diff options
Diffstat (limited to '')
38 files changed, 402 insertions, 705 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index ce13c272c3..48ce750bf7 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -129,12 +129,9 @@ static inline bool can_inc_bucket_gen(struct bucket *b) bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b) { - BUG_ON(!ca->set->gc_mark_valid); - - return (!GC_MARK(b) || - GC_MARK(b) == GC_MARK_RECLAIMABLE) && - !atomic_read(&b->pin) && - can_inc_bucket_gen(b); + return (ca->set->gc_mark_valid || b->reclaimable_in_gc) && + ((!GC_MARK(b) || GC_MARK(b) == GC_MARK_RECLAIMABLE) && + !atomic_read(&b->pin) && can_inc_bucket_gen(b)); } void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b) @@ -148,6 +145,7 @@ void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b) bch_inc_gen(ca, b); b->prio = INITIAL_PRIO; atomic_inc(&b->pin); + b->reclaimable_in_gc = 0; } static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b) @@ -352,8 +350,7 @@ static int bch_allocator_thread(void *arg) */ retry_invalidate: - allocator_wait(ca, ca->set->gc_mark_valid && - !ca->invalidate_needs_gc); + allocator_wait(ca, !ca->invalidate_needs_gc); invalidate_buckets(ca); /* @@ -501,8 +498,8 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve, ca = c->cache; b = bch_bucket_alloc(ca, reserve, wait); - if (b == -1) - goto err; + if (b < 0) + return -1; k->ptr[0] = MAKE_PTR(ca->buckets[b].gen, bucket_to_sector(c, b), @@ -511,10 +508,6 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve, SET_KEY_PTRS(k, 1); return 0; -err: - bch_bucket_free(c, k); - bkey_put(c, k); - return -1; } int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve, diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 4e6afa8992..1d33e40d26 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -200,6 +200,7 @@ struct bucket { uint8_t gen; uint8_t last_gc; /* Most out of date gen in the btree */ uint16_t gc_mark; /* Bitfield used by GC. See below for field */ + uint16_t reclaimable_in_gc:1; }; /* diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index d011a7154d..4e6ccf2c8a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1741,18 +1741,20 @@ static void btree_gc_start(struct cache_set *c) mutex_lock(&c->bucket_lock); - c->gc_mark_valid = 0; c->gc_done = ZERO_KEY; ca = c->cache; for_each_bucket(b, ca) { b->last_gc = b->gen; + if (bch_can_invalidate_bucket(ca, b)) + b->reclaimable_in_gc = 1; if (!atomic_read(&b->pin)) { SET_GC_MARK(b, 0); SET_GC_SECTORS_USED(b, 0); } } + c->gc_mark_valid = 0; mutex_unlock(&c->bucket_lock); } @@ -1809,6 +1811,9 @@ static void bch_btree_gc_finish(struct cache_set *c) for_each_bucket(b, ca) { c->need_gc = max(c->need_gc, bucket_gc_gen(b)); + if (b->reclaimable_in_gc) + b->reclaimable_in_gc = 0; + if (atomic_read(&b->pin)) continue; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 83d112bd2b..af345dc6fd 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -369,10 +369,24 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) struct io *i; if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || - c->gc_stats.in_use > CUTOFF_CACHE_ADD || (bio_op(bio) == REQ_OP_DISCARD)) goto skip; + if (c->gc_stats.in_use > CUTOFF_CACHE_ADD) { + /* + * If cached buckets are all clean now, 'true' will be + * returned and all requests will bypass the cache device. + * Then c->sectors_to_gc has no chance to be negative, and + * gc thread won't wake up and caching won't work forever. + * Here call force_wake_up_gc() to avoid such aftermath. + */ + if (BDEV_STATE(&dc->sb) == BDEV_STATE_CLEAN && + c->gc_mark_valid) + force_wake_up_gc(c); + + goto skip; + } + if (mode == CACHE_MODE_NONE || (mode == CACHE_MODE_WRITEAROUND && op_is_write(bio_op(bio)))) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index b0819be048..4d11fc664c 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -171,7 +171,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, struct page *page; unsigned int i; - page = read_cache_page_gfp(bdev->bd_inode->i_mapping, + page = read_cache_page_gfp(bdev->bd_mapping, SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL); if (IS_ERR(page)) return "IO error"; @@ -881,8 +881,8 @@ static void bcache_device_free(struct bcache_device *d) bcache_device_detach(d); if (disk) { - ida_simple_remove(&bcache_device_idx, - first_minor_to_idx(disk->first_minor)); + ida_free(&bcache_device_idx, + first_minor_to_idx(disk->first_minor)); put_disk(disk); } @@ -940,8 +940,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, if (!d->full_dirty_stripes) goto out_free_stripe_sectors_dirty; - idx = ida_simple_get(&bcache_device_idx, 0, - BCACHE_DEVICE_IDX_MAX, GFP_KERNEL); + idx = ida_alloc_max(&bcache_device_idx, BCACHE_DEVICE_IDX_MAX - 1, + GFP_KERNEL); if (idx < 0) goto out_free_full_dirty_stripes; @@ -986,7 +986,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, out_bioset_exit: bioset_exit(&d->bio_split); out_ida_remove: - ida_simple_remove(&bcache_device_idx, idx); + ida_free(&bcache_device_idx, idx); out_free_full_dirty_stripes: kvfree(d->full_dirty_stripes); out_free_stripe_sectors_dirty: @@ -2555,10 +2555,6 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (IS_ERR(bdev_file)) goto out_free_sb; - err = "failed to set blocksize"; - if (set_blocksize(file_bdev(bdev_file), 4096)) - goto out_blkdev_put; - err = read_super(sb, file_bdev(bdev_file), &sb_disk); if (err) goto out_blkdev_put; diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index fd852981ef..cf433b0cf7 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -321,8 +321,7 @@ static bool __unlock(struct dm_bio_prison_v2 *prison, { BUG_ON(!cell->exclusive_lock); - bio_list_merge(bios, &cell->bios); - bio_list_init(&cell->bios); + bio_list_merge_init(bios, &cell->bios); if (cell->shared_count) { cell->exclusive_lock = false; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 911f73f7eb..16884b5850 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -115,8 +115,7 @@ static void __commit(struct work_struct *_ws) */ spin_lock_irq(&b->lock); list_splice_init(&b->work_items, &work_items); - bio_list_merge(&bios, &b->bios); - bio_list_init(&b->bios); + bio_list_merge_init(&bios, &b->bios); b->commit_scheduled = false; spin_unlock_irq(&b->lock); @@ -565,8 +564,7 @@ static void defer_bio(struct cache *cache, struct bio *bio) static void defer_bios(struct cache *cache, struct bio_list *bios) { spin_lock_irq(&cache->lock); - bio_list_merge(&cache->deferred_bios, bios); - bio_list_init(bios); + bio_list_merge_init(&cache->deferred_bios, bios); spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); @@ -1816,8 +1814,7 @@ static void process_deferred_bios(struct work_struct *ws) bio_list_init(&bios); spin_lock_irq(&cache->lock); - bio_list_merge(&bios, &cache->deferred_bios); - bio_list_init(&cache->deferred_bios); + bio_list_merge_init(&bios, &cache->deferred_bios); spin_unlock_irq(&cache->lock); while ((bio = bio_list_pop(&bios))) { @@ -1847,8 +1844,7 @@ static void requeue_deferred_bios(struct cache *cache) struct bio_list bios; bio_list_init(&bios); - bio_list_merge(&bios, &cache->deferred_bios); - bio_list_init(&cache->deferred_bios); + bio_list_merge_init(&bios, &cache->deferred_bios); while ((bio = bio_list_pop(&bios))) { bio->bi_status = BLK_STS_DM_REQUEUE; @@ -3394,8 +3390,8 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits) if (!cache->features.discard_passdown) { /* No passdown is done so setting own virtual limits */ - limits->max_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024, - cache->origin_sectors); + limits->max_hw_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024, + cache->origin_sectors); limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT; return; } @@ -3404,7 +3400,6 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits) * cache_iterate_devices() is stacking both origin and fast device limits * but discards aren't passed to fast device, so inherit origin's limits. */ - limits->max_discard_sectors = origin_limits->max_discard_sectors; limits->max_hw_discard_sectors = origin_limits->max_hw_discard_sectors; limits->discard_granularity = origin_limits->discard_granularity; limits->discard_alignment = origin_limits->discard_alignment; diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index c43d55672b..47c1fa7aad 