == 6 && s.to_write && s.failed) - || (s.syncing && (s.uptodate + s.compute < disks)) - || s.replacing - || s.expanding) - handle_stripe_fill(sh, &s, disks); - /* Now we check to see if any write operations have recently * completed */ @@ -3403,9 +3803,11 @@ static void handle_stripe(struct stripe_head *sh) /* All the 'written' buffers and the parity block are ready to * be written back to disk */ - BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags)); + BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags) && + !test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)); BUG_ON(sh->qd_idx >= 0 && - !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags)); + !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags) && + !test_bit(R5_Discard, &sh->dev[sh->qd_idx].flags)); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_bit(R5_LOCKED, &dev->flags) && @@ -3425,6 +3827,40 @@ static void handle_stripe(struct stripe_head *sh) s.dec_preread_active = 1; } + /* + * might be able to return some write requests if the parity blocks + * are safe, or on a failed drive + */ + pdev = &sh->dev[sh->pd_idx]; + s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx) + || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx); + qdev = &sh->dev[sh->qd_idx]; + s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx) + || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx) + || conf->level < 6; + + if (s.written && + (s.p_failed || ((test_bit(R5_Insync, &pdev->flags) + && !test_bit(R5_LOCKED, &pdev->flags) + && (test_bit(R5_UPTODATE, &pdev->flags) || + test_bit(R5_Discard, &pdev->flags))))) && + (s.q_failed || ((test_bit(R5_Insync, &qdev->flags) + && !test_bit(R5_LOCKED, &qdev->flags) + && (test_bit(R5_UPTODATE, &qdev->flags) || + test_bit(R5_Discard, &qdev->flags)))))) + handle_stripe_clean_event(conf, sh, disks, &s.return_bi); + + /* Now we might consider reading some blocks, either to check/generate + * parity, or to satisfy requests + * or to load a block that is being partially written. + */ + if (s.to_read || s.non_overwrite + || (conf->level == 6 && s.to_write && s.failed) + || (s.syncing && (s.uptodate + s.compute < disks)) + || s.replacing + || s.expanding) + handle_stripe_fill(sh, &s, disks); + /* Now to consider new write requests and what else, if anything * should be read. We do not handle new writes when: * 1/ A 'write' operation (copy+xor) is already in flight. @@ -3449,22 +3885,28 @@ static void handle_stripe(struct stripe_head *sh) handle_parity_checks5(conf, sh, &s, disks); } - if (s.replacing && s.locked == 0 - && !test_bit(STRIPE_INSYNC, &sh->state)) { + if ((s.replacing || s.syncing) && s.locked == 0 + && !test_bit(STRIPE_COMPUTE_RUN, &sh->state) + && !test_bit(STRIPE_REPLACED, &sh->state)) { /* Write out to replacement devices where possible */ for (i = 0; i < conf->raid_disks; i++) - if (test_bit(R5_UPTODATE, &sh->dev[i].flags) && - test_bit(R5_NeedReplace, &sh->dev[i].flags)) { + if (test_bit(R5_NeedReplace, &sh->dev[i].flags)) { + WARN_ON(!test_bit(R5_UPTODATE, &sh->dev[i].flags)); set_bit(R5_WantReplace, &sh->dev[i].flags); set_bit(R5_LOCKED, &sh->dev[i].flags); s.locked++; } - set_bit(STRIPE_INSYNC, &sh->state); + if (s.replacing) + set_bit(STRIPE_INSYNC, &sh->state); + set_bit(STRIPE_REPLACED, &sh->state); } if ((s.syncing || s.replacing) && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state) && test_bit(STRIPE_INSYNC, &sh->state)) { md_done_sync(conf->mddev, STRIPE_SECTORS, 1); clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); } /* If the failed drives are just a ReadError, then we might need @@ -3539,8 +3981,18 @@ static void handle_stripe(struct stripe_head *sh) finish: /* wait for this device to become unblocked */ - if (conf->mddev->external && unlikely(s.blocked_rdev)) - md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev); + if (unlikely(s.blocked_rdev)) { + if (conf->mddev->external) + md_wait_for_blocked_rdev(s.blocked_rdev, + conf->mddev); + else + /* Internal metadata will immediately + * be written by raid5d, so we don't + * need to wait here. + */ + rdev_dec_pending(s.blocked_rdev, + conf->mddev); + } if (s.handle_bad_blocks) for (i = disks; i--; ) { @@ -3557,7 +4009,7 @@ finish: if (test_and_clear_bit(R5_MadeGood, &dev->flags)) { rdev = conf->disks[i].rdev; rdev_clear_badblocks(rdev, sh->sector, - STRIPE_SECTORS); + STRIPE_SECTORS, 0); rdev_dec_pending(rdev, conf->mddev); } if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) { @@ -3566,7 +4018,7 @@ finish: /* rdev have been moved down */ rdev = conf->disks[i].rdev; rdev_clear_badblocks(rdev, sh->sector, - STRIPE_SECTORS); + STRIPE_SECTORS, 0); rdev_dec_pending(rdev, conf->mddev); } } @@ -3604,11 +4056,13 @@ static void raid5_activate_delayed(struct r5conf *conf) if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); list_add_tail(&sh->lru, &conf->hold_list); + raid5_wakeup_stripe_thread(sh); } } } -static void activate_bit_delay(struct r5conf *conf) +static void activate_bit_delay(struct r5conf *conf, + struct list_head *temp_inactive_list) { /* device_lock is held */ struct list_head head; @@ -3616,9 +4070,11 @@ static void activate_bit_delay(struct r5conf *conf) list_del_init(&conf->bitmap_list); while (!list_empty(&head)) { struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru); + int hash; list_del_init(&sh->lru); atomic_inc(&sh->count); - __release_stripe(conf, sh); + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &temp_inactive_list[hash]); } } @@ -3634,7 +4090,7 @@ int md_raid5_congested(struct mddev *mddev, int bits) return 1; if (conf->quiesce) return 1; - if (list_empty_careful(&conf->inactive_list)) + if (atomic_read(&conf->empty_inactive_list_nr)) return 1; return 0; @@ -3678,9 +4134,9 @@ static int raid5_mergeable_bvec(struct request_queue *q, static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) { - sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev); + sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev); unsigned int chunk_sectors = mddev->chunk_sectors; - unsigned int bio_sectors = bio->bi_size >> 9; + unsigned int bio_sectors = bio_sectors(bio); if (mddev->new_chunk_sectors < mddev->chunk_sectors) chunk_sectors = mddev->new_chunk_sectors; @@ -3723,7 +4179,7 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf) * this sets the active strip count to 1 and the processed * strip count to zero (upper 8 bits) */ - bi->bi_phys_segments = 1; /* biased count of active stripes */ + raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */ } return bi; @@ -3754,6 +4210,8 @@ static void raid5_align_endio(struct bio *bi, int error) rdev_dec_pending(rdev, conf->mddev); if (!error && uptodate) { + trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev), + raid_bi, 0); bio_endio(raid_bi, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); @@ -3770,7 +4228,7 @@ static int bio_fits_rdev(struct bio *bi) { struct request_queue *q = bdev_get_queue(bi->bi_bdev); - if ((bi->bi_size>>9) > queue_max_sectors(q)) + if (bio_sectors(bi) > queue_max_sectors(q)) return 0; blk_recount_segments(q, bi); if (bi->bi_phys_segments > queue_max_segments(q)) @@ -3813,11 +4271,11 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) /* * compute position */ - align_bi->bi_sector = raid5_compute_sector(conf, raid_bio->bi_sector, - 0, - &dd_idx, NULL); + align_bi->bi_iter.bi_sector = + raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, + 0, &dd_idx, NULL); - end_sector = align_bi->bi_sector + (align_bi->bi_size >> 9); + end_sector = bio_end_sector(align_bi); rcu_read_lock(); rdev = rcu_dereference(conf->disks[dd_idx].replacement); if (!rdev || test_bit(Faulty, &rdev->flags) || @@ -3838,10 +4296,10 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) raid_bio->bi_next = (void*)rdev; align_bi->bi_bdev = rdev->bdev; align_bi->bi_flags &= ~(1 << BIO_SEG_VALID); - align_bi->bi_sector += rdev->data_offset; if (!bio_fits_rdev(align_bi) || - is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9, + is_badblock(rdev, align_bi->bi_iter.bi_sector, + bio_sectors(align_bi), &first_bad, &bad_sectors)) { /* too big in some way, or has a known bad block */ bio_put(align_bi); @@ -3849,13 +4307,20 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) return 0; } + /* No reshape active, so we can trust rdev->data_offset */ + align_bi->bi_iter.bi_sector += rdev->data_offset; + spin_lock_irq(&conf->device_lock); wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0, - conf->device_lock, /* nothing */); + conf->device_lock); atomic_inc(&conf->active_aligned_reads); spin_unlock_irq(&conf->device_lock); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev), + align_bi, disk_devt(mddev->gendisk), + raid_bio->bi_iter.bi_sector); generic_make_request(align_bi); return 1; } else { @@ -3875,18 +4340,35 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) * head of the hold_list has changed, i.e. the head was promoted to the * handle_list. */ -static struct stripe_head *__get_priority_stripe(struct r5conf *conf) +static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) { - struct stripe_head *sh; + struct stripe_head *sh = NULL, *tmp; + struct list_head *handle_list = NULL; + struct r5worker_group *wg = NULL; + + if (conf->worker_cnt_per_group == 0) { + handle_list = &conf->handle_list; + } else if (group != ANY_GROUP) { + handle_list = &conf->worker_groups[group].handle_list; + wg = &conf->worker_groups[group]; + } else { + int i; + for (i = 0; i < conf->group_cnt; i++) { + handle_list = &conf->worker_groups[i].handle_list; + wg = &conf->worker_groups[i]; + if (!list_empty(handle_list)) + break; + } + } pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n", __func__, - list_empty(&conf->handle_list) ? "empty" : "busy", + list_empty(handle_list) ? "empty" : "busy", list_empty(&conf->hold_list) ? "empty" : "busy", atomic_read(&conf->pending_full_writes), conf->bypass_count); - if (!list_empty(&conf->handle_list)) { - sh = list_entry(conf->handle_list.next, typeof(*sh), lru); + if (!list_empty(handle_list)) { + sh = list_entry(handle_list->next, typeof(*sh), lru); if (list_empty(&conf->hold_list)) conf->bypass_count = 0; @@ -3904,20 +4386,200 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf) ((conf->bypass_threshold && conf->bypass_count > conf->bypass_threshold) || atomic_read(&conf->pending_full_writes) == 0)) { - sh = list_entry(conf->hold_list.next, - typeof(*sh), lru); - conf->bypass_count -= conf->bypass_threshold; - if (conf->bypass_count < 0) - conf->bypass_count = 0; - } else + + list_for_each_entry(tmp, &conf->hold_list, lru) { + if (conf->worker_cnt_per_group == 0 || + group == ANY_GROUP || + !cpu_online(tmp->cpu) || + cpu_to_group(tmp->cpu) == group) { + sh = tmp; + break; + } + } + + if (sh) { + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } + wg = NULL; + } + + if (!sh) return NULL; + if (wg) { + wg->stripes_cnt--; + sh->group = NULL; + } list_del_init(&sh->lru); - atomic_inc(&sh->count); - BUG_ON(atomic_read(&sh->count) != 1); + BUG_ON(atomic_inc_return(&sh->count) != 1); return sh; } +struct raid5_plug_cb { + struct blk_plug_cb cb; + struct list_head list; + struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; +}; + +static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule) +{ + struct raid5_plug_cb *cb = container_of( + blk_cb, struct raid5_plug_cb, cb); + struct stripe_head *sh; + struct mddev *mddev = cb->cb.data; + struct r5conf *conf = mddev->private; + int cnt = 0; + int hash; + + if (cb->list.next && !list_empty(&cb->list)) { + spin_lock_irq(&conf->device_lock); + while (!list_empty(&cb->list)) { + sh = list_first_entry(&cb->list, struct stripe_head, lru); + list_del_init(&sh->lru); + /* + * avoid race release_stripe_plug() sees + * STRIPE_ON_UNPLUG_LIST clear but the stripe + * is still in our list + */ + smp_mb__before_atomic(); + clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state); + /* + * STRIPE_ON_RELEASE_LIST could be set here. In that + * case, the count is always > 1 here + */ + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &cb->temp_inactive_list[hash]); + cnt++; + } + spin_unlock_irq(&conf->device_lock); + } + release_inactive_stripe_list(conf, cb->temp_inactive_list, + NR_STRIPE_HASH_LOCKS); + if (mddev->queue) + trace_block_unplug(mddev->queue, cnt, !from_schedule); + kfree(cb); +} + +static void release_stripe_plug(struct mddev *mddev, + struct stripe_head *sh) +{ + struct blk_plug_cb *blk_cb = blk_check_plugged( + raid5_unplug, mddev, + sizeof(struct raid5_plug_cb)); + struct raid5_plug_cb *cb; + + if (!blk_cb) { + release_stripe(sh); + return; + } + + cb = container_of(blk_cb, struct raid5_plug_cb, cb); + + if (cb->list.next == NULL) { + int i; + INIT_LIST_HEAD(&cb->list); + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(cb->temp_inactive_list + i); + } + + if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)) + list_add_tail(&sh->lru, &cb->list); + else + release_stripe(sh); +} + +static void make_discard_request(struct mddev *mddev, struct bio *bi) +{ + struct r5conf *conf = mddev->private; + sector_t logical_sector, last_sector; + struct stripe_head *sh; + int remaining; + int stripe_sectors; + + if (mddev->reshape_position != MaxSector) + /* Skip discard while reshape is happening */ + return; + + logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1); + last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9); + + bi->bi_next = NULL; + bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ + + stripe_sectors = conf->chunk_sectors * + (conf->raid_disks - conf->max_degraded); + logical_sector = DIV_ROUND_UP_SECTOR_T(logical_sector, + stripe_sectors); + sector_div(last_sector, stripe_sectors); + + logical_sector *= conf->chunk_sectors; + last_sector *= conf->chunk_sectors; + + for (; logical_sector < last_sector; + logical_sector += STRIPE_SECTORS) { + DEFINE_WAIT(w); + int d; + again: + sh = get_active_stripe(conf, logical_sector, 0, 0, 0); + prepare_to_wait(&conf->wait_for_overlap, &w, + TASK_UNINTERRUPTIBLE); + set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); + if (test_bit(STRIPE_SYNCING, &sh->state)) { + release_stripe(sh); + schedule(); + goto again; + } + clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); + spin_lock_irq(&sh->stripe_lock); + for (d = 0; d < conf->raid_disks; d++) { + if (d == sh->pd_idx || d == sh->qd_idx) + continue; + if (sh->dev[d].towrite || sh->dev[d].toread) { + set_bit(R5_Overlap, &sh->dev[d].flags); + spin_unlock_irq(&sh->stripe_lock); + release_stripe(sh); + schedule(); + goto