diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/bcache.h | 1 | ||||
-rw-r--r-- | drivers/md/bcache/bset.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/btree.c | 22 | ||||
-rw-r--r-- | drivers/md/bcache/journal.c | 4 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 12 | ||||
-rw-r--r-- | drivers/md/dm-cache-metadata.c | 8 | ||||
-rw-r--r-- | drivers/md/dm-cache-target.c | 166 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-rq.c | 3 | ||||
-rw-r--r-- | drivers/md/dm-table.c | 10 | ||||
-rw-r--r-- | drivers/md/dm-thin-metadata.c | 8 | ||||
-rw-r--r-- | drivers/md/dm-zoned-metadata.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-zoned-reclaim.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-zoned-target.c | 2 | ||||
-rw-r--r-- | drivers/md/dm.c | 15 | ||||
-rw-r--r-- | drivers/md/md-cluster.c | 1 | ||||
-rw-r--r-- | drivers/md/md.c | 16 | ||||
-rw-r--r-- | drivers/md/raid0.c | 3 | ||||
-rw-r--r-- | drivers/md/raid5.c | 3 |
20 files changed, 139 insertions, 149 deletions
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index e4a3f692057b..a3763d664a67 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -548,6 +548,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock; /* * When we free a btree node, we increment the gen of the bucket the diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 1edf9515345e..03fb06c61e1c 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -319,7 +319,7 @@ int bch_btree_keys_alloc(struct btree_keys *b, unsigned page_order, gfp_t gfp) b->page_order = page_order; - t->data = (void *) __get_free_pages(gfp, b->page_order); + t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order); if (!t->data) goto err; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 96a6583e7b52..fba0fff8040d 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -794,7 +794,7 @@ int bch_btree_cache_alloc(struct cache_set *c) mutex_init(&c->verify_lock); c->verify_ondisk = (void *) - __get_free_pages(GFP_KERNEL, ilog2(bucket_pages(c))); + __get_free_pages(GFP_KERNEL|__GFP_COMP, ilog2(bucket_pages(c))); c->verify_data = mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL); @@ -840,15 +840,17 @@ out: static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock); return 0; } @@ -883,10 +885,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, @@ -1374,7 +1378,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, if (__set_blocks(n1, n1->keys + n2->keys, block_bytes(b->c)) > btree_blocks(new_nodes[i])) - goto out_nocoalesce; + goto out_unlock_nocoalesce; keys = n2->keys; /* Take the key of the node we're getting rid of */ @@ -1403,7 +1407,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, if (__bch_keylist_realloc(&keylist, bkey_u64s(&new_nodes[i]->key))) - goto out_nocoalesce; + goto out_unlock_nocoalesce; bch_btree_node_write(new_nodes[i], &cl); bch_keylist_add(&keylist, &new_nodes[i]->key); @@ -1449,6 +1453,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, /* Invalidated our iterator */ return -EINTR; +out_unlock_nocoalesce: + for (i = 0; i < nodes; i++) + mutex_unlock(&new_nodes[i]->write_lock); + out_nocoalesce: closure_sync(&cl); bch_keylist_free(&keylist); diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 6394be5ee9a8..6aafda26903c 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -838,8 +838,8 @@ int bch_journal_alloc(struct cache_set *c) j->w[1].c = c; if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) || - !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) || - !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS))) + !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) || + !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS))) return -ENOMEM; return 0; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 690aeb09bbf5..6bf1559a1f0d 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1468,7 +1468,7 @@ void bch_cache_set_unregister(struct cache_set *c) } #define alloc_bucket_pages(gfp, c) \ - ((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c)))) + ((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c)))) struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) { @@ -1510,6 +1510,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); @@ -1780,7 +1781,14 @@ found: sysfs_create_link(&c->kobj, &ca->kobj, buf)) goto err; - if (ca->sb.seq > c->sb.seq) { + /* + * A special case is both ca->sb.seq and c->sb.seq are 0, + * such condition happens on a new created cache device whose + * super block is never flushed yet. In this case c->sb.version + * and other members should be updated too, otherwise we will + * have a mistaken super block version in cache set. + */ + if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) { c->sb.version = ca->sb.version; memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16); c->sb.flags = ca->sb.flags; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 394e53afc259..0acd10d3b7bf 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -536,12 +536,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, CACHE_MAX_CONCURRENT_LOCKS); if (IS_ERR(cmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(cmd->bm); + r = PTR_ERR(cmd->bm); + cmd->bm = NULL; + return r; } r = __open_or_format_metadata(cmd, may_format_device); - if (r) + if (r) { dm_block_manager_destroy(cmd->bm); + cmd->bm = NULL; + } return r; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 69cdb29ef6be..280873b13e74 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -410,7 +410,6 @@ struct cache { spinlock_t lock; struct list_head deferred_cells; struct bio_list deferred_bios; - struct bio_list deferred_writethrough_bios; sector_t migration_threshold; wait_queue_head_t migration_wait; atomic_t nr_allocated_migrations; @@ -446,10 +445,10 @@ struct cache { struct dm_kcopyd_client *copier; struct workqueue_struct *wq; struct work_struct deferred_bio_worker; - struct work_struct deferred_writethrough_worker; struct work_struct migration_worker; struct delayed_work waker; struct dm_bio_prison_v2 *prison; + struct bio_set *bs; mempool_t *migration_pool; @@ -490,15 +489,6 @@ struct per_bio_data { struct dm_bio_prison_cell_v2 *cell; struct dm_hook_info hook_info; sector_t len; - - /* - * writethrough fields. These MUST remain at the end of this - * structure and the 'cache' member must be the first as it - * is used to determine the offset of the writethrough fields. - */ - struct cache *cache; - dm_cblock_t cblock; - struct dm_bio_details bio_details; }; struct dm_cache_migration { @@ -515,19 +505,19 @@ struct dm_cache_migration { /*----------------------------------------------------------------*/ -static bool writethrough_mode(struct cache_features *f) +static bool writethrough_mode(struct cache *cache) { - return f->io_mode == CM_IO_WRITETHROUGH; + return cache->features.io_mode == CM_IO_WRITETHROUGH; } -static bool writeback_mode(struct cache_features *f) +static bool writeback_mode(struct cache *cache) { - return f->io_mode == CM_IO_WRITEBACK; + return cache->features.io_mode == CM_IO_WRITEBACK; } -static inline bool passthrough_mode(struct cache_features *f) +static inline bool passthrough_mode(struct cache *cache) { - return unlikely(f->io_mode == CM_IO_PASSTHROUGH); + return unlikely(cache->features.io_mode == CM_IO_PASSTHROUGH); } /*----------------------------------------------------------------*/ @@ -537,14 +527,9 @@ static void wake_deferred_bio_worker(struct cache *cache) queue_work(cache->wq, &cache->deferred_bio_worker); } -static void wake_deferred_writethrough_worker(struct cache *cache) -{ - queue_work(cache->wq, &cache->deferred_writethrough_worker); -} - static void wake_migration_worker(struct cache *cache) { - if (passthrough_mode(&cache->features)) + if (passthrough_mode(cache)) return; queue_work(cache->wq, &cache->migration_worker); @@ -618,15 +603,9 @@ static unsigned lock_level(struct bio *bio) * Per bio data *--------------------------------------------------------------*/ -/* - * If using writeback, leave out struct per_bio_data's writethrough fields. - */ -#define PB_DATA_SIZE_WB (offsetof(struct per_bio_data, cache)) -#define PB_DATA_SIZE_WT (sizeof(struct per_bio_data)) - static size_t get_per_bio_data_size(struct cache *cache) { - return writethrough_mode(&cache->features) ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB; + return sizeof(struct per_bio_data); } static struct per_bio_data *get_per_bio_data(struct bio *bio, size_t data_size) @@ -868,16 +847,23 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) spin_unlock_irqrestore(&cache->lock, flags); } -static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, - dm_oblock_t oblock) +static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, + dm_oblock_t oblock, bool bio_has_pbd) { - // FIXME: this is called way too much. - check_if_tick_bio_needed(cache, bio); + if (bio_has_pbd) + check_if_tick_bio_needed(cache, bio); remap_to_origin(cache, bio); if (bio_data_dir(bio) == WRITE) clear_discard(cache, oblock_to_dblock(cache, oblock)); } +static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, + dm_oblock_t oblock) +{ + // FIXME: check_if_tick_bio_needed() is called way too much through this interface + __remap_to_origin_clear_discard(cache, bio, oblock, true); +} + static void remap_to_cache_dirty(struct cache *cache, struct bio *bio, dm_oblock_t oblock, dm_cblock_t cblock) { @@ -937,57 +923,26 @@ static void issue_op(struct bio *bio, void *context) accounted_request(cache, bio); } -static void defer_writethrough_bio(struct