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd) /*---------------------------------------------------------------------------*/ -static size_t bitmap_size(unsigned long nr_bits) -{ - return BITS_TO_LONGS(nr_bits) * sizeof(long); -} - static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, unsigned long nr_regions) { diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 94b2fc33f6..ad79b52ffc 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1181,8 +1181,7 @@ static void process_deferred_discards(struct clone *clone) struct bio_list discards = BIO_EMPTY_LIST; spin_lock_irq(&clone->lock); - bio_list_merge(&discards, &clone->deferred_discard_bios); - bio_list_init(&clone->deferred_discard_bios); + bio_list_merge_init(&discards, &clone->deferred_discard_bios); spin_unlock_irq(&clone->lock); if (bio_list_empty(&discards)) @@ -1215,8 +1214,7 @@ static void process_deferred_bios(struct clone *clone) struct bio_list bios = BIO_EMPTY_LIST; spin_lock_irq(&clone->lock); - bio_list_merge(&bios, &clone->deferred_bios); - bio_list_init(&clone->deferred_bios); + bio_list_merge_init(&bios, &clone->deferred_bios); spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios)) @@ -1237,11 +1235,9 @@ static void process_deferred_flush_bios(struct clone *clone) * before issuing them or signaling their completion. */ spin_lock_irq(&clone->lock); - bio_list_merge(&bios, &clone->deferred_flush_bios); - bio_list_init(&clone->deferred_flush_bios); - - bio_list_merge(&bio_completions, &clone->deferred_flush_completions); - bio_list_init(&clone->deferred_flush_completions); + bio_list_merge_init(&bios, &clone->deferred_flush_bios); + bio_list_merge_init(&bio_completions, + &clone->deferred_flush_completions); spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && @@ -2050,7 +2046,8 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits) if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) { /* No passdown is done so we set our own virtual limits */ limits->discard_granularity = clone->region_size << SECTOR_SHIFT; - limits->max_discard_sectors = round_down(UINT_MAX >> SECTOR_SHIFT, clone->region_size); + limits->max_hw_discard_sectors = round_down(UINT_MAX >> SECTOR_SHIFT, + clone->region_size); return; } @@ -2059,7 +2056,6 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits) * device limits but discards aren't passed to the source device, so * inherit destination's limits. */ - limits->max_discard_sectors = dest_limits->max_discard_sectors; limits->max_hw_discard_sectors = dest_limits->max_hw_discard_sectors; limits->discard_granularity = dest_limits->discard_granularity; limits->discard_alignment = dest_limits->discard_alignment; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index e6757a30dc..08700bfc3e 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -140,7 +140,7 @@ struct mapped_device { #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_zones; - unsigned int *zwp_offset; + void *zone_revalidate_map; #endif #ifdef CONFIG_IMA diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9a74c6316c..1b7a97cc37 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -47,6 +47,8 @@ #define DM_MSG_PREFIX "crypt" +static DEFINE_IDA(workqueue_ida); + /* * context holding the current state of a multi-part conversion */ @@ -137,9 +139,9 @@ struct iv_elephant_private { * and encrypts / decrypts at the same time. */ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID, - DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD, - DM_CRYPT_NO_READ_WORKQUEUE, DM_CRYPT_NO_WRITE_WORKQUEUE, - DM_CRYPT_WRITE_INLINE }; + DM_CRYPT_SAME_CPU, DM_CRYPT_HIGH_PRIORITY, + DM_CRYPT_NO_OFFLOAD, DM_CRYPT_NO_READ_WORKQUEUE, + DM_CRYPT_NO_WRITE_WORKQUEUE, DM_CRYPT_WRITE_INLINE }; enum cipher_flags { CRYPT_MODE_INTEGRITY_AEAD, /* Use authenticated mode for cipher */ @@ -184,6 +186,7 @@ struct crypt_config { struct crypto_aead **tfms_aead; } cipher_tfm; unsigned int tfms_count; + int workqueue_id; unsigned long cipher_flags; /* @@ -1653,8 +1656,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone); /* * Generate a new unfragmented bio with the given size - * This should never violate the device limitations (but only because - * max_segment_size is being constrained to PAGE_SIZE). + * This should never violate the device limitations (but if it did then block + * core should split the bio as needed). * * This function may be called concurrently. If we allocate from the mempool * concurrently, there is a possibility of deadlock. For example, if we have @@ -2771,6 +2774,9 @@ static void crypt_dtr(struct dm_target *ti) if (cc->crypt_queue) destroy_workqueue(cc->crypt_queue); + if (cc->workqueue_id) + ida_free(&workqueue_ida, cc->workqueue_id); + crypt_free_tfms(cc); bioset_exit(&cc->bs); @@ -3134,7 +3140,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar struct crypt_config *cc = ti->private; struct dm_arg_set as; static const struct dm_arg _args[] = { - {0, 8, "Invalid number of feature args"}, + {0, 9, "Invalid number of feature args"}, }; unsigned int opt_params, val; const char *opt_string, *sval; @@ -3161,6 +3167,8 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar else if (!strcasecmp(opt_string, "same_cpu_crypt")) set_bit(DM_CRYPT_SAME_CPU, &cc->flags); + else if (!strcasecmp(opt_string, "high_priority")) + set_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags); else if (!strcasecmp(opt_string, "submit_from_crypt_cpus")) set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags); @@ -3230,8 +3238,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct crypt_config *cc; const char *devname = dm_table_device_name(ti->table); - int key_size; + int key_size, wq_id; unsigned int align_mask; + unsigned int common_wq_flags; unsigned long long tmpll; int ret; size_t iv_size_padding, additional_req_size; @@ -3398,20 +3407,38 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->tag_pool_max_sectors <<= cc->sector_shift; } + wq_id = ida_alloc_min(&workqueue_ida, 1, GFP_KERNEL); + if (wq_id < 0) { + ti->error = "Couldn't get workqueue id"; + ret = wq_id; + goto bad; + } + cc->workqueue_id = wq_id; + ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname); + common_wq_flags = WQ_MEM_RECLAIM | WQ_SYSFS; + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + common_wq_flags |= WQ_HIGHPRI; + + cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", common_wq_flags, 1, devname, wq_id); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } - if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); - else - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, - num_online_cpus(), devname); + if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) { + cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d", + common_wq_flags | WQ_CPU_INTENSIVE, + 1, devname, wq_id); + } else { + /* + * While crypt_queue is certainly CPU intensive, the use of + * WQ_CPU_INTENSIVE is meaningless with WQ_UNBOUND. + */ + cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d", + common_wq_flags | WQ_UNBOUND, + num_online_cpus(), devname, wq_id); + } if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; goto bad; @@ -3427,6 +3454,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Couldn't spawn write thread"; goto bad; } + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + set_user_nice(cc->write_thread, MIN_NICE); ti->num_flush_bios = 1; ti->limit_swap_bios = true; @@ -3547,6 +3576,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type, num_feature_args += !!ti->num_discard_bios; num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags); + num_feature_args += test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags); num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags); num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags); num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); @@ -3560,6 +3590,8 @@ static void crypt_status(struct dm_target *ti, status_type_t type, DMEMIT(" allow_discards"); if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) DMEMIT(" same_cpu_crypt"); + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + DMEMIT(" high_priority"); if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) DMEMIT(" submit_from_crypt_cpus"); if (test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) @@ -3579,6 +3611,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type, DMEMIT_TARGET_NAME_VERSION(ti->type); DMEMIT(",allow_discards=%c", ti->num_discard_bios ? 