Merge tag 'for-5.8/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - The largest change for this cycle is the DM zoned target's metadata
   version 2 feature that adds support for pairing regular block devices
   with a zoned device to ease the performance impact associated with
   finite random zones of zoned device.

   The changes came in three batches: the first prepared for and then
   added the ability to pair a single regular block device, the second
   was a batch of fixes to improve zoned's reclaim heuristic, and the
   third removed the limitation of only adding a single additional
   regular block device to allow many devices.

   Testing has shown linear scaling as more devices are added.

 - Add new emulated block size (ebs) target that emulates a smaller
   logical_block_size than a block device supports

   The primary use-case is to emulate "512e" devices that have 512 byte
   logical_block_size and 4KB physical_block_size. This is useful to
   some legacy applications that otherwise wouldn't be able to be used
   on 4K devices because they depend on issuing IO in 512 byte
   granularity.

 - Add discard interfaces to DM bufio. First consumer of the interface
   is the dm-ebs target that makes heavy use of dm-bufio.

 - Fix DM crypt's block queue_limits stacking to not truncate
   logic_block_size.

 - Add Documentation for DM integrity's status line.

 - Switch DMDEBUG from a compile time config option to instead use
   dynamic debug via pr_debug.

 - Fix DM multipath target's hueristic for how it manages
   "queue_if_no_path" state internally.

   DM multipath now avoids disabling "queue_if_no_path" unless it is
   actually needed (e.g. in response to configure timeout or explicit
   "fail_if_no_path" message).

   This fixes reports of spurious -EIO being reported back to userspace
   application during fault tolerance testing with an NVMe backend.
   Added various dynamic DMDEBUG messages to assist with debugging
   queue_if_no_path in the future.

 - Add a new DM multipath "Historical Service Time" Path Selector.

 - Fix DM multipath's dm_blk_ioctl() to switch paths on IO error.

 - Improve DM writecache target performance by using explicit cache
   flushing for target's single-threaded usecase and a small cleanup to
   remove unnecessary test in persistent_memory_claim.

 - Other small cleanups in DM core, dm-persistent-data, and DM
   integrity.

* tag 'for-5.8/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (62 commits)
  dm crypt: avoid truncating the logical block size
  dm mpath: add DM device name to Failing/Reinstating path log messages
  dm mpath: enhance queue_if_no_path debugging
  dm mpath: restrict queue_if_no_path state machine
  dm mpath: simplify __must_push_back
  dm zoned: check superblock location
  dm zoned: prefer full zones for reclaim
  dm zoned: select reclaim zone based on device index
  dm zoned: allocate zone by device index
  dm zoned: support arbitrary number of devices
  dm zoned: move random and sequential zones into struct dmz_dev
  dm zoned: per-device reclaim
  dm zoned: add metadata pointer to struct dmz_dev
  dm zoned: add device pointer to struct dm_zone
  dm zoned: allocate temporary superblock for tertiary devices
  dm zoned: convert to xarray
  dm zoned: add a 'reserved' zone flag
  dm zoned: improve logging messages for reclaim
  dm zoned: avoid unnecessary device recalulation for secondary superblock
  dm zoned: add debugging message for reading superblocks
  ...

1 files changed, 771 insertions, 275 deletions

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index bf2245370305..130b5a6d9f12 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -16,7 +16,7 @@
 /*
  * Metadata version.
  */
-#define DMZ_META_VER	1
+#define DMZ_META_VER	2
 
 /*
  * On-disk super block magic.
@@ -69,8 +69,17 @@ struct dmz_super {
 	/* Checksum */
 	__le32		crc;			/*  48 */
 
+	/* DM-Zoned label */
+	u8		dmz_label[32];		/*  80 */
+
+	/* DM-Zoned UUID */
+	u8		dmz_uuid[16];		/*  96 */
+
+	/* Device UUID */
+	u8		dev_uuid[16];		/* 112 */
+
 	/* Padding to full 512B sector */
-	u8		reserved[464];		/* 512 */
+	u8		reserved[400];		/* 512 */
 };
 
 /*
@@ -122,8 +131,10 @@ enum {
  */
 struct dmz_sb {
 	sector_t		block;
+	struct dmz_dev		*dev;
 	struct dmz_mblock	*mblk;
 	struct dmz_super	*sb;
+	struct dm_zone		*zone;
 };
 
 /*
@@ -131,28 +142,41 @@ struct dmz_sb {
  */
 struct dmz_metadata {
 	struct dmz_dev		*dev;
+	unsigned int		nr_devs;
+
+	char			devname[BDEVNAME_SIZE];
+	char			label[BDEVNAME_SIZE];
+	uuid_t			uuid;
 
 	sector_t		zone_bitmap_size;
 	unsigned int		zone_nr_bitmap_blocks;
 	unsigned int		zone_bits_per_mblk;
 
+	sector_t		zone_nr_blocks;
+	sector_t		zone_nr_blocks_shift;
+
+	sector_t		zone_nr_sectors;
+	sector_t		zone_nr_sectors_shift;
+
 	unsigned int		nr_bitmap_blocks;
 	unsigned int		nr_map_blocks;
 
