diff options
Diffstat (limited to 'drivers/md')
43 files changed, 844 insertions, 309 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 8c13a9036d07..ada94a01e142 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -325,10 +325,11 @@ static int bch_allocator_thread(void *arg) * possibly issue discards to them, then we add the bucket to * the free list: */ - while (!fifo_empty(&ca->free_inc)) { + while (1) { long bucket; - fifo_pop(&ca->free_inc, bucket); + if (!fifo_pop(&ca->free_inc, bucket)) + break; if (ca->discard) { mutex_unlock(&ca->set->bucket_lock); diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index e56d3ecdbfcb..1edf9515345e 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -825,12 +825,22 @@ unsigned bch_btree_insert_key(struct btree_keys *b, struct bkey *k, struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; struct btree_iter iter; + struct bkey preceding_key_on_stack = ZERO_KEY; + struct bkey *preceding_key_p = &preceding_key_on_stack; BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); - m = bch_btree_iter_init(b, &iter, b->ops->is_extents - ? PRECEDING_KEY(&START_KEY(k)) - : PRECEDING_KEY(k)); + /* + * If k has preceding key, preceding_key_p will be set to address + * of k's preceding key; otherwise preceding_key_p will be set + * to NULL inside preceding_key(). + */ + if (b->ops->is_extents) + preceding_key(&START_KEY(k), &preceding_key_p); + else + preceding_key(k, &preceding_key_p); + + m = bch_btree_iter_init(b, &iter, preceding_key_p); if (b->ops->insert_fixup(b, k, &iter, replace_key)) return status; diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index fa506c1aa524..8d1964b472e7 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -418,20 +418,26 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k) return __bch_cut_back(where, k); } -#define PRECEDING_KEY(_k) \ -({ \ - struct bkey *_ret = NULL; \ - \ - if (KEY_INODE(_k) || KEY_OFFSET(_k)) { \ - _ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0); \ - \ - if (!_ret->low) \ - _ret->high--; \ - _ret->low--; \ - } \ - \ - _ret; \ -}) +/* + * Pointer '*preceding_key_p' points to a memory object to store preceding + * key of k. If the preceding key does not exist, set '*preceding_key_p' to + * NULL. So the caller of preceding_key() needs to take care of memory + * which '*preceding_key_p' pointed to before calling preceding_key(). + * Currently the only caller of preceding_key() is bch_btree_insert_key(), + * and it points to an on-stack variable, so the memory release is handled + * by stackframe itself. + */ +static inline void preceding_key(struct bkey *k, struct bkey **preceding_key_p) +{ + if (KEY_INODE(k) || KEY_OFFSET(k)) { + (**preceding_key_p) = KEY(KEY_INODE(k), KEY_OFFSET(k), 0); + if (!(*preceding_key_p)->low) + (*preceding_key_p)->high--; + (*preceding_key_p)->low--; + } else { + (*preceding_key_p) = NULL; + } +} static inline bool bch_ptr_invalid(struct btree_keys *b, const struct bkey *k) { diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 9406326216f1..96a6583e7b52 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -685,6 +685,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, * IO can always make forward progress: */ nr /= c->btree_pages; + if (nr == 0) + nr = 1; nr = min_t(unsigned long, nr, mca_can_free(c)); i = 0; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 03cc0722ae48..6394be5ee9a8 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -310,6 +310,18 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list) } } +bool is_discard_enabled(struct cache_set *s) +{ + struct cache *ca; + unsigned int i; + + for_each_cache(ca, s, i) + if (ca->discard) + return true; + + return false; +} + int bch_journal_replay(struct cache_set *s, struct list_head *list) { int ret = 0, keys = 0, entries = 0; @@ -323,9 +335,17 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) list_for_each_entry(i, list, list) { BUG_ON(i->pin && atomic_read(i->pin) != 1); - cache_set_err_on(n != i->j.seq, s, -"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", - n, i->j.seq - 1, start, end); + if (n != i->j.seq) { + if (n == start && is_discard_enabled(s)) + pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); + else { + pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); + ret = -EIO; + goto err; + } + } for (k = i->j.start; k < bset_bkey_last(&i->j); @@ -512,11 +532,11 @@ static void journal_reclaim(struct cache_set *c) ca->sb.nr_this_dev); } - bkey_init(k); - SET_KEY_PTRS(k, n); - - if (n) + if (n) { + bkey_init(k); + SET_KEY_PTRS(k, n); c->journal.blocks_free = c->sb.bucket_size >> c->block_bits; + } out: if (!journal_full(&c->journal)) __closure_wake_up(&c->journal.wait); @@ -641,6 +661,9 @@ static void journal_write_unlocked(struct closure *cl) ca->journal.seq[ca->journal.cur_idx] = w->data->seq; } + /* If KEY_PTRS(k) == 0, this jset gets lost in air */ + BUG_ON(i == 0); + atomic_dec_bug(&fifo_back(&c->journal.pin)); bch_journal_next(&c->journal); journal_reclaim(c); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index fe6e4c319b7c..690aeb09bbf5 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -905,6 +905,7 @@ static void cached_dev_detach_finish(struct work_struct *w) bch_write_bdev_super(dc, &cl); closure_sync(&cl); + calc_cached_dev_sectors(dc->disk.c); bcache_device_detach(&dc->disk); list_move(&dc->list, &uncached_devices); @@ -1045,12 +1046,13 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, } if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) { - bch_sectors_dirty_init(&dc->disk); atomic_set(&dc->has_dirty, 1); atomic_inc(&dc->count); bch_writeback_queue(dc); } + bch_sectors_dirty_init(&dc->disk); + bch_cached_dev_run(dc); bcache_device_link(&dc->disk, c, "bdev"); @@ -1356,6 +1358,7 @@ static void cache_set_free(struct closure *cl) bch_btree_cache_free(c); bch_journal_free(c); + mutex_lock(&bch_register_lock); for_each_cache(ca, c, i) if (ca) { ca->set = NULL; @@ -1378,7 +1381,6 @@ static void cache_set_free(struct closure *cl) mempool_destroy(c->search); kfree(c->devices); - mutex_lock(&bch_register_lock); list_del(&c->list); mutex_unlock(&bch_register_lock); @@ -1401,7 +1403,7 @@ static void cache_set_flush(struct closure *cl) kobject_put(&c->internal); kobject_del(&c->kobj); - if (c->gc_thread) + if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread); if (!IS_ERR_OR_NULL(c->root)) @@ -1559,7 +1561,7 @@ err: return NULL; } -static void run_cache_set(struct cache_set *c) +static int run_cache_set(struct cache_set *c) { const char *err = "cannot allocate memory"; struct cached_dev *dc, *t; @@ -1651,7 +1653,9 @@ static void run_cache_set(struct cache_set *c) if (j->version < BCACHE_JSET_VERSION_UUID) __uuid_write(c); - bch_journal_replay(c, &journal); + err = "bcache: replay journal failed"; + if (bch_journal_replay(c, &journal)) + goto err; } else { pr_notice("invalidating existing data"); @@ -1719,11 +1723,13 @@ static void run_cache_set(struct cache_set *c) flash_devs_run(c); set_bit(CACHE_SET_RUNNING, &c->flags); - return; + return 0; err: closure_sync(&cl); /* XXX: test this, it's broken */ bch_cache_set_error(c, "%s", err); + + return -EIO; } static bool can_attach_cache(struct cache *ca, struct cache_set *c) @@ -1787,8 +1793,11 @@ found: ca->set->cache[ca->sb.nr_this_dev] = ca; c->cache_by_alloc[c->caches_loaded++] = ca; - if (c->caches_loaded == c->sb.nr_in_set) - run_cache_set(c); + if (c->caches_loaded == c->sb.nr_in_set) { + err = "failed to run cache set"; + if (run_cache_set(c) < 0) + goto err; + } return NULL; err: diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 5d81cd06af00..def9c3478b89 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -217,7 +217,9 @@ STORE(__cached_dev) d_strtoul(writeback_rate_d_term); d_strtoul_nonzero(writeback_rate_p_term_inverse); - d_strtoi_h(sequential_cutoff); + sysfs_strtoul_clamp(sequential_cutoff, + dc->sequential_cutoff, + 0, UINT_MAX); d_strtoi_h(readahead); if (attr == &sysfs_clear_stats) @@ -660,8 +662,17 @@ STORE(__bch_cache_set) c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT; /* See count_io_errors() for why 88 */ - if (attr == &sysfs_io_error_halflife) - c->error_decay = strtoul_or_return(buf) / 88; + if (attr == &sysfs_io_error_halflife) { + unsigned long v = 0; + ssize_t ret; + + ret = strtoul_safe_clamp(buf, v, 0, UINT_MAX); + if (!ret) { + c->error_decay = v / 88; + return size; + } + return ret; + } sysfs_strtoul(journal_delay_ms, c->journal_delay_ms); sysfs_strtoul(verify, c->verify); diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index b54fe9602529..e6e258f897ca 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -81,9 +81,16 @@ do { \ #define sysfs_strtoul_clamp(file, var, min, max) \ do { \ - if (attr == &sysfs_ ## file) \ - return strtoul_safe_clamp(buf, var, min, max) \ - ?: (ssize_t) size; \ + if (attr == &sysfs_ ## file) { \ + unsigned long v = 0; \ + ssize_t ret; \ + ret = strtoul_safe_clamp(buf, v, min, max); \ + if (!ret) { \ + var = v; \ + return size; \ + } \ + return ret; \ + } \ } while (0) #define strtoul_or_return(cp) \ diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 151544740148..973847e027a8 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -69,6 +69,9 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, in_use > CUTOFF_WRITEBACK_SYNC) return false; + if (bio_op(bio) == REQ_OP_DISCARD) + return false; + if (dc->partial_stripes_expensive && bcache_dev_stripe_dirty(dc, bio->bi_iter.bi_sector, bio_sectors(bio))) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 0cabf31fb163..7eb76a1a2505 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1729,7 +1729,7 @@ void bitmap_flush(struct mddev *mddev) /* * free memory that was allocated */ -void bitmap_free(struct bitmap *bitmap) +void md_bitmap_free(struct bitmap *bitmap) { unsigned long k, pages; struct bitmap_page *bp; @@ -1763,7 +1763,7 @@ void bitmap_free(struct bitmap *bitmap) kfree(bp); kfree(bitmap); } -EXPORT_SYMBOL(bitmap_free); +EXPORT_SYMBOL(md_bitmap_free); void