again; + } + } + set_bit(STRIPE_DISCARD, &sh->state); + finish_wait(&conf->wait_for_overlap, &w); + for (d = 0; d < conf->raid_disks; d++) { + if (d == sh->pd_idx || d == sh->qd_idx) + continue; + sh->dev[d].towrite = bi; + set_bit(R5_OVERWRITE, &sh->dev[d].flags); + raid5_inc_bi_active_stripes(bi); + } + spin_unlock_irq(&sh->stripe_lock); + if (conf->mddev->bitmap) { + for (d = 0; + d < conf->raid_disks - conf->max_degraded; + d++) + bitmap_startwrite(mddev->bitmap, + sh->sector, + STRIPE_SECTORS, + 0); + sh->bm_seq = conf->seq_flush + 1; + set_bit(STRIPE_BIT_DELAY, &sh->state); + } + + set_bit(STRIPE_HANDLE, &sh->state); + clear_bit(STRIPE_DELAYED, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe_plug(mddev, sh); + } + + remaining = raid5_dec_bi_active_stripes(bi); + if (remaining == 0) { + md_write_end(mddev); + bio_endio(bi, 0); + } +} + static void make_request(struct mddev *mddev, struct bio * bi) { struct r5conf *conf = mddev->private; @@ -3927,7 +4589,8 @@ static void make_request(struct mddev *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; - int plugged; + DEFINE_WAIT(w); + bool do_prepare; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -3941,21 +4604,28 @@ static void make_request(struct mddev *mddev, struct bio * bi) chunk_aligned_read(mddev,bi)) return; - logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1); - last_sector = bi->bi_sector + (bi->bi_size>>9); + if (unlikely(bi->bi_rw & REQ_DISCARD)) { + make_discard_request(mddev, bi); + return; + } + + logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1); + last_sector = bio_end_sector(bi); bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ - plugged = mddev_check_plugged(mddev); + prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { - DEFINE_WAIT(w); - int disks, data_disks; int previous; + int seq; + do_prepare = false; retry: + seq = read_seqcount_begin(&conf->gen_lock); previous = 0; - disks = conf->raid_disks; - prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); + if (do_prepare) + prepare_to_wait(&conf->wait_for_overlap, &w, + TASK_UNINTERRUPTIBLE); if (unlikely(conf->reshape_progress != MaxSector)) { /* spinlock is needed as reshape_progress may be * 64bit on a 32bit platform, and so it might be @@ -3966,29 +4636,28 @@ static void make_request(struct mddev *mddev, struct bio * bi) * to check again. */ spin_lock_irq(&conf->device_lock); - if (mddev->delta_disks < 0 + if (mddev->reshape_backwards ? logical_sector < conf->reshape_progress : logical_sector >= conf->reshape_progress) { - disks = conf->previous_raid_disks; previous = 1; } else { - if (mddev->delta_disks < 0 + if (mddev->reshape_backwards ? logical_sector < conf->reshape_safe : logical_sector >= conf->reshape_safe) { spin_unlock_irq(&conf->device_lock); schedule(); + do_prepare = true; goto retry; } } spin_unlock_irq(&conf->device_lock); } - data_disks = disks - conf->max_degraded; new_sector = raid5_compute_sector(conf, logical_sector, previous, &dd_idx, NULL); pr_debug("raid456: make_request, sector %llu logical %llu\n", - (unsigned long long)new_sector, + (unsigned long long)new_sector, (unsigned long long)logical_sector); sh = get_active_stripe(conf, new_sector, previous, @@ -4005,7 +4674,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) */ int must_retry = 0; spin_lock_irq(&conf->device_lock); - if (mddev->delta_disks < 0 + if (mddev->reshape_backwards ? logical_sector >= conf->reshape_progress : logical_sector < conf->reshape_progress) /* mismatch, need to try again */ @@ -4014,9 +4683,17 @@ static void make_request(struct mddev *mddev, struct bio * bi) if (must_retry) { release_stripe(sh); schedule(); + do_prepare = true; goto retry; } } + if (read_seqcount_retry(&conf->gen_lock, seq)) { + /* Might have got the wrong stripe_head + * by accident + */ + release_stripe(sh); + goto retry; + } if (rw == WRITE && logical_sector >= mddev->suspend_lo && @@ -4030,8 +4707,10 @@ static void make_request(struct mddev *mddev, struct bio * bi) prepare_to_wait(&conf->wait_for_overlap, &w, TASK_INTERRUPTIBLE); if (logical_sector >= mddev->suspend_lo && - logical_sector < mddev->suspend_hi) + logical_sector < mddev->suspend_hi) { schedule(); + do_prepare = true; + } goto retry; } @@ -4044,34 +4723,31 @@ static void make_request(struct mddev *mddev, struct bio * bi) md_wakeup_thread(mddev->thread); release_stripe(sh); schedule(); + do_prepare = true; goto retry; } - finish_wait(&conf->wait_for_overlap, &w); set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); - release_stripe(sh); + release_stripe_plug(mddev, sh); } else { /* cannot get stripe for read-ahead, just give-up */ clear_bit(BIO_UPTODATE, &bi->bi_flags); - finish_wait(&conf->wait_for_overlap, &w); break; } - } - if (!plugged) - md_wakeup_thread(mddev->thread); + finish_wait(&conf->wait_for_overlap, &w); - spin_lock_irq(&conf->device_lock); - remaining = raid5_dec_bi_phys_segments(bi); - spin_unlock_irq(&conf->device_lock); + remaining = raid5_dec_bi_active_stripes(bi); if (remaining == 0) { if ( rw == WRITE ) md_write_end(mddev); + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); bio_endio(bi, 0); } } @@ -4104,11 +4780,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk if (sector_nr == 0) { /* If restarting in the middle, skip the initial sectors */ - if (mddev->delta_disks < 0 && + if (mddev->reshape_backwards && conf->reshape_progress < raid5_size(mddev, 0, 0)) { sector_nr = raid5_size(mddev, 0, 0) - conf->reshape_progress; - } else if (mddev->delta_disks >= 0 && + } else if (!mddev->reshape_backwards && conf->reshape_progress > 0) sector_nr = conf->reshape_progress; sector_div(sector_nr, new_data_disks); @@ -4129,13 +4805,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk else reshape_sectors = mddev->chunk_sectors; - /* we update the metadata when there is more than 3Meg - * in the block range (that is rather arbitrary, should - * probably be time based) or when the data about to be - * copied would over-write the source of the data at - * the front of the range. - * i.e. one new_stripe along from reshape_progress new_maps - * to after where reshape_safe old_maps to + /* We update the metadata at least every 10 seconds, or when + * the data about to be copied would over-write the source of + * the data at the front of the range. i.e. one new_stripe + * along from reshape_progress new_maps to after where + * reshape_safe old_maps to */ writepos = conf->reshape_progress; sector_div(writepos, new_data_disks); @@ -4143,7 +4817,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk sector_div(readpos, data_disks); safepos = conf->reshape_safe; sector_div(safepos, data_disks); - if (mddev->delta_disks < 0) { + if (mddev->reshape_backwards) { writepos -= min_t(sector_t, reshape_sectors, writepos); readpos += reshape_sectors; safepos += reshape_sectors; @@ -4153,11 +4827,29 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk safepos -= min_t(sector_t, reshape_sectors, safepos); } + /* Having calculated the 'writepos' possibly use it + * to set 'stripe_addr' which is where we will write to. + */ + if (mddev->reshape_backwards) { + BUG_ON(conf->reshape_progress == 0); + stripe_addr = writepos; + BUG_ON((mddev->dev_sectors & + ~((sector_t)reshape_sectors - 1)) + - reshape_sectors - stripe_addr + != sector_nr); + } else { + BUG_ON(writepos != sector_nr + reshape_sectors); + stripe_addr = sector_nr; + } + /* 'writepos' is the most advanced device address we might write. * 'readpos' is the least advanced device address we might read. * 'safepos' is the least address recorded in the metadata as having * been reshaped. - * If 'readpos' is behind 'writepos', then there is no way that we can + * If there is a min_offset_diff, these are adjusted either by + * increasing the safepos/readpos if diff is negative, or + * increasing writepos if diff is positive. + * If 'readpos' is then behind 'writepos', there is no way that we can * ensure safety in the face of a crash - that must be done by userspace * making a backup of the data. So in that case there is no particular * rush to update metadata. @@ -4170,20 +4862,31 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk * Maybe that number should be configurable, but I'm not sure it is * worth it.... maybe it could be a multiple of safemode_delay??? */ - if ((mddev->delta_disks < 0 + if (conf->min_offset_diff < 0) { + safepos += -conf->min_offset_diff; + readpos += -conf->min_offset_diff; + } else + writepos += conf->min_offset_diff; + + if ((mddev->reshape_backwards ? (safepos > writepos && readpos < writepos) : (safepos < writepos && readpos > writepos)) || time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) { /* Cannot proceed until we've updated the superblock... */ wait_event(conf->wait_for_overlap, - atomic_read(&conf->reshape_stripes)==0); + atomic_read(&conf->reshape_stripes)==0 + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (atomic_read(&conf->reshape_stripes) != 0) + return 0; mddev->reshape_position = conf->reshape_progress; mddev->curr_resync_completed = sector_nr; conf->reshape_checkpoint = jiffies; set_bit(MD_CHANGE_DEVS, &mddev->flags); md_wakeup_thread(mddev->thread); wait_event(mddev->sb_wait, mddev->flags == 0 || - kthread_should_stop()); + test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) + return 0; spin_lock_irq(&conf->device_lock); conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); @@ -4191,17 +4894,6 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } - if (mddev->delta_disks < 0) { - BUG_ON(conf->reshape_progress == 0); - stripe_addr = writepos; - BUG_ON((mddev->dev_sectors & - ~((sector_t)reshape_sectors - 1)) - - reshape_sectors - stripe_addr - != sector_nr); - } else { - BUG_ON(writepos != sector_nr + reshape_sectors); - stripe_addr = sector_nr; - } INIT_LIST_HEAD(&stripes); for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) { int j; @@ -4235,7 +4927,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk list_add(&sh->lru, &stripes); } spin_lock_irq(&conf->device_lock); - if (mddev->delta_disks < 0) + if (mddev->reshape_backwards) conf->reshape_progress -= reshape_sectors * new_data_disks; else conf->reshape_progress += reshape_sectors * new_data_disks; @@ -4277,7 +4969,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk >= mddev->resync_max - mddev->curr_resync_completed) { /* Cannot proceed until we've updated the superblock... */ wait_event(conf->wait_for_overlap, - atomic_read(&conf->reshape_stripes) == 0); + atomic_read(&conf->reshape_stripes) == 0 + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (atomic_read(&conf->reshape_stripes) != 0) + goto ret; mddev->reshape_position = conf->reshape_progress; mddev->curr_resync_completed = sector_nr; conf->reshape_checkpoint = jiffies; @@ -4285,13 +4980,16 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk md_wakeup_thread(mddev->thread); wait_event(mddev->sb_wait, !test_bit(MD_CHANGE_DEVS, &mddev->flags) - || kthread_should_stop()); + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) + goto ret; spin_lock_irq(&conf->device_lock); conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } +ret: return reshape_sectors; } @@ -4345,9 +5043,10 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped = 1; return rv; } - if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) && - !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && - !conf->fullsync && sync_blocks >= STRIPE_SECTORS) { + if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && + !conf->fullsync && + !bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) && + sync_blocks >= STRIPE_SECTORS) { /* we can skip this block, and probably more */ sync_blocks /= STRIPE_SECTORS; *skipped = 1; @@ -4375,8 +5074,8 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded); set_bit(STRIPE_SYNC_REQUESTED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); - handle_stripe(sh); release_stripe(sh); return STRIPE_SECTORS; @@ -4401,50 +5100,129 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) int remaining; int handled = 0; - logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1); + logical_sector = raid_bio->bi_iter.bi_sector & + ~((sector_t)STRIPE_SECTORS-1); sector = raid5_compute_sector(conf, logical_sector, 0, &dd_idx, NULL); - last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9); + last_sector = bio_end_sector(raid_bio); for (; logical_sector < last_sector; logical_sector += STRIPE_SECTORS, sector += STRIPE_SECTORS, scnt++) { - if (scnt < raid5_bi_hw_segments(raid_bio)) + if (scnt < raid5_bi_processed_stripes(raid_bio)) /* already done this stripe */ continue; - sh = get_active_stripe(conf, sector, 0, 1, 0); + sh = get_active_stripe(conf, sector, 0, 1, 1); if (!sh) { /* failed to get a stripe - must wait */ - raid5_set_bi_hw_segments(raid_bio, scnt); + raid5_set_bi_processed_stripes(raid_bio, scnt); conf->retry_read_aligned = raid_bio; return handled; } if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) { release_stripe(sh); - raid5_set_bi_hw_segments(raid_bio, scnt); + raid5_set_bi_processed_stripes(raid_bio, scnt); conf->retry_read_aligned = raid_bio; return handled; } + set_bit(R5_ReadNoMerge, &sh->dev[dd_idx].flags); handle_stripe(sh); release_stripe(sh); handled++; } - spin_lock_irq(&conf->device_lock); - remaining = raid5_dec_bi_phys_segments(raid_bio); - spin_unlock_irq(&conf->device_lock); - if (remaining == 0) + remaining = raid5_dec_bi_active_stripes(raid_bio); + if (remaining == 0) { + trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev), + raid_bio, 0); bio_endio(raid_bio, 0); + } if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); return handled; } +static int handle_active_stripes(struct r5conf *conf, int group, + struct r5worker *worker, + struct list_head *temp_inactive_list) +{ + struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; + int i, batch_size = 0, hash; + bool release_inactive = false; + + while (batch_size < MAX_STRIPE_BATCH && + (sh = __get_priority_stripe(conf, group)) != NULL) + batch[batch_size++] = sh; + + if (batch_size == 0) { + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + if (!list_empty(temp_inactive_list + i)) + break; + if (i == NR_STRIPE_HASH_LOCKS) + return batch_size; + release_inactive = true; + } + spin_unlock_irq(&conf->device_lock); + + release_inactive_stripe_list(conf, temp_inactive_list, + NR_STRIPE_HASH_LOCKS); + + if (release_inactive) { + spin_lock_irq(&conf->device_lock); + return 0; + } + + for (i = 0; i < batch_size; i++) + handle_stripe(batch[i]); + + cond_resched(); + + spin_lock_irq(&conf->device_lock); + for (i = 0; i < batch_size; i++) { + hash = batch[i]->hash_lock_index; + __release_stripe(conf, batch[i], &temp_inactive_list[hash]); + } + return batch_size; +} + +static void raid5_do_work(struct work_struct *work) +{ + struct r5worker *worker = container_of(work, struct r5worker, work); + struct r5worker_group *group = worker->group; + struct r5conf *conf = group->conf; + int group_id = group - conf->worker_groups; + int handled; + struct blk_plug plug; + + pr_debug("+++ raid5worker active\n"); + + blk_start_plug(&plug); + handled = 0; + spin_lock_irq(&conf->device_lock); + while (1) { + int batch_size, released; + + released = release_stripe_list(conf, worker->temp_inactive_list); + + batch_size = handle_active_stripes(conf, group_id, worker, + worker->temp_inactive_list); + worker->working = false; + if (!batch_size && !released) + break; + handled += batch_size; + } + pr_debug("%d stripes handled\n", handled); + + spin_unlock_irq(&conf->device_lock); + blk_finish_plug(&plug); + + pr_debug("--- raid5worker inactive\n"); +} /* * This is our raid5 kernel thread. @@ -4453,9 +5231,9 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) * During the scan, completed stripes are saved for us by the interrupt * handler, so that they will not have to wait for our next wakeup. */ -static void raid5d(struct mddev *mddev) +static void raid5d(struct md_thread *thread) { - struct stripe_head *sh; + struct mddev *mddev = thread->mddev; struct r5conf *conf = mddev->private; int handled; struct blk_plug plug; @@ -4469,8 +5247,11 @@ static void raid5d(struct mddev *mddev) spin_lock_irq(&conf->device_lock); while (1) { struct bio *bio; + int batch_size, released; + + released = release_stripe_list(conf, conf->temp_inactive_list); - if (atomic_read(&mddev->plug_cnt) == 0 && + if ( !list_empty(&conf->bitmap_list)) { /* Now is a good time to flush some bitmap updates */ conf->seq_flush++; @@ -4478,10 +5259,9 @@ static void raid5d(struct mddev *mddev) bitmap_unplug(mddev->bitmap); spin_lock_irq(&conf->device_lock); conf->seq_write = conf->seq_flush; - activate_bit_delay(conf); + activate_bit_delay(conf, conf->temp_inactive_list); } - if (atomic_read(&mddev->plug_cnt) == 0) - raid5_activate_delayed(conf); + raid5_activate_delayed(conf); while ((bio = remove_bio_from_retry(conf))) { int ok; @@ -4493,21 +5273,17 @@ static void raid5d(struct mddev *mddev) handled++; } - sh = __get_priority_stripe(conf); - - if (!sh) + batch_size = handle_active_stripes(conf, ANY_GROUP, NULL, + conf->temp_inactive_list); + if (!batch_size && !released) break; - spin_unlock_irq(&conf->device_lock); - - handled++; - handle_stripe(sh); - release_stripe(sh); - cond_resched(); + handled += batch_size; - if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) + if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) { + spin_unlock_irq(&conf->device_lock); md_check_recovery(mddev); - - spin_lock_irq(&conf->device_lock); + spin_lock_irq(&conf->device_lock); + } } pr_debug("%d stripes handled\n", handled); @@ -4534,22 +5310,29 @@ raid5_set_cache_size(struct mddev *mddev, int size) { struct r5conf *conf = mddev->private; int err; + int hash; if (size <= 16 || size > 32768) return -EINVAL; + hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; while (size < conf->max_nr_stripes) { - if (drop_one_stripe(conf)) + if (drop_one_stripe(conf, hash)) conf->max_nr_stripes--; else break; + hash--; + if (hash < 0) + hash = NR_STRIPE_HASH_LOCKS - 1; } err = md_allow_write(mddev); if (err) return err; + hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; while (size > conf->max_nr_stripes) { - if (grow_one_stripe(conf)) + if (grow_one_stripe(conf, hash)) conf->max_nr_stripes++; else break; + hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; } return 0; } @@ -4567,7 +5350,7 @@ raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len) if (!conf) return -ENODEV; - if (strict_strtoul(page, 10, &new)) + if (kstrtoul(page, 10, &new)) return -EINVAL; err = raid5_set_cache_size(mddev, new); if (err) @@ -4600,7 +5383,7 @@ raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len) if (!conf) return -ENODEV; - if (strict_strtoul(page, 10, &new)) + if (kstrtoul(page, 10, &new)) return -EINVAL; if (new > conf->max_nr_stripes) return -EINVAL; @@ -4615,6 +5398,50 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold, raid5_store_preread_threshold); static ssize_t +raid5_show_skip_copy(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->skip_copy); + else + return 0; +} + +static ssize_t +raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + new = !!new; + if (new == conf->skip_copy) + return len; + + mddev_suspend(mddev); + conf->skip_copy = new; + if (new) + mddev->queue->backing_dev_info.capabilities |= + BDI_CAP_STABLE_WRITES; + else + mddev->queue->backing_dev_info.capabilities &= + ~BDI_CAP_STABLE_WRITES; + mddev_resume(mddev); + return len; +} + +static struct md_sysfs_entry +raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR, + raid5_show_skip_copy, + raid5_store_skip_copy); + + +static ssize_t stripe_cache_active_show(struct mddev *mddev, char *page) { struct r5conf *conf = mddev->private; @@ -4627,10 +5454,79 @@ stripe_cache_active_show(struct mddev *mddev, char *page) static struct md_sysfs_entry raid5_stripecache_active = __ATTR_RO(stripe_cache_active); +static ssize_t +raid5_show_group_thread_cnt(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->worker_cnt_per_group); + else + return 0; +} + +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups); +static ssize_t +raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + int err; + struct r5worker_group *new_groups, *old_groups; + int group_cnt, worker_cnt_per_group; + + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + + if (new == conf->worker_cnt_per_group) + return len; + + mddev_suspend(mddev); + + old_groups = conf->worker_groups; + if (old_groups) + flush_workqueue(raid5_wq); + + err = alloc_thread_groups(conf, new, + &group_cnt, &worker_cnt_per_group, + &new_groups); + if (!err) { + spin_lock_irq(&conf->device_lock); + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_groups; + spin_unlock_irq(&conf->device_lock); + + if (old_groups) + kfree(old_groups[0].workers); + kfree(old_groups); + } + + mddev_resume(mddev); + + if (err) + return err; + return len; +} + +static struct md_sysfs_entry +raid5_group_thread_cnt = __ATTR(group_thread_cnt, S_IRUGO | S_IWUSR, + raid5_show_group_thread_cnt, + raid5_store_group_thread_cnt); + static struct attribute *raid5_attrs[] = { &raid5_stripecache_size.attr, &raid5_stripecache_active.attr, &raid5_preread_bypass_threshold.attr, + &raid5_group_thread_cnt.attr, + &raid5_skip_copy.attr, NULL, }; static struct attribute_group raid5_attrs_group = { @@ -4638,6 +5534,61 @@ static struct attribute_group raid5_attrs_group = { .attrs = raid5_attrs, }; +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups) +{ + int i, j, k; + ssize_t size; + struct r5worker *workers; + + *worker_cnt_per_group = cnt; + if (cnt == 0) { + *group_cnt = 0; + *worker_groups = NULL; + return 0; + } + *group_cnt = num_possible_nodes(); + size = sizeof(struct r5worker) * cnt; + workers = kzalloc(size * *group_cnt, GFP_NOIO); + *worker_groups = kzalloc(sizeof(struct r5worker_group) * + *group_cnt, GFP_NOIO); + if (!