diff options
Diffstat (limited to 'drivers/md/dm-zoned-target.c')
| -rw-r--r-- | drivers/md/dm-zoned-target.c | 463 |
1 files changed, 324 insertions, 139 deletions
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index f4f83d39b3dc..a907a9446c0b 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -17,7 +17,7 @@ * Zone BIO context. */ struct dmz_bioctx { - struct dmz_target *target; + struct dmz_dev *dev; struct dm_zone *zone; struct bio *bio; refcount_t ref; @@ -38,9 +38,10 @@ struct dm_chunk_work { * Target descriptor. */ struct dmz_target { - struct dm_dev *ddev; + struct dm_dev **ddev; + unsigned int nr_ddevs; - unsigned long flags; + unsigned int flags; /* Zoned block device information */ struct dmz_dev *dev; @@ -48,9 +49,6 @@ struct dmz_target { /* For metadata handling */ struct dmz_metadata *metadata; - /* For reclaim */ - struct dmz_reclaim *reclaim; - /* For chunk work */ struct radix_tree_root chunk_rxtree; struct workqueue_struct *chunk_wq; @@ -76,12 +74,13 @@ struct dmz_target { */ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); 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 (bioctx->dev && bio->bi_status != BLK_STS_OK) + bioctx->dev->flags |= DMZ_CHECK_BDEV; if (refcount_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -118,14 +117,20 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio, sector_t chunk_block, unsigned int nr_blocks) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_dev *dev = zone->dev; struct bio *clone; + if (dev->flags & DMZ_BDEV_DYING) + return -EIO; + clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set); if (!clone) return -ENOMEM; - bio_set_dev(clone, dmz->dev->bdev); + bio_set_dev(clone, dev->bdev); + bioctx->dev = dev; clone->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT; @@ -165,7 +170,8 @@ static void dmz_handle_read_zero(struct dmz_target *dmz, struct bio *bio, static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio) { - sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio)); + struct dmz_metadata *zmd = dmz->metadata; + sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio)); unsigned int nr_blocks = dmz_bio_blocks(bio); sector_t end_block = chunk_block + nr_blocks; struct dm_zone *rzone, *bzone; @@ -177,19 +183,22 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, return 0; } - dmz_dev_debug(dmz->dev, "READ chunk %llu -> %s zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (dmz_is_rnd(zone) ? "RND" : "SEQ"), - dmz_id(dmz->metadata, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): READ chunk %llu -> %s zone %u, block %llu, %u blocks", + dmz_metadata_label(zmd), + (unsigned long long)dmz_bio_chunk(zmd, bio), + (dmz_is_rnd(zone) ? "RND" : + (dmz_is_cache(zone) ? "CACHE" : "SEQ")), + zone->id, + (unsigned long long)chunk_block, nr_blocks); /* Check block validity to determine the read location */ bzone = zone->bzone; while (chunk_block < end_block) { nr_blocks = 0; - if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) { + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block < zone->wp_block) { /* Test block validity in the data zone */ - ret = dmz_block_valid(dmz->metadata, zone, chunk_block); + ret = dmz_block_valid(zmd, zone, chunk_block); if (ret < 0) return ret; if (ret > 0) { @@ -204,7 +213,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, * Check the buffer zone, if there is one. */ if (!nr_blocks && bzone) { - ret = dmz_block_valid(dmz->metadata, bzone, chunk_block); + ret = dmz_block_valid(zmd, bzone, chunk_block); if (ret < 0) return ret; if (ret > 0) { @@ -216,8 +225,10 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks) { /* Valid blocks found: read them */ - nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block); - ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks); + nr_blocks = min_t(unsigned int, nr_blocks, + end_block - chunk_block); + ret = dmz_submit_bio(dmz, rzone, bio, + chunk_block, nr_blocks); if (ret) return ret; chunk_block += nr_blocks; @@ -308,25 +319,30 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, static int dmz_handle_write(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio) { - sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio)); + struct dmz_metadata *zmd = dmz->metadata; + sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio)); unsigned int nr_blocks = dmz_bio_blocks(bio); if (!zone) return -ENOSPC; - dmz_dev_debug(dmz->dev, "WRITE chunk %llu -> %s zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (dmz_is_rnd(zone) ? "RND" : "SEQ"), - dmz_id(dmz->metadata, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): WRITE chunk %llu -> %s zone %u, block %llu, %u blocks", + dmz_metadata_label(zmd), + (unsigned long long)dmz_bio_chunk(zmd, bio), + (dmz_is_rnd(zone) ? "RND" : + (dmz_is_cache(zone) ? "CACHE" : "SEQ")), + zone->id, + (unsigned long long)chunk_block, nr_blocks); - if (dmz_is_rnd(zone) || chunk_block == zone->wp_block) { + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block == zone->wp_block) { /* * zone is a random zone or it is a sequential zone * and the BIO is aligned to the zone write pointer: * direct write the zone. */ - return dmz_handle_direct_write(dmz, zone, bio, chunk_block, nr_blocks); + return dmz_handle_direct_write(dmz, zone, bio, + chunk_block, nr_blocks); } /* @@ -345,7 +361,7 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, struct dmz_metadata *zmd = dmz->metadata; sector_t block = dmz_bio_block(bio); unsigned int nr_blocks = dmz_bio_blocks(bio); - sector_t chunk_block = dmz_chunk_block(dmz->dev, block); + sector_t chunk_block = dmz_chunk_block(zmd, block); int ret = 0; /* For unmapped chunks, there is nothing to do */ @@ -355,16 +371,18 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, if (dmz_is_readonly(zone)) return -EROFS; - dmz_dev_debug(dmz->dev, "DISCARD chunk %llu -> zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - dmz_id(zmd, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): DISCARD chunk %llu -> zone %u, block %llu, %u blocks", + dmz_metadata_label(dmz->metadata), + (unsigned long long)dmz_bio_chunk(zmd, bio), + zone->id, + (unsigned long long)chunk_block, nr_blocks); /* * Invalidate blocks in the data zone and its * buffer zone if one is mapped. */ - if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block < zone->wp_block) ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks); if (ret == 0 && zone->bzone) ret = dmz_invalidate_blocks(zmd, zone->bzone, @@ -378,31 +396,28 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, struct bio *bio) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); struct dmz_metadata *zmd = dmz->metadata; struct dm_zone *zone; - int ret; + int i, ret; /* * Write may trigger a zone allocation. So make sure the * allocation can succeed. */ if (bio_op(bio) == REQ_OP_WRITE) - dmz_schedule_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_schedule_reclaim(dmz->dev[i].reclaim); 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, + the zone returned will be set to active state. */ - zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(dmz->dev, bio), + zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(zmd, bio), bio_op(bio)); if (IS_ERR(zone)) { ret = PTR_ERR(zone); @@ -413,6 +428,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, if (zone) { dmz_activate_zone(zone); bioctx->zone = zone; + dmz_reclaim_bio_acc(zone->dev->reclaim); } switch (bio_op(bio)) { @@ -427,8 +443,8 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, ret = dmz_handle_discard(dmz, zone, bio); break; default: - dmz_dev_err(dmz->dev, "Unsupported BIO operation 0x%x", - bio_op(bio)); + DMERR("(%s): Unsupported BIO operation 