bitmap_wait_behind_writes(struct mddev *mddev) { @@ -1796,7 +1796,7 @@ void bitmap_destroy(struct mddev *mddev) if (mddev->thread) mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; - bitmap_free(bitmap); + md_bitmap_free(bitmap); } /* @@ -1887,7 +1887,7 @@ struct bitmap *bitmap_create(struct mddev *mddev, int slot) return bitmap; error: - bitmap_free(bitmap); + md_bitmap_free(bitmap); return ERR_PTR(err); } @@ -1958,7 +1958,7 @@ struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot) rv = bitmap_init_from_disk(bitmap, 0); if (rv) { - bitmap_free(bitmap); + md_bitmap_free(bitmap); return ERR_PTR(rv); } diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index 5df35ca90f58..dd53a978c5f2 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -271,7 +271,7 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot); int bitmap_copy_from_slot(struct mddev *mddev, int slot, sector_t *lo, sector_t *hi, bool clear_bits); -void bitmap_free(struct bitmap *bitmap); +void md_bitmap_free(struct bitmap *bitmap); void bitmap_wait_behind_writes(struct mddev *mddev); #endif diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index 874841f0fc83..10532a76688e 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -33,7 +33,7 @@ static struct kmem_cache *_cell_cache; */ struct dm_bio_prison *dm_bio_prison_create(void) { - struct dm_bio_prison *prison = kmalloc(sizeof(*prison), GFP_KERNEL); + struct dm_bio_prison *prison = kzalloc(sizeof(*prison), GFP_KERNEL); if (!prison) return NULL; diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index 8ce3a1a588cf..c34ec615420f 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -35,7 +35,7 @@ static struct kmem_cache *_cell_cache; */ struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq) { - struct dm_bio_prison_v2 *prison = kmalloc(sizeof(*prison), GFP_KERNEL); + struct dm_bio_prison_v2 *prison = kzalloc(sizeof(*prison), GFP_KERNEL); if (!prison) return NULL; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index bc60db87e6f1..394e53afc259 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1166,11 +1166,18 @@ static int __load_discards(struct dm_cache_metadata *cmd, if (r) return r; - for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) { + for (b = 0; ; b++) { r = fn(context, cmd->discard_block_size, to_dblock(b), dm_bitset_cursor_get_value(&c)); if (r) break; + + if (b >= (from_dblock(cmd->discard_nr_blocks) - 1)) + break; + + r = dm_bitset_cursor_next(&c); + if (r) + break; } dm_bitset_cursor_end(&c); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 1f6d8b6be5c7..94b8d81f6020 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -334,7 +334,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) sg_init_one(&sg, cc->key, cc->key_size); ahash_request_set_tfm(req, essiv->hash_tfm); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + ahash_request_set_callback(req, 0, NULL, NULL); ahash_request_set_crypt(req, &sg, essiv->salt, cc->key_size); err = crypto_ahash_digest(req); @@ -609,7 +609,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, int i, r; desc->tfm = lmk->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (r) @@ -771,7 +771,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, /* calculate crc32 for every 32bit part and xor it */ desc->tfm = tcw->crc32_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; for (i = 0; i < 4; i++) { r = crypto_shash_init(desc); if (r) @@ -935,7 +935,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) if (IS_ERR(bip)) return PTR_ERR(bip); - tag_len = io->cc->on_disk_tag_size * bio_sectors(bio); + tag_len = io->cc->on_disk_tag_size * (bio_sectors(bio) >> io->cc->sector_shift); bip->bip_iter.bi_size = tag_len; bip->bip_iter.bi_sector = io->cc->start + io->sector; @@ -1254,7 +1254,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, * requests if driver request queue is full. */ skcipher_request_set_callback(ctx->r.req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); } @@ -1271,7 +1271,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, * requests if driver request queue is full. */ aead_request_set_callback(ctx->r.req_aead, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 2209a9700acd..cb733a5afdc8 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -222,7 +222,8 @@ static void delay_dtr(struct dm_target *ti) { struct delay_c *dc = ti->private; - destroy_workqueue(dc->kdelayd_wq); + if (dc->kdelayd_wq) + destroy_workqueue(dc->kdelayd_wq); dm_put_device(ti, dc->dev_read); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 0c1ef63c3461..b1b68e01b889 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -282,20 +282,31 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc) { - unsigned bio_bytes = bio_cur_bytes(bio); - char *data = bio_data(bio); + unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1; + + struct bvec_iter iter; + struct bio_vec bvec; + + if (!bio_has_data(bio)) + return; /* - * Overwrite the Nth byte of the data returned. + * Overwrite the Nth byte of the bio's data, on whichever page + * it falls. */ - if (data && bio_bytes >= fc->corrupt_bio_byte) { - data[fc->corrupt_bio_byte - 1] = fc->corrupt_bio_value; - - DMDEBUG("Corrupting data bio=%p by writing %u to byte %u " - "(rw=%c bi_opf=%u bi_sector=%llu cur_bytes=%u)\n", - bio, fc->corrupt_bio_value, fc->corrupt_bio_byte, - (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf, - (unsigned long long)bio->bi_iter.bi_sector, bio_bytes); + bio_for_each_segment(bvec, bio, iter) { + if (bio_iter_len(bio, iter) > corrupt_bio_byte) { + char *segment = (page_address(bio_iter_page(bio, iter)) + + bio_iter_offset(bio, iter)); + segment[corrupt_bio_byte] = fc->corrupt_bio_value; + DMDEBUG("Corrupting data bio=%p by writing %u to byte %u " + "(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n", + bio, fc->corrupt_bio_value, fc->corrupt_bio_byte, + (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf, + (unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size); + break; + } + corrupt_bio_byte -= bio_iter_len(bio, iter); } } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index b10e4c5641ea..23f0f4eaaa2e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -493,7 +493,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result unsigned j, size; desc->tfm = ic->journal_mac; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (unlikely(r)) { @@ -637,7 +637,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err) static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp) { int r; - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, complete_journal_encrypt, comp); if (likely(encrypt)) r = crypto_skcipher_encrypt(req); @@ -1276,8 +1276,8 @@ again: checksums_ptr - checksums, !dio->write ? TAG_CMP : TAG_WRITE); if (unlikely(r)) { if (r > 0) { - DMERR("Checksum failed at sector 0x%llx", - (unsigned long long)(sector - ((r + ic->tag_size - 1) / ic->tag_size))); + DMERR_LIMIT("Checksum failed at sector 0x%llx", + (unsigned long long)(sector - ((r + ic->tag_size - 1) / ic->tag_size))); r = -EILSEQ; atomic64_inc(&ic->number_of_mismatches); } @@ -1469,8 +1469,8 @@ retry_kmap: integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack); if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) { - DMERR("Checksum failed when reading from journal, at sector 0x%llx", - (unsigned long long)logical_sector); + DMERR_LIMIT("Checksum failed when reading from journal, at sector 0x%llx", + (unsigned long long)logical_sector); } } #endif @@ -2917,17 +2917,17 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } ic->sectors_per_block = val >> SECTOR_SHIFT; - } else if (!memcmp(opt_string, "internal_hash:", strlen("internal_hash:"))) { + } else if (!strncmp(opt_string, "internal_hash:", strlen("internal_hash:"))) { r = get_alg_and_key(opt_string, &ic->internal_hash_alg, &ti->error, "Invalid internal_hash argument"); if (r) goto bad; - } else if (!memcmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) { + } else if (!strncmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) { r = get_alg_and_key(opt_string, &ic->journal_crypt_alg, &ti->error, "Invalid journal_crypt argument"); if (r) goto bad; - } else if (!memcmp(opt_string, "journal_mac:", strlen("journal_mac:"))) { + } else if (!strncmp(opt_string, "journal_mac:", strlen("journal_mac:"))) { r = get_alg_and_key(opt_string, &ic->journal_mac_alg, &ti->error, "Invalid journal_mac argument"); if (r) diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index b4357ed4d541..56e2c0e079d7 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -50,7 +50,7 @@ struct dm_io_client *dm_io_client_create(void) struct dm_io_client *client; unsigned min_ios = dm_get_reserved_bio_based_ios(); - client = kmalloc(sizeof(*client), GFP_KERNEL); + client = kzalloc(sizeof(*client), GFP_KERNEL); if (!client) return ERR_PTR(-ENOMEM); diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index b9d1897bcf5b..7ca2b1aaa79d 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -545,8 +545,10 @@ static int run_io_job(struct kcopyd_job *job) * no point in continuing. */ if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) && - job->master_job->write_err) + job->master_job->write_err) { + job->write_err = job->master_job->write_err; return -EIO; + } io_job_start(job->kc->throttle); @@ -598,6 +600,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc, else job->read_err = 1; push(&kc->complete_jobs, job); + wake(kc); break; } @@ -889,7 +892,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro int r = -ENOMEM; struct dm_kcopyd_client *kc; - kc = kmalloc(sizeof(*kc), GFP_KERNEL); + kc = kzalloc(sizeof(*kc), GFP_KERNEL); if (!kc) return ERR_PTR(-ENOMEM); diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 8b80a9ce9ea9..dafedbc28bcc 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -57,6 +57,7 @@ #define WRITE_LOG_VERSION 1ULL #define WRITE_LOG_MAGIC 0x6a736677736872ULL +#define WRITE_LOG_SUPER_SECTOR 0 /* * The disk format for this is braindead