+	unsigned int		nr_zones;
 	unsigned int		nr_useable_zones;
 	unsigned int		nr_meta_blocks;
 	unsigned int		nr_meta_zones;
 	unsigned int		nr_data_zones;
+	unsigned int		nr_cache_zones;
 	unsigned int		nr_rnd_zones;
 	unsigned int		nr_reserved_seq;
 	unsigned int		nr_chunks;
 
 	/* Zone information array */
-	struct dm_zone		*zones;
+	struct xarray		zones;
 
-	struct dm_zone		*sb_zone;
 	struct dmz_sb		sb[2];
 	unsigned int		mblk_primary;
+	unsigned int		sb_version;
 	u64			sb_gen;
 	unsigned int		min_nr_mblks;
 	unsigned int		max_nr_mblks;
@@ -168,15 +192,11 @@ struct dmz_metadata {
 	/* Zone allocation management */
 	struct mutex		map_lock;
 	struct dmz_mblock	**map_mblk;
-	unsigned int		nr_rnd;
-	atomic_t		unmap_nr_rnd;
-	struct list_head	unmap_rnd_list;
-	struct list_head	map_rnd_list;
 
-	unsigned int		nr_seq;
-	atomic_t		unmap_nr_seq;
-	struct list_head	unmap_seq_list;
-	struct list_head	map_seq_list;
+	unsigned int		nr_cache;
+	atomic_t		unmap_nr_cache;
+	struct list_head	unmap_cache_list;
+	struct list_head	map_cache_list;
 
 	atomic_t		nr_reserved_seq_zones;
 	struct list_head	reserved_seq_zones_list;
@@ -184,22 +204,65 @@ struct dmz_metadata {
 	wait_queue_head_t	free_wq;
 };
 
+#define dmz_zmd_info(zmd, format, args...)	\
+	DMINFO("(%s): " format, (zmd)->label, ## args)
+
+#define dmz_zmd_err(zmd, format, args...)	\
+	DMERR("(%s): " format, (zmd)->label, ## args)
+
+#define dmz_zmd_warn(zmd, format, args...)	\
+	DMWARN("(%s): " format, (zmd)->label, ## args)
+
+#define dmz_zmd_debug(zmd, format, args...)	\
+	DMDEBUG("(%s): " format, (zmd)->label, ## args)
 /*
  * Various accessors
  */
-unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone)
+static unsigned int dmz_dev_zone_id(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	return ((unsigned int)(zone - zmd->zones));
+	if (WARN_ON(!zone))
+		return 0;
+
+	return zone->id - zone->dev->zone_offset;
 }
 
 sector_t dmz_start_sect(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	return (sector_t)dmz_id(zmd, zone) << zmd->dev->zone_nr_sectors_shift;
+	unsigned int zone_id = dmz_dev_zone_id(zmd, zone);
+
+	return (sector_t)zone_id << zmd->zone_nr_sectors_shift;
 }
 
 sector_t dmz_start_block(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	return (sector_t)dmz_id(zmd, zone) << zmd->dev->zone_nr_blocks_shift;
+	unsigned int zone_id = dmz_dev_zone_id(zmd, zone);
+
+	return (sector_t)zone_id << zmd->zone_nr_blocks_shift;
+}
+
+unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd)
+{
+	return zmd->zone_nr_blocks;
+}
+
+unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd)
+{
+	return zmd->zone_nr_blocks_shift;
+}
+
+unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd)
+{
+	return zmd->zone_nr_sectors;
+}
+
+unsigned int dmz_zone_nr_sectors_shift(struct dmz_metadata *zmd)
+{
+	return zmd->zone_nr_sectors_shift;
+}
+
+unsigned int dmz_nr_zones(struct dmz_metadata *zmd)
+{
+	return zmd->nr_zones;
 }
 
 unsigned int dmz_nr_chunks(struct dmz_metadata *zmd)
@@ -207,14 +270,88 @@ unsigned int dmz_nr_chunks(struct dmz_metadata *zmd)
 	return zmd->nr_chunks;
 }
 
-unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd)
+unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd, int idx)
 {
-	return zmd->nr_rnd;
+	return zmd->dev[idx].nr_rnd;
 }
 
-unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd)
+unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx)
 {
-	return atomic_read(&zmd->unmap_nr_rnd);
+	return atomic_read(&zmd->dev[idx].unmap_nr_rnd);
+}
+
+unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd)
+{
+	return zmd->nr_cache;
+}
+
+unsigned int dmz_nr_unmap_cache_zones(struct dmz_metadata *zmd)
+{
+	return atomic_read(&zmd->unmap_nr_cache);
+}
+
+unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx)
+{
+	return zmd->dev[idx].nr_seq;
+}
+
+unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx)
+{
+	return atomic_read(&zmd->dev[idx].unmap_nr_seq);
+}
+
+static struct dm_zone *dmz_get(struct dmz_metadata *zmd, unsigned int zone_id)
+{
+	return xa_load(&zmd->zones, zone_id);
+}
+
+static struct dm_zone *dmz_insert(struct dmz_metadata *zmd,
+				  unsigned int zone_id, struct dmz_dev *dev)
+{
+	struct dm_zone *zone = kzalloc(sizeof(struct dm_zone), GFP_KERNEL);
+
+	if (!zone)
+		return ERR_PTR(-ENOMEM);
+
+	if (xa_insert(&zmd->zones, zone_id, zone, GFP_KERNEL)) {
+		kfree(zone);
+		return ERR_PTR(-EBUSY);
+	}
+
+	INIT_LIST_HEAD(&zone->link);
+	atomic_set(&zone->refcount, 0);
+	zone->id = zone_id;
+	zone->chunk = DMZ_MAP_UNMAPPED;
+	zone->dev = dev;
+
+	return zone;
+}
+
+const char *dmz_metadata_label(struct dmz_metadata *zmd)
+{
+	return (const char *)zmd->label;
+}
+
+bool dmz_check_dev(struct dmz_metadata *zmd)
+{
+	unsigned int i;
+
+	for (i = 0; i < zmd->nr_devs; i++) {
+		if (!dmz_check_bdev(&zmd->dev[i]))
+			return false;
+	}
+	return true;
+}
+
+bool dmz_dev_is_dying(struct dmz_metadata *zmd)
+{
+	unsigned int i;
+
+	for (i = 0; i < zmd->nr_devs; i++) {
+		if (dmz_bdev_is_dying(&zmd->dev[i]))
+			return true;
+	}
+	return false;
 }
 