*worker_groups || !workers) { + kfree(workers); + kfree(*worker_groups); + return -ENOMEM; + } + + for (i = 0; i < *group_cnt; i++) { + struct r5worker_group *group; + + group = &(*worker_groups)[i]; + INIT_LIST_HEAD(&group->handle_list); + group->conf = conf; + group->workers = workers + i * cnt; + + for (j = 0; j < cnt; j++) { + struct r5worker *worker = group->workers + j; + worker->group = group; + INIT_WORK(&worker->work, raid5_do_work); + + for (k = 0; k < NR_STRIPE_HASH_LOCKS; k++) + INIT_LIST_HEAD(worker->temp_inactive_list + k); + } + } + + return 0; +} + +static void free_thread_groups(struct r5conf *conf) +{ + if (conf->worker_groups) + kfree(conf->worker_groups[0].workers); + kfree(conf->worker_groups); + conf->worker_groups = NULL; +} + static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) { @@ -4654,23 +5605,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) return sectors * (raid_disks - conf->max_degraded); } +static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + safe_put_page(percpu->spare_page); + kfree(percpu->scribble); + percpu->spare_page = NULL; + percpu->scribble = NULL; +} + +static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + if (conf->level == 6 && !percpu->spare_page) + percpu->spare_page = alloc_page(GFP_KERNEL); + if (!percpu->scribble) + percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + + if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { + free_scratch_buffer(conf, percpu); + return -ENOMEM; + } + + return 0; +} + static void raid5_free_percpu(struct r5conf *conf) { - struct raid5_percpu *percpu; unsigned long cpu; if (!conf->percpu) return; - get_online_cpus(); - for_each_possible_cpu(cpu) { - percpu = per_cpu_ptr(conf->percpu, cpu); - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - } #ifdef CONFIG_HOTPLUG_CPU unregister_cpu_notifier(&conf->cpu_notify); #endif + + get_online_cpus(); + for_each_possible_cpu(cpu) + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); put_online_cpus(); free_percpu(conf->percpu); @@ -4678,6 +5649,7 @@ static void raid5_free_percpu(struct r5conf *conf) static void free_conf(struct r5conf *conf) { + free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); kfree(conf->disks); @@ -4696,15 +5668,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - if (conf->level == 6 && !percpu->spare_page) - percpu->spare_page = alloc_page(GFP_KERNEL); - if (!percpu->scribble) - percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - - if (!percpu->scribble || - (conf->level == 6 && !percpu->spare_page)) { - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); + if (alloc_scratch_buffer(conf, percpu)) { pr_err("%s: failed memory allocation for cpu%ld\n", __func__, cpu); return notifier_from_errno(-ENOMEM); @@ -4712,10 +5676,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, break; case CPU_DEAD: case CPU_DEAD_FROZEN: - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - percpu->spare_page = NULL; - percpu->scribble = NULL; + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); break; default: break; @@ -4727,40 +5688,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, static int raid5_alloc_percpu(struct r5conf *conf) { unsigned long cpu; - struct page *spare_page; - struct raid5_percpu __percpu *allcpus; - void *scribble; - int err; + int err = 0; - allcpus = alloc_percpu(struct raid5_percpu); - if (!allcpus) + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) return -ENOMEM; - conf->percpu = allcpus; + +#ifdef CONFIG_HOTPLUG_CPU + conf->cpu_notify.notifier_call = raid456_cpu_notify; + conf->cpu_notify.priority = 0; + err = register_cpu_notifier(&conf->cpu_notify); + if (err) + return err; +#endif get_online_cpus(); - err = 0; for_each_present_cpu(cpu) { - if (conf->level == 6) { - spare_page = alloc_page(GFP_KERNEL); - if (!spare_page) { - err = -ENOMEM; - break; - } - per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page; - } - scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - if (!scribble) { - err = -ENOMEM; + err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + if (err) { + pr_err("%s: failed memory allocation for cpu%ld\n", + __func__, cpu); break; } - per_cpu_ptr(conf->percpu, cpu)->scribble = scribble; } -#ifdef CONFIG_HOTPLUG_CPU - conf->cpu_notify.notifier_call = raid456_cpu_notify; - conf->cpu_notify.priority = 0; - if (err == 0) - err = register_cpu_notifier(&conf->cpu_notify); -#endif put_online_cpus(); return err; @@ -4772,6 +5722,10 @@ static struct r5conf *setup_conf(struct mddev *mddev) int raid_disk, memory, max_disks; struct md_rdev *rdev; struct disk_info *disk; + char pers_name[6]; + int i; + int group_cnt, worker_cnt_per_group; + struct r5worker_group *new_group; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -4805,14 +5759,23 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL); if (conf == NULL) goto abort; + /* Don't enable multi-threading by default*/ + if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group, + &new_group)) { + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_group; + } else + goto abort; spin_lock_init(&conf->device_lock); + seqcount_init(&conf->gen_lock); 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); INIT_LIST_HEAD(&conf->delayed_list); INIT_LIST_HEAD(&conf->bitmap_list); - INIT_LIST_HEAD(&conf->inactive_list); + init_llist_head(&conf->released_stripes); atomic_set(&conf->active_stripes, 0); atomic_set(&conf->preread_active_stripes, 0); atomic_set(&conf->active_aligned_reads, 0); @@ -4837,13 +5800,28 @@ static struct r5conf *setup_conf(struct mddev *mddev) if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL) goto abort; + /* We init hash_locks[0] separately to that it can be used + * as the reference lock in the spin_lock_nest_lock() call + * in lock_all_device_hash_locks_irq in order to convince + * lockdep that we know what we are doing. + */ + spin_lock_init(conf->hash_locks); + for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) + spin_lock_init(conf->hash_locks + i); + + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(conf->inactive_list + i); + + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(conf->temp_inactive_list + i); + conf->level = mddev->new_level; if (raid5_alloc_percpu(conf) != 0) goto abort; pr_debug("raid456: run(%s) called.\n", mdname(mddev)); - list_for_each_entry(rdev, &mddev->disks, same_set) { + rdev_for_each(rdev, mddev) { raid_disk = rdev->raid_disk; if (raid_disk >= max_disks || raid_disk < 0) @@ -4877,7 +5855,6 @@ static struct r5conf *setup_conf(struct mddev *mddev) else conf->max_degraded = 1; conf->algorithm = mddev->new_layout; - conf->max_nr_stripes = NR_STRIPES; conf->reshape_progress = mddev->reshape_position; if (conf->reshape_progress != MaxSector) { conf->prev_chunk_sectors = mddev->chunk_sectors; @@ -4886,7 +5863,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) memory = conf->max_nr_stripes * (sizeof(struct stripe_head) + max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024; - if (grow_stripes(conf, conf->max_nr_stripes)) { + atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS); + if (grow_stripes(conf, NR_STRIPES)) { printk(KERN_ERR "md/raid:%s: couldn't allocate %dkB for buffers\n", mdname(mddev), memory); @@ -4895,7 +5873,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); - conf->thread = md_register_thread(raid5d, mddev, NULL); + sprintf(pers_name, "raid%d", mddev->new_level); + conf->thread = md_register_thread(raid5d, mddev, pers_name); if (!conf->thread) { printk(KERN_ERR "md/raid:%s: couldn't allocate thread.