diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/alloc.c | 5 | ||||
-rw-r--r-- | drivers/md/bcache/bcache.h | 1 | ||||
-rw-r--r-- | drivers/md/bcache/extents.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/journal.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/request.c | 21 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 13 | ||||
-rw-r--r-- | drivers/md/bcache/sysfs.c | 4 | ||||
-rw-r--r-- | drivers/md/bcache/util.c | 50 | ||||
-rw-r--r-- | drivers/md/bcache/writeback.c | 20 | ||||
-rw-r--r-- | drivers/md/bcache/writeback.h | 21 | ||||
-rw-r--r-- | drivers/md/bitmap.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-bufio.c | 15 | ||||
-rw-r--r-- | drivers/md/dm.c | 12 | ||||
-rw-r--r-- | drivers/md/linear.c | 3 | ||||
-rw-r--r-- | drivers/md/md-cluster.c | 1 | ||||
-rw-r--r-- | drivers/md/raid10.c | 19 | ||||
-rw-r--r-- | drivers/md/raid5.c | 20 |
17 files changed, 156 insertions, 58 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 8eeab72b93e2..4d46f2ce606f 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -406,7 +406,8 @@ long bch_bucket_alloc(struct cache *ca, unsigned reserve, bool wait) finish_wait(&ca->set->bucket_wait, &w); out: - wake_up_process(ca->alloc_thread); + if (ca->alloc_thread) + wake_up_process(ca->alloc_thread); trace_bcache_alloc(ca, reserve); @@ -478,7 +479,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve, if (b == -1) goto err; - k->ptr[i] = PTR(ca->buckets[b].gen, + k->ptr[i] = MAKE_PTR(ca->buckets[b].gen, bucket_to_sector(c, b), ca->sb.nr_this_dev); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index c3ea03c9a1a8..02619cabda8b 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -333,6 +333,7 @@ struct cached_dev { /* Limit number of writeback bios in flight */ struct semaphore in_flight; struct task_struct *writeback_thread; + struct workqueue_struct *writeback_write_wq; struct keybuf writeback_keys; diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index 243de0bf15cd..4bf15182c4da 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -584,7 +584,7 @@ static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey return false; for (i = 0; i < KEY_PTRS(l); i++) - if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] || + if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] || PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i)) return false; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 29eba7219b01..6ed066a0e7c0 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -508,7 +508,7 @@ static void journal_reclaim(struct cache_set *c) continue; ja->cur_idx = next; - k->ptr[n++] = PTR(0, + k->ptr[n++] = MAKE_PTR(0, bucket_to_sector(c, ca->sb.d[ja->cur_idx]), ca->sb.nr_this_dev); } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 2410df1c2a05..e73aeb0e892c 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -196,12 +196,12 @@ static void bch_data_insert_start(struct closure *cl) struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); struct bio *bio = op->bio, *n; - if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) - wake_up_gc(op->c); - if (op->bypass) return bch_data_invalidate(cl); + if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) + wake_up_gc(op->c); + /* * Journal writes are marked REQ_FLUSH; if the original write was a * flush, it'll wait on the journal write. @@ -468,6 +468,7 @@ struct search { unsigned recoverable:1; unsigned write:1; unsigned read_dirty_data:1; + unsigned cache_missed:1; unsigned long start_time; @@ -653,6 +654,7 @@ static inline struct search *search_alloc(struct bio *bio, s->orig_bio = bio; s->cache_miss = NULL; + s->cache_missed = 0; s->d = d; s->recoverable = 1; s->write = (bio->bi_rw & REQ_WRITE) != 0; @@ -708,7 +710,14 @@ static void cached_dev_read_error(struct closure *cl) struct search *s = container_of(cl, struct search, cl); struct bio *bio = &s->bio.bio; - if (s->recoverable) { + /* + * If read request hit dirty data (s->read_dirty_data is true), + * then recovery a failed read request from cached device may + * get a stale data back. So read failure recovery is only + * permitted when read request hit clean data in cache device, + * or when cache read race happened. + */ + if (s->recoverable && !s->read_dirty_data) { /* Retry from the backing device: */ trace_bcache_read_retry(s->orig_bio); @@ -769,7 +778,7 @@ static void cached_dev_read_done_bh(struct closure *cl) struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); bch_mark_cache_accounting(s->iop.c, s->d, - !s->cache_miss, s->iop.bypass); + !s->cache_missed, s->iop.bypass); trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass); if (s->iop.error) @@ -788,6 +797,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); struct bio *miss, *cache_bio; + s->cache_missed = 1; + if (s->cache_miss || s->iop.bypass) { miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split); ret = miss == bio ? MAP_DONE : MAP_CONTINUE; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 7b5880b8874c..8eaadd9869bc 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1023,7 +1023,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) } if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) { - bch_sectors_dirty_init(dc); + bch_sectors_dirty_init(&dc->disk); atomic_set(&dc->has_dirty, 1); atomic_inc(&dc->count); bch_writeback_queue(dc); @@ -1056,6 +1056,8 @@ static void cached_dev_free(struct closure *cl) cancel_delayed_work_sync(&dc->writeback_rate_update); if (!IS_ERR_OR_NULL(dc->writeback_thread)) kthread_stop(dc->writeback_thread); + if (dc->writeback_write_wq) + destroy_workqueue(dc->writeback_write_wq); mutex_lock(&bch_register_lock); @@ -1227,6 +1229,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) goto err; bcache_device_attach(d, c, u - c->uuids); + bch_sectors_dirty_init(d); bch_flash_dev_request_init(d); add_disk(d->disk); @@ -1959,6 +1962,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, else err = "device busy"; mutex_unlock(&bch_register_lock); + if (!IS_ERR(bdev)) + bdput(bdev); if (attr == &ksysfs_register_quiet) goto out; } @@ -2078,6 +2083,7 @@ static void bcache_exit(void) if (bcache_major) unregister_blkdev(bcache_major, "bcache"); unregister_reboot_notifier(&reboot); + mutex_destroy(&bch_register_lock); } static int __init bcache_init(void) @@ -2096,14 +2102,15 @@ static int __init bcache_init(void) bcache_major = register_blkdev(0, "bcache"); if (bcache_major < 0) { unregister_reboot_notifier(&reboot); + mutex_destroy(&bch_register_lock); return bcache_major; } if (!(bcache_wq = create_workqueue("bcache")) || !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) || - sysfs_create_files(bcache_kobj, files) || bch_request_init() || - bch_debug_init(bcache_kobj)) + bch_debug_init(bcache_kobj) || + sysfs_create_files(bcache_kobj, files)) goto err; return 0; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index b3ff57d61dde..4fbb5532f24c 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); - unsigned v = size; + ssize_t v = size; struct cache_set *c; struct kobj_uevent_env *env; @@ -226,7 +226,7 @@ STORE(__cached_dev) bch_cached_dev_run(dc); if (attr == &sysfs_cache_mode) { - ssize_t v = bch_read_string_list(buf, bch_cache_modes + 1); + v = bch_read_string_list(buf, bch_cache_modes + 1); if (v < 0) return v; diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index db3ae4c2b223..6c18e3ec3e48 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -73,24 +73,44 @@ STRTO_H(strtouint, unsigned int) STRTO_H(strtoll, long long) STRTO_H(strtoull, unsigned long long) +/** + * bch_hprint() - formats @v to human readable string for sysfs. + * + * @v - signed 64 bit integer + * @buf - the (at least 8 byte) buffer to format the result into. + * + * Returns the number of bytes used by format. + */ ssize_t bch_hprint(char *buf, int64_t v) { static const char units[] = "?kMGTPEZY"; - char dec[4] = ""; - int u, t = 0; - - for (u = 0; v >= 1024 || v <= -1024; u++) { - t = v & ~(~0 << 10); - v >>= 10; - } - - if (!u) - return sprintf(buf, "%llu", v); - - if (v < 100 && v > -100) - snprintf(dec, sizeof(dec), ".%i", t / 100); - - return sprintf(buf, "%lli%s%c", v, dec, units[u]); + int u = 0, t; + + uint64_t q; + + if (v < 0) + q = -v; + else + q = v; + + /* For as long as the number is more than 3 digits, but at least + * once, shift right / divide by 1024. Keep the remainder for + * a digit after the decimal point. + */ + do { + u++; + + t = q & ~(~0 << 10); + q >>= 10; + } while (q >= 1000); + + if (v < 0) + /* '-', up to 3 digits, '.', 1 digit, 1 character, null; + * yields 8 bytes. + */ + return sprintf(buf, "-%llu.