0x%x", + dmz_metadata_label(dmz->metadata), bio_op(bio)); ret = -EIO; } @@ -502,7 +518,8 @@ 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); + DMDEBUG("(%s): Metadata flush failed, rc=%d", + dmz_metadata_label(dmz->metadata), ret); /* Process queued flush requests */ while (1) { @@ -525,7 +542,7 @@ static void dmz_flush_work(struct work_struct *work) */ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) { - unsigned int chunk = dmz_bio_chunk(dmz->dev, bio); + unsigned int chunk = dmz_bio_chunk(dmz->metadata, bio); struct dm_chunk_work *cw; int ret = 0; @@ -558,7 +575,6 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) bio_list_add(&cw->bio_list, bio); - dmz_reclaim_bio_acc(dmz->reclaim); if (queue_work(dmz->chunk_wq, &cw->work)) dmz_get_chunk_work(cw); out: @@ -618,23 +634,22 @@ bool dmz_check_bdev(struct dmz_dev *dmz_dev) static int dmz_map(struct dm_target *ti, struct bio *bio) { struct dmz_target *dmz = ti->private; - struct dmz_dev *dev = dmz->dev; + struct dmz_metadata *zmd = dmz->metadata; struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); 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)) + if (dmz_dev_is_dying(zmd)) 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, - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (unsigned long long)dmz_chunk_block(dmz->dev, dmz_bio_block(bio)), - (unsigned int)dmz_bio_blocks(bio)); - - bio_set_dev(bio, dev->bdev); + DMDEBUG("(%s): BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", + dmz_metadata_label(zmd), + bio_op(bio), (unsigned long long)sector, nr_sectors, + (unsigned long long)dmz_bio_chunk(zmd, bio), + (unsigned long long)dmz_chunk_block(zmd, dmz_bio_block(bio)), + (unsigned int)dmz_bio_blocks(bio)); if (!nr_sectors && bio_op(bio) != REQ_OP_WRITE) return DM_MAPIO_REMAPPED; @@ -644,7 +659,7 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_KILL; /* Initialize the BIO context */ - bioctx->target = dmz; + bioctx->dev = NULL; bioctx->zone = NULL; bioctx->bio = bio; refcount_set(&bioctx->ref, 1); @@ -659,17 +674,17 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) } /* Split zone BIOs to fit entirely into a zone */ - chunk_sector = sector & (dev->zone_nr_sectors - 1); - if (chunk_sector + nr_sectors > dev->zone_nr_sectors) - dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector); + chunk_sector = sector & (dmz_zone_nr_sectors(zmd) - 1); + if (chunk_sector + nr_sectors > dmz_zone_nr_sectors(zmd)) + dm_accept_partial_bio(bio, dmz_zone_nr_sectors(zmd) - chunk_sector); /* Now ready to handle this 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); + DMDEBUG("(%s): BIO op %d, can't process chunk %llu, err %i", + dmz_metadata_label(zmd), + bio_op(bio), (u64)dmz_bio_chunk(zmd, bio), + ret); return DM_MAPIO_REQUEUE; } @@ -679,64 +694,65 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) /* * Get zoned device information. */ -static int dmz_get_zoned_device(struct dm_target *ti, char *path) +static int dmz_get_zoned_device(struct dm_target *ti, char *path, + int idx, int nr_devs) { struct dmz_target *dmz = ti->private; - struct request_queue *q; + struct dm_dev *ddev; struct dmz_dev *dev; - sector_t aligned_capacity; int ret; + struct block_device *bdev; /* Get the target device */ - ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &dmz->ddev); + ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &ddev); if (ret) { ti->error = "Get target device failed"; - dmz->ddev = NULL; return ret; } - dev = kzalloc(sizeof(struct dmz_dev), GFP_KERNEL); - if (!dev) { - ret = -ENOMEM; - goto err; + bdev = ddev->bdev; + if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) { + if (nr_devs == 1) { + ti->error = "Invalid regular device"; + goto err; + } + if (idx != 0) { + ti->error = "First device must be a regular device"; + goto err; + } + if (dmz->ddev[0]) { + ti->error = "Too many regular