\n", @@ -4948,16 +5927,42 @@ static int run(struct mddev *mddev) struct md_rdev *rdev; sector_t reshape_offset = 0; int i; + long long min_offset_diff = 0; + int first = 1; if (mddev->recovery_cp != MaxSector) printk(KERN_NOTICE "md/raid:%s: not clean" " -- starting background reconstruction\n", mdname(mddev)); + + rdev_for_each(rdev, mddev) { + long long diff; + if (rdev->raid_disk < 0) + continue; + diff = (rdev->new_data_offset - rdev->data_offset); + if (first) { + min_offset_diff = diff; + first = 0; + } else if (mddev->reshape_backwards && + diff < min_offset_diff) + min_offset_diff = diff; + else if (!mddev->reshape_backwards && + diff > min_offset_diff) + min_offset_diff = diff; + } + if (mddev->reshape_position != MaxSector) { /* Check that we can continue the reshape. - * Currently only disks can change, it must - * increase, and we must be past the point where - * a stripe over-writes itself + * Difficulties arise if the stripe we would write to + * next is at or after the stripe we would read from next. + * For a reshape that changes the number of devices, this + * is only possible for a very short time, and mdadm makes + * sure that time appears to have past before assembling + * the array. So we fail if that time hasn't passed. + * For a reshape that keeps the number of devices the same + * mdadm must be monitoring the reshape can keeping the + * critical areas read-only and backed up. It will start + * the array in read-only mode, so we check for that. */ sector_t here_new, here_old; int old_disks; @@ -4989,26 +5994,34 @@ static int run(struct mddev *mddev) /* here_old is the first stripe that we might need to read * from */ if (mddev->delta_disks == 0) { + if ((here_new * mddev->new_chunk_sectors != + here_old * mddev->chunk_sectors)) { + printk(KERN_ERR "md/raid:%s: reshape position is" + " confused - aborting\n", mdname(mddev)); + return -EINVAL; + } /* We cannot be sure it is safe to start an in-place - * reshape. It is only safe if user-space if monitoring + * reshape. It is only safe if user-space is monitoring * and taking constant backups. * mdadm always starts a situation like this in * readonly mode so it can take control before * allowing any writes. So just check for that. */ - if ((here_new * mddev->new_chunk_sectors != - here_old * mddev->chunk_sectors) || - mddev->ro == 0) { - printk(KERN_ERR "md/raid:%s: in-place reshape must be started" - " in read-only mode - aborting\n", + if (abs(min_offset_diff) >= mddev->chunk_sectors && + abs(min_offset_diff) >= mddev->new_chunk_sectors) + /* not really in-place - so OK */; + else if (mddev->ro == 0) { + printk(KERN_ERR "md/raid:%s: in-place reshape " + "must be started in read-only mode " + "- aborting\n", mdname(mddev)); return -EINVAL; } - } else if (mddev->delta_disks < 0 - ? (here_new * mddev->new_chunk_sectors <= + } else if (mddev->reshape_backwards + ? (here_new * mddev->new_chunk_sectors + min_offset_diff <= here_old * mddev->chunk_sectors) : (here_new * mddev->new_chunk_sectors >= - here_old * mddev->chunk_sectors)) { + here_old * mddev->chunk_sectors + (-min_offset_diff))) { /* Reading from the same stripe as writing to - bad */ printk(KERN_ERR "md/raid:%s: reshape_position too early for " "auto-recovery - aborting.\n", @@ -5033,6 +6046,7 @@ static int run(struct mddev *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); + conf->min_offset_diff = min_offset_diff; mddev->thread = conf->thread; conf->thread = NULL; mddev->private = conf; @@ -5072,7 +6086,7 @@ static int run(struct mddev *mddev) if (mddev->major_version == 0 && mddev->minor_version > 90) rdev->recovery_offset = reshape_offset; - + if (rdev->recovery_offset < reshape_offset) { /* We need to check old and new layout */ if (!only_parity(rdev->raid_disk, @@ -5158,6 +6172,7 @@ static int run(struct mddev *mddev) if (mddev->queue) { int chunk_size; + bool discard_supported = true; /* read-ahead size must cover two whole stripes, which * is 2 * (datadisks) * chunksize where 'n' is the * number of raid devices @@ -5177,10 +6192,55 @@ static int run(struct mddev *mddev) blk_queue_io_min(mddev->queue, chunk_size); blk_queue_io_opt(mddev->queue, chunk_size * (conf->raid_disks - conf->max_degraded)); + mddev->queue->limits.raid_partial_stripes_expensive = 1; + /* + * We can only discard a whole stripe. It doesn't make sense to + * discard data disk but write parity disk + */ + stripe = stripe * PAGE_SIZE; + /* Round up to power of 2, as discard handling + * currently assumes that */ + while ((stripe-1) & stripe) + stripe = (stripe | (stripe-1)) + 1; + mddev->queue->limits.discard_alignment = stripe; + mddev->queue->limits.discard_granularity = stripe; + /* + * unaligned part of discard request will be ignored, so can't + * guarantee discard_zerors_data + */ + mddev->queue->limits.discard_zeroes_data = 0; - list_for_each_entry(rdev, &mddev->disks, same_set) + blk_queue_max_write_same_sectors(mddev->queue, 0); + + rdev_for_each(rdev, mddev) { disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->new_data_offset << 9); + /* + * discard_zeroes_data is required, otherwise data + * could be lost. Consider a scenario: discard a stripe + * (the stripe could be inconsistent if + * discard_zeroes_data is 0); write one disk of the + * stripe (the stripe could be inconsistent again + * depending on which disks are used to calculate + * parity); the disk is broken; The stripe data of this + * disk is lost. + */ + if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) || + !bdev_get_queue(rdev->bdev)-> + limits.discard_zeroes_data) + discard_supported = false; + } + + if (discard_supported && + mddev->queue->limits.max_discard_sectors >= stripe && + mddev->queue->limits.discard_granularity >= stripe) + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, + mddev->queue); + else + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, + mddev->queue); } return 0; @@ -5362,7 +6422,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; - if (has_failed(conf)) + if (rdev->saved_raid_disk < 0 && has_failed(conf)) /* no point adding a device */ return -EINVAL; @@ -5376,10 +6436,9 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk >= 0 && rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) - disk = rdev->saved_raid_disk; - else - disk = first; - for ( ; disk <= last ; disk++) { + first = rdev->saved_raid_disk; + + for (disk = first; disk <= last; disk++) { p = conf->disks + disk; if (p->rdev == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5388,8 +6447,11 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); - break; + goto out; } + } + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; if (test_bit(WantReplacement, &p->rdev->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5401,6 +6463,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } +out: print_raid5_conf(conf); return err; } @@ -5414,12 +6477,18 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) * any io in the removed space