cache *cache, struct bio *bio) -{ - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); - bio_list_add(&cache->deferred_writethrough_bios, bio); - spin_unlock_irqrestore(&cache->lock, flags); - - wake_deferred_writethrough_worker(cache); -} - -static void writethrough_endio(struct bio *bio) -{ - struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); - - dm_unhook_bio(&pb->hook_info, bio); - - if (bio->bi_status) { - bio_endio(bio); - return; - } - - dm_bio_restore(&pb->bio_details, bio); - remap_to_cache(pb->cache, bio, pb->cblock); - - /* - * We can't issue this bio directly, since we're in interrupt - * context. So it gets put on a bio list for processing by the - * worker thread. - */ - defer_writethrough_bio(pb->cache, bio); -} - /* - * FIXME: send in parallel, huge latency as is. * When running in writethrough mode we need to send writes to clean blocks - * to both the cache and origin devices. In future we'd like to clone the - * bio and send them in parallel, but for now we're doing them in - * series as this is easier. + * to both the cache and origin devices. Clone the bio and send them in parallel. */ -static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, - dm_oblock_t oblock, dm_cblock_t cblock) +static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio, + dm_oblock_t oblock, dm_cblock_t cblock) { - struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); + struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs); - pb->cache = cache; - pb->cblock = cblock; - dm_hook_bio(&pb->hook_info, bio, writethrough_endio, NULL); - dm_bio_record(&pb->bio_details, bio); + BUG_ON(!origin_bio); - remap_to_origin_clear_discard(pb->cache, bio, oblock); + bio_chain(origin_bio, bio); + /* + * Passing false to __remap_to_origin_clear_discard() skips + * all code that might use per_bio_data (since clone doesn't have it) + */ + __remap_to_origin_clear_discard(cache, origin_bio, oblock, false); + submit_bio(origin_bio); + + remap_to_cache(cache, bio, cblock); } /*---------------------------------------------------------------- @@ -1209,7 +1164,7 @@ static bool bio_writes_complete_block(struct cache *cache, struct bio *bio) static bool optimisable_bio(struct cache *cache, struct bio *bio, dm_oblock_t block) { - return writeback_mode(&cache->features) && + return writeback_mode(cache) && (is_discarded_oblock(cache, block) || bio_writes_complete_block(cache, bio)); } @@ -1862,7 +1817,7 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, * Passthrough always maps to the origin, invalidating any * cache blocks that are written to. */ - if (passthrough_mode(&cache->features)) { + if (passthrough_mode(cache)) { if (bio_data_dir(bio) == WRITE) { bio_drop_shared_lock(cache, bio); atomic_inc(&cache->stats.demotion); @@ -1871,9 +1826,9 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, remap_to_origin_clear_discard(cache, bio, block); } else { - if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) && + if (bio_data_dir(bio) == WRITE && writethrough_mode(cache) && !is_dirty(cache, cblock)) { - remap_to_origin_then_cache(cache, bio, block, cblock); + remap_to_origin_and_cache(cache, bio, block, cblock); accounted_begin(cache, bio); } else remap_to_cache_dirty(cache, bio, block, cblock); @@ -2003,28 +1958,6 @@ static void process_deferred_bios(struct work_struct *ws) schedule_commit(&cache->committer); } -static void process_deferred_writethrough_bios(struct work_struct *ws) -{ - struct cache *cache = container_of(ws, struct cache, deferred_writethrough_worker); - - unsigned long flags; - struct bio_list bios; - struct bio *bio; - - bio_list_init(&bios); - - spin_lock_irqsave(&cache->lock, flags); - bio_list_merge(&bios, &cache->deferred_writethrough_bios); - bio_list_init(&cache->deferred_writethrough_bios); - spin_unlock_irqrestore(&cache->lock, flags); - - /* - * These bios have already been through accounted_begin() - */ - while ((bio = bio_list_pop(&bios))) - generic_make_request(bio); -} - /*---------------------------------------------------------------- * Main worker loop *--------------------------------------------------------------*/ @@ -2132,6 +2065,9 @@ static void destroy(struct cache *cache) kfree(cache->ctr_args[i]); kfree(cache->ctr_args); + if (cache->bs) + bioset_free(cache->bs); + kfree(cache); } @@ -2589,6 +2525,13 @@ static int cache_create(struct cache_args *ca, struct cache **result) cache->features = ca->features; ti->per_io_data_size = get_per_bio_data_size(cache); + if (writethrough_mode(cache)) { + /* Create bioset for writethrough bios issued to origin */ + cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0); + if (!cache->bs) + goto bad; + } + cache->callbacks.congested_fn = cache_is_congested; dm_table_add_target_callbacks(ti->table, &cache->callbacks); @@ -2649,7 +2592,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - if (passthrough_mode(&cache->features)) { + if (passthrough_mode(cache)) { bool all_clean; r = dm_cache_metadata_all_clean(cache->cmd, &all_clean); @@ -2670,7 +2613,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) spin_lock_init(&cache->lock); INIT_LIST_HEAD(&cache->deferred_cells); bio_list_init(&cache->deferred_bios); - bio_list_init(&cache->deferred_writethrough_bios); atomic_set(&cache->nr_allocated_migrations, 0); atomic_set(&cache->nr_io_migrations, 0); init_waitqueue_head(&cache->migration_wait); @@ -2709,8 +2651,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } INIT_WORK(&cache->deferred_bio_worker, process_deferred_bios); - INIT_WORK(&cache->deferred_writethrough_worker, - process_deferred_writethrough_bios); INIT_WORK(&cache->migration_worker, check_migrations); INIT_DELAYED_WORK(&cache->waker, do_waker); @@ -3279,13 +3219,13 @@ static void cache_status(struct dm_target *ti, status_type_t type, else DMEMIT("1 "); - if (writethrough_mode(&cache->features)) + if (writethrough_mode(cache)) DMEMIT("writethrough "); - else if (passthrough_mode(&cache->features)) + else if (passthrough_mode(cache)) DMEMIT("passthrough "); - else if (writeback_mode(&cache->features)) + else if (writeback_mode(cache)) DMEMIT("writeback "); else { @@ -3451,7 +3391,7 @@ static int process_invalidate_cblocks_message(struct cache *cache, unsigned coun unsigned i; struct cblock_range range; - if (!passthrough_mode(&cache->features)) { + if (!passthrough_mode(cache)) { DMERR("%s: cache has to be in passthrough mode for invalidation", cache_device_name(cache)); return -EPERM; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index d9a67759fdb5..5e38ceb36000 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3088,7 +3088,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->max_segment_size = PAGE_SIZE; limits->logical_block_size = - max_t(unsigned short, limits->logical_block_size, cc->sector_size); + max_t(unsigned, limits->logical_block_size, cc->sector_size); limits->physical_block_size = max_t(unsigned, limits->physical_block_size, cc->sector_size); limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 8b7328666eaa..7c60aace8d25 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1815,7 +1815,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, int r; current_pgpath = READ_ONCE(m->current_pgpath); - if (!current_pgpath) + if (!current_pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) current_pgpath = choose_pgpath(m, 0); if (current_pgpath) { diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index eadfcfd106ff..cac8ec16e603 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -95,9 +95,6 @@ static void dm_old_stop_queue(struct request_queue *q) static void dm_mq_stop_queue(struct request_queue *q) { - if (blk_mq_queue_stopped(q)) - return; - blk_mq_quiesce_queue(q); } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 8f070debe498..777343cff5f1 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -547,14 +547,14 @@ static int adjoin(struct dm_table *table, struct dm_target *ti) * On the other hand, dm-switch needs to process bulk data using messages and * excessive use of GFP_NOIO could cause trouble. */ -static char **realloc_argv(unsigned *array_size, char **old_argv) +static char **realloc_argv(unsigned *size, char **old_argv) { char **argv; unsigned new_size; gfp_t gfp; - if (*array_size) { - new_size = *array_size * 2; + if (*size) { + new_size = *size * 2; gfp = GFP_KERNEL; } else { new_size = 8; @@ -562,8 +562,8 @@ static char **realloc_argv(unsigned *array_size, char **old_argv) } argv = kmalloc(new_size * sizeof(*argv), gfp); if (argv) { - memcpy(argv, old_argv, *array_size * sizeof(*argv)); - *array_size = new_size; + memcpy(argv, old_argv, *size * sizeof(*argv)); + *size = new_size; } kfree(old_argv); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index b85a66f42814..29f8a632b42b 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -698,12 +698,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f THIN_MAX_CONCURRENT_LOCKS); if (IS_ERR(pmd->bm)) { DMERR("could not create block manager"); - return PTR_ERR(pmd->bm); + r = PTR_ERR(pmd->bm); + pmd->bm = NULL; + return r; } r = __open_or_format_metadata(pmd, format_device); - if (r) + if (r) { dm_block_manager_destroy(pmd->bm); + pmd->bm = NULL; + } return r; } diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 4d658a0c6025..c6d3a4bc811c 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1580,7 +1580,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) return dzone; } - return ERR_PTR(-EBUSY); + return NULL; } /* @@ -1600,7 +1600,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) return