simple. @@ -112,6 +113,7 @@ struct log_writes_c { struct list_head logging_blocks; wait_queue_head_t wait; struct task_struct *log_kthread; + struct completion super_done; }; struct pending_block { @@ -177,6 +179,14 @@ static void log_end_io(struct bio *bio) bio_put(bio); } +static void log_end_super(struct bio *bio) +{ + struct log_writes_c *lc = bio->bi_private; + + complete(&lc->super_done); + log_end_io(bio); +} + /* * Meant to be called if there is an error, it will free all the pages * associated with the block. @@ -212,7 +222,8 @@ static int write_metadata(struct log_writes_c *lc, void *entry, bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; bio_set_dev(bio, lc->logdev->bdev); - bio->bi_end_io = log_end_io; + bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ? + log_end_super : log_end_io; bio->bi_private = lc; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -334,11 +345,18 @@ static int log_super(struct log_writes_c *lc) super.nr_entries = cpu_to_le64(lc->logged_entries); super.sectorsize = cpu_to_le32(lc->sectorsize); - if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) { + if (write_metadata(lc, &super, sizeof(super), NULL, 0, + WRITE_LOG_SUPER_SECTOR)) { DMERR("Couldn't write super"); return -1; } + /* + * Super sector should be writen in-order, otherwise the + * nr_entries could be rewritten incorrectly by an old bio. + */ + wait_for_completion_io(&lc->super_done); + return 0; } @@ -447,6 +465,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_LIST_HEAD(&lc->unflushed_blocks); INIT_LIST_HEAD(&lc->logging_blocks); init_waitqueue_head(&lc->wait); + init_completion(&lc->super_done); atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 151211b4cb1b..2c5912e75514 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2441,7 +2441,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) } /* Enable bitmap creation for RAID levels != 0 */ - mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096); + mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096); mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; if (!test_and_clear_bit(FirstUse, &rdev->flags)) { diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 85c32b22a420..91c6f6d72eee 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -179,7 +179,7 @@ struct dm_region_hash *dm_region_hash_create( ; nr_buckets >>= 1; - rh = kmalloc(sizeof(*rh), GFP_KERNEL); + rh = kzalloc(sizeof(*rh), GFP_KERNEL); if (!rh) { DMERR("unable to allocate region hash memory"); return ERR_PTR(-ENOMEM); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index c5534d294773..00025569e807 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -17,7 +17,7 @@ #include "dm-bufio.h" #define DM_MSG_PREFIX "persistent snapshot" -#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32 /* 16KB */ +#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32U /* 16KB */ #define DM_PREFETCH_CHUNKS 12 diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index b502debc6df3..2170f6c118b8 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -19,7 +19,6 @@ #include <linux/vmalloc.h> #include <linux/log2.h> #include <linux/dm-kcopyd.h> -#include <linux/semaphore.h> #include "dm.h" @@ -48,7 +47,7 @@ struct dm_exception_table { }; struct dm_snapshot { - struct rw_semaphore lock; + struct mutex lock; struct dm_dev *origin; struct dm_dev *cow; @@ -106,8 +105,8 @@ struct dm_snapshot { /* The on disk metadata handler */ struct dm_exception_store *store; - /* Maximum number of in-flight COW jobs. */ - struct semaphore cow_count; + unsigned in_progress; + struct wait_queue_head in_progress_wait; struct dm_kcopyd_client *kcopyd_client; @@ -158,8 +157,8 @@ struct dm_snapshot { */ #define DEFAULT_COW_THRESHOLD 2048 -static int cow_threshold = DEFAULT_COW_THRESHOLD; -module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644); +static unsigned cow_threshold = DEFAULT_COW_THRESHOLD; +module_param_named(snapshot_cow_threshold, cow_threshold, uint, 0644); MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write"); DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, @@ -456,9 +455,9 @@ static int __find_snapshots_sharing_cow(struct dm_snapshot *snap, if (!bdev_equal(s->cow->bdev, snap->cow->bdev)) continue; - down_read(&s->lock); + mutex_lock(&s->lock); active = s->active; - up_read(&s->lock); + mutex_unlock(&s->lock); if (active) { if (snap_src) @@ -926,7 +925,7 @@ static int remove_single_exception_chunk(struct dm_snapshot *s) int r; chunk_t old_chunk = s->first_merging_chunk + s->num_merging_chunks - 1; - down_write(&s->lock); + mutex_lock(&s->lock); /* * Process chunks (and associated exceptions) in reverse order @@ -941,7 +940,7 @@ static int remove_single_exception_chunk(struct dm_snapshot *s) b = __release_queued_bios_after_merge(s); out: - up_write(&s->lock); + mutex_unlock(&s->lock); if (b) flush_bios(b); @@ -1000,9 +999,9 @@ static void snapshot_merge_next_chunks(struct dm_snapshot *s) if (linear_chunks < 0) { DMERR("Read error in exception store: " "shutting down merge"); - down_write(&s->lock); + mutex_lock(&s->lock); s->merge_failed = 1; - up_write(&s->lock); + mutex_unlock(&s->lock); } goto shut; } @@ -1043,10 +1042,10 @@ static void snapshot_merge_next_chunks(struct dm_snapshot *s) previous_count = read_pending_exceptions_done_count(); } - down_write(&s->lock); + mutex_lock(&s->lock); s->first_merging_chunk = old_chunk; s->num_merging_chunks = linear_chunks; - up_write(&s->lock); + mutex_unlock(&s->lock); /* Wait until writes to all 'linear_chunks' drain */ for (i = 0; i < linear_chunks; i++) @@ -1088,10 +1087,10 @@ static void merge_callback(int read_err, unsigned long write_err, void *context) return; shut: - down_write(&s->lock); + mutex_lock(&s->lock); s->merge_failed = 1; b = __release_queued_bios_after_merge(s); - up_write(&s->lock); + mutex_unlock(&s->lock); error_bios(b); merge_shutdown(s); @@ -1137,7 +1136,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) origin_mode = FMODE_WRITE; } - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) { ti->error = "Cannot allocate private snapshot structure"; r = -ENOMEM; @@ -1190,7 +1189,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) s->exception_start_sequence = 0; s->exception_complete_sequence = 0; INIT_LIST_HEAD(&s->out_of_order_list); - init_rwsem(&s->lock); + mutex_init(&s->lock); INIT_LIST_HEAD(&s->list); spin_lock_init(&s->pe_lock); s->state_bits = 0; @@ -1206,7 +1205,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_hash_tables; } - sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX); + init_waitqueue_head(&s->in_progress_wait); s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(s->kcopyd_client)) { @@ -1357,9 +1356,9 @@ static void snapshot_dtr(struct dm_target *ti) /* Check whether exception handover must be cancelled */ (void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL); if (snap_src && snap_dest && (s == snap_src)) { - down_write(&snap_dest->lock); + mutex_lock(&snap_dest->lock); snap_dest->valid = 0; - up_write(&snap_dest->lock); + mutex_unlock(&snap_dest->lock); DMERR("Cancelling snapshot handover."); } up_read(&_origins_lock); @@ -1390,13 +1389,62 @@ static void snapshot_dtr(struct dm_target *ti) dm_exception_store_destroy(s->store); + mutex_destroy(&s->lock); + dm_put_device(ti, s->cow); dm_put_device(ti, s->origin); + WARN_ON(s->in_progress); + kfree(s); } +static void account_start_copy(struct dm_snapshot *s) +{ + spin_lock(&s->in_progress_wait.lock); + s->in_progress++; + spin_unlock(&s->in_progress_wait.lock); +} + +static void account_end_copy(struct dm_snapshot *s) +{ + spin_lock(&s->in_progress_wait.lock); + BUG_ON(!s->in_progress); + s->in_progress--; + if (likely(s->in_progress <= cow_threshold) && + unlikely(waitqueue_active(&s->in_progress_wait))) + wake_up_locked(&s->in_progress_wait); + spin_unlock(&s->in_progress_wait.lock); +} + +static bool wait_for_in_progress(struct dm_snapshot *s, bool unlock_origins) +{ + if (unlikely(s->in_progress > cow_threshold)) { + spin_lock(&s->in_progress_wait.lock); + if (likely(s->in_progress > cow_threshold)) { + /* + * NOTE: this throttle doesn't account for whether + * the caller is servicing an IO that will trigger a COW + * so excess throttling may result for chunks not required + * to be COW'd. But if cow_threshold was reached, extra + * throttling is unlikely to negatively impact performance. + */ + DECLARE_WAITQUEUE(wait, current); + __add_wait_queue(&s->in_progress_wait, &wait); + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&s->in_progress_wait.lock); + if (unlock_origins) + up_read(&_origins_lock); + io_schedule(); + remove_wait_queue(&s->in_progress_wait, &wait); + return false; + } + spin_unlock(&s->in_progress_wait.lock); + } + return true; +} + /* * Flush a list of buffers. */ @@ -1412,7 +1460,7 @@ static void flush_bios(struct bio *bio) } } -static int do_origin(struct dm_dev *origin, struct bio *bio); +static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit); /* * Flush a list of buffers. @@ -1425,7 +1473,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio) while (bio) { n = bio->bi_next; bio->bi_next = NULL; - r = do_origin(s->origin, bio); + r = do_origin(s->origin, bio, false); if (r == DM_MAPIO_REMAPPED) generic_make_request(bio); bio = n; @@ -1477,7 +1525,7 @@ static void pending_complete(void *context, int success) if (!success) { /* Read/write error - snapshot is unusable */ - down_write(&s->lock); + mutex_lock(&s->lock); __invalidate_snapshot(s, -EIO); error = 1; goto out; @@ -1485,14 +1533,14 @@ static void pending_complete(void *context, int success) e = alloc_completed_exception(GFP_NOIO); if (!e) { - down_write(&s->lock); + mutex_lock(&s->lock); __invalidate_snapshot(s, -ENOMEM); error = 1; goto out; } *e = pe->e; - down_write(&s->lock); + mutex_lock(&s->lock); if (!s->valid) { free_completed_exception(e); error = 1; @@ -1517,7 +1565,7 @@ out: full_bio->bi_end_io = pe->full_bio_end_io; increment_pending_exceptions_done_count(); - up_write(&s->lock); + mutex_unlock(&s->lock); /* Submit