diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/alloc.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/bcache.h | 2 | ||||
-rw-r--r-- | drivers/md/bcache/btree.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/closure.h | 3 | ||||
-rw-r--r-- | drivers/md/bcache/debug.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/extents.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/request.c | 9 | ||||
-rw-r--r-- | drivers/md/bcache/request.h | 2 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 113 | ||||
-rw-r--r-- | drivers/md/bcache/sysfs.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-flakey.c | 30 | ||||
-rw-r--r-- | drivers/md/dm-integrity.c | 26 | ||||
-rw-r--r-- | drivers/md/dm-linear.c | 35 | ||||
-rw-r--r-- | drivers/md/dm-table.c | 10 | ||||
-rw-r--r-- | drivers/md/dm-verity-fec.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-zoned-target.c | 3 | ||||
-rw-r--r-- | drivers/md/dm.c | 169 | ||||
-rw-r--r-- | drivers/md/raid0.c | 2 |
18 files changed, 270 insertions, 149 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 7a28232d868b..5002838ea476 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -484,7 +484,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve, int i; lockdep_assert_held(&c->bucket_lock); - BUG_ON(!n || n > c->caches_loaded || n > 8); + BUG_ON(!n || n > c->caches_loaded || n > MAX_CACHES_PER_SET); bkey_init(k); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 954dad29e6e8..b61b83bbcfff 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -1004,7 +1004,7 @@ void bch_open_buckets_free(struct cache_set *c); int bch_cache_allocator_start(struct cache *ca); void bch_debug_exit(void); -void bch_debug_init(struct kobject *kobj); +void bch_debug_init(void); void bch_request_exit(void); int bch_request_init(void); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index e7d4817681f2..3f4211b5cd33 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -2434,7 +2434,7 @@ static int refill_keybuf_fn(struct btree_op *op, struct btree *b, struct keybuf *buf = refill->buf; int ret = MAP_CONTINUE; - if (bkey_cmp(k, refill->end) >= 0) { + if (bkey_cmp(k, refill->end) > 0) { ret = MAP_DONE; goto out; } diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h index eca0d496b686..c88cdc4ae4ec 100644 --- a/drivers/md/bcache/closure.h +++ b/drivers/md/bcache/closure.h @@ -345,7 +345,8 @@ do { \ } while (0) /** - * closure_return - finish execution of a closure, with destructor + * closure_return_with_destructor - finish execution of a closure, + * with destructor * * Works like closure_return(), except @destructor will be called when all * outstanding refs on @cl have been dropped; @destructor may be used to safely diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 06da66b2488a..8f448b9c96a1 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -253,7 +253,7 @@ void bch_debug_exit(void) debugfs_remove_recursive(bcache_debug); } -void __init bch_debug_init(struct kobject *kobj) +void __init bch_debug_init(void) { /* * it is unnecessary to check return value of diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index c809724e6571..956004366699 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -553,7 +553,7 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k) for (i = 0; i < KEY_PTRS(k); i++) { stale = ptr_stale(b->c, k, i); - btree_bug_on(stale > 96, b, + btree_bug_on(stale > BUCKET_GC_GEN_MAX, b, "key too stale: %i, need_gc %u", stale, b->c->need_gc); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 51be355a3309..3bf35914bb57 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -395,7 +395,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) * unless the read-ahead request is for metadata (eg, for gfs2). */ if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) && - !(bio->bi_opf & REQ_META)) + !(bio->bi_opf & REQ_PRIO)) goto skip; if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) || @@ -850,7 +850,7 @@ static void cached_dev_read_done_bh(struct closure *cl) bch_mark_cache_accounting(s->iop.c, s->d, !s->cache_missed, s->iop.bypass); - trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass); + trace_bcache_read(s->orig_bio, !s->cache_missed, s->iop.bypass); if (s->iop.status) continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq); @@ -877,7 +877,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, } if (!