diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/journal.c | 11 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-cache-metadata.c | 9 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 9 | ||||
-rw-r--r-- | drivers/md/dm-delay.c | 3 | ||||
-rw-r--r-- | drivers/md/dm-integrity.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-zoned-metadata.c | 5 | ||||
-rw-r--r-- | drivers/md/md.c | 180 | ||||
-rw-r--r-- | drivers/md/md.h | 25 | ||||
-rw-r--r-- | drivers/md/raid5.c | 29 |
11 files changed, 141 insertions, 138 deletions
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index b2fd412715b1..d3725c17ce3a 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -540,11 +540,11 @@ 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); @@ -671,6 +671,9 @@ 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 4dee119c3664..ee36e6b3bcad 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1516,6 +1516,7 @@ 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; @@ -1534,7 +1535,6 @@ static void cache_set_free(struct closure *cl) mempool_exit(&c->search); kfree(c->devices); - mutex_lock(&bch_register_lock); list_del(&c->list); mutex_unlock(&bch_register_lock); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 6fc93834da44..151aa95775be 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1167,11 +1167,18 @@ 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 dd538e6b2748..df39b07de800 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -949,6 +949,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) { #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk); + struct mapped_device *md = dm_table_get_md(ti->table); /* From now we require underlying device with our integrity profile */ if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) { @@ -968,7 +969,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) if (crypt_integrity_aead(cc)) { cc->integrity_tag_size = cc->on_disk_tag_size - cc->integrity_iv_size; - DMINFO("Integrity AEAD, tag size %u, IV size %u.", + DMDEBUG("%s: Integrity AEAD, tag size %u, IV size %u.", dm_device_name(md), cc->integrity_tag_size, cc->integrity_iv_size); if (crypto_aead_setauthsize(any_tfm_aead(cc), cc->integrity_tag_size)) { @@ -976,7 +977,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) return -EINVAL; } } else if (cc->integrity_iv_size) - DMINFO("Additional per-sector space %u bytes for IV.", + DMDEBUG("%s: Additional per-sector space %u bytes for IV.", dm_device_name(md), cc->integrity_iv_size); if ((cc->integrity_tag_size + cc->integrity_iv_size) != bi->tag_size) { @@ -1890,7 +1891,7 @@ static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) * algorithm implementation is used. Help people debug performance * problems by logging the ->cra_driver_name. */ - DMINFO("%s using implementation \"%s\"", ciphermode, + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, crypto_skcipher_alg(any_tfm(cc))->base.cra_driver_name); return 0; } @@ -1910,7 +1911,7 @@ static int crypt_alloc_tfms_aead(struct crypt_config *cc, char *ciphermode) return err; } - DMINFO("%s using implementation \"%s\"", ciphermode, + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, crypto_aead_alg(any_tfm_aead(cc))->base.cra_driver_name); return 0; } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index fddffe251bf6..f496213f8b67 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -121,7 +121,8 @@ 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); if (dc->read.dev) dm_put_device(ti, dc->read.dev); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index f535fd8ac82d..a4fe187d50d0 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2568,7 +2568,7 @@ static int calculate_device_limits(struct dm_integrity_c *ic) if (last_sector < ic->start || last_sector >= ic->meta_device_sectors) return -EINVAL; } else { - __u64 meta_size = ic->provided_data_sectors * ic->tag_size; + __u64 meta_size = (ic->provided_data_sectors >> ic->sb->log2_sectors_per_block) * ic->tag_size; meta_size = (meta_size + ((1U << (ic->log2_buffer_sectors + SECTOR_SHIFT)) - 1)) >> (ic->log2_buffer_sectors + SECTOR_SHIFT); meta_size <<= ic->log2_buffer_sectors; @@ -3439,7 +3439,7 @@ try_smaller_buffer: DEBUG_print(" journal_sections %u\n", (unsigned)le32_to_cpu(ic->sb->journal_sections)); DEBUG_print(" journal_entries %u\n", ic->journal_entries); DEBUG_print(" log2_interleave_sectors %d\n", ic->sb->log2_interleave_sectors); - DEBUG_print(" device_sectors 0x%llx\n", (unsigned long long)ic->device_sectors); + DEBUG_print(" data_device_sectors 0x%llx\n", (unsigned long long)ic->data_device_sectors); DEBUG_print(" initial_sectors 0x%x\n", ic->initial_sectors); DEBUG_print(" metadata_run 0x%x\n", ic->metadata_run); DEBUG_print(" log2_metadata_run %d\n", ic->log2_metadata_run); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 2ee5e357a0a7..cc5173dfd466 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -882,6 +882,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps if (attached_handler_name || m->hw_handler_name) { INIT_DELAYED_WORK(&p->activate_path, activate_path_work); r = setup_scsi_dh(p->path.dev->bdev, m, &attached_handler_name, &ti->error); + kfree(attached_handler_name); if (r) { dm_put_device(ti, p->path.dev); goto bad; @@ -896,7 +897,6 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps return p; bad: - kfree(attached_handler_name); free_pgpath(p); return ERR_PTR(r); } diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index fa68336560c3..d8334cd45d7c 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1169,6 +1169,9 @@ 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]); @@ -1204,6 +1207,8 @@ 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)); diff --git a/drivers/md/md.c b/drivers/md/md.c index 05ffffb8b769..295ff09cff4c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -132,24 +132,6 @@ static inline int speed_max(struct mddev *mddev) mddev->sync_speed_max : sysctl_speed_limit_max; } -static void * flush_info_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_info), gfp_flags); -} -static void flush_info_free(void *flush_info, void *data) -{ - kfree(flush_info); -} - -static void * flush_bio_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_bio), gfp_flags); -} -static void flush_bio_free(void *flush_bio, void *data) -{ - kfree(flush_bio); -} - static struct ctl_table_header *raid_table_header; static struct ctl_table raid_table[] = { @@ -423,54 +405,31 @@ static int md_congested(void *data, int bits) /* * Generic flush handling for md */ -static void submit_flushes(struct work_struct *ws) -{ - struct flush_info *fi = container_of(ws, struct flush_info, flush_work); - struct mddev *mddev = fi->mddev; - struct bio *bio = fi->bio; - - bio->bi_opf &= ~REQ_PREFLUSH; - md_handle_request(mddev, bio); - - mempool_free(fi, mddev->flush_pool); -} -static void md_end_flush(struct bio *fbio) +static void md_end_flush(struct bio *bio) { - struct flush_bio *fb = fbio->bi_private; - struct md_rdev *rdev = fb->rdev; - struct flush_info *fi = fb->fi; - struct bio *bio = fi->bio; - struct mddev *mddev = fi->mddev; + struct md_rdev *rdev = bio->bi_private; + struct mddev *mddev = rdev->mddev; rdev_dec_pending(rdev, mddev); - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { - /* an empty barrier - all done */ - bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); - } + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pre-request flush has finished */ + queue_work(md_wq, &mddev->flush_work); } - - mempool_free(fb, mddev->flush_bio_pool); - bio_put(fbio); + bio_put(bio); } -void md_flush_request(struct mddev *mddev, struct bio *bio) +static void md_submit_flush_data(struct work_struct *ws); + +static void submit_flushes(struct work_struct *ws) { + struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct md_rdev *rdev; - struct flush_info *fi; - - fi = mempool_alloc(mddev->flush_pool, GFP_NOIO); - - fi->bio = bio; - fi->mddev = mddev; - atomic_set(&fi->flush_pending, 1); + mddev->start_flush = ktime_get_boottime(); + INIT_WORK(&mddev->flush_work, md_submit_flush_data); + atomic_set(&mddev->flush_pending, 1); rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (rdev->raid_disk >= 0 && @@ -480,37 +439,74 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) * we reclaim rcu_read_lock */ struct bio *bi; - struct flush_bio *fb; atomic_inc(&rdev->nr_pending); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - - fb = mempool_alloc(mddev->flush_bio_pool, GFP_NOIO); - fb->fi = fi; - fb->rdev = rdev; - bi = bio_alloc_mddev(GFP_NOIO, 0, mddev); - bio_set_dev(bi, rdev->bdev); bi->bi_end_io = md_end_flush; - bi->bi_private = fb; + bi->bi_private = rdev; + bio_set_dev(bi, rdev->bdev); bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - - atomic_inc(&fi->flush_pending); + atomic_inc(&mddev->flush_pending); submit_bio(bi); - rcu_read_lock(); rdev_dec_pending(rdev, mddev); } rcu_read_unlock(); + if (atomic_dec_and_test(&mddev->flush_pending)) + queue_work(md_wq, &mddev->flush_work); +} + +static void md_submit_flush_data(struct work_struct *ws) +{ + struct mddev *mddev = container_of(ws, struct mddev, flush_work); + struct bio *bio = mddev->flush_bio; + + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->last_flush = mddev->start_flush; + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + + if (bio->bi_iter.bi_size == 0) { + /* an empty barrier - all done */ + bio_endio(bio); + } else { + bio->bi_opf &= ~REQ_PREFLUSH; + md_handle_request(mddev, bio); + } +} - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { +void md_flush_request(struct mddev *mddev, struct bio *bio) +{ + ktime_t start = ktime_get_boottime(); + spin_lock_irq(&mddev->lock); + wait_event_lock_irq(mddev->sb_wait, + !mddev->flush_bio || + ktime_after(mddev->last_flush, start), + mddev->lock); + if (!ktime_after(mddev->last_flush, start)) { + WARN_ON(mddev->flush_bio); + mddev->flush_bio = bio; + bio = NULL; + } + spin_unlock_irq(&mddev->lock); + + if (!bio) { + INIT_WORK(&mddev->flush_work, submit_flushes); + queue_work(md_wq, &mddev->flush_work); + } else { + /* flush was performed for some other bio while we waited. */ + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); + else { + bio->bi_opf &= ~REQ_PREFLUSH; + mddev->pers->make_request(mddev, bio); } } } @@ -560,6 +556,7 @@ void mddev_init(struct mddev *mddev) atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); spin_lock_init(&mddev->lock); + atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); init_waitqueue_head(&mddev->recovery_wait); mddev->reshape_position = MaxSector; @@ -2855,8 +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 @@ -5511,22 +5510,6 @@ int md_run(struct mddev *mddev) if (err) return err; } - if (mddev->flush_pool == NULL) { - mddev->flush_pool = mempool_create(NR_FLUSH_INFOS, flush_info_alloc, - flush_info_free, mddev); - if (!mddev->flush_pool) { - err = -ENOMEM; - goto abort; - } - } - if (mddev->flush_bio_pool == NULL) { - mddev->flush_bio_pool = mempool_create(NR_FLUSH_BIOS, flush_bio_alloc, - flush_bio_free, mddev); - if (!mddev->flush_bio_pool) { - err = -ENOMEM; - goto abort; - } - } spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -5686,11 +5669,8 @@ int md_run(struct mddev *mddev) return 0; abort: - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -5894,14 +5874,6 @@ static void __md_stop(struct mddev *mddev) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - if (mddev->flush_bio_pool) { - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - } - if (mddev->flush_pool) { - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - } } void md_stop(struct mddev *mddev) @@ -9257,7 +9229,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) * reshape is happening in the remote node, we need to * update reshape_position and call start_reshape. */ - mddev->reshape_position = sb->reshape_position; + mddev->reshape_position = le64_to_cpu(sb->reshape_position); if (mddev->pers->update_reshape_pos) mddev->pers->update_reshape_pos(mddev); if (mddev->pers->start_reshape) diff --git a/drivers/md/md.h b/drivers/md/md.h index c52afb52c776..257cb4c9e22b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -252,19 +252,6 @@ enum mddev_sb_flags { MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; -#define NR_FLUSH_INFOS 8 -#define NR_FLUSH_BIOS 64 -struct flush_info { - struct bio *bio; - struct mddev *mddev; - struct work_struct flush_work; - atomic_t flush_pending; -}; -struct flush_bio { - struct flush_info *fi; - struct md_rdev *rdev; -}; - struct mddev { void *private; struct md_personality *pers; @@ -470,8 +457,16 @@ struct mddev { * metadata and bitmap writes */ - mempool_t *flush_pool; - mempool_t *flush_bio_pool; + /* Generic flush handling. + * The last to finish preflush schedules a worker to submit + * the rest of the request (without the REQ_PREFLUSH flag). + */ + struct bio *flush_bio; + atomic_t flush_pending; + ktime_t start_flush, last_flush; /* last_flush is when the last completed + * flush was started. + */ + struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 3ae13c06b200..f9c90ab220b9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4197,7 +4197,7 @@ 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++; @@ -4222,6 +4222,14 @@ 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); @@ -4233,15 +4241,26 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, case check_state_check_result: sh->check_state = check_state_idle; - if (s->failed > 1) - break; /* handle a successful check operation, if parity is correct * we are done. Otherwise update the mismatch count and repair * parity if !MD_RECOVERY_CHECK */ if (sh->ops.zero_sum_result == 0) { - /* Any parity checked was correct */ - set_bit(STRIPE_INSYNC, &sh->state); + /* both parities are correct */ + if (!s->failed) + set_bit(STRIPE_INSYNC, &sh->state); + else { + /* in contrast to the raid5 case we can validate + * parity, but still have a failure to write + * back + */ + sh->check_state = check_state_compute_result; + /* Returning at this point means that we may go + * off and bring p and/or q uptodate again so + * we make sure to check zero_sum_result again + * to verify if p or q need writeback + */ + } } else { atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) { |