any pending write bios */ if (error) { @@ -1579,7 +1627,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context) } list_add(&pe->out_of_order_entry, lh); } - up(&s->cow_count); + account_end_copy(s); } /* @@ -1603,7 +1651,7 @@ static void start_copy(struct dm_snap_pending_exception *pe) dest.count = src.count; /* Hand over to kcopyd */ - down(&s->cow_count); + account_start_copy(s); dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe); } @@ -1623,7 +1671,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio = bio; pe->full_bio_end_io = bio->bi_end_io; - down(&s->cow_count); + account_start_copy(s); callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe); @@ -1714,9 +1762,12 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (!s->valid) return DM_MAPIO_KILL; - /* FIXME: should only take write lock if we need - * to copy an exception */ - down_write(&s->lock); + if (bio_data_dir(bio) == WRITE) { + while (unlikely(!wait_for_in_progress(s, false))) + ; /* wait_for_in_progress() has slept */ + } + + mutex_lock(&s->lock); if (!s->valid || (unlikely(s->snapshot_overflowed) && bio_data_dir(bio) == WRITE)) { @@ -1739,9 +1790,9 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (bio_data_dir(bio) == WRITE) { pe = __lookup_pending_exception(s, chunk); if (!pe) { - up_write(&s->lock); + mutex_unlock(&s->lock); pe = alloc_pending_exception(s); - down_write(&s->lock); + mutex_lock(&s->lock); if (!s->valid || s->snapshot_overflowed) { free_pending_exception(pe); @@ -1776,7 +1827,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) bio->bi_iter.bi_size == (s->store->chunk_size << SECTOR_SHIFT)) { pe->started = 1; - up_write(&s->lock); + mutex_unlock(&s->lock); start_full_bio(pe, bio); goto out; } @@ -1786,7 +1837,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (!pe->started) { /* this is protected by snap->lock */ pe->started = 1; - up_write(&s->lock); + mutex_unlock(&s->lock); start_copy(pe); goto out; } @@ -1796,7 +1847,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) } out_unlock: - up_write(&s->lock); + mutex_unlock(&s->lock); out: return r; } @@ -1832,7 +1883,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio) chunk = sector_to_chunk(s->store, bio->bi_iter.bi_sector); - down_write(&s->lock); + mutex_lock(&s->lock); /* Full merging snapshots are redirected to the origin */ if (!s->valid) @@ -1863,12 +1914,12 @@ redirect_to_origin: bio_set_dev(bio, s->origin->bdev); if (bio_data_dir(bio) == WRITE) { - up_write(&s->lock); - return do_origin(s->origin, bio); + mutex_unlock(&s->lock); + return do_origin(s->origin, bio, false); } out_unlock: - up_write(&s->lock); + mutex_unlock(&s->lock); return r; } @@ -1900,7 +1951,7 @@ static int snapshot_preresume(struct dm_target *ti) down_read(&_origins_lock); (void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL); if (snap_src && snap_dest) { - down_read(&snap_src->lock); + mutex_lock(&snap_src->lock); if (s == snap_src) { DMERR("Unable to resume snapshot source until " "handover completes."); @@ -1910,7 +1961,7 @@ static int snapshot_preresume(struct dm_target *ti) "source is suspended."); r = -EINVAL; } - up_read(&snap_src->lock); + mutex_unlock(&snap_src->lock); } up_read(&_origins_lock); @@ -1956,11 +2007,11 @@ static void snapshot_resume(struct dm_target *ti) (void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL); if (snap_src && snap_dest) { - down_write(&snap_src->lock); - down_write_nested(&snap_dest->lock, SINGLE_DEPTH_NESTING); + mutex_lock(&snap_src->lock); + mutex_lock_nested(&snap_dest->lock, SINGLE_DEPTH_NESTING); __handover_exceptions(snap_src, snap_dest); - up_write(&snap_dest->lock); - up_write(&snap_src->lock); + mutex_unlock(&snap_dest->lock); + mutex_unlock(&snap_src->lock); } up_read(&_origins_lock); @@ -1975,9 +2026,9 @@ static void snapshot_resume(struct dm_target *ti) /* Now we have correct chunk size, reregister */ reregister_snapshot(s); - down_write(&s->lock); + mutex_lock(&s->lock); s->active = 1; - up_write(&s->lock); + mutex_unlock(&s->lock); } static uint32_t get_origin_minimum_chunksize(struct block_device *bdev) @@ -2017,7 +2068,7 @@ static void snapshot_status(struct dm_target *ti, status_type_t type, switch (type) { case STATUSTYPE_INFO: - down_write(&snap->lock); + mutex_lock(&snap->lock); if (!snap->valid) DMEMIT("Invalid"); @@ -2042,7 +2093,7 @@ static void snapshot_status(struct dm_target *ti, status_type_t type, DMEMIT("Unknown"); } - up_write(&snap->lock); + mutex_unlock(&snap->lock); break; @@ -2108,7 +2159,7 @@ static int __origin_write(struct list_head *snapshots, sector_t sector, if (dm_target_is_snapshot_merge(snap->ti)) continue; - down_write(&snap->lock); + mutex_lock(&snap->lock); /* Only deal with valid and active snapshots */ if (!snap->valid || !snap->active) @@ -2135,9 +2186,9 @@ static int __origin_write(struct list_head *snapshots, sector_t sector, pe = __lookup_pending_exception(snap, chunk); if (!pe) { - up_write(&snap->lock); + mutex_unlock(&snap->lock); pe = alloc_pending_exception(snap); - down_write(&snap->lock); + mutex_lock(&snap->lock); if (!snap->valid) { free_pending_exception(pe); @@ -2180,7 +2231,7 @@ static int __origin_write(struct list_head *snapshots, sector_t sector, } next_snapshot: - up_write(&snap->lock); + mutex_unlock(&snap->lock); if (pe_to_start_now) { start_copy(pe_to_start_now); @@ -2201,15 +2252,24 @@ next_snapshot: /* * Called on a write from the origin driver. */ -static int do_origin(struct dm_dev *origin, struct bio *bio) +static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit) { struct origin *o; int r = DM_MAPIO_REMAPPED; +again: down_read(&_origins_lock); o = __lookup_origin(origin->bdev); - if (o) + if (o) { + if (limit) { + struct dm_snapshot *s; + list_for_each_entry(s, &o->snapshots, list) + if (unlikely(!wait_for_in_progress(s, true))) + goto again; + } + r = __origin_write(&o->snapshots, bio->bi_iter.bi_sector, bio); + } up_read(&_origins_lock); return r; @@ -2322,7 +2382,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio) dm_accept_partial_bio(bio, available_sectors); /* Only tell snapshots if this is a write */ - return do_origin(o->dev, bio); + return do_origin(o->dev, bio, true); } static long origin_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index f9cd81375f28..8f070debe498 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1308,7 +1308,7 @@ void dm_table_event(struct dm_table *t) } EXPORT_SYMBOL(dm_table_event); -sector_t dm_table_get_size(struct dm_table *t) +inline sector_t dm_table_get_size(struct dm_table *t) { return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0; } @@ -1333,6 +1333,9 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) unsigned int l, n = 0, k = 0; sector_t *node; + if (unlikely(sector >= dm_table_get_size(t))) + return &t->targets[t->num_targets]; + for (l = 0; l < t->depth; l++) { n = get_child(n, k); node = get_node(t, l, n); @@ -1789,6 +1792,36 @@ static bool dm_table_supports_discards(struct dm_table *t) return true; } +static int device_requires_stable_pages(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && bdi_cap_stable_pages_required(q->backing_dev_info); +} + +/* + * If any underlying device requires stable pages, a table must require + * them as well. Only targets that support iterate_devices are considered: + * don't want error, zero, etc to require stable pages. + */ +static bool dm_table_requires_stable_pages(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i; + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, device_requires_stable_pages, NULL)) + return true; + } + + return false; +} + void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { @@ -1838,6 +1871,15 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, dm_table_verify_integrity(t); /* + * Some devices don't use blk_integrity but still want stable pages + * because they do their own checksumming. + */ + if (dm_table_requires_stable_pages(t)) + q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + else + q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + + /* * Determine whether or not this queue's I/O timings contribute * to the entropy pool, Only request-based targets use this. * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 40b624d8255d..0ee5eae71690 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -257,6 +257,7 @@ struct pool { spinlock_t lock; struct bio_list deferred_flush_bios; + struct bio_list deferred_flush_completions; struct list_head prepared_mappings; struct list_head prepared_discards; struct list_head prepared_discards_pt2; @@ -950,6 +951,39 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) mempool_free(m, m->tc->pool->mapping_pool); } +static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + /* + * If the bio has the REQ_FUA flag set we must commit the metadata + * before signaling its completion. + */ + if (!bio_triggers_commit(tc, bio)) { + bio_endio(bio); + return; + } + + /* + * Complete bio with an error if earlier I/O caused changes to the + * metadata that can't be committed, e.g, due to I/O errors on the + * metadata device. + */ + if (dm_thin_aborted_changes(tc->td)) { + bio_io_error(bio); + return; + } + + /* + * Batch together any bios that trigger commits and then issue a + * single commit for them in process_deferred_bios(). + */ + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_flush_completions, bio); + spin_unlock_irqrestore(&pool->lock, flags); +} + static void process_prepared_mapping(struct dm_thin_new_mapping *m) { struct thin_c *tc = m->tc; @@ -982,7 +1016,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) */ if (bio) { inc_remap_and_issue_cell(tc, m->cell, m->data_block); - bio_endio(bio); + complete_overwrite_bio(tc, bio); } else { inc_all_io_entry(tc->pool, m->cell->holder); remap_and_issue(tc, m->cell->holder, m->data_block); @@ -2328,7 +2362,7 @@ static void process_deferred_bios(struct pool *pool) { unsigned long flags; struct