(bio->bi_opf & REQ_RAHEAD) && - !(bio->bi_opf & REQ_META) && + !(bio->bi_opf & REQ_PRIO) && s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA) reada = min_t(sector_t, dc->readahead >> 9, get_capacity(bio->bi_disk) - bio_end_sector(bio)); @@ -1218,6 +1218,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, { struct cached_dev *dc = container_of(d, struct cached_dev, disk); + if (dc->io_disable) + return -EIO; + return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); } diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index aa055cfeb099..721bf336ed1a 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -39,6 +39,6 @@ void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); -extern struct kmem_cache *bch_search_cache, *bch_passthrough_cache; +extern struct kmem_cache *bch_search_cache; #endif /* _BCACHE_REQUEST_H_ */ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 30ba9aeb5ee8..7bbd670a5a84 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -418,6 +418,7 @@ static int __uuid_write(struct cache_set *c) { BKEY_PADDED(key) k; struct closure cl; + struct cache *ca; closure_init_stack(&cl); lockdep_assert_held(&bch_register_lock); @@ -429,6 +430,10 @@ static int __uuid_write(struct cache_set *c) uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl); closure_sync(&cl); + /* Only one bucket used for uuid write */ + ca = PTR_CACHE(c, &k.key, 0); + atomic_long_add(ca->sb.bucket_size, &ca->meta_sectors_written); + bkey_copy(&c->uuid_bucket, &k.key); bkey_put(c, &k.key); return 0; @@ -643,10 +648,6 @@ static int ioctl_dev(struct block_device *b, fmode_t mode, unsigned int cmd, unsigned long arg) { struct bcache_device *d = b->bd_disk->private_data; - struct cached_dev *dc = container_of(d, struct cached_dev, disk); - - if (dc->io_disable) - return -EIO; return d->ioctl(d, mode, cmd, arg); } @@ -1008,6 +1009,7 @@ 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); @@ -1152,11 +1154,12 @@ 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); bch_writeback_queue(dc); } + bch_sectors_dirty_init(&dc->disk); + bch_cached_dev_run(dc); bcache_device_link(&dc->disk, c, "bdev"); atomic_inc(&c->attached_dev_nr); @@ -2049,6 +2052,8 @@ static int cache_alloc(struct cache *ca) size_t free; size_t btree_buckets; struct bucket *b; + int ret = -ENOMEM; + const char *err = NULL; __module_get(THIS_MODULE); kobject_init(&ca->kobj, &bch_cache_ktype); @@ -2066,27 +2071,93 @@ static int cache_alloc(struct cache *ca) */ btree_buckets = ca->sb.njournal_buckets ?: 8; free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; + if (!free) { + ret = -EPERM; + err = "ca->sb.nbuckets is too small"; + goto err_free; + } - if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) || - !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || - !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) || - !init_heap(&ca->heap, free << 3, GFP_KERNEL) || - !(ca->buckets = vzalloc(array_size(sizeof(struct bucket), - ca->sb.nbuckets))) || - !(ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t), - prio_buckets(ca), 2), - GFP_KERNEL)) || - !(ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca))) - return -ENOMEM; + if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, + GFP_KERNEL)) { + err = "ca->free[RESERVE_BTREE] alloc failed"; + goto err_btree_alloc; + } + + if (!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), + GFP_KERNEL)) { + err = "ca->free[RESERVE_PRIO] alloc failed"; + goto err_prio_alloc; + } + + if (!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL)) { + err = "ca->free[RESERVE_MOVINGGC] alloc failed"; + goto err_movinggc_alloc; + } + + if (!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL)) { + err = "ca->free[RESERVE_NONE] alloc failed"; + goto err_none_alloc; + } + + if (!