 /*
@@ -402,9 +539,10 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd,
 {
 	struct dmz_mblock *mblk, *m;
 	sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no;
+	struct dmz_dev *dev = zmd->sb[zmd->mblk_primary].dev;
 	struct bio *bio;
 
-	if (dmz_bdev_is_dying(zmd->dev))
+	if (dmz_bdev_is_dying(dev))
 		return ERR_PTR(-EIO);
 
 	/* Get a new block and a BIO to read it */
@@ -440,7 +578,7 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd,
 
 	/* Submit read BIO */
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
-	bio_set_dev(bio, zmd->dev->bdev);
+	bio_set_dev(bio, dev->bdev);
 	bio->bi_private = mblk;
 	bio->bi_end_io = dmz_mblock_bio_end_io;
 	bio_set_op_attrs(bio, REQ_OP_READ, REQ_META | REQ_PRIO);
@@ -537,6 +675,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 					 sector_t mblk_no)
 {
 	struct dmz_mblock *mblk;
+	struct dmz_dev *dev = zmd->sb[zmd->mblk_primary].dev;
 
 	/* Check rbtree */
 	spin_lock(&zmd->mblk_lock);
@@ -555,7 +694,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 		       TASK_UNINTERRUPTIBLE);
 	if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 		dmz_release_mblock(zmd, mblk);
-		dmz_check_bdev(zmd->dev);
+		dmz_check_bdev(dev);
 		return ERR_PTR(-EIO);
 	}
 
@@ -579,10 +718,11 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
 static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 			    unsigned int set)
 {
+	struct dmz_dev *dev = zmd->sb[set].dev;
 	sector_t block = zmd->sb[set].block + mblk->no;
 	struct bio *bio;
 
-	if (dmz_bdev_is_dying(zmd->dev))
+	if (dmz_bdev_is_dying(dev))
 		return -EIO;
 
 	bio = bio_alloc(GFP_NOIO, 1);
@@ -594,7 +734,7 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 	set_bit(DMZ_META_WRITING, &mblk->state);
 
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
-	bio_set_dev(bio, zmd->dev->bdev);
+	bio_set_dev(bio, dev->bdev);
 	bio->bi_private = mblk;
 	bio->bi_end_io = dmz_mblock_bio_end_io;
 	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO);
@@ -607,13 +747,16 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 /*
  * Read/write a metadata block.
  */
-static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
-			  struct page *page)
+static int dmz_rdwr_block(struct dmz_dev *dev, int op,
+			  sector_t block, struct page *page)
 {
 	struct bio *bio;
 	int ret;
 
-	if (dmz_bdev_is_dying(zmd->dev))
+	if (WARN_ON(!dev))
+		return -EIO;
+
+	if (dmz_bdev_is_dying(dev))
 		return -EIO;
 
 	bio = bio_alloc(GFP_NOIO, 1);
@@ -621,14 +764,14 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 		return -ENOMEM;
 
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
-	bio_set_dev(bio, zmd->dev->bdev);
+	bio_set_dev(bio, dev->bdev);
 	bio_set_op_attrs(bio, op, REQ_SYNC | REQ_META | REQ_PRIO);
 	bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0);
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
 	if (ret)
-		dmz_check_bdev(zmd->dev);
+		dmz_check_bdev(dev);
 	return ret;
 }
 
@@ -637,18 +780,32 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
  */
 static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set)
 {
-	sector_t block = zmd->sb[set].block;
 	struct dmz_mblock *mblk = zmd->sb[set].mblk;
 	struct dmz_super *sb = zmd->sb[set].sb;
+	struct dmz_dev *dev = zmd->sb[set].dev;
+	sector_t sb_block;
 	u64 sb_gen = zmd->sb_gen + 1;
 	int ret;
 
 	sb->magic = cpu_to_le32(DMZ_MAGIC);
-	sb->version = cpu_to_le32(DMZ_META_VER);
+
+	sb->version = cpu_to_le32(zmd->sb_version);
+	if (zmd->sb_version > 1) {
+		BUILD_BUG_ON(UUID_SIZE != 16);
+		export_uuid(sb->dmz_uuid, &zmd->uuid);
+		memcpy(sb->dmz_label, zmd->label, BDEVNAME_SIZE);
+		export_uuid(sb->dev_uuid, &dev->uuid);
+	}
 
 	sb->gen = cpu_to_le64(sb_gen);
 
