diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/alloc.c | 4 | ||||
-rw-r--r-- | drivers/md/bcache/bcache.h | 2 | ||||
-rw-r--r-- | drivers/md/bcache/btree.c | 9 | ||||
-rw-r--r-- | drivers/md/bcache/request.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 23 | ||||
-rw-r--r-- | drivers/md/bcache/sysfs.c | 11 | ||||
-rw-r--r-- | drivers/md/bcache/writeback.c | 27 | ||||
-rw-r--r-- | drivers/md/md.c | 13 | ||||
-rw-r--r-- | drivers/md/raid1.c | 11 | ||||
-rw-r--r-- | drivers/md/raid10.c | 14 | ||||
-rw-r--r-- | drivers/md/raid5.c | 15 |
11 files changed, 92 insertions, 39 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index d23337e8c4ee..dd344ee9e62b 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -284,8 +284,10 @@ do { \ break; \ \ mutex_unlock(&(ca)->set->bucket_lock); \ - if (kthread_should_stop()) \ + if (kthread_should_stop()) { \ + set_current_state(TASK_RUNNING); \ return 0; \ + } \ \ schedule(); \ mutex_lock(&(ca)->set->bucket_lock); \ diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 02619cabda8b..7fe7df56fa33 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -904,7 +904,7 @@ void bcache_write_super(struct cache_set *); int bch_flash_dev_create(struct cache_set *c, uint64_t size); -int bch_cached_dev_attach(struct cached_dev *, struct cache_set *); +int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *); void bch_cached_dev_detach(struct cached_dev *); void bch_cached_dev_run(struct cached_dev *); void bcache_device_stop(struct bcache_device *); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index cac297f8170e..cf7c68920b33 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1864,14 +1864,17 @@ void bch_initial_gc_finish(struct cache_set *c) */ for_each_cache(ca, c, i) { for_each_bucket(b, ca) { - if (fifo_full(&ca->free[RESERVE_PRIO])) + if (fifo_full(&ca->free[RESERVE_PRIO]) && + fifo_full(&ca->free[RESERVE_BTREE])) break; if (bch_can_invalidate_bucket(ca, b) && !GC_MARK(b)) { __bch_invalidate_one_bucket(ca, b); - fifo_push(&ca->free[RESERVE_PRIO], - b - ca->buckets); + if (!fifo_push(&ca->free[RESERVE_PRIO], + b - ca->buckets)) + fifo_push(&ca->free[RESERVE_BTREE], + b - ca->buckets); } } } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index edb8d1a1a69f..bd6f6f4b4256 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -633,11 +633,11 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio) static void search_free(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); - bio_complete(s); if (s->iop.bio) bio_put(s->iop.bio); + bio_complete(s); closure_debug_destroy(cl); mempool_free(s, s->d->c->search); } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4af7cd423c71..894992ae9be0 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -938,7 +938,8 @@ void bch_cached_dev_detach(struct cached_dev *dc) cached_dev_put(dc); } -int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) +int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, + uint8_t *set_uuid) { uint32_t rtime = cpu_to_le32(get_seconds()); struct uuid_entry *u; @@ -947,7 +948,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) bdevname(dc->bdev, buf); - if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)) + if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) || + (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))) return -ENOENT; if (dc->disk.c) { @@ -1191,7 +1193,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page, list_add(&dc->list, &uncached_devices); list_for_each_entry(c, &bch_cache_sets, list) - bch_cached_dev_attach(dc, c); + bch_cached_dev_attach(dc, c, NULL); if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE || BDEV_STATE(&dc->sb) == BDEV_STATE_STALE) @@ -1714,7 +1716,7 @@ static void run_cache_set(struct cache_set *c) bcache_write_super(c); list_for_each_entry_safe(dc, t, &uncached_devices, list) - bch_cached_dev_attach(dc, c); + bch_cached_dev_attach(dc, c, NULL); flash_devs_run(c); @@ -1831,6 +1833,7 @@ void bch_cache_release(struct kobject *kobj) static int cache_alloc(struct cache *ca) { size_t free; + size_t btree_buckets; struct bucket *b; __module_get(THIS_MODULE); @@ -1840,9 +1843,19 @@ static int cache_alloc(struct cache *ca) ca->journal.bio.bi_max_vecs = 8; ca->journal.bio.bi_io_vec = ca->journal.bio.bi_inline_vecs; + /* + * when ca->sb.njournal_buckets is not zero, journal exists, + * and in bch_journal_replay(), tree node may split, + * so bucket of RESERVE_BTREE type is needed, + * the worst situation is all journal buckets are valid journal, + * and all the keys need to replay, + * so the number of RESERVE_BTREE type buckets should be as much + * as journal buckets + */ + btree_buckets = ca->sb.njournal_buckets ?: 8; free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; - if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || + if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) || !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 4fbb5532f24c..5a5c1f1bd8a5 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -191,7 +191,7 @@ STORE(__cached_dev) { struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj); - ssize_t v = size; + ssize_t v; struct cache_set *c; struct kobj_uevent_env *env; @@ -263,17 +263,20 @@ STORE(__cached_dev) } if (attr == &sysfs_attach) { - if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16) + uint8_t set_uuid[16]; + + if (bch_parse_uuid(buf, set_uuid) < 16) return -EINVAL; + v = -ENOENT; list_for_each_entry(c, &bch_cache_sets, list) { - v = bch_cached_dev_attach(dc, c); + v = bch_cached_dev_attach(dc, c, set_uuid); if (!v) return size; } pr_err("Can't attach %s: cache set not found", buf); - size = v; + return v; } if (attr == &sysfs_detach && dc->disk.c) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 4ce2b19fe120..bb7aa31c2a08 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -420,18 +420,27 @@ static int bch_writeback_thread(void *arg) while (!kthread_should_stop()) { down_write(&dc->writeback_lock); - if (!atomic_read(&dc->has_dirty) || - (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) && - !dc->writeback_running)) { + set_current_state(TASK_INTERRUPTIBLE); + /* + * If the bache device is detaching, skip here and continue + * to perform writeback. Otherwise, if no dirty data on cache, + * or there is dirty data on cache but writeback is disabled, + * the writeback thread should sleep here and wait for others + * to wake up it. + */ + if (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) && + (!atomic_read(&dc->has_dirty) || !dc->writeback_running)) { up_write(&dc->writeback_lock); - set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) + if (kthread_should_stop()) { + set_current_state(TASK_RUNNING); return 0; + } schedule(); continue; } + set_current_state(TASK_RUNNING); searched_full_index = refill_dirty(dc); @@ -441,6 +450,14 @@ static int bch_writeback_thread(void *arg) cached_dev_put(dc); SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN); bch_write_bdev_super(dc, NULL); + /* + * If bcache device is detaching via sysfs interface, + * writeback thread should stop after there is no dirty + * data on cache. BCACHE_DEV_DETACHING flag is set in + * bch_cached_dev_detach(). + */ + if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) + break; } up_write(&dc->writeback_lock); diff --git a/drivers/md/md.c b/drivers/md/md.c index a7bc70334f0e..cae8f3c12e32 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8200,6 +8200,19 @@ void md_do_sync(struct md_thread *thread) set_mask_bits(&mddev->flags, 0, BIT(MD_CHANGE_PENDING) | BIT(MD_CHANGE_DEVS)); + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + !test_bit(MD_RECOVERY_INTR, &mddev->recovery) && + mddev->delta_disks > 0 && + mddev->pers->finish_reshape && + mddev->pers->size && + mddev->queue) { + mddev_lock_nointr(mddev); + md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); + mddev_unlock(mddev); + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + } + spin_lock(&mddev->lock); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* We completed so min/max setting can be forgotten if used. */ diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 81a78757bc78..998102697619 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1673,6 +1673,17 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct md_rdev *repl = conf->mirrors[conf->raid_disks + number].rdev; freeze_array(conf, 0); + if (atomic_read(&repl->nr_pending)) { + /* It means that some queued IO of retry_list + * hold repl. Thus, we cannot set replacement + * as NULL, avoiding rdev NULL pointer + * dereference in sync_request_write and + * handle_write_finished. + */ + err = -EBUSY; + unfreeze_array(conf); + goto abort; + } clear_bit(Replacement, &repl->flags); p->rdev = repl; conf->mirrors[conf->raid_disks + number].rdev = NULL; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6a7b9b1dcfe3..b138b5cba286 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2636,7 +2636,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) for (m = 0; m < conf->copies; m++) { int dev = r10_bio->devs[m].devnum; rdev = conf->mirrors[dev].rdev; - if (r10_bio->devs[m].bio == NULL) + if (r10_bio->devs[m].bio == NULL || + r10_bio->devs[m].bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].bio->bi_error) { rdev_clear_badblocks( @@ -2651,7 +2652,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) md_error(conf->mddev, rdev); } rdev = conf->mirrors[dev].replacement; - if (r10_bio->devs[m].repl_bio == NULL) + if (r10_bio->devs[m].repl_bio == NULL || + r10_bio->devs[m].repl_bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].repl_bio->bi_error) { @@ -4682,17 +4684,11 @@ static void raid10_finish_reshape(struct mddev *mddev) return; if (mddev->delta_disks > 0) { - sector_t size = raid10_size(mddev, 0, 0); - md_set_array_sectors(mddev, size); if (mddev->recovery_cp > mddev->resync_max_sectors) { mddev->recovery_cp = mddev->resync_max_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } - mddev->resync_max_sectors = size; - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } + mddev->resync_max_sectors = mddev->array_sectors; } else { int d; rcu_read_lock(); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 724eb6fff81d..cfd153e50fa6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2051,15 +2051,16 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; + size_t namelen = sizeof(conf->cache_name[0]); int devs = max(conf->raid_disks, conf->previous_raid_disks); if (conf->mddev->gendisk) - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%s", conf->level, mdname(conf->mddev)); else - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%p", conf->level, conf->mddev); - sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]); + snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]); conf->active_name = 0; sc = kmem_cache_create(conf->cache_name[conf->active_name], @@ -7616,13 +7617,7 @@ static void raid5_finish_reshape(struct mddev *mddev) if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { - if (mddev->delta_disks > 0) { - md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } - } else { + if (mddev->delta_disks <= 0) { int d; spin_lock_irq(&conf->device_lock); mddev->degraded = calc_degraded(conf); |