%i%c", q, t * 10 / 1024, units[u]); + else + return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]); } ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[], diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index b9346cd9cda1..bbb1dc9e1639 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -21,7 +21,8 @@ static void __update_writeback_rate(struct cached_dev *dc) { struct cache_set *c = dc->disk.c; - uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size; + uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size - + bcache_flash_devs_sectors_dirty(c); uint64_t cache_dirty_target = div_u64(cache_sectors * dc->writeback_percent, 100); @@ -190,7 +191,7 @@ static void write_dirty(struct closure *cl) closure_bio_submit(&io->bio, cl); - continue_at(cl, write_dirty_finish, system_wq); + continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq); } static void read_dirty_endio(struct bio *bio) @@ -210,7 +211,7 @@ static void read_dirty_submit(struct closure *cl) closure_bio_submit(&io->bio, cl); - continue_at(cl, write_dirty, system_wq); + continue_at(cl, write_dirty, io->dc->writeback_write_wq); } static void read_dirty(struct cached_dev *dc) @@ -488,17 +489,17 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, return MAP_CONTINUE; } -void bch_sectors_dirty_init(struct cached_dev *dc) +void bch_sectors_dirty_init(struct bcache_device *d) { struct sectors_dirty_init op; bch_btree_op_init(&op.op, -1); - op.inode = dc->disk.id; + op.inode = d->id; - bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0), + bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0), sectors_dirty_init_fn, 0); - dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk); + d->sectors_dirty_last = bcache_dev_sectors_dirty(d); } void bch_cached_dev_writeback_init(struct cached_dev *dc) @@ -522,6 +523,11 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc) int bch_cached_dev_writeback_start(struct cached_dev *dc) { + dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq", + WQ_MEM_RECLAIM, 0); + if (!dc->writeback_write_wq) + return -ENOMEM; + dc->writeback_thread = kthread_create(bch_writeback_thread, dc, "bcache_writeback"); if (IS_ERR(dc->writeback_thread)) diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 073a042aed24..daec4fd782ea 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -14,6 +14,25 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d) return ret; } +static inline uint64_t bcache_flash_devs_sectors_dirty(struct cache_set *c) +{ + uint64_t i, ret = 0; + + mutex_lock(&bch_register_lock); + + for (i = 0; i < c->nr_uuids; i++) { + struct bcache_device *d = c->devices[i]; + + if (!d || !UUID_FLASH_ONLY(&c->uuids[i])) + continue; + ret += bcache_dev_sectors_dirty(d); + } + + mutex_unlock(&bch_register_lock); + + return ret; +} + static inline unsigned offset_to_stripe(struct bcache_device *d, uint64_t offset) { @@ -85,7 +104,7 @@ static inline void bch_writeback_add(struct cached_dev *dc) void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int); -void bch_sectors_dirty_init(struct cached_dev *dc); +void bch_sectors_dirty_init(struct bcache_device *); void bch_cached_dev_writeback_init(struct cached_dev *); int bch_cached_dev_writeback_start(struct cached_dev *); diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 4f22e919787a..7a50728b9389 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1960,6 +1960,11 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, long pages; struct bitmap_page *new_bp; + if (bitmap->storage.file && !init) { + pr_info("md: cannot resize file-based bitmap\n"); + return -EINVAL; + } + if (chunksize == 0) { /* If there is enough space, leave the chunk size unchanged, * else increase by factor of two until there is enough space. diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index cdceefd0e57d..2ec7f90e3455 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -928,7 +928,8 @@ static void __get_memory_limit(struct dm_bufio_client *c, buffers = c->minimum_buffers; *limit_buffers = buffers; - *threshold_buffers = buffers * DM_BUFIO_WRITEBACK_PERCENT / 100; + *threshold_buffers = mult_frac(buffers, + DM_BUFIO_WRITEBACK_PERCENT, 100); } /* @@ -1829,19 +1830,15 @@ static int __init dm_bufio_init(void) memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches); memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names); - mem = (__u64)((totalram_pages - totalhigh_pages) * - DM_BUFIO_MEMORY_PERCENT / 100) << PAGE_SHIFT; + mem = (__u64)mult_frac(totalram_pages - totalhigh_pages, + DM_BUFIO_MEMORY_PERCENT, 100) << PAGE_SHIFT; if (mem > ULONG_MAX) mem = ULONG_MAX; #ifdef CONFIG_MMU - /* - * Get the size of vmalloc space