-	sb->sb_block = cpu_to_le64(block);
+	/*
+	 * The metadata always references the absolute block address,
+	 * ie relative to the entire block range, not the per-device
+	 * block address.
+	 */
+	sb_block = zmd->sb[set].zone->id << zmd->zone_nr_blocks_shift;
+	sb->sb_block = cpu_to_le64(sb_block);
 	sb->nr_meta_blocks = cpu_to_le32(zmd->nr_meta_blocks);
 	sb->nr_reserved_seq = cpu_to_le32(zmd->nr_reserved_seq);
 	sb->nr_chunks = cpu_to_le32(zmd->nr_chunks);
@@ -659,9 +816,10 @@ static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set)
 	sb->crc = 0;
 	sb->crc = cpu_to_le32(crc32_le(sb_gen, (unsigned char *)sb, DMZ_BLOCK_SIZE));
 
-	ret = dmz_rdwr_block(zmd, REQ_OP_WRITE, block, mblk->page);
+	ret = dmz_rdwr_block(dev, REQ_OP_WRITE, zmd->sb[set].block,
+			     mblk->page);
 	if (ret == 0)
-		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
 
 	return ret;
 }
@@ -674,6 +832,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 				   unsigned int set)
 {
 	struct dmz_mblock *mblk;
+	struct dmz_dev *dev = zmd->sb[set].dev;
 	struct blk_plug plug;
 	int ret = 0, nr_mblks_submitted = 0;
 
@@ -695,7 +854,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 			       TASK_UNINTERRUPTIBLE);
 		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 			clear_bit(DMZ_META_ERROR, &mblk->state);
-			dmz_check_bdev(zmd->dev);
+			dmz_check_bdev(dev);
 			ret = -EIO;
 		}
 		nr_mblks_submitted--;
@@ -703,7 +862,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 
 	/* Flush drive cache (this will also sync data) */
 	if (ret == 0)
-		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
 
 	return ret;
 }
@@ -740,6 +899,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 {
 	struct dmz_mblock *mblk;
 	struct list_head write_list;
+	struct dmz_dev *dev;
 	int ret;
 
 	if (WARN_ON(!zmd))
@@ -753,6 +913,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 * from modifying metadata.
 	 */
 	down_write(&zmd->mblk_sem);
+	dev = zmd->sb[zmd->mblk_primary].dev;
 
 	/*
 	 * This is called from the target flush work and reclaim work.
@@ -760,7 +921,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	dmz_lock_flush(zmd);
 
-	if (dmz_bdev_is_dying(zmd->dev)) {
+	if (dmz_bdev_is_dying(dev)) {
 		ret = -EIO;
 		goto out;
 	}
@@ -772,7 +933,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 
 	/* If there are no dirty metadata blocks, just flush the device cache */
 	if (list_empty(&write_list)) {
-		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
 		goto err;
 	}
 
@@ -821,7 +982,7 @@ err:
 		list_splice(&write_list, &zmd->mblk_dirty_list);
 		spin_unlock(&zmd->mblk_lock);
 	}
-	if (!dmz_check_bdev(zmd->dev))
+	if (!dmz_check_bdev(dev))
 		ret = -EIO;
 	goto out;
 }
@@ -829,12 +990,31 @@ err:
 /*
  * Check super block.
  */
-static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb)
+static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb,
+			bool tertiary)
 {
+	struct dmz_super *sb = dsb->sb;
+	struct dmz_dev *dev = dsb->dev;
 	unsigned int nr_meta_zones, nr_data_zones;
-	struct dmz_dev *dev = zmd->dev;
 	u32 crc, stored_crc;
-	u64 gen;
+	u64 gen, sb_block;
+
+	if (le32_to_cpu(sb->magic) != DMZ_MAGIC) {
+		dmz_dev_err(dev, "Invalid meta magic (needed 0x%08x, got 0x%08x)",
+			    DMZ_MAGIC, le32_to_cpu(sb->magic));
+		return -ENXIO;
+	}
+
+	zmd->sb_version = le32_to_cpu(sb->version);
+	if (zmd->sb_version > DMZ_META_VER) {
+		dmz_dev_err(dev, "Invalid meta version (needed %d, got %d)",
+			    DMZ_META_VER, zmd->sb_version);
+		return -EINVAL;
+	}
+	if (zmd->sb_version < 2 && tertiary) {
+		dmz_dev_err(dev, "Tertiary superblocks are not supported");
+		return -EINVAL;
+	}
 
 	gen = le64_to_cpu(sb->gen);
 	stored_crc = le32_to_cpu(sb->crc);
@@ -846,20 +1026,57 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb)
 		return -ENXIO;
 	}
 