'y' : 'n'); DMEMIT(",same_cpu_crypt=%c", test_bit(DM_CRYPT_SAME_CPU, &cc->flags) ? 'y' : 'n'); + DMEMIT(",high_priority=%c", test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags) ? 'y' : 'n'); DMEMIT(",submit_from_crypt_cpus=%c", test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags) ? 'y' : 'n'); DMEMIT(",no_read_workqueue=%c", test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags) ? @@ -3688,14 +3721,6 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct crypt_config *cc = ti->private; - /* - * Unfortunate constraint that is required to avoid the potential - * for exceeding underlying device's max_segments limits -- due to - * crypt_alloc_buffer() possibly allocating pages for the encryption - * bio that are not as physically contiguous as the original bio. - */ - limits->max_segment_size = PAGE_SIZE; - limits->logical_block_size = max_t(unsigned int, limits->logical_block_size, cc->sector_size); limits->physical_block_size = @@ -3706,7 +3731,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type crypt_target = { .name = "crypt", - .version = {1, 25, 0}, + .version = {1, 26, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 2ac43d1f1b..08f6387620 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -28,7 +28,8 @@ struct delay_class { struct delay_c { struct timer_list delay_timer; - struct mutex timer_lock; + struct mutex process_bios_lock; /* hold while removing bios to be processed from list */ + spinlock_t delayed_bios_lock; /* hold on all accesses to delayed_bios list */ struct workqueue_struct *kdelayd_wq; struct work_struct flush_expired_bios; struct list_head delayed_bios; @@ -49,8 +50,6 @@ struct dm_delay_info { unsigned long expires; }; -static DEFINE_MUTEX(delayed_bios_lock); - static void handle_delayed_timer(struct timer_list *t) { struct delay_c *dc = from_timer(dc, t, delay_timer); @@ -60,12 +59,7 @@ static void handle_delayed_timer(struct timer_list *t) static void queue_timeout(struct delay_c *dc, unsigned long expires) { - mutex_lock(&dc->timer_lock); - - if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires) - mod_timer(&dc->delay_timer, expires); - - mutex_unlock(&dc->timer_lock); + timer_reduce(&dc->delay_timer, expires); } static inline bool delay_is_fast(struct delay_c *dc) @@ -89,12 +83,16 @@ static void flush_delayed_bios(struct delay_c *dc, bool flush_all) { struct dm_delay_info *delayed, *next; struct bio_list flush_bio_list; + LIST_HEAD(local_list); unsigned long next_expires = 0; bool start_timer = false; bio_list_init(&flush_bio_list); - mutex_lock(&delayed_bios_lock); - list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) { + mutex_lock(&dc->process_bios_lock); + spin_lock(&dc->delayed_bios_lock); + list_replace_init(&dc->delayed_bios, &local_list); + spin_unlock(&dc->delayed_bios_lock); + list_for_each_entry_safe(delayed, next, &local_list, list) { cond_resched(); if (flush_all || time_after_eq(jiffies, delayed->expires)) { struct bio *bio = dm_bio_from_per_bio_data(delayed, @@ -114,7 +112,10 @@ static void flush_delayed_bios(struct delay_c *dc, bool flush_all) } } } - mutex_unlock(&delayed_bios_lock); + spin_lock(&dc->delayed_bios_lock); + list_splice(&local_list, &dc->delayed_bios); + spin_unlock(&dc->delayed_bios_lock); + mutex_unlock(&dc->process_bios_lock); if (start_timer) queue_timeout(dc, next_expires); @@ -128,13 +129,13 @@ static int flush_worker_fn(void *data) while (!kthread_should_stop()) { flush_delayed_bios(dc, false); - mutex_lock(&delayed_bios_lock); + spin_lock(&dc->delayed_bios_lock); if (unlikely(list_empty(&dc->delayed_bios))) { set_current_state(TASK_INTERRUPTIBLE); - mutex_unlock(&delayed_bios_lock); + spin_unlock(&dc->delayed_bios_lock); schedule(); } else { - mutex_unlock(&delayed_bios_lock); + spin_unlock(&dc->delayed_bios_lock); cond_resched(); } } @@ -168,7 +169,7 @@ static void delay_dtr(struct dm_target *ti) if (dc->worker) kthread_stop(dc->worker); - mutex_destroy(&dc->timer_lock); + mutex_destroy(&dc->process_bios_lock); kfree(dc); } @@ -226,7 +227,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->private = dc; INIT_LIST_HEAD(&dc->delayed_bios); - mutex_init(&dc->timer_lock); + mutex_init(&dc->process_bios_lock); + spin_lock_init(&dc->delayed_bios_lock); dc->may_delay = true; dc->argc = argc; @@ -309,14 +311,14 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio) delayed->context = dc; delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay); - mutex_lock(&delayed_bios_lock); + spin_lock(&dc->delayed_bios_lock); if (unlikely(!dc->may_delay)) { - mutex_unlock(&delayed_bios_lock); + spin_unlock(&dc->delayed_bios_lock); return DM_MAPIO_REMAPPED; } c->ops++; list_add_tail(&delayed->list, &dc->delayed_bios); - mutex_unlock(&delayed_bios_lock); + spin_unlock(&dc->delayed_bios_lock); if (delay_is_fast(dc)) wake_up_process(dc->worker); @@ -330,9 +332,9 @@ static void delay_presuspend(struct dm_target *ti) { struct delay_c *dc = ti->private; - mutex_lock(&delayed_bios_lock); + spin_lock(&dc->delayed_bios_lock); dc->may_delay = false; - mutex_unlock(&delayed_bios_lock); + spin_unlock(&dc->delayed_bios_lock); if (!delay_is_fast(dc)) timer_delete(&dc->delay_timer); diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 6acfa5bf97..8f81e59785 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1272,8 +1272,7 @@ static void process_deferred_bios(struct era *era) bio_list_init(&marked_bios); spin_lock(&era->deferred_lock); - bio_list_merge(&deferred_bios, &era->deferred_bios); - bio_list_init(&era->deferred_bios); + bio_list_merge_init(&deferred_bios, &era->deferred_bios); spin_unlock(&era->deferred_lock); if (bio_list_empty(&deferred_bios)) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index f17a6cf228..8d7df8303d 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -871,7 +871,7 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit if (!bdev_max_discard_sectors(lc->dev->bdev)) { lc->device_supports_discard = false; limits->discard_granularity = lc->sectorsize; - limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); + limits->max_hw_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); } limits->logical_block_size = bdev_logical_block_size(lc->dev->bdev); limits->physical_block_size = bdev_physical_block_size(lc->dev->bdev); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 05d1328d18..15b681b901 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -704,8 +704,7 @@ static void process_queued_bios(struct work_struct *work) return; } - bio_list_merge(&bios, &m->queued_bios); - bio_list_init(&m->queued_bios); + bio_list_merge_init(&bios, &m->queued_bios); spin_unlock_irqrestore(&m->lock, flags); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index abe88d1e67..b149ac46a9 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -4101,10 +4101,11 @@ static void raid_resume(struct dm_target *ti) if (mddev->delta_disks < 0) rs_set_capacity(rs); + mddev_lock_nointr(mddev); WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)); - WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + WARN_ON_ONCE(rcu_dereference_protected(mddev->sync_thread, + lockdep_is_held(&mddev->reconfig_mutex))); clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); - mddev_lock_nointr(mddev); mddev->ro = 0; mddev->in_sync = 0; md_unfrozen_sync_thread(mddev); diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 0ace06d1be..f40c18da40 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -2410,7 +2410,7 @@ static void snapshot_io_hints(struct dm_target *ti, struct queue_limits *limits) /* All discards are split on chunk_size boundary */ limits->discard_granularity = snap->store->chunk_size; - limits->max_discard_sectors = snap->store->chunk_size; + limits->max_hw_discard_sectors = snap->store->chunk_size; up_read(&_origins_lock); } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 41f1d731ae..2fc847af25 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1963,26 +1963,23 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, bool wc = false, fua = false; int r; - /* - * Copy table's limits to the DM device's request_queue - */ - q->limits = *limits; - if (dm_table_supports_nowait(t)) blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); else blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); if (!dm_table_supports_discards(t)) { - q->limits.max_discard_sectors = 0; - q->limits.max_hw_discard_sectors = 0; - q->limits.discard_granularity = 0; - q->limits.discard_alignment = 0; - q->limits.discard_misaligned = 0; + limits->max_hw_discard_sectors = 0; + limits->discard_granularity = 0; + limits->discard_alignment = 0; + limits->discard_misaligned = 0; } + if (!dm_table_supports_write_zeroes(t)) + limits->max_write_zeroes_sectors = 0; + if (!dm_table_supports_secure_erase(t)) - q->limits.max_secure_erase_sectors = 0; + limits->max_secure_erase_sectors = 0; if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; @@ -2007,9 +2004,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, else blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - if (!dm_table_supports_write_zeroes(t)) - q->limits.max_write_zeroes_sectors = 0; - dm_table_verify_integrity(t); /* @@ -2034,20 +2028,28 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, dm_table_any_dev_attr(t, device_is_not_random, NULL)) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + /* For a zoned table, setup the zone related queue attributes. */ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) { + r = dm_set_zones_restrictions(t, q, limits); + if (r) + return r; + } + + r = queue_limits_set(q, limits); + if (r) + return r; + /* - * For a zoned target, setup the zones related queue attributes - * and resources necessary for zone append emulation if necessary. + * Now that the limits are set, check the zones mapped by the table + * and setup the resources for zone append emulation if necessary. */ - if (blk_queue_is_zoned(q)) { - r = dm_set_zones_restrictions(t, q); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) { + r = dm_revalidate_zones(t, q); if (r) return r; - if (!static_key_enabled(&zoned_enabled.key)) - static_branch_enable(&zoned_enabled); } dm_update_crypto_profile(q, t); - disk_update_readahead(t->md->disk); /* * Check for request-based device is left to diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 0c4efb0bef..652627aea1 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -249,7 +249,6 @@ static int io_err_iterate_devices(struct dm_target *ti, static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits) { - limits->max_discard_sectors = UINT_MAX; limits->max_hw_discard_sectors = UINT_MAX; limits->discard_granularity = 512; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 4793ad2aa1..991f77a588 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -592,12 +592,6 @@ struct dm_thin_endio_hook { struct dm_bio_prison_cell *cell; }; -static void __merge_bio_list(struct bio_list *bios, struct bio_list *master) -{ - bio_list_merge(bios, master); - bio_list_init(master); -} - static void error_bio_list(struct bio_list *bios, blk_status_t error) { struct bio *bio; @@ -616,7 +610,7 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, bio_list_init(&bios); spin_lock_irq(&tc->lock); - __merge_bio_list(&bios, master); + bio_list_merge_init(&bios, master); spin_unlock_irq(&tc->lock); error_bio_list(&bios, error); @@ -645,8 +639,8 @@ static void requeue_io(struct thin_c *tc) bio_list_init(&bios); spin_lock_irq(&tc->lock); - __merge_bio_list(&bios, &tc->deferred_bio_list); - __merge_bio_list(&bios, &tc->retry_on_resume_list); + bio_list_merge_init(&bios, &tc->deferred_bio_list); + bio_list_merge_init(&bios, &tc->retry_on_resume_list); spin_unlock_irq(&tc->lock); error_bio_list(&bios, BLK_STS_DM_REQUEUE); @@ -4100,7 +4094,7 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) if (pt->adjusted_pf.discard_enabled) { disable_discard_passdown_if_not_supported(pt); if (!pt->adjusted_pf.discard_passdown) - limits->max_discard_sectors = 0; + limits->max_hw_discard_sectors = 0; /* * The pool uses the same discard limits as the underlying data * device. DM core has already set this up. @@ -4497,7 +4491,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) if (pool->pf.discard_enabled) { limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; - limits->max_discard_sectors = pool->sectors_per_block * BIO_PRISON_MAX_RANGE; + limits->max_hw_discard_sectors = pool->sectors_per_block * BIO_PRISON_MAX_RANGE; } } diff --git a/drivers/md/dm-vdo/Makefile b/drivers/md/dm-vdo/Makefile index 33e09abc6a..9476957bfb 100644 --- a/drivers/md/dm-vdo/Makefile +++ b/drivers/md/dm-vdo/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I$(srctree)/$(src) -I$(srctree)/$(src)/indexer +ccflags-y := -I$(src) -I$(src)/indexer obj-$(CONFIG_DM_VDO) += dm-vdo.o diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c index 94f6f1ccfb..ab3ea83378 100644 --- a/drivers/md/dm-vdo/data-vio.c +++ b/drivers/md/dm-vdo/data-vio.c @@ -604,8 +604,7 @@ static void assign_discard_permit(struct limiter *limiter) static void get_waiters(struct limiter *limiter) { - bio_list_merge(&limiter->waiters, &limiter->new_waiters); - bio_list_init(&limiter->new_waiters); + bio_list_merge_init(&limiter->waiters, &limiter->new_waiters); } static inline struct data_vio *get_available_data_vio(struct data_vio_pool *pool) diff --git a/drivers/md/dm-vdo/dm-vdo-target.c b/drivers/md/dm-vdo/dm-vdo-target.c index 5a4b0a927f..9d51f72a9d 100644 --- a/drivers/md/dm-vdo/dm-vdo-target.c +++ b/drivers/md/dm-vdo/dm-vdo-target.c @@ -878,7 +878,7 @@ static int parse_device_config(int argc, char **argv, struct dm_target *ti, } if (config->version == 0) { - u64 device_size = i_size_read(config->owned_device->bdev->bd_inode); + u64 device_size = bdev_nr_bytes(config->owned_device->bdev); config->physical_blocks = device_size / VDO_BLOCK_SIZE; } @@ -945,7 +945,7 @@ static void vdo_io_hints(struct dm_target *ti, struct queue_limits *limits) * The value is used by dm-thin to determine whether to pass down discards. The block layer * splits large discards on this boundary when this is set. */ - limits->max_discard_sectors = + limits->max_hw_discard_sectors = (vdo->device_config->max_discard_blocks * VDO_SECTORS_PER_BLOCK); /* @@ -1011,7 +1011,7 @@ static void vdo_status(struct dm_target *ti, status_type_t status_type, static block_count_t __must_check get_underlying_device_block_count(const struct vdo *vdo) { - return i_size_read(vdo_get_backing_device(vdo)->bd_inode) / VDO_BLOCK_SIZE; + return bdev_nr_bytes(vdo_get_backing_device(vdo)) / VDO_BLOCK_SIZE; } static int __must_check process_vdo_message_locked(struct vdo *vdo, unsigned int argc, diff --git a/drivers/md/dm-vdo/flush.c b/drivers/md/dm-vdo/flush.c index 57e87f0d70..dd4fdee2ca 100644 --- a/drivers/md/dm-vdo/flush.c +++ b/drivers/md/dm-vdo/flush.c @@ -369,8 +369,7 @@ void vdo_dump_flusher(const struct flusher *flusher) static void initialize_flush(struct vdo_flush *flush, struct vdo *vdo) { bio_list_init(&flush->bios); - bio_list_merge(&flush->bios, &vdo->flusher->waiting_flush_bios); - bio_list_init(&vdo->flusher->waiting_flush_bios); + bio_list_merge_init(&flush->bios, &vdo->flusher->waiting_flush_bios); } static void launch_flush(struct vdo_flush *flush) diff --git a/drivers/md/dm-vdo/indexer/io-factory.c b/drivers/md/dm-vdo/indexer/io-factory.c index 515765d357..1bee9d63dc 100644 --- a/drivers/md/dm-vdo/indexer/io-factory.c +++ b/drivers/md/dm-vdo/indexer/io-factory.c @@ -90,7 +90,7 @@ void uds_put_io_factory(struct io_factory *factory) size_t uds_get_writable_size(struct io_factory *factory) { - return i_size_read(factory->bdev->bd_inode); + return bdev_nr_bytes(factory->bdev); } /* Create a struct dm_bufio_client for an index region starting at offset. */ diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index bb5da66da4..431a61e1a8 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1539,14 +1539,6 @@ bad: } /* - * Check whether a DM target is a verity target. - */ -bool dm_is_verity_target(struct dm_target *ti) -{ - return ti->type->module == THIS_MODULE; -} - -/* * Get the verity mode (error behavior) of a verity target. * * Returns the verity mode of the target, or -EINVAL if 'ti' is not a verity @@ -1599,6 +1591,14 @@ static struct target_type verity_target = { }; module_dm(verity); +/* + * Check whether a DM target is a verity target. + */ +bool dm_is_verity_target(struct dm_target *ti) +{ + return ti->type == &verity_target; +} + MODULE_AUTHOR("Mikulas Patocka <mpatocka@redhat.com>"); MODULE_AUTHOR("Mandeep Baines <msb@chromium.org>"); MODULE_AUTHOR("Will Drewry <wad@chromium.org>"); diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index 