bio *bio; - struct bio_list bios; + struct bio_list bios, bio_completions; struct thin_c *tc; tc = get_first_thin(pool); @@ -2339,26 +2373,36 @@ static void process_deferred_bios(struct pool *pool) } /* - * If there are any deferred flush bios, we must commit - * the metadata before issuing them. + * If there are any deferred flush bios, we must commit the metadata + * before issuing them or signaling their completion. */ bio_list_init(&bios); + bio_list_init(&bio_completions); + spin_lock_irqsave(&pool->lock, flags); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); + + bio_list_merge(&bio_completions, &pool->deferred_flush_completions); + bio_list_init(&pool->deferred_flush_completions); spin_unlock_irqrestore(&pool->lock, flags); - if (bio_list_empty(&bios) && + if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) return; if (commit(pool)) { + bio_list_merge(&bios, &bio_completions); + while ((bio = bio_list_pop(&bios))) bio_io_error(bio); return; } pool->last_commit_jiffies = jiffies; + while ((bio = bio_list_pop(&bio_completions))) + bio_endio(bio); + while ((bio = bio_list_pop(&bios))) generic_make_request(bio); } @@ -2918,7 +2962,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, return (struct pool *)pmd; } - pool = kmalloc(sizeof(*pool), GFP_KERNEL); + pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) { *error = "Error allocating memory for pool"; err_p = ERR_PTR(-ENOMEM); @@ -2965,6 +3009,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout); spin_lock_init(&pool->lock); bio_list_init(&pool->deferred_flush_bios); + bio_list_init(&pool->deferred_flush_completions); INIT_LIST_HEAD(&pool->prepared_mappings); INIT_LIST_HEAD(&pool->prepared_discards); INIT_LIST_HEAD(&pool->prepared_discards_pt2); @@ -3247,6 +3292,13 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) as.argc = argc; as.argv = argv; + /* make sure metadata and data are different devices */ + if (!strcmp(argv[0], argv[1])) { + ti->error = "Error setting metadata or data device"; + r = -EINVAL; + goto out_unlock; + } + /* * Set default pool features. */ @@ -4128,6 +4180,12 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) tc->sort_bio_list = RB_ROOT; if (argc == 3) { + if (!strcmp(argv[0], argv[2])) { + ti->error = "Error setting origin device"; + r = -EINVAL; + goto bad_origin_dev; + } + r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev); if (r) { ti->error = "Error opening origin device"; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index ae0ec0abb667..7eeb8dd119ca 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -235,8 +235,8 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, BUG(); } - DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str, - block); + DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name, + type_str, block); if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) DMERR("%s: reached maximum errors", v->data_dev->name); diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 34968ca6b84a..9b78f4a74a12 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -401,15 +401,18 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no; struct bio *bio; + if (dmz_bdev_is_dying(zmd->dev)) + return ERR_PTR(-EIO); + /* Get a new block and a BIO to read it */ mblk = dmz_alloc_mblock(zmd, mblk_no); if (!mblk) - return NULL; + return ERR_PTR(-ENOMEM); bio = bio_alloc(GFP_NOIO, 1); if (!bio) { dmz_free_mblock(zmd, mblk); - return NULL; + return ERR_PTR(-ENOMEM); } spin_lock(&zmd->mblk_lock); @@ -540,8 +543,8 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, if (!mblk) { /* Cache miss: read the block from disk */ mblk = dmz_get_mblock_slow(zmd, mblk_no); - if (!mblk) - return ERR_PTR(-ENOMEM); + if (IS_ERR(mblk)) + return mblk; } /* Wait for on-going read I/O and check for error */ @@ -549,6 +552,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { dmz_release_mblock(zmd, mblk); + dmz_check_bdev(zmd->dev); return ERR_PTR(-EIO); } @@ -569,16 +573,19 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk) /* * Issue a metadata block write BIO. */ -static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, - unsigned int set) +static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, + unsigned int set) { sector_t block = zmd->sb[set].block + mblk->no; struct bio *bio; + if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) { set_bit(DMZ_META_ERROR, &mblk->state); - return; + return -ENOMEM; } set_bit(DMZ_META_WRITING, &mblk->state); @@ -590,6 +597,8 @@ static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO); bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); + + return 0; } /* @@ -601,6 +610,9 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, struct bio *bio; int ret; + if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) return -ENOMEM; @@ -612,6 +624,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, ret = submit_bio_wait(bio); bio_put(bio); + if (ret) + dmz_check_bdev(zmd->dev); return ret; } @@ -658,22 +672,30 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, { struct dmz_mblock *mblk; struct blk_plug plug; - int ret = 0; + int ret = 0, nr_mblks_submitted = 0; /* Issue writes */ blk_start_plug(&plug); - list_for_each_entry(mblk, write_list, link) - dmz_write_mblock(zmd, mblk, set); + list_for_each_entry(mblk, write_list, link) { + ret = dmz_write_mblock(zmd, mblk, set); + if (ret) + break; + nr_mblks_submitted++; + } blk_finish_plug(&plug); /* Wait for completion */ list_for_each_entry(mblk, write_list, link) { + if (!nr_mblks_submitted) + break; wait_on_bit_io(&mblk->state, DMZ_META_WRITING, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); + dmz_check_bdev(zmd->dev); ret = -EIO; } + nr_mblks_submitted--; } /* Flush drive cache (this will also sync data) */ @@ -735,6 +757,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ dmz_lock_flush(zmd); + if (dmz_bdev_is_dying(zmd->dev)) { + ret = -EIO; + goto out; + } + /* Get dirty blocks */ spin_lock(&zmd->mblk_lock); list_splice_init(&zmd->mblk_dirty_list, &write_list); @@ -743,7 +770,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) /* If there are no dirty metadata blocks, just flush the device cache */ if (list_empty(&write_list)) { ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL); - goto out; + goto err; } /* @@ -753,7 +780,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_log_dirty_mblocks(zmd, &write_list); if (ret) - goto out; + goto err; /* * The log is on disk. It is now safe to update in place @@ -761,11 +788,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary); if (ret) - goto out; + goto err; ret = dmz_write_sb(zmd, zmd->mblk_primary); if (ret) - goto out; + goto err; while (!list_empty(&write_list)) { mblk = list_first_entry(&write_list, struct dmz_mblock, link); @@ -780,16 +807,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) zmd->sb_gen++; out: - if (ret && !list_empty(&write_list)) { - spin_lock(&zmd->mblk_lock); - list_splice(&write_list, &zmd->mblk_dirty_list); - spin_unlock(&zmd->mblk_lock); - } - dmz_unlock_flush(zmd); up_write(&zmd->mblk_sem); return ret; + +err: + if (!list_empty(&write_list)) { + spin_lock(&zmd->mblk_lock); + list_splice(&write_list, &zmd->mblk_dirty_list); + spin_unlock(&zmd->mblk_lock); + } + if (!dmz_check_bdev(zmd->dev)) + ret = -EIO; + goto out; } /* @@ -1169,6 +1200,9 @@ static int dmz_init_zones(struct dmz_metadata *zmd) goto out; } + if (!nr_blkz) + break; + /* Process report */ for (i = 0; i < nr_blkz; i++) { ret = dmz_init_zone(zmd, zone, &blkz[i]); @@ -1204,9 +1238,12 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) /* Get zone information from disk */ ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), &blkz, &nr_blkz, GFP_NOIO); + if (!nr_blkz) + ret = -EIO; if (ret) { dmz_dev_err(zmd->dev, "Get zone %u report failed", dmz_id(zmd, zone)); + dmz_check_bdev(zmd->dev); return ret; } @@ -1529,7 +1566,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) struct dm_zone *zone; if (list_empty(&zmd->map_rnd_list)) - return NULL; + return ERR_PTR(-EBUSY); list_for_each_entry(zone, &zmd->map_rnd_list, link) { if (dmz_is_buf(zone)) @@ -1540,7 +1577,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) return dzone; } - return NULL; + return ERR_PTR(-EBUSY); } /* @@ -1551,7 +1588,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) struct dm_zone *zone; if (list_empty(&zmd->map_seq_list)) - return NULL; + return ERR_PTR(-EBUSY); list_for_each_entry(zone, &zmd->map_seq_list, link) { if (!zone->bzone) @@ -1560,7 +1597,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) return zone; } - return NULL; + return ERR_PTR(-EBUSY); } /* @@ -1589,30 +1626,6 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd) } /* - * Activate a zone (increment its reference count). - */ -void dmz_activate_zone(struct dm_zone *zone) -{ - set_bit(DMZ_ACTIVE, &zone->flags); - atomic_inc(&zone->refcount); -} - -/* - * Deactivate a zone. This decrement the zone reference counter - * and clears the active state of the zone once the count reaches 0, - * indicating that all BIOs to the zone have completed. Returns - * true if the zone was deactivated. - */ -void dmz_deactivate_zone(struct dm_zone *zone) -{ - if (atomic_dec_and_test(&zone->refcount)) { - WARN_ON(!test_bit(DMZ_ACTIVE, &zone->flags)); - clear_bit_unlock(DMZ_ACTIVE, &zone->flags); - smp_mb__after_atomic(); - } -} - -/* * Get the zone mapping a chunk, if the chunk is mapped already. * If no mapping exist and the operation is WRITE, a zone is * allocated and used to map the chunk. @@ -1642,6 +1655,10 @@ again: /* Alloate a random zone */ dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!dzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + dzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } @@ -1739,6 +1756,10 @@ again: /* Alloate a random zone */ bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!bzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + bzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 