the same way as VMALLOC_TOTAL - * in fs/proc/internal.h - */ - if (mem > (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100) - mem = (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100; + if (mem > mult_frac(VMALLOC_TOTAL, DM_BUFIO_VMALLOC_PERCENT, 100)) + mem = mult_frac(VMALLOC_TOTAL, DM_BUFIO_VMALLOC_PERCENT, 100); #endif dm_bufio_default_cache_size = mem; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 320eb3c4bb6b..9ec6948e3b8b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -3507,11 +3507,15 @@ struct mapped_device *dm_get_from_kobject(struct kobject *kobj) md = container_of(kobj, struct mapped_device, kobj_holder.kobj); - if (test_bit(DMF_FREEING, &md->flags) || - dm_deleting_md(md)) - return NULL; - + spin_lock(&_minor_lock); + if (test_bit(DMF_FREEING, &md->flags) || dm_deleting_md(md)) { + md = NULL; + goto out; + } dm_get(md); +out: + spin_unlock(&_minor_lock); + return md; } diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 6ba3227e29b2..7ffb20ec1a46 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -223,7 +223,8 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev) * oldconf until no one uses it anymore. */ mddev_suspend(mddev); - oldconf = rcu_dereference(mddev->private); + oldconf = rcu_dereference_protected(mddev->private, + lockdep_is_held(&mddev->reconfig_mutex)); mddev->raid_disks++; WARN_ONCE(mddev->raid_disks != newconf->raid_disks, "copied raid_disks doesn't match mddev->raid_disks"); diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index d6a1126d85ce..494d01d0e92a 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -821,6 +821,7 @@ static int leave(struct mddev *mddev) lockres_free(cinfo->no_new_dev_lockres); lockres_free(cinfo->bitmap_lockres); dlm_release_lockspace(cinfo->lockspace, 2); + kfree(cinfo); return 0; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index e5ee4e9e0ea5..a8a86d450d76 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1414,11 +1414,24 @@ retry_write: mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); + + cb = blk_check_plugged(raid10_unplug, mddev, + sizeof(*plug)); + if (cb) + plug = container_of(cb, struct raid10_plug_cb, + cb); + else + plug = NULL; spin_lock_irqsave(&conf->device_lock, flags); - bio_list_add(&conf->pending_bio_list, mbio); - conf->pending_count++; + if (plug) { + bio_list_add(&plug->pending, mbio); + plug->pending_cnt++; + } else { + bio_list_add(&conf->pending_bio_list, mbio); + conf->pending_count++; + } spin_unlock_irqrestore(&conf->device_lock, flags); - if (!mddev_check_plugged(mddev)) + if (!plug) md_wakeup_thread(mddev->thread); } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8f60520c8392..86ab6d14d782 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -818,6 +818,14 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh spin_unlock(&head->batch_head->batch_lock); goto unlock_out; } + /* + * We must assign batch_head of this stripe within the + * batch_lock, otherwise clear_batch_ready of batch head + * stripe could clear BATCH_READY bit of this stripe and + * this stripe->batch_head doesn't get assigned, which + * could confuse clear_batch_ready for this stripe + */ + sh->batch_head = head->batch_head; /* * at this point, head's BATCH_READY could be cleared, but we @@ -825,8 +833,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh */ list_add(&sh->batch_list, &head->batch_list); spin_unlock(&head->batch_head->batch_lock); - - sh->batch_head = head->batch_head; } else { head->batch_head = head; sh->batch_head = head->batch_head; @@ -1675,8 +1681,11 @@ static void ops_complete_reconstruct(void *stripe_head_ref) struct r5dev *dev = &sh->dev[i]; if (dev->written || i == pd_idx || i == qd_idx) { - if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) + if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) { set_bit(R5_UPTODATE, &dev->flags); + if (test_bit(STRIPE_EXPAND_READY, &sh->state)) + set_bit(R5_Expanded, &dev->flags); + } if (fua) set_bit(R5_WantFUA, &dev->flags); if (sync) @@ -4258,7 +4267,8 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED)), + (1 << STRIPE_DEGRADED) | + (1 << STRIPE_ON_UNPLUG_LIST)), head_sh->state & (1 << STRIPE_INSYNC)); sh->check_state = head_sh->check_state; @@ -5822,6 +5832,8 @@ static void raid5_do_work(struct work_struct *work) spin_unlock_irq(&conf->device_lock); + r5l_flush_stripe_to_raid(conf->log); + async_tx_issue_pending_all(); blk_finish_plug(&plug); |