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL)) { + err = "ca->free_inc alloc failed"; + goto err_free_inc_alloc; + } + + if (!init_heap(&ca->heap, free << 3, GFP_KERNEL)) { + err = "ca->heap alloc failed"; + goto err_heap_alloc; + } + + ca->buckets = vzalloc(array_size(sizeof(struct bucket), + ca->sb.nbuckets)); + if (!ca->buckets) { + err = "ca->buckets alloc failed"; + goto err_buckets_alloc; + } + + ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t), + prio_buckets(ca), 2), + GFP_KERNEL); + if (!ca->prio_buckets) { + err = "ca->prio_buckets alloc failed"; + goto err_prio_buckets_alloc; + } + + ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca); + if (!ca->disk_buckets) { + err = "ca->disk_buckets alloc failed"; + goto err_disk_buckets_alloc; + } ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca); for_each_bucket(b, ca) atomic_set(&b->pin, 0); - return 0; + +err_disk_buckets_alloc: + kfree(ca->prio_buckets); +err_prio_buckets_alloc: + vfree(ca->buckets); +err_buckets_alloc: + free_heap(&ca->heap); +err_heap_alloc: + free_fifo(&ca->free_inc); +err_free_inc_alloc: + free_fifo(&ca->free[RESERVE_NONE]); +err_none_alloc: + free_fifo(&ca->free[RESERVE_MOVINGGC]); +err_movinggc_alloc: + free_fifo(&ca->free[RESERVE_PRIO]); +err_prio_alloc: + free_fifo(&ca->free[RESERVE_BTREE]); +err_btree_alloc: +err_free: + module_put(THIS_MODULE); + if (err) + pr_notice("error %s: %s", ca->cache_dev_name, err); + return ret; } static int register_cache(struct cache_sb *sb, struct page *sb_page, @@ -2112,6 +2183,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; + else if (ret == -EPERM) + err = "cache_alloc(): cache device is too small"; else err = "cache_alloc(): unknown error"; goto err; @@ -2386,7 +2459,7 @@ static int __init bcache_init(void) sysfs_create_files(bcache_kobj, files)) goto err; - bch_debug_init(bcache_kobj); + bch_debug_init(); closure_debug_init(); return 0; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 150cf4f4cf74..26f035a0c5b9 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -285,6 +285,7 @@ STORE(__cached_dev) 1, WRITEBACK_RATE_UPDATE_SECS_MAX); d_strtoul(writeback_rate_i_term_inverse); d_strtoul_nonzero(writeback_rate_p_term_inverse); + d_strtoul_nonzero(writeback_rate_minimum); sysfs_strtoul_clamp(io_error_limit, dc->error_limit, 0, INT_MAX); @@ -412,6 +413,7 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_update_seconds, &sysfs_writeback_rate_i_term_inverse, &sysfs_writeback_rate_p_term_inverse, + &sysfs_writeback_rate_minimum, &sysfs_writeback_rate_debug, &sysfs_errors, &sysfs_io_error_limit, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 32aabe27b37c..3cb97fa4c11d 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -315,10 +315,6 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) if (bio_op(bio) == REQ_OP_ZONE_RESET) goto map_bio; - /* We need to remap reported zones, so remember the BIO iter */ - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - goto map_bio; - /* Are we alive ? */ elapsed = (jiffies - fc->start_time) / HZ; if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) { @@ -380,11 +376,6 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, if (bio_op(bio) == REQ_OP_ZONE_RESET) return DM_ENDIO_DONE; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) { - dm_remap_zone_report(ti, bio, fc->start); - return DM_ENDIO_DONE; - } - if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && all_corrupt_bio_flags_match(bio, fc)) { @@ -457,6 +448,26 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int flakey_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct flakey_c *fc = ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, fc->start, zones, nr_zones); + return 0; +} +#endif + static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct flakey_c *fc = ti->private; @@ -469,6 +480,7 @@ static struct target_type flakey_target = { .version = {1, 5, 0}, #ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM, + .report_zones = flakey_report_zones, #endif .module = THIS_MODULE, .ctr = flakey_ctr, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 89ccb64342de..bb3096bf2cc6 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -559,7 +559,12 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result } memset(result + size, 0, JOURNAL_MAC_SIZE - size); } else { - __u8 digest[size]; + __u8 digest[HASH_MAX_DIGESTSIZE]; + + if (WARN_ON(size > sizeof(digest))) { + dm_integrity_io_error(ic, "digest_size", -EINVAL); + goto