zone; } - return ERR_PTR(-EBUSY); + return NULL; } /* diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 2fad512dce98..1015b200330b 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -350,8 +350,8 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) /* Get a data zone */ dzone = dmz_get_zone_for_reclaim(zmd); - if (IS_ERR(dzone)) - return PTR_ERR(dzone); + if (!dzone) + return -EBUSY; start = jiffies; diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 497a2bc5da51..9d8d453b2735 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -789,7 +789,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) } /* Set target (no write same support) */ - ti->max_io_len = dev->zone_nr_sectors << 9; + ti->max_io_len = dev->zone_nr_sectors; ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_write_zeroes_bios = 1; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 02ba6849f89d..6e741f19a732 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/blkpg.h> #include <linux/bio.h> @@ -2665,17 +2666,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast); int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie) { + int r; + unsigned noio_flag; char udev_cookie[DM_COOKIE_LENGTH]; char *envp[] = { udev_cookie, NULL }; + noio_flag = memalloc_noio_save(); + if (!cookie) - return kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action); else { snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", DM_COOKIE_ENV_VAR_NAME, cookie); - return kobject_uevent_env(&disk_to_dev(md->disk)->kobj, - action, envp); + r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj, + action, envp); } + + memalloc_noio_restore(noio_flag); + + return r; } uint32_t dm_next_uevent_seq(struct mapped_device *md) diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 10057ac85476..035d5ec8e677 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1423,6 +1423,7 @@ static void unlock_all_bitmaps(struct mddev *mddev) } } kfree(cinfo->other_bitmap_lockres); + cinfo->other_bitmap_lockres = NULL; } } diff --git a/drivers/md/md.c b/drivers/md/md.c index b942c74f1ce8..702a7d2c7e1e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1168,6 +1168,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; } + if (mddev->level == 0) + mddev->layout = -1; if (sb->state & (1<<MD_SB_CLEAN)) mddev->recovery_cp = MaxSector; @@ -1584,6 +1586,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset; } + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) && + sb->level != 0) + return -EINVAL; + if (!refdev) { ret = 1; } else { @@ -1694,6 +1700,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_chunk_sectors = mddev->chunk_sectors; } + if (mddev->level == 0 && + !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT)) + mddev->layout = -1; + if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) set_bit(MD_HAS_JOURNAL, &mddev->flags); @@ -6757,6 +6767,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->external = 0; mddev->layout = info->layout; + if (mddev->level == 0) + /* Cannot trust RAID0 layout info here */ + mddev->layout = -1; mddev->chunk_sectors = info->chunk_size >> 9; if (mddev->persistent) { @@ -7411,7 +7424,8 @@ static int md_open(struct block_device *bdev, fmode_t mode) */ mddev_put(mddev); /* Wait until bdev->bd_disk is definitely gone */ - flush_workqueue(md_misc_wq); + if (work_pending(&mddev->del_work)) + flush_workqueue(md_misc_wq); /* Then retry the open from the top */ return -ERESTARTSYS; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index cdafa5e0ea6d..e179c121c030 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -152,6 +152,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) if (conf->nr_strip_zones == 1) { conf->layout = RAID0_ORIG_LAYOUT; + } else if (mddev->layout == RAID0_ORIG_LAYOUT || + mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = mddev->layout; } else if (default_layout == RAID0_ORIG_LAYOUT || default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = default_layout; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d5c14d56a714..cd055664dce3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3593,6 +3593,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, * is missing/faulty, then we need to read everything we can. */ if (sh->raid_conf->level != 6 && + sh->raid_conf->rmw_level != PARITY_DISABLE_RMW && sh->sector < sh->raid_conf->mddev->recovery_cp) /* reconstruct-write isn't being forced */ return 0; @@ -4829,7 +4830,7 @@ static void handle_stripe(struct stripe_head *sh) * or to load a block that is being partially written. */ if (s.to_read || s.non_overwrite - || (conf->level == 6 && s.to_write && s.failed) + || (s.to_write && s.failed) || (s.syncing && (s.uptodate + s.compute < disks)) || s.replacing || s.expanding) |