3b13e6eb1a..9a0bb623e8 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -61,7 +61,6 @@ static int zero_map(struct dm_target *ti, struct bio *bio) static void zero_io_hints(struct dm_target *ti, struct queue_limits *limits) { - limits->max_discard_sectors = UINT_MAX; limits->max_hw_discard_sectors = UINT_MAX; limits->discard_granularity = 512; } diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index eb9832b22b..75d0019a06 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -60,16 +60,23 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, struct dm_table *map; int srcu_idx, ret; - if (dm_suspended_md(md)) - return -EAGAIN; + if (!md->zone_revalidate_map) { + /* Regular user context */ + if (dm_suspended_md(md)) + return -EAGAIN; - map = dm_get_live_table(md, &srcu_idx); - if (!map) - return -EIO; + map = dm_get_live_table(md, &srcu_idx); + if (!map) + return -EIO; + } else { + /* Zone revalidation during __bind() */ + map = md->zone_revalidate_map; + } ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data); - dm_put_live_table(md, srcu_idx); + if (!md->zone_revalidate_map) + dm_put_live_table(md, srcu_idx); return ret; } @@ -138,81 +145,17 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) } } -void dm_cleanup_zoned_dev(struct mapped_device *md) -{ - if (md->disk) { - bitmap_free(md->disk->conv_zones_bitmap); - md->disk->conv_zones_bitmap = NULL; - bitmap_free(md->disk->seq_zones_wlock); - md->disk->seq_zones_wlock = NULL; - } - - kvfree(md->zwp_offset); - md->zwp_offset = NULL; - md->nr_zones = 0; -} - -static unsigned int dm_get_zone_wp_offset(struct blk_zone *zone) -{ - switch (zone->cond) { - case BLK_ZONE_COND_IMP_OPEN: - case BLK_ZONE_COND_EXP_OPEN: - case BLK_ZONE_COND_CLOSED: - return zone->wp - zone->start; - case BLK_ZONE_COND_FULL: - return zone->len; - case BLK_ZONE_COND_EMPTY: - case BLK_ZONE_COND_NOT_WP: - case BLK_ZONE_COND_OFFLINE: - case BLK_ZONE_COND_READONLY: - default: - /* - * Conventional, offline and read-only zones do not have a valid - * write pointer. Use 0 as for an empty zone. - */ - return 0; - } -} - -static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx, - void *data) +/* + * Count conventional zones of a mapped zoned device. If the device + * only has conventional zones, do not expose it as zoned. + */ +static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx, + void *data) { - struct mapped_device *md = data; - struct gendisk *disk = md->disk; + unsigned int *nr_conv_zones = data; - switch (zone->type) { - case BLK_ZONE_TYPE_CONVENTIONAL: - if (!disk->conv_zones_bitmap) { - disk->conv_zones_bitmap = bitmap_zalloc(disk->nr_zones, - GFP_NOIO); - if (!disk->conv_zones_bitmap) - return -ENOMEM; - } - set_bit(idx, disk->conv_zones_bitmap); - break; - case BLK_ZONE_TYPE_SEQWRITE_REQ: - case BLK_ZONE_TYPE_SEQWRITE_PREF: - if (!disk->seq_zones_wlock) { - disk->seq_zones_wlock = bitmap_zalloc(disk->nr_zones, - GFP_NOIO); - if (!disk->seq_zones_wlock) - return -ENOMEM; - } - if (!md->zwp_offset) { - md->zwp_offset = - kvcalloc(disk->nr_zones, sizeof(unsigned int), - GFP_KERNEL); - if (!md->zwp_offset) - return -ENOMEM; - } - md->zwp_offset[idx] = dm_get_zone_wp_offset(zone); - - break; - default: - DMERR("Invalid zone type 0x%x at sectors %llu", - (int)zone->type, zone->start); - return -ENODEV; - } + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + (*nr_conv_zones)++; return 0; } @@ -223,44 +166,43 @@ static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx, * blk_revalidate_disk_zones() function here as the mapped device is suspended * (this is called from __bind() context). */ -static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t) +int dm_revalidate_zones(struct dm_table *t, struct request_queue *q) { + struct mapped_device *md = t->md; struct gendisk *disk = md->disk; - unsigned int noio_flag; int ret; - /* - * Check if something changed. If yes, cleanup the current resources - * and reallocate everything. - */ - if (!disk->nr_zones || disk->nr_zones != md->nr_zones) - dm_cleanup_zoned_dev(md); + if (!get_capacity(disk)) + return 0; + + /* Revalidate only if something changed. */ + if (!disk->nr_zones || disk->nr_zones != md->nr_zones) { + DMINFO("%s using %s zone append", + disk->disk_name, + queue_emulates_zone_append(q) ? "emulated" : "native"); + md->nr_zones = 0; + } + if (md->nr_zones) return 0; /* - * Scan all zones to initialize everything. Ensure that all vmalloc - * operations in this context are done as if GFP_NOIO was specified. + * Our table is not live yet. So the call to dm_get_live_table() + * in dm_blk_report_zones() will fail. Set a temporary pointer to + * our table for dm_blk_report_zones() to use directly. */ - noio_flag = memalloc_noio_save(); - ret = dm_blk_do_report_zones(md, t, 0, disk->nr_zones, - dm_zone_revalidate_cb, md); - memalloc_noio_restore(noio_flag); - if (ret < 0) - goto err; - if (ret != disk->nr_zones) { - ret = -EIO; - goto err; + md->zone_revalidate_map = t; + ret = blk_revalidate_disk_zones(disk); + md->zone_revalidate_map = NULL; + + if (ret) { + DMERR("Revalidate zones failed %d", ret); + return ret; } md->nr_zones = disk->nr_zones; return 0; - -err: - DMERR("Revalidate zones failed %d", ret); - dm_cleanup_zoned_dev(md); - return ret; } static int device_not_zone_append_capable(struct dm_target *ti, @@ -286,297 +228,55 @@ static bool dm_table_supports_zone_append(struct dm_table *t) return true; } -int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q) +int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *lim) { struct mapped_device *md = t->md; + struct gendisk *disk = md->disk; + unsigned int nr_conv_zones = 0; + int ret; /* - * For a zoned target, the number of zones should be updated for the - * correct value to be exposed in sysfs queue/nr_zones. + * Check if zone append is natively supported, and if not, set the + * mapped device queue as needing zone append emulation. */ WARN_ON_ONCE(queue_is_mq(q)); - md->disk->nr_zones = bdev_nr_zones(md->disk->part0); - - /* Check if zone append is natively supported */ if (dm_table_supports_zone_append(t)) { clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); - dm_cleanup_zoned_dev(md); - return 0; + } else { + set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + lim->max_zone_append_sectors = 0; } /* - * Mark the mapped device as needing zone append emulation and - * initialize the emulation resources once the capacity is set. + * Count conventional zones to check that the mapped device will indeed + * have sequential write required zones. */ - set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); - if (!get_capacity(md->disk)) - return 0; - - return dm_revalidate_zones(md, t); -} - -static int dm_update_zone_wp_offset_cb(struct blk_zone *zone, unsigned int idx, - void *data) -{ - unsigned int *wp_offset = data; - - *wp_offset = dm_get_zone_wp_offset(zone); - - return 0; -} - -static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno, - unsigned int *wp_ofst) -{ - sector_t sector = zno * bdev_zone_sectors(md->disk->part0); - unsigned int noio_flag; - struct dm_table *t; - int srcu_idx, ret; - - t = dm_get_live_table(md, &srcu_idx); - if (!t) - return -EIO; - - /* - * Ensure that all memory allocations in this context are done as if - * GFP_NOIO was specified. - */ - noio_flag = memalloc_noio_save(); - ret = dm_blk_do_report_zones(md, t, sector, 1, - dm_update_zone_wp_offset_cb, wp_ofst); - memalloc_noio_restore(noio_flag); - - dm_put_live_table(md, srcu_idx); - - if (ret != 1) - return -EIO; - - return 0; -} - -struct orig_bio_details { - enum req_op op; - unsigned int nr_sectors; -}; - -/* - * First phase of BIO mapping for targets with zone append emulation: - * check all BIO that change a zone writer pointer and change zone - * append operations into regular write operations. - */ -static bool dm_zone_map_bio_begin(struct mapped_device *md, - unsigned int zno, struct bio *clone) -{ - sector_t zsectors = bdev_zone_sectors(md->disk->part0); - unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); - - /* - * If the target zone is in an error state, recover by inspecting the - * zone to get its current write pointer position. Note that since the - * target zone is already locked, a BIO issuing context should never - * see the zone write in the DM_ZONE_UPDATING_WP_OFST