err; + } r = crypto_shash_final(desc, digest); if (unlikely(r)) { dm_integrity_io_error(ic, "crypto_shash_final", r); @@ -1324,7 +1329,7 @@ static void integrity_metadata(struct work_struct *w) struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); char *checksums; unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0; - char checksums_onstack[ic->tag_size + extra_space]; + char checksums_onstack[HASH_MAX_DIGESTSIZE]; unsigned sectors_to_process = dio->range.n_sectors; sector_t sector = dio->range.logical_sector; @@ -1333,8 +1338,14 @@ static void integrity_metadata(struct work_struct *w) checksums = kmalloc((PAGE_SIZE >> SECTOR_SHIFT >> ic->sb->log2_sectors_per_block) * ic->tag_size + extra_space, GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN); - if (!checksums) + if (!checksums) { checksums = checksums_onstack; + if (WARN_ON(extra_space && + digest_size > sizeof(checksums_onstack))) { + r = -EINVAL; + goto error; + } + } __bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) { unsigned pos; @@ -1546,7 +1557,7 @@ retry_kmap: } while (++s < ic->sectors_per_block); #ifdef INTERNAL_VERIFY if (ic->internal_hash) { - char checksums_onstack[max(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)]; + char checksums_onstack[max(HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)]; 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))) { @@ -1596,7 +1607,7 @@ retry_kmap: if (ic->internal_hash) { unsigned digest_size = crypto_shash_digestsize(ic->internal_hash); if (unlikely(digest_size > ic->tag_size)) { - char checksums_onstack[digest_size]; + char checksums_onstack[HASH_MAX_DIGESTSIZE]; integrity_sector_checksum(ic, logical_sector, (char *)js, checksums_onstack); memcpy(journal_entry_tag(ic, je), checksums_onstack, ic->tag_size); } else @@ -2023,7 +2034,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, unlikely(from_replay) && #endif ic->internal_hash) { - char test_tag[max(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)]; + char test_tag[max_t(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)]; integrity_sector_checksum(ic, sec + ((l - j) << ic->sb->log2_sectors_per_block), (char *)access_journal_data(ic, i, l), test_tag); @@ -3462,7 +3473,8 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - ic->recalc_tags = kvmalloc((RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size, GFP_KERNEL); + ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block, + ic->tag_size, GFP_KERNEL); if (!ic->recalc_tags) { ti->error = "Cannot allocate tags for recalculating"; r = -ENOMEM; diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 2f7c44a006c4..8d7ddee6ac4d 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -102,19 +102,6 @@ static int linear_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -#ifdef CONFIG_BLK_DEV_ZONED -static int linear_end_io(struct dm_target *ti, struct bio *bio, - blk_status_t *error) -{ - struct linear_c *lc = ti->private; - - if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT) - dm_remap_zone_report(ti, bio, lc->start); - - return DM_ENDIO_DONE; -} -#endif - static void linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { @@ -148,6 +135,26 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int linear_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct linear_c *lc = (struct linear_c *) ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, lc->start, zones, nr_zones); + return 0; +} +#endif + static int linear_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { @@ -211,8 +218,8 @@ static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, #ifdef CONFIG_BLK_DEV_ZONED - .end_io = linear_end_io, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, + .report_zones = linear_report_zones, #else .features = DM_TARGET_PASSES_INTEGRITY, #endif diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 49ab0cbef739..9038c302d5c2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1917,6 +1917,16 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + + /* + * For a zoned target, the number of zones should be updated for the + * correct value to be exposed in sysfs queue/nr_zones. For a BIO based + * target, this