diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/super.c | 7 | ||||
-rw-r--r-- | drivers/md/dm-cache-policy-cleaner.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-exception-store.h | 2 | ||||
-rw-r--r-- | drivers/md/dm-flakey.c | 32 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 7 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 3 | ||||
-rw-r--r-- | drivers/md/dm-snap-persistent.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-snap-transient.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 20 | ||||
-rw-r--r-- | drivers/md/dm-thin-metadata.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-thin.c | 4 | ||||
-rw-r--r-- | drivers/md/dm.c | 5 | ||||
-rw-r--r-- | drivers/md/md.c | 2 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-internal.h | 6 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-remove.c | 29 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-spine.c | 37 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree.c | 29 | ||||
-rw-r--r-- | drivers/md/raid1.c | 2 | ||||
-rw-r--r-- | drivers/md/raid10.c | 7 | ||||
-rw-r--r-- | drivers/md/raid5.c | 4 |
20 files changed, 144 insertions, 69 deletions
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index b4713cea191..2a4c13af482 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1295,6 +1295,9 @@ static void cache_set_flush(struct closure *cl) set_bit(CACHE_SET_STOPPING_2, &c->flags); wake_up(&c->alloc_wait); + if (!c) + closure_return(cl); + bch_cache_accounting_destroy(&c->accounting); kobject_put(&c->internal); @@ -1959,8 +1962,10 @@ static int __init bcache_init(void) closure_debug_init(); bcache_major = register_blkdev(0, "bcache"); - if (bcache_major < 0) + if (bcache_major < 0) { + unregister_reboot_notifier(&reboot); return bcache_major; + } if (!(bcache_wq = create_workqueue("bcache")) || !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) || diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c index b04d1f904d0..2eca9084def 100644 --- a/drivers/md/dm-cache-policy-cleaner.c +++ b/drivers/md/dm-cache-policy-cleaner.c @@ -434,7 +434,7 @@ static struct dm_cache_policy *wb_create(dm_cblock_t cache_size, static struct dm_cache_policy_type wb_policy_type = { .name = "cleaner", .version = {1, 0, 0}, - .hint_size = 0, + .hint_size = 4, .owner = THIS_MODULE, .create = wb_create }; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 0b2536247cf..84e27708ad9 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -70,7 +70,7 @@ struct dm_exception_store_type { * Update the metadata with this exception. */ void (*commit_exception) (struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 7fcf21cb4ff..ace01a30f31 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -286,10 +286,14 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) pb->bio_submitted = true; /* - * Map reads as normal. + * Error reads if neither corrupt_bio_byte or drop_writes are set. + * Otherwise, flakey_end_io() will decide if the reads should be modified. */ - if (bio_data_dir(bio) == READ) + if (bio_data_dir(bio) == READ) { + if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags)) + return -EIO; goto map_bio; + } /* * Drop writes? @@ -325,14 +329,22 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - /* - * Corrupt successful READs while in down state. - * If flags were specified, only corrupt those that match. - */ - if (fc->corrupt_bio_byte && !error && pb->bio_submitted && - (bio_data_dir(bio) == READ) && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) - corrupt_bio_data(bio, fc); + 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)) { + /* + * Corrupt successful matching READs while in down state. + */ + corrupt_bio_data(bio, fc); + + } else if (!test_bit(DROP_WRITES, &fc->flags)) { + /* + * Error read during the down_interval if drop_writes + * wasn't configured. + */ + return -EIO; + } + } return error; } diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 0ba21b0f397..eb7ddb20fd4 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1608,11 +1608,8 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd, /* * Only pass ioctls through if the device sizes match exactly. */ - if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) { - int err = scsi_verify_blk_ioctl(NULL, cmd); - if (err) - r = err; - } + if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) + r = scsi_verify_blk_ioctl(NULL, cmd); if (r == -ENOTCONN && !fatal_signal_pending(current)) queue_work(kmultipathd, &m->process_queued_ios); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 84cddccc024..4805c15185c 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -325,8 +325,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) */ if (min_region_size > (1 << 13)) { /* If not a power of 2, make it the next power of 2 */ - if (min_region_size & (min_region_size - 1)) - region_size = 1 << fls(region_size); + region_size = roundup_pow_of_two(min_region_size); DMINFO("Choosing default region size of %lu sectors", region_size); } else { diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 2d2b1b7588d..8f6d3ea5540 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -646,7 +646,7 @@ static int persistent_prepare_exception(struct dm_exception_store *store, } static void persistent_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { @@ -655,6 +655,9 @@ static void persistent_commit_exception(struct dm_exception_store *store, struct core_exception ce; struct commit_callback *cb; + if (!valid) + ps->valid = 0; + ce.old_chunk = e->old_chunk; ce.new_chunk = e->new_chunk; write_exception(ps, ps->current_committed++, &ce); diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 1ce9a2586e4..31439d53cf7 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -52,12 +52,12 @@ static int transient_prepare_exception(struct dm_exception_store *store, } static void transient_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { /* Just succeed */ - callback(callback_context, 1); + callback(callback_context, valid); } static void transient_usage(struct dm_exception_store *store, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index d892a05c84f..dbd0f00f739 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1388,8 +1388,9 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err) dm_table_event(s->ti->table); } -static void pending_complete(struct dm_snap_pending_exception *pe, int success) +static void pending_complete(void *context, int success) { + struct dm_snap_pending_exception *pe = context; struct dm_exception *e; struct dm_snapshot *s = pe->snap; struct bio *origin_bios = NULL; @@ -1459,24 +1460,13 @@ out: free_pending_exception(pe); } -static void commit_callback(void *context, int success) -{ - struct dm_snap_pending_exception *pe = context; - - pending_complete(pe, success); -} - static void complete_exception(struct dm_snap_pending_exception *pe) { struct dm_snapshot *s = pe->snap; - if (unlikely(pe->copy_error)) - pending_complete(pe, 0); - - else - /* Update the metadata if we are persistent */ - s->store->type->commit_exception(s->store, &pe->e, - commit_callback, pe); + /* Update the metadata if we are persistent */ + s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error, + pending_complete, pe); } /* diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 43f6250baad..4bf9211b274 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1191,6 +1191,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) dm_block_t held_root; /* + * We commit to ensure the btree roots which we increment in a + * moment are up to date. + */ + __commit_transaction(pmd); + + /* * Copy the superblock. */ dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 39996ca58ce..295f74d4f0a 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2109,7 +2109,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) metadata_low_callback, pool); if (r) - goto out_free_pt; + goto out_flags_changed; pt->callbacks.congested_fn = pool_is_congested; dm_table_add_target_callbacks(ti->table, &pt->callbacks); @@ -2281,7 +2281,7 @@ static void pool_postsuspend(struct dm_target *ti) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - cancel_delayed_work(&pool->waker); + cancel_delayed_work_sync(&pool->waker); flush_workqueue(pool->wq); (void) commit_or_fallback(pool); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f69fed826a5..a77ef6cac62 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2323,6 +2323,7 @@ EXPORT_SYMBOL_GPL(dm_device_name); static void __dm_destroy(struct mapped_device *md, bool wait) { + struct request_queue *q = md->queue; struct dm_table *map; might_sleep(); @@ -2333,6 +2334,10 @@ static void __dm_destroy(struct mapped_device *md, bool wait) set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); + /* * Take suspend_lock so that presuspend and postsuspend methods * do not race with internal suspend. diff --git a/drivers/md/md.c b/drivers/md/md.c index 37ff00d014b..7c45286e266 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5306,6 +5306,8 @@ EXPORT_SYMBOL_GPL(md_stop_writes); static void __md_stop(struct mddev *mddev) { mddev->ready = 0; + /* Ensure ->event_work is done */ + flush_workqueue(md_misc_wq); mddev->pers->stop(mddev); if (mddev->pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index bf2b80d5c47..8731b6ea026 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key); extern struct dm_block_validator btree_node_validator; +/* + * Value type for upper levels of multi-level btrees. + */ +extern void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt); + #endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index a03178e91a7..92cd09f3c69 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -301,11 +301,16 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, { int s; uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned target = (nr_left + nr_center + nr_right) / 3; - BUG_ON(target > max_entries); + unsigned total = nr_left + nr_center + nr_right; + unsigned target_right = total / 3; + unsigned remainder = (target_right * 3) != total; + unsigned target_left = target_right + remainder; + + BUG_ON(target_left > max_entries); + BUG_ON(target_right > max_entries); if (nr_left < nr_right) { - s = nr_left - target; + s = nr_left - target_left; if (s < 0 && nr_center < -s) { /* not enough in central node */ @@ -316,10 +321,10 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(left, center, s); - shift(center, right, target - nr_right); + shift(center, right, target_right - nr_right); } else { - s = target - nr_right; + s = target_right - nr_right; if (s > 0 && nr_center < s) { /* not enough in central node */ shift(center, right, nr_center); @@ -329,7 +334,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(center, right, s); - shift(left, center, nr_left - target); + shift(left, center, nr_left - target_left); } *key_ptr(parent, c->index) = center->keys[0]; @@ -544,14 +549,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, return