-	if (le32_to_cpu(sb->magic) != DMZ_MAGIC) {
-		dmz_dev_err(dev, "Invalid meta magic (needed 0x%08x, got 0x%08x)",
-			    DMZ_MAGIC, le32_to_cpu(sb->magic));
-		return -ENXIO;
-	}
+	sb_block = le64_to_cpu(sb->sb_block);
+	if (sb_block != (u64)dsb->zone->id << zmd->zone_nr_blocks_shift ) {
+		dmz_dev_err(dev, "Invalid superblock position "
+			    "(is %llu expected %llu)",
+			    sb_block,
+			    (u64)dsb->zone->id << zmd->zone_nr_blocks_shift);
+		return -EINVAL;
+	}
+	if (zmd->sb_version > 1) {
+		uuid_t sb_uuid;
+
+		import_uuid(&sb_uuid, sb->dmz_uuid);
+		if (uuid_is_null(&sb_uuid)) {
+			dmz_dev_err(dev, "NULL DM-Zoned uuid");
+			return -ENXIO;
+		} else if (uuid_is_null(&zmd->uuid)) {
+			uuid_copy(&zmd->uuid, &sb_uuid);
+		} else if (!uuid_equal(&zmd->uuid, &sb_uuid)) {
+			dmz_dev_err(dev, "mismatching DM-Zoned uuid, "
+				    "is %pUl expected %pUl",
+				    &sb_uuid, &zmd->uuid);
+			return -ENXIO;
+		}
+		if (!strlen(zmd->label))
+			memcpy(zmd->label, sb->dmz_label, BDEVNAME_SIZE);
+		else if (memcmp(zmd->label, sb->dmz_label, BDEVNAME_SIZE)) {
+			dmz_dev_err(dev, "mismatching DM-Zoned label, "
+				    "is %s expected %s",
+				    sb->dmz_label, zmd->label);
+			return -ENXIO;
+		}
+		import_uuid(&dev->uuid, sb->dev_uuid);
+		if (uuid_is_null(&dev->uuid)) {
+			dmz_dev_err(dev, "NULL device uuid");
+			return -ENXIO;
+		}
 
-	if (le32_to_cpu(sb->version) != DMZ_META_VER) {
-		dmz_dev_err(dev, "Invalid meta version (needed %d, got %d)",
-			    DMZ_META_VER, le32_to_cpu(sb->version));
-		return -ENXIO;
+		if (tertiary) {
+			/*
+			 * Generation number should be 0, but it doesn't
+			 * really matter if it isn't.
+			 */
+			if (gen != 0)
+				dmz_dev_warn(dev, "Invalid generation %llu",
+					    gen);
+			return 0;
+		}
 	}
 
-	nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + dev->zone_nr_blocks - 1)
-		>> dev->zone_nr_blocks_shift;
+	nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1)
+		>> zmd->zone_nr_blocks_shift;
 	if (!nr_meta_zones ||
 	    nr_meta_zones >= zmd->nr_rnd_zones) {
 		dmz_dev_err(dev, "Invalid number of metadata blocks");
@@ -895,10 +1112,13 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb)
 /*
  * Read the first or second super block from disk.
  */
-static int dmz_read_sb(struct dmz_metadata *zmd, unsigned int set)
+static int dmz_read_sb(struct dmz_metadata *zmd, struct dmz_sb *sb, int set)
 {
-	return dmz_rdwr_block(zmd, REQ_OP_READ, zmd->sb[set].block,
-			      zmd->sb[set].mblk->page);
+	dmz_zmd_debug(zmd, "read superblock set %d dev %s block %llu",
+		      set, sb->dev->name, sb->block);
+
+	return dmz_rdwr_block(sb->dev, REQ_OP_READ,
+			      sb->block, sb->mblk->page);
 }
 
 /*
@@ -908,8 +1128,9 @@ static int dmz_read_sb(struct dmz_metadata *zmd, unsigned int set)
  */
 static int dmz_lookup_secondary_sb(struct dmz_metadata *zmd)
 {
-	unsigned int zone_nr_blocks = zmd->dev->zone_nr_blocks;
+	unsigned int zone_nr_blocks = zmd->zone_nr_blocks;
 	struct dmz_mblock *mblk;
+	unsigned int zone_id = zmd->sb[0].zone->id;
 	int i;
 
 	/* Allocate a block */
@@ -922,24 +1143,29 @@ static int dmz_lookup_secondary_sb(struct dmz_metadata *zmd)
 
 	/* Bad first super block: search for the second one */
 	zmd->sb[1].block = zmd->sb[0].block + zone_nr_blocks;
-	for (i = 0; i < zmd->nr_rnd_zones - 1; i++) {
-		if (dmz_read_sb(zmd, 1) != 0)
+	zmd->sb[1].zone = dmz_get(zmd, zone_id + 1);
+	zmd->sb[1].dev = zmd->sb[0].dev;
+	for (i = 1; i < zmd->nr_rnd_zones; i++) {
+		if (dmz_read_sb(zmd, &zmd->sb[1], 1) != 0)
 			break;
 		if (le32_to_cpu(zmd->sb[1].sb->magic) == DMZ_MAGIC)
 			return 0;
 		zmd->sb[1].block += zone_nr_blocks;
+		zmd->sb[1].zone = dmz_get(zmd, zone_id + i);
 	}
 
 	dmz_free_mblock(zmd, mblk);
 	zmd->sb[1].mblk = NULL;
+	zmd->sb[1].zone = NULL;
+	zmd->sb[1].dev = NULL;
 
 	return -EIO;
 }
 
 /*
- * Read the first or second super block from disk.
+ * Read a super block from disk.
  */
-static int dmz_get_sb(struct dmz_metadata *zmd, unsigned int set)
+static int dmz_get_sb(struct dmz_metadata *zmd, struct dmz_sb *sb, int set)
 {
 	struct dmz_mblock *mblk;
 	int ret;
@@ -949,14 +1175,14 @@ static int dmz_get_sb(struct dmz_metadata *zmd, unsigned int set)
 	if (!mblk)
 		return -ENOMEM;
 