completes, but it hardly seems * worth it. */ + sector_t newsize; sectors &= ~((sector_t)mddev->chunk_sectors - 1); - md_set_array_sectors(mddev, raid5_size(mddev, sectors, - mddev->raid_disks)); - if (mddev->array_sectors > - raid5_size(mddev, sectors, mddev->raid_disks)) + newsize = raid5_size(mddev, sectors, mddev->raid_disks); + if (mddev->external_size && + mddev->array_sectors > newsize) return -EINVAL; + if (mddev->bitmap) { + int ret = bitmap_resize(mddev->bitmap, sectors, 0, 0); + if (ret) + return ret; + } + md_set_array_sectors(mddev, newsize); set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && @@ -5464,12 +6533,9 @@ static int check_reshape(struct mddev *mddev) mddev->new_layout == mddev->layout && mddev->new_chunk_sectors == mddev->chunk_sectors) return 0; /* nothing to do */ - if (mddev->bitmap) - /* Cannot grow a bitmap yet */ - return -EBUSY; if (has_failed(conf)) return -EINVAL; - if (mddev->delta_disks < 0) { + if (mddev->delta_disks < 0 && mddev->reshape_position == MaxSector) { /* We might be able to shrink, but the devices must * be made bigger first. * For raid6, 4 is the minimum size. @@ -5485,7 +6551,8 @@ static int check_reshape(struct mddev *mddev) if (!check_stripe_cache(mddev)) return -ENOSPC; - return resize_stripes(conf, conf->raid_disks + mddev->delta_disks); + return resize_stripes(conf, (conf->previous_raid_disks + + mddev->delta_disks)); } static int raid5_start_reshape(struct mddev *mddev) @@ -5501,10 +6568,14 @@ static int raid5_start_reshape(struct mddev *mddev) if (!check_stripe_cache(mddev)) return -ENOSPC; - list_for_each_entry(rdev, &mddev->disks, same_set) + if (has_failed(conf)) + return -EINVAL; + + rdev_for_each(rdev, mddev) { if (!test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) spares++; + } if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded) /* Not enough devices even to make a degraded array @@ -5525,20 +6596,33 @@ static int raid5_start_reshape(struct mddev *mddev) atomic_set(&conf->reshape_stripes, 0); spin_lock_irq(&conf->device_lock); + write_seqcount_begin(&conf->gen_lock); conf->previous_raid_disks = conf->raid_disks; conf->raid_disks += mddev->delta_disks; conf->prev_chunk_sectors = conf->chunk_sectors; conf->chunk_sectors = mddev->new_chunk_sectors; conf->prev_algo = conf->algorithm; conf->algorithm = mddev->new_layout; - if (mddev->delta_disks < 0) + conf->generation++; + /* Code that selects data_offset needs to see the generation update + * if reshape_progress has been set - so a memory barrier needed. + */ + smp_mb(); + if (mddev->reshape_backwards) conf->reshape_progress = raid5_size(mddev, 0, 0); else conf->reshape_progress = 0; conf->reshape_safe = conf->reshape_progress; - conf->generation++; + write_seqcount_end(&conf->gen_lock); spin_unlock_irq(&conf->device_lock); + /* Now make sure any requests that proceeded on the assumption + * the reshape wasn't running - like Discard or Read - have + * completed. + */ + mddev_suspend(mddev); + mddev_resume(mddev); + /* Add some new drives, as many as will fit. * We know there are enough to make the newly sized array work. * Don't add devices if we are reducing the number of @@ -5547,16 +6631,14 @@ static int raid5_start_reshape(struct mddev *mddev) * such devices during the reshape and confusion could result. */ if (mddev->delta_disks >= 0) { - int added_devices = 0; - list_for_each_entry(rdev, &mddev->disks, same_set) + rdev_for_each(rdev, mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { if (raid5_add_disk(mddev, rdev) == 0) { if (rdev->raid_disk - >= conf->previous_raid_disks) { + >= conf->previous_raid_disks) set_bit(In_sync, &rdev->flags); - added_devices++; - } else + else rdev->recovery_offset = 0; if (sysfs_link_rdev(mddev, rdev)) @@ -5566,7 +6648,6 @@ static int raid5_start_reshape(struct mddev *mddev) && !test_bit(Faulty, &rdev->flags)) { /* This is a spare that was manually added */ set_bit(In_sync, &rdev->flags); - added_devices++; } /* When a reshape changes the number of devices, @@ -5590,8 +6671,18 @@ static int raid5_start_reshape(struct mddev *mddev) if (!mddev->sync_thread) { mddev->recovery = 0; spin_lock_irq(&conf->device_lock); + write_seqcount_begin(&conf->gen_lock); mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks; + mddev->new_chunk_sectors = + conf->chunk_sectors = conf->prev_chunk_sectors; + mddev->new_layout = conf->algorithm = conf->prev_algo; + rdev_for_each(rdev, mddev) + rdev->new_data_offset = rdev->data_offset; + smp_wmb(); + conf->generation --; conf->reshape_progress = MaxSector; + mddev->reshape_position = MaxSector; + write_seqcount_end(&conf->gen_lock); spin_unlock_irq(&conf->device_lock); return -EAGAIN; } @@ -5608,9 +6699,13 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { + struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; + rdev_for_each(rdev, conf->mddev) + rdev->data_offset = rdev->new_data_offset; + smp_wmb(); conf->reshape_progress = MaxSector; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); @@ -5650,17 +6745,18 @@ static void raid5_finish_reshape(struct mddev *mddev) d < conf->raid_disks - mddev->delta_disks; d++) { struct md_rdev *rdev = conf->disks[d].rdev; - if (rdev && - raid5_remove_disk(mddev, rdev) == 0) { - sysfs_unlink_rdev(mddev, rdev); - rdev->raid_disk = -1; - } + if (rdev) + clear_bit(In_sync, &rdev->flags); + rdev = conf->disks[d].replacement; + if (rdev) + clear_bit(In_sync, &rdev->flags); } } mddev->layout = conf->algorithm; mddev->chunk_sectors = conf->chunk_sectors; mddev->reshape_position = MaxSector; mddev->delta_disks = 0; + mddev->reshape_backwards = 0; } } @@ -5674,27 +6770,28 @@ static void raid5_quiesce(struct mddev *mddev, int state) break; case 1: /* stop all writes */ - spin_lock_irq(&conf->device_lock); + lock_all_device_hash_locks_irq(conf); /* '2' tells resync/reshape to pause so that all * active stripes can drain */ conf->quiesce = 2; - wait_event_lock_irq(conf->wait_for_stripe, + wait_event_cmd(conf->wait_for_stripe, atomic_read(&conf->active_stripes) == 0 && atomic_read(&conf->active_aligned_reads) == 0, - conf->device_lock, /* nothing */); + unlock_all_device_hash_locks_irq(conf), + lock_all_device_hash_locks_irq(conf)); conf->quiesce = 1; - spin_unlock_irq(&conf->device_lock); + unlock_all_device_hash_locks_irq(conf); /* allow reshape to continue */ wake_up(&conf->wait_for_overlap); break; case 0: /* re-enable writes */ - spin_lock_irq(&conf->device_lock); + lock_all_device_hash_locks_irq(conf); conf->quiesce = 0; wake_up(&conf->wait_for_stripe); wake_up(&conf->wait_for_overlap); - spin_unlock_irq(&conf->device_lock); + unlock_all_device_hash_locks_irq(conf); break; } } @@ -6007,6 +7104,10 @@ static struct md_personality raid4_personality = static int __init raid5_init(void) { + raid5_wq = alloc_workqueue("raid5wq", + WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0); + if (!raid5_wq) + return -ENOMEM; register_md_personality(&raid6_personality); register_md_personality(&raid5_personality); register_md_personality(&raid4_personality); @@ -6018,6 +7119,7 @@ static void raid5_exit(void) unregister_md_personality(&raid6_personality); unregister_md_personality(&raid5_personality); unregister_md_personality(&raid4_personality); + destroy_workqueue(raid5_wq); } module_init(raid5_init); |