is all that is needed. For a request based target, the + * queue zone bitmaps must also be updated. + * Use blk_revalidate_disk_zones() to handle this. + */ + if (blk_queue_is_zoned(q)) + blk_revalidate_disk_zones(t->md->disk); } unsigned int dm_table_get_num_targets(struct dm_table *t) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 684af08d0747..0ce04e5b4afb 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -212,12 +212,15 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, struct dm_verity_fec_io *fio = fec_io(io); u64 block, ileaved; u8 *bbuf, *rs_block; - u8 want_digest[v->digest_size]; + u8 want_digest[HASH_MAX_DIGESTSIZE]; unsigned n, k; if (neras) *neras = 0; + if (WARN_ON(v->digest_size > sizeof(want_digest))) + return -EINVAL; + /* * read each of the rsn data blocks that are part of the RS block, and * interleave contents to available bufs diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index fa36825c1eff..981154e59461 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -702,8 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path) dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - dev->nr_zones = (dev->capacity + dev->zone_nr_sectors - 1) - >> dev->zone_nr_sectors_shift; + dev->nr_zones = blkdev_nr_zones(dev->bdev); dmz->dev = dev; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1fbc28ab157c..c510179a7f84 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,6 +458,57 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ +#ifdef CONFIG_BLK_DEV_ZONED + struct mapped_device *md = disk->private_data; + struct dm_target *tgt; + struct dm_table *map; + int srcu_idx, ret; + + if (dm_suspended_md(md)) + return -EAGAIN; + + map = dm_get_live_table(md, &srcu_idx); + if (!map) + return -EIO; + + tgt = dm_table_find_target(map, sector); + if (!dm_target_is_valid(tgt)) { + ret = -EIO; + goto out; + } + + /* + * If we are executing this, we already know that the block device + * is a zoned device and so each target should have support for that + * type of drive. A missing report_zones method means that the target + * driver has a problem. + */ + if (WARN_ON(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } + + /* + * blkdev_report_zones() will loop and call this again to cover all the + * zones of the target, eventually moving on to the next target. + * So there is no need to loop here trying to fill the entire array + * of zones. + */ + ret = tgt->type->report_zones(tgt, sector, zones, + nr_zones, gfp_mask); + +out: + dm_put_live_table(md, srcu_idx); + return ret; +#else + return -ENOTSUPP; +#endif +} + static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) __acquires(md->io_barrier) @@ -1155,93 +1206,49 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) EXPORT_SYMBOL_GPL(dm_accept_partial_bio); /* - * The zone descriptors obtained with a zone report indicate zone positions - * within the target backing device, regardless of that device is a partition - * and regardless of the target mapping start sector on the device or partition. - * The zone descriptors start sector and write pointer position must be adjusted - * to match their relative position within the dm device. - * A target may call dm_remap_zone_report() after completion of a - * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained from the - * backing device. + * The zone descriptors obtained with a zone report indicate + * zone positions within the underlying device of the target. The zone + * descriptors must be remapped to match their position within the dm device. + * The caller target should obtain the zones information using + * blkdev_report_zones() to ensure that remapping for partition offset is + * already handled. */ -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones) { #ifdef CONFIG_BLK_DEV_ZONED - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); - struct bio *report_bio = tio->io->orig_bio; - struct blk_zone_report_hdr *hdr = NULL; struct blk_zone *zone; - unsigned int nr_rep = 0; - unsigned int ofst; - sector_t part_offset; - struct bio_vec bvec; - struct bvec_iter iter; - void *addr; - - if (bio->bi_status) - return; - - /* - * bio sector was incremented by the request size on