devices"; + goto err; + } + dev = &dmz->dev[idx]; + dev->flags = DMZ_BDEV_REGULAR; + } else { + if (dmz->ddev[idx]) { + ti->error = "Too many zoned devices"; + goto err; + } + if (nr_devs > 1 && idx == 0) { + ti->error = "First device must be a regular device"; + goto err; + } + dev = &dmz->dev[idx]; } - - dev->bdev = dmz->ddev->bdev; + dev->bdev = bdev; + dev->dev_idx = idx; (void)bdevname(dev->bdev, dev->name); - if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE) { - ti->error = "Not a zoned block device"; - ret = -EINVAL; + dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + if (ti->begin) { + ti->error = "Partial mapping is not supported"; goto err; } - q = bdev_get_queue(dev->bdev); - dev->capacity = i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; - aligned_capacity = dev->capacity & - ~((sector_t)blk_queue_zone_sectors(q) - 1); - if (ti->begin || - ((ti->len != dev->capacity) && (ti->len != aligned_capacity))) { - ti->error = "Partial mapping not supported"; - ret = -EINVAL; - goto err; - } - - dev->zone_nr_sectors = blk_queue_zone_sectors(q); - dev->zone_nr_sectors_shift = ilog2(dev->zone_nr_sectors); - - dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); - dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - - dev->nr_zones = blkdev_nr_zones(dev->bdev->bd_disk); - - dmz->dev = dev; + dmz->ddev[idx] = ddev; return 0; err: - dm_put_device(ti, dmz->ddev); - kfree(dev); - - return ret; + dm_put_device(ti, ddev); + return -EINVAL; } /* @@ -745,10 +761,78 @@ err: static void dmz_put_zoned_device(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; - dm_put_device(ti, dmz->ddev); - kfree(dmz->dev); - dmz->dev = NULL; + for (i = 0; i < dmz->nr_ddevs; i++) { + if (dmz->ddev[i]) { + dm_put_device(ti, dmz->ddev[i]); + dmz->ddev[i] = NULL; + } + } +} + +static int dmz_fixup_devices(struct dm_target *ti) +{ + struct dmz_target *dmz = ti->private; + struct dmz_dev *reg_dev, *zoned_dev; + struct request_queue *q; + sector_t zone_nr_sectors = 0; + int i; + + /* + * When we have more than on devices, the first one must be a + * regular block device and the others zoned block devices. + */ + if (dmz->nr_ddevs > 1) { + reg_dev = &dmz->dev[0]; + if (!(reg_dev->flags & DMZ_BDEV_REGULAR)) { + ti->error = "Primary disk is not a regular device"; + return -EINVAL; + } + for (i = 1; i < dmz->nr_ddevs; i++) { + zoned_dev = &dmz->dev[i]; + if (zoned_dev->flags & DMZ_BDEV_REGULAR) { + ti->error = "Secondary disk is not a zoned device"; + return -EINVAL; + } + q = bdev_get_queue(zoned_dev->bdev); + if (zone_nr_sectors && + zone_nr_sectors != blk_queue_zone_sectors(q)) { + ti->error = "Zone nr sectors mismatch"; + return -EINVAL; + } + zone_nr_sectors = blk_queue_zone_sectors(q); + zoned_dev->zone_nr_sectors = zone_nr_sectors; + zoned_dev->nr_zones = + blkdev_nr_zones(zoned_dev->bdev->bd_disk); + } + } else { + reg_dev = NULL; + zoned_dev = &dmz->dev[0]; + if (zoned_dev->flags & DMZ_BDEV_REGULAR) { + ti->error = "Disk is not a zoned device"; + return -EINVAL; + } + q = bdev_get_queue(zoned_dev->bdev); + zoned_dev->zone_nr_sectors = blk_queue_zone_sectors(q); + zoned_dev->nr_zones = blkdev_nr_zones(zoned_dev->bdev->bd_disk); + } + + if (reg_dev) { + sector_t zone_offset; + + reg_dev->zone_nr_sectors = zone_nr_sectors; + reg_dev->nr_zones = + DIV_ROUND_UP_SECTOR_T(reg_dev->capacity, + reg_dev->zone_nr_sectors); + reg_dev->zone_offset = 0; + zone_offset = reg_dev->nr_zones; + for (i = 1; i < dmz->nr_ddevs; i++) { + dmz->dev[i].zone_offset = zone_offset; + zone_offset += dmz->dev[i].nr_zones; + } + } + return 0; } /* @@ -757,11 +841,10 @@ static void dmz_put_zoned_device(struct dm_target *ti) static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct dmz_target *dmz; - struct dmz_dev *dev; - int ret; + int ret, i; /* Check arguments */ - if (argc != 1) { + if (argc < 