44a119e12f1a..2fad512dce98 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -37,7 +37,7 @@ enum { /* * Number of seconds of target BIO inactivity to consider the target idle. */ -#define DMZ_IDLE_PERIOD (10UL * HZ) +#define DMZ_IDLE_PERIOD (10UL * HZ) /* * Percentage of unmapped (free) random zones below which reclaim starts @@ -81,6 +81,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", dmz_id(zmd, zone), (unsigned long long)wp_block, (unsigned long long)block, nr_blocks, ret); + dmz_check_bdev(zrc->dev); return ret; } @@ -134,6 +135,9 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, set_bit(DM_KCOPYD_WRITE_SEQ, &flags); while (block < end_block) { + if (dev->flags & DMZ_BDEV_DYING) + return -EIO; + /* Get a valid region from the source zone */ ret = dmz_first_valid_block(zmd, src_zone, &block); if (ret <= 0) @@ -217,7 +221,7 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone) dmz_unlock_flush(zmd); - return 0; + return ret; } /* @@ -261,7 +265,7 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) dmz_unlock_flush(zmd); - return 0; + return ret; } /* @@ -314,7 +318,7 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) dmz_unlock_flush(zmd); - return 0; + return ret; } /* @@ -336,7 +340,7 @@ static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone) /* * Find a candidate zone for reclaim and process it. */ -static void dmz_reclaim(struct dmz_reclaim *zrc) +static int dmz_do_reclaim(struct dmz_reclaim *zrc) { struct dmz_metadata *zmd = zrc->metadata; struct dm_zone *dzone; @@ -346,8 +350,8 @@ static void dmz_reclaim(struct dmz_reclaim *zrc) /* Get a data zone */ dzone = dmz_get_zone_for_reclaim(zmd); - if (!dzone) - return; + if (IS_ERR(dzone)) + return PTR_ERR(dzone); start = jiffies; @@ -393,13 +397,20 @@ static void dmz_reclaim(struct dmz_reclaim *zrc) out: if (ret) { dmz_unlock_zone_reclaim(dzone); - return; + return ret; } - (void) dmz_flush_metadata(zrc->metadata); + ret = dmz_flush_metadata(zrc->metadata); + if (ret) { + dmz_dev_debug(zrc->dev, + "Metadata flush for zone %u failed, err %d\n", + dmz_id(zmd, rzone), ret); + return ret; + } dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms", dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start)); + return 0; } /* @@ -444,6 +455,10 @@ static void dmz_reclaim_work(struct work_struct *work) struct dmz_metadata *zmd = zrc->metadata; unsigned int nr_rnd, nr_unmap_rnd; unsigned int p_unmap_rnd; + int ret; + + if (dmz_bdev_is_dying(zrc->dev)) + return; if (!dmz_should_reclaim(zrc)) { mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD); @@ -473,7 +488,12 @@ static void dmz_reclaim_work(struct work_struct *work) (dmz_target_idle(zrc) ? "Idle" : "Busy"), p_unmap_rnd, nr_unmap_rnd, nr_rnd); - dmz_reclaim(zrc); + ret = dmz_do_reclaim(zrc); + if (ret) { + dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); + if (!dmz_check_bdev(zrc->dev)) + return; + } dmz_schedule_reclaim(zrc); } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 532bfce7f072..497a2bc5da51 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -79,6 +79,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) bio->bi_status = status; + if (bio->bi_status != BLK_STS_OK) + bioctx->target->dev->flags |= DMZ_CHECK_BDEV; if (atomic_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -277,8 +279,8 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, /* Get the buffer zone. One will be allocated if needed */ bzone = dmz_get_chunk_buffer(zmd, zone); - if (!bzone) - return -ENOSPC; + if (IS_ERR(bzone)) + return PTR_ERR(bzone); if (dmz_is_readonly(bzone)) return -EROFS; @@ -389,6 +391,11 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, dmz_lock_metadata(zmd); + if (dmz->dev->flags & DMZ_BDEV_DYING) { + ret = -EIO; + goto out; + } + /* * Get the data zone mapping the chunk. There may be no * mapping for read and discard. If a mapping is obtained, @@ -493,6 +500,8 @@ static void dmz_flush_work(struct work_struct *work) /* Flush dirty metadata blocks */ ret = dmz_flush_metadata(dmz->metadata); + if (ret) + dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret); /* Process queued flush requests */ while (1) { @@ -513,22 +522,24 @@ static void dmz_flush_work(struct work_struct *work) * Get a chunk work and start it to process a new BIO. * If the BIO chunk has no work yet, create one. */ -static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) +static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) { unsigned int chunk = dmz_bio_chunk(dmz->dev, bio); struct dm_chunk_work *cw; + int ret = 0; mutex_lock(&dmz->chunk_lock); /* Get the BIO chunk work. If one is not active yet, create one */ cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk); if (!cw) { - int ret; /* Create a new chunk work */ cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO); - if (!cw) + if (unlikely(!cw)) { + ret = -ENOMEM; goto out; + } INIT_WORK(&cw->work, dmz_chunk_work); atomic_set(&cw->refcount, 0); @@ -539,7 +550,6 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw); if (unlikely(ret)) { kfree(cw); - cw = NULL; goto out; } } @@ -547,10 +557,58 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) bio_list_add(&cw->bio_list, bio); dmz_get_chunk_work(cw); + dmz_reclaim_bio_acc(dmz->reclaim); if (queue_work(dmz->chunk_wq, &cw->work)) dmz_get_chunk_work(cw); out: mutex_unlock(&dmz->chunk_lock); + return ret; +} + +/* + * Check if the backing device is being removed. If it's on the way out, + * start failing I/O. Reclaim and metadata components also call this + * function to cleanly abort operation in the event of such failure. + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) +{ + if (dmz_dev->flags & DMZ_BDEV_DYING) + return true; + + if (dmz_dev->flags & DMZ_CHECK_BDEV) + return !dmz_check_bdev(dmz_dev); + + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + + return dmz_dev->flags & DMZ_BDEV_DYING; +} + +/* + * Check the backing device availability. This detects such events as + * backing device going offline due to errors, media removals, etc. + * This check is less efficient than dmz_bdev_is_dying() and should + * only be performed as a part of error handling. + */ +bool dmz_check_bdev(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + dmz_dev->flags &= ~DMZ_CHECK_BDEV; + + if (dmz_bdev_is_dying(dmz_dev)) + return false; + + disk = dmz_dev->bdev->bd_disk; + if (disk->fops->check_events && + disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + + return !(dmz_dev->flags & DMZ_BDEV_DYING); } /* @@ -564,6 +622,10 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) sector_t sector = bio->bi_iter.bi_sector; unsigned int nr_sectors = bio_sectors(bio); sector_t chunk_sector; + int ret; + + if (dmz_bdev_is_dying(dmz->dev)) + return DM_MAPIO_KILL; dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", bio_op(bio), (unsigned long long)sector, nr_sectors, @@ -601,8 +663,14 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector); /* Now ready to handle this BIO */ - dmz_reclaim_bio_acc(dmz->reclaim); - dmz_queue_chunk_work(dmz, bio); + ret = dmz_queue_chunk_work(dmz, bio); + if (ret) { + dmz_dev_debug(dmz->dev, + "BIO op %d, can't process chunk %llu, err %i\n", + bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio), + ret); + return DM_MAPIO_REQUEUE; + } return DM_MAPIO_SUBMITTED; } @@ -855,6 +923,9 @@ static int dmz_prepare_ioctl(struct dm_target *ti, { struct dmz_target *dmz = ti->private; + if (!dmz_check_bdev(dmz->dev)) + return -EIO; + *bdev = dmz->dev->bdev; return 0; diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index 12419f0bfe78..2662746ba8b9 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -56,6 +56,8 @@ struct dmz_dev { unsigned int nr_zones; + unsigned int flags; + sector_t zone_nr_sectors; unsigned int zone_nr_sectors_shift; @@ -67,6 +69,10 @@ struct dmz_dev { (dev)->zone_nr_sectors_shift) #define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1)) +/* Device flags. */ +#define DMZ_BDEV_DYING (1 << 0) +#define DMZ_CHECK_BDEV (2 << 0) + /* * Zone descriptor. */ @@ -115,7 +121,6 @@ enum { DMZ_BUF, /* Zone internal state */ - DMZ_ACTIVE, DMZ_RECLAIM, DMZ_SEQ_WRITE_ERR, }; @@ -128,7 +133,6 @@ enum { #define dmz_is_empty(z) ((z)->wp_block == 0) #define dmz_is_offline(z) test_bit(DMZ_OFFLINE, &(z)->flags) #define dmz_is_readonly(z) test_bit(DMZ_READ_ONLY, &(z)->flags) -#define dmz_is_active(z) test_bit(DMZ_ACTIVE, &(z)->flags) #define dmz_in_reclaim(z) test_bit(DMZ_RECLAIM, &(z)->flags) #define dmz_seq_write_err(z) test_bit(DMZ_SEQ_WRITE_ERR, &(z)->flags) @@ -188,8 +192,30 @@ void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone); unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd); unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd); -void dmz_activate_zone(struct dm_zone *zone); -void dmz_deactivate_zone(struct dm_zone *zone); +/* + * Activate a zone (increment its reference count). + */ +static inline void dmz_activate_zone(struct dm_zone *zone) +{ + atomic_inc(&zone->refcount); +} + +/* + * Deactivate a zone. This decrement the zone reference counter + * indicating that all BIOs to the zone have completed when the count is 0. + */ +static inline void dmz_deactivate_zone(struct dm_zone *zone) +{ + atomic_dec(&zone->refcount); +} + +/* + * Test if a zone is active, that is, has a refcount > 0. + */ +static inline bool dmz_is_active(struct dm_zone *zone) +{ + return atomic_read(&zone->refcount); +} int dmz_lock_zone_reclaim(struct dm_zone *zone); void dmz_unlock_zone_reclaim(struct dm_zone *zone); @@ -225,4 +251,10 @@ void dmz_resume_reclaim(struct dmz_reclaim *zrc); void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc); void dmz_schedule_reclaim(struct dmz_reclaim *zrc); +/* + * Functions defined in dm-zoned-target.c + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); +bool dmz_check_bdev(struct dmz_dev *dmz_dev); + #endif /* DM_ZONED_H */ diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 717aaffc227d..10057ac85476 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1128,7 +1128,7 @@ int cluster_check_sync_size(struct mddev *mddev) bm_lockres = lockres_init(mddev, str, NULL, 1); if (!bm_lockres) { pr_err("md-cluster: Cannot initialize %s\n", str); - bitmap_free(bitmap); + md_bitmap_free(bitmap); return -1; } bm_lockres->flags |= DLM_LKF_NOQUEUE; @@ -1142,11 +1142,11 @@ int cluster_check_sync_size(struct mddev *mddev) sync_size = sb->sync_size; else if (sync_size != sb->sync_size) { kunmap_atomic(sb); - bitmap_free(bitmap); + md_bitmap_free(bitmap); return -1; } kunmap_atomic(sb); - bitmap_free(bitmap); + md_bitmap_free(bitmap); } return (my_sync_size == sync_size) ? 