completion. Taking - * into account the original request sector, the target start offset on - * the backing device and the target mapping offset (ti->begin), the - * start sector of the backing device. The partition offset is always 0 - * if the target uses a whole device. - */ - part_offset = bio->bi_iter.bi_sector + ti->begin - (start + bio_end_sector(report_bio)); + unsigned int nrz = *nr_zones; + int i; /* - * Remap the start sector of the reported zones. For sequential zones, - * also remap the write pointer position. + * Remap the start sector and write pointer position of the zones in + * the array. Since we may have obtained from the target underlying + * device more zones that the target size, also adjust the number + * of zones. */ - bio_for_each_segment(bvec, report_bio, iter) { - addr = kmap_atomic(bvec.bv_page); - - /* Remember the report header in the first page */ - if (!hdr) { - hdr = addr; - ofst = sizeof(struct blk_zone_report_hdr); - } else - ofst = 0; - - /* Set zones start sector */ - while (hdr->nr_zones && ofst < bvec.bv_len) { - zone = addr + ofst; - zone->start -= part_offset; - if (zone->start >= start + ti->len) { - hdr->nr_zones = 0; - break; - } - zone->start = zone->start + ti->begin - start; - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start - part_offset; - } - ofst += sizeof(struct blk_zone); - hdr->nr_zones--; - nr_rep++; + for (i = 0; i < nrz; i++) { + zone = zones + i; + if (zone->start >= start + ti->len) { + memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); + break; } - if (addr != hdr) - kunmap_atomic(addr); + zone->start = zone->start + ti->begin - start; + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + continue; - if (!hdr->nr_zones) - break; - } - - if (hdr) { - hdr->nr_zones = nr_rep; - kunmap_atomic(hdr); + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp = zone->wp + ti->begin - start; } - bio_advance(report_bio, report_bio->bi_iter.bi_size); - + *nr_zones = i; #else /* !CONFIG_BLK_DEV_ZONED */ - bio->bi_status = BLK_STS_NOTSUPP; + *nr_zones = 0; #endif } EXPORT_SYMBOL_GPL(dm_remap_zone_report); @@ -1327,8 +1334,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - if (bio_op(bio) != REQ_OP_ZONE_REPORT) - bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); clone->bi_iter.bi_size = to_bytes(len); if (unlikely(bio_integrity(bio) != NULL)) @@ -1541,7 +1547,6 @@ static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti, */ static int __split_and_process_non_flush(struct clone_info *ci) { - struct bio *bio = ci->bio; struct dm_target *ti; unsigned len; int r; @@ -1553,11 +1558,7 @@ static int __split_and_process_non_flush(struct clone_info *ci) if (unlikely(__process_abnormal_io(ci, ti, &r))) return r; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - len = ci->sector_count; - else - len = min_t(sector_t, max_io_len(ci->sector, ti), - ci->sector_count); + len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count); r = __clone_and_map_data_bio(ci, ti, ci->sector, &len); if (r < 0) @@ -1616,9 +1617,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * We take a clone of the original to store in * ci.io->orig_bio to be used by end_io_acct() and * for dec_pending to use for completion handling. - * As this path is not used for REQ_OP_ZONE_REPORT, - * the usage of io->orig_bio in dm_remap_zone_report() - * won't be affected by this reassignment. */ struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count, GFP_NOIO, &md->queue->bio_split); @@ -3146,6 +3144,7 @@ static const struct block_device_operations dm_blk_dops = { .release = dm_blk_close, .ioctl = dm_blk_ioctl, .getgeo = dm_blk_getgeo, + .report_zones = dm_blk_report_zones, .pr_ops = &dm_pr_ops, .owner = THIS_MODULE }; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index ac1cffd2a09b..f3fb5bb8c82a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -542,7 +542,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) !discard_bio) continue; bio_chain(discard_bio, bio); - bio_clone_blkcg_association(discard_bio, bio); + bio_clone_blkg_association(discard_bio, bio); if (mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rdev->bdev), discard_bio, disk_devt(mddev->gendisk), |