r; } -static struct dm_btree_value_type le64_type = { - .context = NULL, - .size = sizeof(__le64), - .inc = NULL, - .dec = NULL, - .equal = NULL -}; - int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root) { @@ -559,12 +556,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; + struct dm_btree_value_type le64_vt; + init_le64_type(info->tm, &le64_vt); init_shadow_spine(&spine, info); for (level = 0; level < info->levels; level++) { r = remove_raw(&spine, info, (level == last_level ? - &info->value_type : &le64_type), + &info->value_type : &le64_vt), root, keys[level], (unsigned *)&index); if (r < 0) break; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 1b5e13ec7f9..0dee514ba4c 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s) { return s->root; } + +static void le64_inc(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_inc(tm, le64_to_cpu(v_le)); +} + +static void le64_dec(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_dec(tm, le64_to_cpu(v_le)); +} + +static int le64_equal(void *context, const void *value1_le, const void *value2_le) +{ + __le64 v1_le, v2_le; + + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + return v1_le == v2_le; +} + +void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt) +{ + vt->context = tm; + vt->size = sizeof(__le64); + vt->inc = le64_inc; + vt->dec = le64_dec; + vt->equal = le64_equal; +} diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index e3ecb0b824b..b07fcda9ca7 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -235,6 +235,16 @@ static bool is_internal_level(struct dm_btree_info *info, struct frame *f) return f->level < (info->levels - 1); } +static void unlock_all_frames(struct del_stack *s) +{ + struct frame *f; + + while (unprocessed_frames(s)) { + f = s->spine + s->top--; + dm_tm_unlock(s->tm, f->b); + } +} + int dm_btree_del(struct dm_btree_info *info, dm_block_t root) { int r; @@ -290,9 +300,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) f->current_child = f->nr_children; } } - out: + if (r) { + /* cleanup all frames of del_stack */ + unlock_all_frames(s); + } kfree(s); + return r; } EXPORT_SYMBOL_GPL(dm_btree_del); @@ -455,8 +469,10 @@ static int btree_split_sibling(struct shadow_spine *s, dm_block_t root, r = insert_at(sizeof(__le64), pn, parent_index + 1, le64_to_cpu(rn->keys[0]), &location); - if (r) + if (r) { + unlock_block(s->info, right); return r; + } if (key < le64_to_cpu(rn->keys[0])) { unlock_block(s->info, right); @@ -507,7 +523,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) r = new_block(s->info, &right); if (r < 0) { - /* FIXME: put left */ + unlock_block(s->info, left); return r; } @@ -651,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, struct btree_node *n; struct dm_btree_value_type le64_type; - le64_type.context = NULL; - le64_type.size = sizeof(__le64); - le64_type.inc = NULL; - le64_type.dec = NULL; - le64_type.equal = NULL; - + init_le64_type(info->tm, &le64_type); init_shadow_spine(&spine, info); for (level = 0; level < (info->levels - 1); level++) { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 72141ee6070..63d42ae56a1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2147,7 +2147,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) md_trim_bio(wbio, sector - r1_bio->sector, sectors); wbio->bi_sector += rdev->data_offset; wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a1ea2a75391..f53f4f89550 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2597,7 +2597,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) choose_data_offset(r10_bio, rdev) + (sector - r10_bio->sector)); wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* Failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -3578,6 +3578,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) /* far_copies must be 1 */ conf->prev.stride = conf->dev_sectors; } + conf->reshape_safe = conf->reshape_progress; spin_lock_init(&conf->device_lock); INIT_LIST_HEAD(&conf->retry_list); @@ -3785,7 +3786,6 @@ static int run(struct mddev *mddev) } conf->offset_diff = min_offset_diff; - conf->reshape_safe = conf->reshape_progress; clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); @@ -4130,6 +4130,7 @@ static int raid10_start_reshape(struct mddev *mddev) conf->reshape_progress = size; } else conf->reshape_progress = 0; + conf->reshape_safe = conf->reshape_progress; spin_unlock_irq(&conf->device_lock); if (mddev->delta_disks && mddev->bitmap) { @@ -4196,6 +4197,7 @@ abort: rdev->new_data_offset = rdev->data_offset; smp_wmb(); conf->reshape_progress = MaxSector; + conf->reshape_safe = MaxSector; mddev->reshape_position = MaxSector; spin_unlock_irq(&conf->device_lock); return ret; @@ -4543,6 +4545,7 @@ static void end_reshape(struct r10conf *conf) md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; + conf->reshape_safe = MaxSector; spin_unlock_irq(&conf->device_lock); /* read-ahead size must cover two whole stripes, which is diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ef18ca745b1..9ee3c460fa3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5658,8 +5658,8 @@ static int run(struct mddev *mddev) } if (discard_supported && - mddev->queue->limits.max_discard_sectors >= stripe && - mddev->queue->limits.discard_granularity >= stripe) + mddev->queue->limits.max_discard_sectors >= (stripe >> 9) && + mddev->queue->limits.discard_granularity >= stripe) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); else |