0 : -1; diff --git a/drivers/md/md.c b/drivers/md/md.c index 5599712d478e..b942c74f1ce8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1763,8 +1763,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_BITMAP)) rdev->saved_raid_disk = -1; - } else - set_bit(In_sync, &rdev->flags); + } else { + /* + * If the array is FROZEN, then the device can't + * be in_sync with rest of array. + */ + if (!test_bit(MD_RECOVERY_FROZEN, + &mddev->recovery)) + set_bit(In_sync, &rdev->flags); + } rdev->raid_disk = role; break; } @@ -2845,8 +2852,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = 0; } } else if (cmd_match(buf, "re-add")) { - if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && - rdev->saved_raid_disk >= 0) { + if (!rdev->mddev->pers) + err = -EINVAL; + else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && + rdev->saved_raid_disk >= 0) { /* clear_bit is performed _after_ all the devices * have their local Faulty bit cleared. If any writes * happen in the meantime in the local node, they @@ -4099,7 +4108,7 @@ array_state_show(struct mddev *mddev, char *page) { enum array_state st = inactive; - if (mddev->pers) + if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) switch(mddev->ro) { case 1: st = readonly; @@ -5660,9 +5669,6 @@ int md_run(struct mddev *mddev) md_update_sb(mddev, 0); md_new_event(mddev); - sysfs_notify_dirent_safe(mddev->sysfs_state); - sysfs_notify_dirent_safe(mddev->sysfs_action); - sysfs_notify(&mddev->kobj, NULL, "degraded"); return 0; abort: @@ -5683,6 +5689,7 @@ static int do_md_run(struct mddev *mddev) { int err; + set_bit(MD_NOT_READY, &mddev->flags); err = md_run(mddev); if (err) goto out; @@ -5700,9 +5707,14 @@ static int do_md_run(struct mddev *mddev) set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); + clear_bit(MD_NOT_READY, &mddev->flags); mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); + sysfs_notify_dirent_safe(mddev->sysfs_state); + sysfs_notify_dirent_safe(mddev->sysfs_action); + sysfs_notify(&mddev->kobj, NULL, "degraded"); out: + clear_bit(MD_NOT_READY, &mddev->flags); return err; } @@ -7603,9 +7615,9 @@ static void status_unused(struct seq_file *seq) static int status_resync(struct seq_file *seq, struct mddev *mddev) { sector_t max_sectors, resync, res; - unsigned long dt, db; - sector_t rt; - int scale; + unsigned long dt, db = 0; + sector_t rt, curr_mark_cnt, resync_mark_cnt; + int scale, recovery_active; unsigned int per_milli; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || @@ -7675,22 +7687,30 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev) * db: blocks written from mark until now * rt: remaining time * - * rt is a sector_t, so could be 32bit or 64bit. - * So we divide before multiply in case it is 32bit and close - * to the limit. - * We scale the divisor (db) by 32 to avoid losing precision - * near the end of resync when the number of remaining sectors - * is close to 'db'. - * We then divide rt by 32 after multiplying by db to compensate. - * The '+1' avoids division by zero if db is very small. + * rt is a sector_t, which is always 64bit now. We are keeping + * the original algorithm, but it is not really necessary. + * + * Original algorithm: + * So we divide before multiply in case it is 32bit and close + * to the limit. + * We scale the divisor (db) by 32 to avoid losing precision + * near the end of resync when the number of remaining sectors + * is close to 'db'. + * We then divide rt by 32 after multiplying by db to compensate. + * The '+1' avoids division by zero if db is very small. */ dt = ((jiffies - mddev->resync_mark) / HZ); if (!dt) dt++; - db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active)) - - mddev->resync_mark_cnt; + + curr_mark_cnt = mddev->curr_mark_cnt; + recovery_active = atomic_read(&mddev->recovery_active); + resync_mark_cnt = mddev->resync_mark_cnt; + + if (curr_mark_cnt >= (recovery_active + resync_mark_cnt)) + db = curr_mark_cnt - (recovery_active + resync_mark_cnt); rt = max_sectors - resync; /* number of remaining sectors */ - sector_div(rt, db/32+1); + rt = div64_u64(rt, db/32+1); rt *= dt; rt >>= 5; @@ -8716,6 +8736,18 @@ static void md_start_sync(struct work_struct *ws) */ void md_check_recovery(struct mddev *mddev) { + if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) { + /* Write superblock - thread that called mddev_suspend() + * holds reconfig_mutex for us. + */ + set_bit(MD_UPDATING_SB, &mddev->flags); + smp_mb__after_atomic(); + if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags)) + md_update_sb(mddev, 0); + clear_bit_unlock(MD_UPDATING_SB, &mddev->flags); + wake_up(&mddev->sb_wait); + } + if (mddev->suspended) return; @@ -8745,6 +8777,7 @@ void md_check_recovery(struct mddev *mddev) if (mddev_trylock(mddev)) { int spares = 0; + bool try_set_sync = mddev->safemode != 0; if (!mddev->external && mddev->safemode == 1) mddev->safemode = 0; @@ -8790,7 +8823,7 @@ void md_check_recovery(struct mddev *mddev) } } - if (!mddev->external && !mddev->in_sync) { + if (try_set_sync && !mddev->external && !mddev->in_sync) { spin_lock(&mddev->lock); set_in_sync(mddev); spin_unlock(&mddev->lock); @@ -8875,16 +8908,6 @@ void md_check_recovery(struct mddev *mddev) unlock: wake_up(&mddev->sb_wait); mddev_unlock(mddev); - } else if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) { - /* Write superblock - thread that called mddev_suspend() - * holds reconfig_mutex for us. - */ - set_bit(MD_UPDATING_SB, &mddev->flags); - smp_mb__after_atomic(); - if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags)) - md_update_sb(mddev, 0); - clear_bit_unlock(MD_UPDATING_SB, &mddev->flags); - wake_up(&mddev->sb_wait); } } EXPORT_SYMBOL(md_check_recovery); @@ -8896,7 +8919,8 @@ void md_reap_sync_thread(struct mddev *mddev) /* resync has finished, collect result */ md_unregister_thread(&mddev->sync_thread); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { + !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && + mddev->degraded != mddev->raid_disks) { /* success...*/ /* activate any spares */ if (mddev->pers->spare_active(mddev)) { diff --git a/drivers/md/md.h b/drivers/md/md.h index 11696aba94e3..69bc0d5550cd 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -243,6 +243,9 @@ enum mddev_flags { MD_UPDATING_SB, /* md_check_recovery is updating the metadata * without explicitly holding reconfig_mutex. */ + MD_NOT_READY, /* do_md_run() is active, so 'array_state' + * must not report that array is ready yet + */ }; enum mddev_sb_flags { diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 21ea537bd55e..eff04fa23dfa 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -203,7 +203,13 @@ static void __rebalance2(struct dm_btree_info *info, struct btree_node *parent, struct btree_node *right = r->n; uint32_t nr_left = le32_to_cpu(left->header.nr_entries); uint32_t nr_right = le32_to_cpu(right->header.nr_entries); - unsigned threshold = 2 * merge_threshold(left) + 1; + /* + * Ensure the number of entries in each child will be greater + * than or equal to (max_entries / 3 + 1), so no matter which + * child is used for removal, the number will still be not + * less than (max_entries / 3). + */ + unsigned int threshold = 2 * (merge_threshold(left) + 1); if (nr_left + nr_right < threshold) { /* diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 58b319757b1e..8aae0624a297 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -628,39 +628,40 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) new_parent = shadow_current(s); + pn = dm_block_data(new_parent); + size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ? + sizeof(__le64) : s->info->value_type.size; + + /* create & init the left block */ r = new_block(s->info, &left); if (r < 0) return r; + ln = dm_block_data(left); + nr_left = le32_to_cpu(pn->header.nr_entries) / 2; + + ln->header.flags = pn->header.flags; + ln->header.nr_entries = cpu_to_le32(nr_left); + ln->header.max_entries = pn->header.max_entries; + ln->header.value_size = pn->header.value_size; + memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0])); + memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size); + + /* create & init the right block */ r = new_block(s->info, &right); if (r < 0) { unlock_block(s->info, left); return r; } - pn = dm_block_data(new_parent); - ln = dm_block_data(left); rn = dm_block_data(right); - - nr_left = le32_to_cpu(pn->header.nr_entries) / 2; nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left; - ln->header.flags = pn->header.flags; - ln->header.nr_entries = cpu_to_le32(nr_left); - ln->header.max_entries = pn->header.max_entries; - ln->header.value_size = pn->header.value_size; - rn->header.flags = pn->header.flags; rn->header.nr_entries = cpu_to_le32(nr_right); rn->header.max_entries = pn->header.max_entries; rn->header.value_size = pn->header.value_size; - - memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0])); memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0])); - - size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ? - sizeof(__le64) : s->info->value_type.size; - memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size); memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left), nr_right * size); diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 4aed69d9dd17..b23cac2c4738 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -248,7 +248,7 @@ static int out(struct sm_metadata *smm) } if (smm->recursion_count == 1) - apply_bops(smm); + r = apply_bops(smm); smm->recursion_count--; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 5ecba9eef441..cdafa5e0ea6d 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -26,6 +26,9 @@ #include "raid0.h" #include "raid5.h" +static int default_layout = 0; +module_param(default_layout, int, 0644); + #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ @@ -91,7 +94,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) char b[BDEVNAME_SIZE]; char b2[BDEVNAME_SIZE]; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - unsigned short blksize = 512; + unsigned blksize = 512; *private_conf = ERR_PTR(-ENOMEM); if (!conf) @@ -146,6 +149,19 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); + + if (conf->nr_strip_zones == 1) { + conf->layout = RAID0_ORIG_LAYOUT; + } else if (default_layout == RAID0_ORIG_LAYOUT || + default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = default_layout; + } else { + pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", + mdname(mddev)); + pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); + err = -ENOTSUPP; + goto abort; + } /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size @@ -552,10 +568,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) static bool raid0_make_request(struct mddev *mddev, struct bio *bio) { + struct r0conf *conf = mddev->private; struct strip_zone *zone; struct md_rdev *tmp_dev; sector_t bio_sector; sector_t sector; + sector_t orig_sector; unsigned chunk_sects; unsigned sectors; @@ -588,8 +606,21 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } + orig_sector = sector; zone = find_zone(mddev->private, §or); - tmp_dev = map_sector(mddev, zone, sector, §or); + switch (conf->layout) { + case RAID0_ORIG_LAYOUT: + tmp_dev = map_sector(mddev, zone, orig_sector, §or); + break; + case RAID0_ALT_MULTIZONE_LAYOUT: + tmp_dev = map_sector(mddev, zone, sector, §or); + break; + default: + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); + bio_io_error(bio); + return true; + } + bio_set_dev(bio, tmp_dev->bdev); bio->bi_iter.bi_sector = sector + zone->dev_start + tmp_dev->data_offset; diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 540e65d92642..3816e5477db1 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -8,11 +8,25 @@ struct strip_zone { int nb_dev; /* # of devices attached to the zone */ }; +/* Linux 3.14 (20d0189b101) made an unintended change to + * the RAID0 layout for multi-zone arrays (where devices aren't all + * the same size. + * RAID0_ORIG_LAYOUT restores the original layout + * RAID0_ALT_MULTIZONE_LAYOUT uses the altered layout + * The layouts are identical when there is only one zone (all + * devices the same size). + */ + +enum r0layout { + RAID0_ORIG_LAYOUT = 1, + RAID0_ALT_MULTIZONE_LAYOUT = 2, +}; struct r0conf { struct strip_zone *strip_zone; struct md_rdev **devlist; /* lists of rdevs, pointed to * by strip_zone->dev */ int nr_strip_zones; + enum r0layout layout; }; #endif diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 205f86f1a6cb..0a9d623b13c2 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -435,19 +435,21 @@ static void raid1_end_write_request(struct bio *bio) /* We never try FailFast to WriteMostly devices */ !test_bit(WriteMostly, &rdev->flags)) { md_error(r1_bio->mddev, rdev); - if (!test_bit(Faulty, &rdev->flags)) - /* This is the only remaining device, - * We need to retry the write without - * FailFast - */ - set_bit(R1BIO_WriteError, &r1_bio->state); - else { - /* Finished with this branch */ - r1_bio->bios[mirror] = NULL; - to_put = bio; - } - } else + } + + /* + * When the device is faulty, it is not necessary to + * handle write error. + * For failfast, this is the only remaining device, + * We need to retry the write without FailFast. + */ + if (!test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_WriteError, &r1_bio->state); + else { + /* Finished with this branch */ + r1_bio->bios[mirror] = NULL; + to_put = bio; + } } else { /* * Set R1BIO_Uptodate in our master bio, so that we @@ -1854,6 +1856,20 @@ static void end_sync_read(struct bio *bio) reschedule_retry(r1_bio); } +static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) +{ + sector_t sync_blocks = 0; + sector_t s = r1_bio->sector; + long sectors_to_go = r1_bio->sectors; + + /* make sure these bits don't get cleared. */ + do { + bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); + s += sync_blocks; + sectors_to_go -= sync_blocks; + } while (sectors_to_go > 0); +} + static void end_sync_write(struct bio *bio) { int uptodate = !bio->bi_status; @@ -1865,16 +1881,7 @@ static void end_sync_write(struct bio *bio) struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; if (!uptodate) { - sector_t sync_blocks = 0; - sector_t s = r1_bio->sector; - long sectors_to_go = r1_bio->sectors; - /* make sure these bits doesn't get cleared. */ - do { - bitmap_end_sync(mddev->bitmap, s, - &sync_blocks, 1); - s += sync_blocks; - sectors_to_go -= sync_blocks; - } while (sectors_to_go > 0); + abort_sync_write(mddev, r1_bio); set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -2164,8 +2171,10 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) (i == r1_bio->read_disk || !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)))) continue; - if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) + if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) { + abort_sync_write(mddev, r1_bio); continue; + } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) @@ -2740,7 +2749,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, write_targets++; } } - if (bio->bi_end_io) { + if (rdev && bio->bi_end_io) { atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; bio_set_dev(bio, rdev->bdev); @@ -3090,6 +3099,13 @@ static int raid1_run(struct mddev *mddev) !test_bit(In_sync, &conf->mirrors[i].rdev->flags) || test_bit(Faulty, &conf->mirrors[i].rdev->flags)) mddev->degraded++; + /* + * RAID1 needs at least one disk in active + */ + if (conf->raid_disks - mddev->degraded < 1) { + ret = -EINVAL; + goto abort; + } if (conf->raid_disks - mddev->degraded == 1) mddev->recovery_cp = MaxSector; @@ -3123,8 +3139,12 @@ static int raid1_run(struct mddev *mddev) ret = md_integrity_register(mddev); if (ret) { md_unregister_thread(&mddev->thread); - raid1_free(mddev, conf); + goto abort; } + return 0; + +abort: + raid1_free(mddev, conf); return ret; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 52ddfa0fca94..d08d77b9674f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -226,7 +226,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: @@ -1190,7 +1190,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, struct bio *split = bio_split(bio, max_sectors, gfp, conf->bio_split); bio_chain(split, bio); + allow_barrier(conf); generic_make_request(bio); + wait_barrier(conf); bio = split; r10_bio->master_bio = bio; r10_bio->sectors = max_sectors; @@ -1479,7 +1481,9 @@ retry_write: struct bio *split = bio_split(bio, r10_bio->sectors, GFP_NOIO, conf->bio_split); bio_chain(split, bio); + allow_barrier(conf); generic_make_request(bio); + wait_barrier(conf); bio = split; r10_bio->master_bio = bio; } @@ -3817,6 +3821,8 @@ static int raid10_run(struct mddev *mddev) set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); mddev->sync_thread = md_register_thread(md_do_sync, mddev, "reshape"); + if (!mddev->sync_thread) + goto out_free_conf; } return 0; @@ -4491,7 +4497,6 @@ read_more: atomic_inc(&r10_bio->remaining); read_bio->bi_next = NULL; generic_make_request(read_bio); - sector_nr += nr_sectors; sectors_done += nr_sectors; if (sector_nr <= last) goto read_more; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7dbb74cd506a..d5c14d56a714 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2538,7 +2538,8 @@ static void raid5_end_read_request(struct bio * bi) int set_bad = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); - atomic_inc(&rdev->read_errors); + if (!(bi->bi_status == BLK_STS_PROTECTION)) + atomic_inc(&rdev->read_errors); if (test_bit(R5_ReadRepl, &sh->dev[i].flags)) pr_warn_ratelimited( "md/raid:%s: read error on replacement device (sector %llu on %s).\n", @@ -2570,7 +2571,9 @@ static void raid5_end_read_request(struct bio * bi) && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) retry = 1; if (retry) - if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) { + if (sh->qd_idx >= 0 && sh->pd_idx == i) + set_bit(R5_ReadError, &sh->dev[i].flags); + else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) { set_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); } else @@ -4182,7 +4185,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, /* now write out any block on a failed drive, * or P or Q if they were recomputed */ - BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */ + dev = NULL; if (s->failed == 2) { dev = &sh->dev[s->failed_num[1]]; s->locked++; @@ -4207,6 +4210,14 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantwrite, &dev->flags); } + if (WARN_ONCE(dev && !test_bit(R5_UPTODATE, &dev->flags), + "%s: disk%td not up to date\n", + mdname(conf->mddev), + dev - (struct r5dev *) &sh->dev)) { + clear_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_Wantwrite, &dev->flags); + s->locked--; + } clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); @@ -5710,7 +5721,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) do_flush = false; } - set_bit(STRIPE_HANDLE, &sh->state); + if (!sh->batch_head || sh == sh->batch_head) + set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); if ((!sh->batch_head || sh == sh->batch_head) && (bi->bi_opf & REQ_SYNC) && @@ -7370,6 +7382,8 @@ static int raid5_run(struct mddev *mddev) set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); mddev->sync_thread = md_register_thread(md_do_sync, mddev, "reshape"); + if (!mddev->sync_thread) + goto abort; } /* Ok, everything is just fine now */ |