-	zmd->sb[set].mblk = mblk;
-	zmd->sb[set].sb = mblk->data;
+	sb->mblk = mblk;
+	sb->sb = mblk->data;
 
 	/* Read super block */
-	ret = dmz_read_sb(zmd, set);
+	ret = dmz_read_sb(zmd, sb, set);
 	if (ret) {
 		dmz_free_mblock(zmd, mblk);
-		zmd->sb[set].mblk = NULL;
+		sb->mblk = NULL;
 		return ret;
 	}
 
@@ -972,14 +1198,13 @@ static int dmz_recover_mblocks(struct dmz_metadata *zmd, unsigned int dst_set)
 	struct page *page;
 	int i, ret;
 
-	dmz_dev_warn(zmd->dev, "Metadata set %u invalid: recovering", dst_set);
+	dmz_dev_warn(zmd->sb[dst_set].dev,
+		     "Metadata set %u invalid: recovering", dst_set);
 
 	if (dst_set == 0)
-		zmd->sb[0].block = dmz_start_block(zmd, zmd->sb_zone);
-	else {
-		zmd->sb[1].block = zmd->sb[0].block +
-			(zmd->nr_meta_zones << zmd->dev->zone_nr_blocks_shift);
-	}
+		zmd->sb[0].block = dmz_start_block(zmd, zmd->sb[0].zone);
+	else
+		zmd->sb[1].block = dmz_start_block(zmd, zmd->sb[1].zone);
 
 	page = alloc_page(GFP_NOIO);
 	if (!page)
@@ -987,11 +1212,11 @@ static int dmz_recover_mblocks(struct dmz_metadata *zmd, unsigned int dst_set)
 
 	/* Copy metadata blocks */
 	for (i = 1; i < zmd->nr_meta_blocks; i++) {
-		ret = dmz_rdwr_block(zmd, REQ_OP_READ,
+		ret = dmz_rdwr_block(zmd->sb[src_set].dev, REQ_OP_READ,
 				     zmd->sb[src_set].block + i, page);
 		if (ret)
 			goto out;
-		ret = dmz_rdwr_block(zmd, REQ_OP_WRITE,
+		ret = dmz_rdwr_block(zmd->sb[dst_set].dev, REQ_OP_WRITE,
 				     zmd->sb[dst_set].block + i, page);
 		if (ret)
 			goto out;
@@ -1023,53 +1248,73 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
 	u64 sb_gen[2] = {0, 0};
 	int ret;
 
+	if (!zmd->sb[0].zone) {
+		dmz_zmd_err(zmd, "Primary super block zone not set");
+		return -ENXIO;
+	}
+
 	/* Read and check the primary super block */
-	zmd->sb[0].block = dmz_start_block(zmd, zmd->sb_zone);
-	ret = dmz_get_sb(zmd, 0);
+	zmd->sb[0].block = dmz_start_block(zmd, zmd->sb[0].zone);
+	zmd->sb[0].dev = zmd->sb[0].zone->dev;
+	ret = dmz_get_sb(zmd, &zmd->sb[0], 0);
 	if (ret) {
-		dmz_dev_err(zmd->dev, "Read primary super block failed");
+		dmz_dev_err(zmd->sb[0].dev, "Read primary super block failed");
 		return ret;
 	}
 
-	ret = dmz_check_sb(zmd, zmd->sb[0].sb);
+	ret = dmz_check_sb(zmd, &zmd->sb[0], false);
 
 	/* Read and check secondary super block */
 	if (ret == 0) {
 		sb_good[0] = true;
-		zmd->sb[1].block = zmd->sb[0].block +
-			(zmd->nr_meta_zones << zmd->dev->zone_nr_blocks_shift);
-		ret = dmz_get_sb(zmd, 1);
+		if (!zmd->sb[1].zone) {
+			unsigned int zone_id =
+				zmd->sb[0].zone->id + zmd->nr_meta_zones;
+
+			zmd->sb[1].zone = dmz_get(zmd, zone_id);
+		}
+		zmd->sb[1].block = dmz_start_block(zmd, zmd->sb[1].zone);
+		zmd->sb[1].dev = zmd->sb[0].dev;
+		ret = dmz_get_sb(zmd, &zmd->sb[1], 1);
 	} else
 		ret = dmz_lookup_secondary_sb(zmd);
 
 	if (ret) {
-		dmz_dev_err(zmd->dev, "Read secondary super block failed");
+		dmz_dev_err(zmd->sb[1].dev, "Read secondary super block failed");
 		return ret;
 	}
 
-	ret = dmz_check_sb(zmd, zmd->sb[1].sb);
+	ret = dmz_check_sb(zmd, &zmd->sb[1], false);
 	if (ret == 0)
 		sb_good[1] = true;
 