state. - */ - if (zwp_offset == DM_ZONE_INVALID_WP_OFST) { - if (dm_update_zone_wp_offset(md, zno, &zwp_offset)) - return false; - WRITE_ONCE(md->zwp_offset[zno], zwp_offset); + md->zone_revalidate_map = t; + ret = dm_blk_report_zones(disk, 0, UINT_MAX, + dm_check_zoned_cb, &nr_conv_zones); + md->zone_revalidate_map = NULL; + if (ret < 0) { + DMERR("Check zoned failed %d", ret); + return ret; } - switch (bio_op(clone)) { - case REQ_OP_ZONE_RESET: - case REQ_OP_ZONE_FINISH: - return true; - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE: - /* Writes must be aligned to the zone write pointer */ - if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset) - return false; - break; - case REQ_OP_ZONE_APPEND: - /* - * Change zone append operations into a non-mergeable regular - * writes directed at the current write pointer position of the - * target zone. - */ - clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE | - (clone->bi_opf & (~REQ_OP_MASK)); - clone->bi_iter.bi_sector += zwp_offset; - break; - default: - DMWARN_LIMIT("Invalid BIO operation"); - return false; - } - - /* Cannot write to a full zone */ - if (zwp_offset >= zsectors) - return false; - - return true; -} - -/* - * Second phase of BIO mapping for targets with zone append emulation: - * update the zone write pointer offset array to account for the additional - * data written to a zone. Note that at this point, the remapped clone BIO - * may already have completed, so we do not touch it. - */ -static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno, - struct orig_bio_details *orig_bio_details, - unsigned int nr_sectors) -{ - unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); - - /* The clone BIO may already have been completed and failed */ - if (zwp_offset == DM_ZONE_INVALID_WP_OFST) - return BLK_STS_IOERR; - - /* Update the zone wp offset */ - switch (orig_bio_details->op) { - case REQ_OP_ZONE_RESET: - WRITE_ONCE(md->zwp_offset[zno], 0); - return BLK_STS_OK; - case REQ_OP_ZONE_FINISH: - WRITE_ONCE(md->zwp_offset[zno], - bdev_zone_sectors(md->disk->part0)); - return BLK_STS_OK; - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE: - WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors); - return BLK_STS_OK; - case REQ_OP_ZONE_APPEND: - /* - * Check that the target did not truncate the write operation - * emulating a zone append. - */ - if (nr_sectors != orig_bio_details->nr_sectors) { - DMWARN_LIMIT("Truncated write for zone append"); - return BLK_STS_IOERR; - } - WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors); - return BLK_STS_OK; - default: - DMWARN_LIMIT("Invalid BIO operation"); - return BLK_STS_IOERR; - } -} - -static inline void dm_zone_lock(struct gendisk *disk, unsigned int zno, - struct bio *clone) -{ - if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))) - return; - - wait_on_bit_lock_io(disk->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE); - bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED); -} - -static inline void dm_zone_unlock(struct gendisk *disk, unsigned int zno, - struct bio *clone) -{ - if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)) - return; - - WARN_ON_ONCE(!test_bit(zno, disk->seq_zones_wlock)); - clear_bit_unlock(zno, disk->seq_zones_wlock); - smp_mb__after_atomic(); - wake_up_bit(disk->seq_zones_wlock, zno); - - bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED); -} - -static bool dm_need_zone_wp_tracking(struct bio *bio) -{ - /* - * Special processing is not needed for operations that do not need the - * zone write lock, that is, all operations that target conventional - * zones and all operations that do not modify directly a sequential - * zone write pointer. - */ - if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) - return false; - switch (bio_op(bio)) { - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE: - case REQ_OP_ZONE_RESET: - case REQ_OP_ZONE_FINISH: - case REQ_OP_ZONE_APPEND: - return bio_zone_is_seq(bio); - default: - return false; - } -} - -/* - * Special IO mapping for targets needing zone append emulation. - */ -int dm_zone_map_bio(struct dm_target_io *tio) -{ - struct dm_io *io = tio->io; - struct dm_target *ti = tio->ti; - struct mapped_device *md = io->md; - struct bio *clone = &tio->clone; - struct orig_bio_details orig_bio_details; - unsigned int zno; - blk_status_t sts; - int r; - /* - * IOs that do not change a zone write pointer do not need - * any additional special processing. + * If we only have conventional zones, expose the mapped device as + * a regular device. */ - if (!dm_need_zone_wp_tracking(clone)) - return ti->type->map(ti, clone); - - /* Lock the target zone */ - zno = bio_zone_no(clone); - dm_zone_lock(md->disk, zno, clone); - - orig_bio_details.nr_sectors = bio_sectors(clone); - orig_bio_details.op = bio_op(clone); - - /* - * Check that the bio and the target zone write pointer offset are - * both valid, and if the bio is a zone append, remap it to a write. - */ - if (!dm_zone_map_bio_begin(md, zno, clone)) { - dm_zone_unlock(md->disk, zno, clone); - return DM_MAPIO_KILL; - } - - /* Let the target do its work */ - r = ti->type->map(ti, clone); - switch (r) { - case DM_MAPIO_SUBMITTED: - /* - * The target submitted the clone BIO. The target zone will - * be unlocked on completion of the clone. - */ - sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, - *tio->len_ptr); - break; - case DM_MAPIO_REMAPPED: - /* - * The target only remapped the clone BIO. In case of error, - * unlock the target zone here as the clone will not be - * submitted. - */ - sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, - *tio->len_ptr); - if (sts != BLK_STS_OK) - dm_zone_unlock(md->disk, zno, clone); - break; - case DM_MAPIO_REQUEUE: - case DM_MAPIO_KILL: - default: - dm_zone_unlock(md->disk, zno, clone); - sts = BLK_STS_IOERR; - break; + if (nr_conv_zones >= ret) { + lim->max_open_zones = 0; + lim->max_active_zones = 0; + lim->zoned = false; + clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + disk->nr_zones = 0; + return 0; } - if (sts != BLK_STS_OK) - return DM_MAPIO_KILL; - - return r; + if (!static_key_enabled(&zoned_enabled.key)) + static_branch_enable(&zoned_enabled); + return 0; } /* @@ -587,61 +287,17 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone) struct mapped_device *md = io->md; struct gendisk *disk = md->disk; struct bio *orig_bio = io->orig_bio; - unsigned int zwp_offset; - unsigned int zno; /* - * For targets that do not emulate zone append, we only need to - * handle native zone-append bios. + * Get the offset within the zone of the written sector + * and add that to the original bio sector position. */ - if (!dm_emulate_zone_append(md)) { - /* - * Get the offset within the zone of the written sector - * and add that to the original bio sector position. - */ - if (clone->bi_status == BLK_STS_OK && - bio_op(clone) == REQ_OP_ZONE_APPEND) { - sector_t mask = - (sector_t)bdev_zone_sectors(disk->part0) - 1; - - orig_bio->bi_iter.bi_sector += - clone->bi_iter.bi_sector & mask; - } - - return; - } + if (clone->bi_status == BLK_STS_OK && + bio_op(clone) == REQ_OP_ZONE_APPEND) { + sector_t mask = bdev_zone_sectors(disk->part0) - 1; - /* - * For targets that do emulate zone append, if the clone BIO does not - * own the target zone write lock, we have nothing to do. - */ - if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)) - return; - - zno = bio_zone_no(orig_bio); - - if (clone->bi_status != BLK_STS_OK) { - /* - * BIOs that modify a zone write pointer may leave the zone - * in an unknown state in case of failure (e.g. the write - * pointer was only partially advanced). In this case, set - * the target zone write pointer as invalid unless it is - * already being updated. - */ - WRITE_ONCE(md->zwp_offset[zno], DM_ZONE_INVALID_WP_OFST); - } else if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { - /* - * Get the written sector for zone append operation that were - * emulated using regular write operations. - */ - zwp_offset = READ_ONCE(md->zwp_offset[zno]); - if (WARN_ON_ONCE(zwp_offset < bio_sectors(orig_bio))) - WRITE_ONCE(md->zwp_offset[zno], - DM_ZONE_INVALID_WP_OFST); - else - orig_bio->bi_iter.bi_sector += - zwp_offset - bio_sectors(orig_bio); + orig_bio->bi_iter.bi_sector += clone->bi_iter.bi_sector & mask; } - dm_zone_unlock(disk, zno, clone); + return; } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 621794a9ed..12236e6f46 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1001,7 +1001,6 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->discard_alignment = 0; limits->discard_granularity = DMZ_BLOCK_SIZE; - limits->max_discard_sectors = chunk_sectors; limits->max_hw_discard_sectors = chunk_sectors; limits->max_write_zeroes_sectors = chunk_sectors; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7d0746b37c..13037d6a6f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1086,7 +1086,7 @@ void disable_discard(struct mapped_device *md) struct queue_limits *limits = dm_get_queue_limits(md); /* device doesn't really support DISCARD, disable it */ - limits->max_discard_sectors = 0; + limits->max_hw_discard_sectors = 0; } void disable_write_zeroes(struct mapped_device *md) @@ -1428,25 +1428,12 @@ static void __map_bio(struct bio *clone) down(&md->swap_bios_semaphore); } - if (static_branch_unlikely(&zoned_enabled)) { - /* - * Check if the IO needs a special mapping due to zone append - * emulation on zoned target. In this case, dm_zone_map_bio() - * calls the target map operation. - */ - if (unlikely(dm_emulate_zone_append(md))) - r = dm_zone_map_bio(tio); - else - goto do_map; - } else { -do_map: - if (likely(ti->type->map == linear_map)) - r = linear_map(ti, clone); - else if (ti->type->map == stripe_map) - r = stripe_map(ti, clone); - else - r = ti->type->map(ti, clone); - } + if (likely(ti->type->map == linear_map)) + r = linear_map(ti, clone); + else if (ti->type->map == stripe_map) + r = stripe_map(ti, clone); + else + r = ti->type->map(ti, clone); switch (r) { case DM_MAPIO_SUBMITTED: @@ -1774,6 +1761,33 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io, ci->sector_count = 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static inline bool dm_zone_bio_needs_split(struct mapped_device *md, + struct bio *bio) +{ + /* + * For mapped device that need zone append emulation, we must + * split any large BIO that straddles zone boundaries. + */ + return dm_emulate_zone_append(md) && bio_straddles_zones(bio) && + !bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); +} +static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio) +{ + return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0); +} +#else +static inline bool dm_zone_bio_needs_split(struct mapped_device *md, + struct bio *bio) +{ + return false; +} +static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio) +{ + return false; +} +#endif + /* * Entry point to split a bio into clones and submit them to the targets. */ @@ -1783,19 +1797,32 @@ static void dm_split_and_process_bio(struct mapped_device *md, struct clone_info ci; struct dm_io *io; blk_status_t error = BLK_STS_OK; - bool is_abnormal; + bool is_abnormal, need_split; + + need_split = is_abnormal = is_abnormal_io(bio); + if (static_branch_unlikely(&zoned_enabled)) + need_split = is_abnormal || dm_zone_bio_needs_split(md, bio); - is_abnormal = is_abnormal_io(bio); - if (unlikely(is_abnormal)) { + if (unlikely(need_split)) { /* * Use bio_split_to_limits() for abnormal IO (e.g. discard, etc) * otherwise associated queue_limits won't be imposed. + * Also split the BIO for mapped devices needing zone append + * emulation to ensure that the BIO does not cross zone + * boundaries. */ bio = bio_split_to_limits(bio); if (!bio) return; } + /* + * Use the block layer zone write plugging for mapped devices that + * need zone append emulation (e.g. dm-crypt). + */ + if (static_branch_unlikely(&zoned_enabled) && dm_zone_plug_bio(md, bio)) + return; + /* Only support nowait for normal IO */ if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) { io = alloc_io(md, bio, GFP_NOWAIT); @@ -2016,7 +2043,6 @@ static void cleanup_mapped_device(struct mapped_device *md) md->dax_dev = NULL; } - dm_cleanup_zoned_dev(md); if (md->disk) { spin_lock(&_minor_lock); md->disk->private_data = NULL; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 7f1acbf6bd..c984ecb64b 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -101,16 +101,16 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t); /* * Zoned targets related functions. */ -int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q); +int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *lim); +int dm_revalidate_zones(struct dm_table *t, struct request_queue *q); void dm_zone_endio(struct dm_io *io, struct bio *clone); #ifdef CONFIG_BLK_DEV_ZONED -void dm_cleanup_zoned_dev(struct mapped_device *md); int dm_blk_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); int dm_zone_map_bio(struct dm_target_io *io); #else -static inline void dm_cleanup_zoned_dev(struct mapped_device *md) {} #define dm_blk_report_zones NULL static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) { diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 0a2d37eb38..08232d8dc8 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; + unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) << + PAGE_SHIFT; loff_t sboff, offset = mddev->bitmap_info.offset; sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE; unsigned int size = PAGE_SIZE; @@ -269,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, if (size == 0) /* bitmap runs in to data */ return -EINVAL; - } else { - /* DATA METADATA BITMAP - no problems */ } - md_super_write(mddev, rdev, sboff + ps, (int) size, page); + md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page); return 0; } diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 8e36a0feec..b5a802ae17 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -15,6 +15,7 @@ #define LVB_SIZE 64 #define NEW_DEV_TIMEOUT 5000 +#define WAIT_DLM_LOCK_TIMEOUT (30 * HZ) struct dlm_lock_resource { dlm_lockspace_t *ls; @@ -130,8 +131,13 @@ static int dlm_lock_sync(struct dlm_lock_resource *res, int mode) 0, sync_ast, res, res->bast); if (ret) return ret; - wait_event(res->sync_locking, res->sync_locking_done); + ret = wait_event_timeout(res->sync_locking, res->sync_locking_done, + WAIT_DLM_LOCK_TIMEOUT); res->sync_locking_done = false; + if (!ret) { + pr_err("locking DLM '%s' timeout!\n", res->name); + return -EBUSY; + } if (res->lksb.sb_status == 0) res->mode = mode; return res->lksb.sb_status; @@ -743,7 +749,7 @@ static void unlock_comm(struct md_cluster_info *cinfo) */ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) { - int error; + int error, unlock_error; int slot = cinfo->slot_number - 1; cmsg->slot = cpu_to_le32(slot); @@ -751,7 +757,7 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX); if (error) { pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error); - goto failed_message; + return error; } memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg, @@ -781,14 +787,10 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) } failed_ack: - error = dlm_unlock_sync(cinfo->message_lockres); - if (unlikely(error != 0)) { + while ((unlock_error = dlm_unlock_sync(cinfo->message_lockres))) pr_err("md-cluster: failed convert to NL on MESSAGE(%d)\n", - error); - /* in case the message can't be released due to some reason */ - goto failed_ack; - } -failed_message: + unlock_error); + return error; } diff --git a/drivers/md/md.c b/drivers/md/md.c index e575e74aab..9c5be016e5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,13 +550,9 @@ static void md_end_flush(struct bio *bio) rdev_dec_pending(rdev, mddev); - if (atomic_dec_and_test(&mddev->flush_pending)) { - /* The pair is percpu_ref_get() from md_flush_request() */ - percpu_ref_put(&mddev->active_io); - + if (atomic_dec_and_test(&mddev->flush_pending)) /* The pre-request flush has finished */ queue_work(md_wq, &mddev->flush_work); - } } static void md_submit_flush_data(struct work_struct *ws); @@ -587,12 +583,8 @@ static void submit_flushes(struct work_struct *ws) rcu_read_lock(); } rcu_read_unlock(); - if (atomic_dec_and_test(&mddev->flush_pending)) { - /* The pair is percpu_ref_get() from md_flush_request() */ - percpu_ref_put(&mddev->active_io); - + if (atomic_dec_and_test(&mddev->flush_pending)) queue_work(md_wq, &mddev->flush_work); - } } static void md_submit_flush_data(struct work_struct *ws) @@ -617,8 +609,20 @@ static void md_submit_flush_data(struct work_struct *ws) bio_endio(bio); } else { bio->bi_opf &= ~REQ_PREFLUSH; - md_handle_request(mddev, bio); + + /* + * make_requst() will never return error here, it only + * returns error in raid5_make_request() by dm-raid. + * Since dm always splits data and flush operation into + * two separate io, io size of flush submitted by dm + * always is 0, make_request() will not be called here. + */ + if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio))) + bio_io_error(bio);; } + + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); } /* @@ -7742,12 +7746,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, return get_bitmap_file(mddev, argp); } - if (cmd == HOT_REMOVE_DISK) - /* need to ensure recovery thread has run */ - wait_event_interruptible_timeout(mddev->sb_wait, - !test_bit(MD_RECOVERY_NEEDED, - &mddev->recovery), - msecs_to_jiffies(5000)); if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) { /* Need to flush page cache, and ensure no-one else opens * and writes @@ -8087,7 +8085,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread) if (t) { pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); set_bit(THREAD_WAKEUP, &t->flags); - wake_up(&t->wqueue); + if (wq_has_sleeper(&t->wqueue)) + wake_up(&t->wqueue); } rcu_read_unlock(); } @@ -8582,6 +8581,10 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; + + if (!init && !blk_queue_io_stat(disk->queue)) + continue; + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats diff --git a/drivers/md/md.h b/drivers/md/md.h index 097d9dbd69..ca085ecad5 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -621,7 +621,8 @@ extern void mddev_unlock(struct mddev *mddev); static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) { - atomic_add(nr_sectors, &bdev->bd_disk->sync_io); + if (blk_queue_io_stat(bdev->bd_disk->queue)) + atomic_add(nr_sectors, &bdev->bd_disk->sync_io); } static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c5d4aeb684..81c01347cd 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -365,18 +365,13 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks return array_sectors; } -static void free_conf(struct mddev *mddev, struct r0conf *conf) -{ - kfree(conf->strip_zone); - kfree(conf->devlist); - kfree(conf); -} - static void raid0_free(struct mddev *mddev, void *priv) { struct r0conf *conf = priv; - free_conf(mddev, conf); + kfree(conf->strip_zone); + kfree(conf->devlist); + kfree(conf); } static int raid0_set_limits(struct mddev *mddev) @@ -415,7 +410,7 @@ static int raid0_run(struct mddev *mddev) if (!mddev_is_dm(mddev)) { ret = raid0_set_limits(mddev); if (ret) - goto out_free_conf; + return ret; } /* calculate array device size */ @@ -427,13 +422,7 @@ static int raid0_run(struct mddev *mddev) dump_zones(mddev); - ret = md_integrity_register(mddev); - if (ret) - goto out_free_conf; - return 0; -out_free_conf: - free_conf(mddev, conf); - return ret; + return md_integrity_register(mddev); } /* diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7b8a71ca66..22bbd06ba6 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -680,6 +680,7 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, len = r1_bio->sectors; read_len = raid1_check_read_range(rdev, this_sector, &len); if (read_len == r1_bio->sectors) { + *max_sectors = read_len; update_read_sectors(conf, disk, this_sector, read_len); return disk; } @@ -3204,7 +3205,6 @@ static int raid1_set_limits(struct mddev *mddev) return queue_limits_set(mddev->gendisk->queue, &lim); } -static void raid1_free(struct mddev *mddev, void *priv); static int raid1_run(struct mddev *mddev) { struct r1conf *conf; @@ -3238,7 +3238,7 @@ static int raid1_run(struct mddev *mddev) if (!mddev_is_dm(mddev)) { ret = raid1_set_limits(mddev); if (ret) - goto abort; + return ret; } mddev->degraded = 0; @@ -3252,8 +3252,7 @@ static int raid1_run(struct mddev *mddev) */ if (conf->raid_disks - mddev->degraded < 1) { md_unregister_thread(mddev, &conf->thread); - ret = -EINVAL; - goto abort; + return -EINVAL; } if (conf->raid_disks - mddev->degraded == 1) @@ -3277,14 +3276,8 @@ static int raid1_run(struct mddev *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); ret = md_integrity_register(mddev); - if (ret) { + if (ret) md_unregister_thread(mddev, &mddev->thread); - goto abort; - } - return 0; - -abort: - raid1_free(mddev, conf); return ret; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2bd1ce9b39..1c6b58adec 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -155,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh, return slot; } -static void print_raid5_conf (struct r5conf *conf); +static void print_raid5_conf(struct r5conf *conf); static int stripe_operations_active(struct stripe_head *sh) { @@ -5899,6 +5899,39 @@ out: return ret; } +enum reshape_loc { + LOC_NO_RESHAPE, + LOC_AHEAD_OF_RESHAPE, + LOC_INSIDE_RESHAPE, + LOC_BEHIND_RESHAPE, +}; + +static enum reshape_loc get_reshape_loc(struct mddev *mddev, + struct r5conf *conf, sector_t logical_sector) +{ + sector_t reshape_progress, reshape_safe; + /* + * Spinlock is needed as reshape_progress may be + * 64bit on a 32bit platform, and so it might be + * possible to see a half-updated value + * Of course reshape_progress could change after + * the lock is dropped, so once we get a reference + * to the stripe that we think it is, we will have + * to check again. + */ + spin_lock_irq(&conf->device_lock); + reshape_progress = conf->reshape_progress; + reshape_safe = conf->reshape_safe; + spin_unlock_irq(&conf->device_lock); + if (reshape_progress == MaxSector) + return LOC_NO_RESHAPE; + if (ahead_of_reshape(mddev, logical_sector, reshape_progress)) + return LOC_AHEAD_OF_RESHAPE; + if (ahead_of_reshape(mddev, logical_sector, reshape_safe)) + return LOC_INSIDE_RESHAPE; + return LOC_BEHIND_RESHAPE; +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -5913,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, seq = read_seqcount_begin(&conf->gen_lock); if (unlikely(conf->reshape_progress != MaxSector)) { - /* - * Spinlock is needed as reshape_progress may be - * 64bit on a 32bit platform, and so it might be - * possible to see a half-updated value - * Of course reshape_progress could change after - * the lock is dropped, so once we get a reference - * to the stripe that we think it is, we will have - * to check again. - */ - spin_lock_irq(&conf->device_lock); - if (ahead_of_reshape(mddev, logical_sector, - conf->reshape_progress)) { - previous = 1; - } else { - if (ahead_of_reshape(mddev, logical_sector, - conf->reshape_safe)) { - spin_unlock_irq(&conf->device_lock); - ret = STRIPE_SCHEDULE_AND_RETRY; - goto out; - } + enum reshape_loc loc = get_reshape_loc(mddev, conf, + logical_sector); + if (loc == LOC_INSIDE_RESHAPE) { + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } - spin_unlock_irq(&conf->device_lock); + if (loc == LOC_AHEAD_OF_RESHAPE) + previous = 1; } new_sector = raid5_compute_sector(conf, logical_sector, previous, @@ -6113,8 +6132,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) /* Bail out if conflicts with reshape and REQ_NOWAIT is set */ if ((bi->bi_opf & REQ_NOWAIT) && (conf->reshape_progress != MaxSector) && - !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) && - ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { + get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) { bio_wouldblock_error(bi); if (rw == WRITE) md_write_end(mddev); @@ -7562,11 +7580,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (test_bit(Replacement, &rdev->flags)) { if (disk->replacement) goto abort; - RCU_INIT_POINTER(disk->replacement, rdev); + disk->replacement = rdev; } else { if (disk->rdev) goto abort; - RCU_INIT_POINTER(disk->rdev, rdev); + disk->rdev = rdev; } if (test_bit(In_sync, &rdev->flags)) { @@ -8048,7 +8066,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev) seq_printf (seq, "]"); } -static void print_raid5_conf (struct r5conf *conf) +static void print_raid5_conf(struct r5conf *conf) { struct md_rdev *rdev; int i; @@ -8062,15 +8080,13 @@ static void print_raid5_conf (struct r5conf *conf) conf->raid_disks, conf->raid_disks - conf->mddev->degraded); - rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - rdev = rcu_dereference(conf->disks[i].rdev); + rdev = conf->disks[i].rdev; if (rdev) pr_debug(" disk %d, o:%d, dev:%pg\n", i, !test_bit(Faulty, &rdev->flags), rdev->bdev); } - rcu_read_unlock(); } static int raid5_spare_active(struct mddev *mddev) |