1) { ti->error = "Invalid argument count"; return -EINVAL; } @@ -772,25 +855,42 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Unable to allocate the zoned target descriptor"; return -ENOMEM; } + dmz->dev = kcalloc(argc, sizeof(struct dmz_dev), GFP_KERNEL); + if (!dmz->dev) { + ti->error = "Unable to allocate the zoned device descriptors"; + kfree(dmz); + return -ENOMEM; + } + dmz->ddev = kcalloc(argc, sizeof(struct dm_dev *), GFP_KERNEL); + if (!dmz->ddev) { + ti->error = "Unable to allocate the dm device descriptors"; + ret = -ENOMEM; + goto err; + } + dmz->nr_ddevs = argc; + ti->private = dmz; /* Get the target zoned block device */ - ret = dmz_get_zoned_device(ti, argv[0]); - if (ret) { - dmz->ddev = NULL; - goto err; + for (i = 0; i < argc; i++) { + ret = dmz_get_zoned_device(ti, argv[i], i, argc); + if (ret) + goto err_dev; } + ret = dmz_fixup_devices(ti); + if (ret) + goto err_dev; /* Initialize metadata */ - dev = dmz->dev; - ret = dmz_ctr_metadata(dev, &dmz->metadata); + ret = dmz_ctr_metadata(dmz->dev, argc, &dmz->metadata, + dm_table_device_name(ti->table)); if (ret) { ti->error = "Metadata initialization failed"; goto err_dev; } /* Set target (no write same support) */ - ti->max_io_len = dev->zone_nr_sectors << 9; + ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9; ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_write_zeroes_bios = 1; @@ -799,7 +899,8 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->discards_supported = true; /* The exposed capacity is the number of chunks that can be mapped */ - ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift; + ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << + dmz_zone_nr_sectors_shift(dmz->metadata); /* Zone BIO */ ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0); @@ -811,8 +912,9 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Chunk BIO work */ mutex_init(&dmz->chunk_lock); INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO); - dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND, - 0, dev->name); + dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0, + dmz_metadata_label(dmz->metadata)); if (!dmz->chunk_wq) { ti->error = "Create chunk workqueue failed"; ret = -ENOMEM; @@ -824,7 +926,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) bio_list_init(&dmz->flush_list); INIT_DELAYED_WORK(&dmz->flush_work, dmz_flush_work); dmz->flush_wq = alloc_ordered_workqueue("dmz_fwq_%s", WQ_MEM_RECLAIM, - dev->name); + dmz_metadata_label(dmz->metadata)); if (!dmz->flush_wq) { ti->error = "Create flush workqueue failed"; ret = -ENOMEM; @@ -833,15 +935,18 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) mod_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD); /* Initialize reclaim */ - ret = dmz_ctr_reclaim(dev, dmz->metadata, &dmz->reclaim); - if (ret) { - ti->error = "Zone reclaim initialization failed"; - goto err_fwq; + for (i = 0; i < dmz->nr_ddevs; i++) { + ret = dmz_ctr_reclaim(dmz->metadata, &dmz->dev[i].reclaim, i); + if (ret) { + ti->error = "Zone reclaim initialization failed"; + goto err_fwq; + } } - dmz_dev_info(dev, "Target device: %llu 512-byte logical sectors (%llu blocks)", - (unsigned long long)ti->len, - (unsigned long long)dmz_sect2blk(ti->len)); + DMINFO("(%s): Target device: %llu 512-byte logical sectors (%llu blocks)", + dmz_metadata_label(dmz->metadata), + (unsigned long long)ti->len, + (unsigned long long)dmz_sect2blk(ti->len)); return 0; err_fwq: @@ -856,6 +961,7 @@ err_meta: err_dev: dmz_put_zoned_device(ti); err: + kfree(dmz->dev); kfree(dmz); return ret; @@ -867,11 +973,13 @@ err: static void dmz_dtr(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; flush_workqueue(dmz->chunk_wq); destroy_workqueue(dmz->chunk_wq); - dmz_dtr_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_dtr_reclaim(dmz->dev[i].reclaim); cancel_delayed_work_sync(&dmz->flush_work); destroy_workqueue(dmz->flush_wq); @@ -886,6 +994,7 @@ static void dmz_dtr(struct dm_target *ti) mutex_destroy(&dmz->chunk_lock); + kfree(dmz->dev); kfree(dmz); } @@ -895,7 +1004,7 @@ static void dmz_dtr(struct dm_target *ti) static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct dmz_target *dmz = ti->private; - unsigned int chunk_sectors = dmz->dev->zone_nr_sectors; + unsigned int chunk_sectors = dmz_zone_nr_sectors(dmz->metadata); limits->logical_block_size = DMZ_BLOCK_SIZE; limits->physical_block_size = DMZ_BLOCK_SIZE; @@ -923,11 +1032,12 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private; + struct dmz_dev *dev = &dmz->dev[0]; - if (!dmz_check_bdev(dmz->dev)) + if (!dmz_check_bdev(dev)) return -EIO; - *bdev = dmz->dev->bdev; + *bdev = dev->bdev; return 0; } @@ -938,9 +1048,11 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) static void dmz_suspend(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; flush_workqueue(dmz->chunk_wq); - dmz_suspend_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_suspend_reclaim(dmz->dev[i].reclaim); cancel_delayed_work_sync(&dmz->flush_work); } @@ -950,24 +1062,95 @@ static void dmz_suspend(struct dm_target *ti) static void dmz_resume(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD); - dmz_resume_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_resume_reclaim(dmz->dev[i].reclaim); } static int dmz_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct dmz_target *dmz = ti->private; - struct dmz_dev *dev = dmz->dev; - sector_t capacity = dev->capacity & ~(dev->zone_nr_sectors - 1); + unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata); + sector_t capacity; + int i, r; + + for (i = 0; i < dmz->nr_ddevs; i++) { + capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1); + r = fn(ti, dmz->ddev[i], 0, capacity, data); + if (r) + break; + } + return r; +} + +static void dmz_status(struct dm_target *ti, status_type_t type, + unsigned int status_flags, char *result, + unsigned int maxlen) +{ + struct dmz_target *dmz = ti->private; + ssize_t sz = 0; + char buf[BDEVNAME_SIZE]; + struct dmz_dev *dev; + int i; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%u zones %u/%u cache", + dmz_nr_zones(dmz->metadata), + dmz_nr_unmap_cache_zones(dmz->metadata), + dmz_nr_cache_zones(dmz->metadata)); + for (i = 0; i < dmz->nr_ddevs; i++) { + /* + * For a multi-device setup the first device + * contains only cache zones. + */ + if ((i == 0) && + (dmz_nr_cache_zones(dmz->metadata) > 0)) + continue; + DMEMIT(" %u/%u random %u/%u sequential", + dmz_nr_unmap_rnd_zones(dmz->metadata, i), + dmz_nr_rnd_zones(dmz->metadata, i), + dmz_nr_unmap_seq_zones(dmz->metadata, i), + dmz_nr_seq_zones(dmz->metadata, i)); + } + break; + case STATUSTYPE_TABLE: + dev = &dmz->dev[0]; + format_dev_t(buf, dev->bdev->bd_dev); + DMEMIT("%s", buf); + for (i = 1; i < dmz->nr_ddevs; i++) { + dev = &dmz->dev[i]; + format_dev_t(buf, dev->bdev->bd_dev); + DMEMIT(" %s", buf); + } + break; + } + return; +} + +static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) +{ + struct dmz_target *dmz = ti->private; + int r = -EINVAL; + + if (!strcasecmp(argv[0], "reclaim")) { + int i; - return fn(ti, dmz->ddev, 0, capacity, data); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_schedule_reclaim(dmz->dev[i].reclaim); + r = 0; + } else + DMERR("unrecognized message %s", argv[0]); + return r; } static struct target_type dmz_type = { .name = "zoned", - .version = {1, 1, 0}, + .version = {2, 0, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM, .module = THIS_MODULE, .ctr = dmz_ctr, @@ -978,6 +1161,8 @@ static struct target_type dmz_type = { .postsuspend = dmz_suspend, .resume = dmz_resume, .iterate_devices = dmz_iterate_devices, + .status = dmz_status, + .message = dmz_message, }; static int __init dmz_init(void) |