 	/* Use highest generation sb first */
 	if (!sb_good[0] && !sb_good[1]) {
-		dmz_dev_err(zmd->dev, "No valid super block found");
+		dmz_zmd_err(zmd, "No valid super block found");
 		return -EIO;
 	}
 
 	if (sb_good[0])
 		sb_gen[0] = le64_to_cpu(zmd->sb[0].sb->gen);
-	else
+	else {
 		ret = dmz_recover_mblocks(zmd, 0);
+		if (ret) {
+			dmz_dev_err(zmd->sb[0].dev,
+				    "Recovery of superblock 0 failed");
+			return -EIO;
+		}
+	}
 
 	if (sb_good[1])
 		sb_gen[1] = le64_to_cpu(zmd->sb[1].sb->gen);
-	else
+	else {
 		ret = dmz_recover_mblocks(zmd, 1);
 
-	if (ret) {
-		dmz_dev_err(zmd->dev, "Recovery failed");
-		return -EIO;
+		if (ret) {
+			dmz_dev_err(zmd->sb[1].dev,
+				    "Recovery of superblock 1 failed");
+			return -EIO;
+		}
 	}
 
 	if (sb_gen[0] >= sb_gen[1]) {
@@ -1080,32 +1325,70 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
 		zmd->mblk_primary = 1;
 	}
 
-	dmz_dev_debug(zmd->dev, "Using super block %u (gen %llu)",
+	dmz_dev_debug(zmd->sb[zmd->mblk_primary].dev,
+		      "Using super block %u (gen %llu)",
 		      zmd->mblk_primary, zmd->sb_gen);
 
-	return 0;
+	if (zmd->sb_version > 1) {
+		int i;
+		struct dmz_sb *sb;
+
+		sb = kzalloc(sizeof(struct dmz_sb), GFP_KERNEL);
+		if (!sb)
+			return -ENOMEM;
+		for (i = 1; i < zmd->nr_devs; i++) {
+			sb->block = 0;
+			sb->zone = dmz_get(zmd, zmd->dev[i].zone_offset);
+			sb->dev = &zmd->dev[i];
+			if (!dmz_is_meta(sb->zone)) {
+				dmz_dev_err(sb->dev,
+					    "Tertiary super block zone %u not marked as metadata zone",
+					    sb->zone->id);
+				ret = -EINVAL;
+				goto out_kfree;
+			}
+			ret = dmz_get_sb(zmd, sb, i + 1);
+			if (ret) {
+				dmz_dev_err(sb->dev,
+					    "Read tertiary super block failed");
+				dmz_free_mblock(zmd, sb->mblk);
+				goto out_kfree;
+			}
+			ret = dmz_check_sb(zmd, sb, true);
+			dmz_free_mblock(zmd, sb->mblk);
+			if (ret == -EINVAL)
+				goto out_kfree;
+		}
+	out_kfree:
+		kfree(sb);
+	}
+	return ret;
 }
 
 /*
  * Initialize a zone descriptor.
  */
-static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
+static int dmz_init_zone(struct blk_zone *blkz, unsigned int num, void *data)
 {
-	struct dmz_metadata *zmd = data;
-	struct dm_zone *zone = &zmd->zones[idx];
-	struct dmz_dev *dev = zmd->dev;
+	struct dmz_dev *dev = data;
+	struct dmz_metadata *zmd = dev->metadata;
+	int idx = num + dev->zone_offset;
+	struct dm_zone *zone;
+
+	zone = dmz_insert(zmd, idx, dev);
+	if (IS_ERR(zone))
+		return PTR_ERR(zone);
 
-	/* Ignore the eventual last runt (smaller) zone */
-	if (blkz->len != dev->zone_nr_sectors) {
-		if (blkz->start + blkz->len == dev->capacity)
+	if (blkz->len != zmd->zone_nr_sectors) {
+		if (zmd->sb_version > 1) {
+			/* Ignore the eventual runt (smaller) zone */
+			set_bit(DMZ_OFFLINE, &zone->flags);
+			return 0;
+		} else if (blkz->start + blkz->len == dev->capacity)
 			return 0;
 		return -ENXIO;
 	}
 
-	INIT_LIST_HEAD(&zone->link);
-	atomic_set(&zone->refcount, 0);
-	zone->chunk = DMZ_MAP_UNMAPPED;
-
 	switch (blkz->type) {
 	case BLK_ZONE_TYPE_CONVENTIONAL:
 		set_bit(DMZ_RND, &zone->flags);
@@ -1131,13 +1414,45 @@ static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
 		zmd->nr_useable_zones++;
 		if (dmz_is_rnd(zone)) {
 			zmd->nr_rnd_zones++;
-			if (!zmd->sb_zone) {
-				/* Super block zone */
-				zmd->sb_zone = zone;
+			if (zmd->nr_devs == 1 && !zmd->sb[0].zone) {
+				/* Primary super block zone */
+				zmd->sb[0].zone = zone;
 			}
 		}
+		if (zmd->nr_devs > 1 && num == 0) {
+			/*
+			 * Tertiary superblock zones are always at the
+			 * start of the zoned devices, so mark them
+			 * as metadata zone.
+			 */
+			set_bit(DMZ_META, &zone->flags);
+		}
 	}
+	return 0;
+}
+
+static int dmz_emulate_zones(struct dmz_metadata *zmd, struct dmz_dev *dev)
+{
+	int idx;
+	sector_t zone_offset = 0;
 
+	for(idx = 0; idx < dev->nr_zones; idx++) {
+		struct dm_zone *zone;
+
+		zone = dmz_insert(zmd, idx, dev);
+		if (IS_ERR(zone))
+			return PTR_ERR(zone);
+		set_bit(DMZ_CACHE, &zone->flags);
+		zone->wp_block = 0;
+		zmd->nr_cache_zones++;
+		zmd->nr_useable_zones++;
+		if (dev->capacity - zone_offset < zmd->zone_nr_sectors) {
+			/* Disable runt zone */
+			set_bit(DMZ_OFFLINE, &zone->flags);
+			break;
+		}
+		zone_offset += zmd->zone_nr_sectors;
+	}
 	return 0;
 }
 
@@ -1146,8 +1461,15 @@ static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
  */
 static void dmz_drop_zones(struct dmz_metadata *zmd)
 {
-	kfree(zmd->zones);
-	zmd->zones = NULL;
+	int idx;
+
+	for(idx = 0; idx < zmd->nr_zones; idx++) {
+		struct dm_zone *zone = xa_load(&zmd->zones, idx);
+
+		kfree(zone);
+		xa_erase(&zmd->zones, idx);
+	}
+	xa_destroy(&zmd->zones);
 }
 
 /*
@@ -1156,32 +1478,87 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
  */
 static int dmz_init_zones(struct dmz_metadata *zmd)
 {
-	struct dmz_dev *dev = zmd->dev;
-	int ret;
+	int i, ret;
+	struct dmz_dev *zoned_dev = &zmd->dev[0];
 
 	/* Init */
-	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
+	zmd->zone_nr_sectors = zmd->dev[0].zone_nr_sectors;
+	zmd->zone_nr_sectors_shift = ilog2(zmd->zone_nr_sectors);
+	zmd->zone_nr_blocks = dmz_sect2blk(zmd->zone_nr_sectors);
+	zmd->zone_nr_blocks_shift = ilog2(zmd->zone_nr_blocks);
+	zmd->zone_bitmap_size = zmd->zone_nr_blocks >> 3;
 	zmd->zone_nr_bitmap_blocks =
 		max_t(sector_t, 1, zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT);
-	zmd->zone_bits_per_mblk = min_t(sector_t, dev->zone_nr_blocks,
+	zmd->zone_bits_per_mblk = min_t(sector_t, zmd->zone_nr_blocks,
 					DMZ_BLOCK_SIZE_BITS);
 
 	/* Allocate zone array */
-	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
-	if (!zmd->zones)
-		return -ENOMEM;
+	zmd->nr_zones = 0;
+	for (i = 0; i < zmd->nr_devs; i++) {
+		struct dmz_dev *dev = &zmd->dev[i];
+
+		dev->metadata = zmd;
+		zmd->nr_zones += dev->nr_zones;
+
+		atomic_set(&dev->unmap_nr_rnd, 0);
+		INIT_LIST_HEAD(&dev->unmap_rnd_list);
+		INIT_LIST_HEAD(&dev->map_rnd_list);
+
+		atomic_set(&dev->unmap_nr_seq, 0);
+		INIT_LIST_HEAD(&dev->unmap_seq_list);
+		INIT_LIST_HEAD(&dev->map_seq_list);
+	}
+
+	if (!zmd->nr_zones) {
+		DMERR("(%s): No zones found", zmd->devname);
+		return -ENXIO;
+	}
+	xa_init(&zmd->zones);
+
+	DMDEBUG("(%s): Using %zu B for zone information",
+		zmd->devname, sizeof(struct dm_zone) * zmd->nr_zones);
 
-	dmz_dev_info(dev, "Using %zu B for zone information",
-		     sizeof(struct dm_zone) * dev->nr_zones);
+	if (zmd->nr_devs > 1) {
+		ret = dmz_emulate_zones(zmd, &zmd->dev[0]);
+		if (ret < 0) {
+			DMDEBUG("(%s): Failed to emulate zones, error %d",
+				zmd->devname, ret);
+			dmz_drop_zones(zmd);
+			return ret;
+		}
+
+		/*
+		 * Primary superblock zone is always at zone 0 when multiple
+		 * drives are present.
+		 */
+		zmd->sb[0].zone = dmz_get(zmd, 0);
+
+		for (i = 1; i < zmd->nr_devs; i++) {
+			zoned_dev = &zmd->dev[i];
+
+			ret = blkdev_report_zones(zoned_dev->bdev, 0,
+						  BLK_ALL_ZONES,
+						  dmz_init_zone, zoned_dev);
+			if (ret < 0) {
+				DMDEBUG("(%s): Failed to report zones, error %d",
+					zmd->devname, ret);
+				dmz_drop_zones(zmd);
+				return ret;
+			}
+		}
+		return 0;
+	}
 
 	/*
 	 * Get zone information and initialize zone descriptors.  At the same
 	 * time, determine where the super block should be: first block of the
 	 * first randomly writable zone.
 	 */
-	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone,
-				  zmd);
+	ret = blkdev_report_zones(zoned_dev->bdev, 0, BLK_ALL_ZONES,
+				  dmz_init_zone, zoned_dev);
 	if (ret < 0) {
+		DMDEBUG("(%s): Failed to report zones, error %d",
+			zmd->devname, ret);
 		dmz_drop_zones(zmd);
 		return ret;
 	}
@@ -1213,9 +1590,13 @@ static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx,