dm zoned: metadata version 2

Implement handling for metadata version 2. The new metadata adds a
label and UUID for the device mapper device, and additional UUID for
the underlying block devices.

It also allows for an additional regular drive to be used for
emulating random access zones. The emulated zones will be placed
logically in front of the zones from the zoned block device, causing
the superblocks and metadata to be stored on that device.

The first zone of the original zoned device will be used to hold
another, tertiary copy of the metadata; this copy carries a generation
number of 0 and is never updated; it's just used for identification.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Documentation/admin-guide/device-mapper/dm-zoned.rst

@@ -37,9 +37,13 @@ Algorithm
 dm-zoned implements an on-disk buffering scheme to handle non-sequential
 write accesses to the sequential zones of a zoned block device.
 Conventional zones are used for caching as well as for storing internal
-metadata.
+metadata. It can also use a regular block device together with the zoned
+block device; in that case the regular block device will be split logically
+in zones with the same size as the zoned block device. These zones will be
+placed in front of the zones from the zoned block device and will be handled
+just like conventional zones.
 
-The zones of the device are separated into 2 types:
+The zones of the device(s) are separated into 2 types:
 
 1) Metadata zones: these are conventional zones used to store metadata.
 Metadata zones are not reported as useable capacity to the user.
@@ -127,6 +131,13 @@ resumed. Flushing metadata thus only temporarily delays write and
 discard requests. Read requests can be processed concurrently while
 metadata flush is being executed.
 
+If a regular device is used in conjunction with the zoned block device,
+a third set of metadata (without the zone bitmaps) is written to the
+start of the zoned block device. This metadata has a generation counter of
+'0' and will never be updated during normal operation; it just serves for
+identification purposes. The first and second copy of the metadata
+are located at the start of the regular block device.
+
 Usage
 =====
 
@@ -138,12 +149,21 @@ Ex::
 
 	dmzadm --format /dev/sdxx
 
-For a formatted device, the target can be created normally with the
-dmsetup utility. The only parameter that dm-zoned requires is the
-underlying zoned block device name. Ex::
 
-	echo "0 `blockdev --getsize ${dev}` zoned ${dev}" | \
-	dmsetup create dmz-`basename ${dev}`
+If two drives are to be used, both devices must be specified, with the
+regular block device as the first device.
+
+Ex::
+
+	dmzadm --format /dev/sdxx /dev/sdyy
+
+
+Fomatted device(s) can be started with the dmzadm utility, too.:
+
+Ex::
+
+	dmzadm --start /dev/sdxx /dev/sdyy
+
 
 Information about the internal layout and current usage of the zones can
 be obtained with the 'status' callback from dmsetup:

drivers/md/dm-zoned-target.c

@@ -13,6 +13,8 @@
 
 #define DMZ_MIN_BIOS		8192
 
+#define DMZ_MAX_DEVS		2
+
 /*
  * Zone BIO context.
  */
@@ -38,7 +40,7 @@ struct dm_chunk_work {
  * Target descriptor.
  */
 struct dmz_target {
-	struct dm_dev		*ddev;
+	struct dm_dev		*ddev[DMZ_MAX_DEVS];
 
 	unsigned long		flags;
 
@@ -81,7 +83,7 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
 
 	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
 		bio->bi_status = status;
-	if (bio->bi_status != BLK_STS_OK)
+	if (bioctx->dev && bio->bi_status != BLK_STS_OK)
 		bioctx->dev->flags |= DMZ_CHECK_BDEV;
 
 	if (refcount_dec_and_test(&bioctx->ref)) {
@@ -690,60 +692,64 @@ 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;
+	bdev = ddev->bdev;
+	if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) {
+		if (nr_devs == 1) {
+			ti->error = "Invalid regular device";
 			goto err;
 		}
-
-	dev->bdev = dmz->ddev->bdev;
-	(void)bdevname(dev->bdev, dev->name);
-
-	if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE) {
-		ti->error = "Not a zoned block device";
-		ret = -EINVAL;
+		if (idx != 0) {
+			ti->error = "First device must be a regular device";
 			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;
+		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 = bdev;
+	(void)bdevname(dev->bdev, dev->name);
 
-	dev->zone_nr_sectors = blk_queue_zone_sectors(q);
-
-	dev->nr_zones = blkdev_nr_zones(dev->bdev->bd_disk);
+	dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+	if (ti->begin) {
+		ti->error = "Partial mapping is not supported";
+		goto err;
+	}
 
-	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;
 }
 
 /*
@@ -752,10 +758,56 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path)
 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_MAX_DEVS; 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;
+
+	/*
+	 * When we have two devices, the first one must be a regular block
+	 * device and the second a zoned block device.
+	 */
+	if (dmz->ddev[0] && dmz->ddev[1]) {
+		reg_dev = &dmz->dev[0];
+		if (!(reg_dev->flags & DMZ_BDEV_REGULAR)) {
+			ti->error = "Primary disk is not a regular device";
+			return -EINVAL;
+		}
+		zoned_dev = &dmz->dev[1];
+		if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
+			ti->error = "Secondary disk is not a zoned device";
+			return -EINVAL;
+		}
+	} 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) {
+		reg_dev->zone_nr_sectors = zoned_dev->zone_nr_sectors;
+		reg_dev->nr_zones = DIV_ROUND_UP(reg_dev->capacity,
+						 reg_dev->zone_nr_sectors);
+		zoned_dev->zone_offset = reg_dev->nr_zones;
+	}
+	return 0;
 }
 
 /*
@@ -764,11 +816,10 @@ 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;
 
 	/* Check arguments */
-	if (argc != 1) {
+	if (argc < 1 || argc > 2) {
 		ti->error = "Invalid argument count";
 		return -EINVAL;
 	}
@@ -779,18 +830,34 @@ 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(2, sizeof(struct dmz_dev), GFP_KERNEL);
+	if (!dmz->dev) {
+		ti->error = "Unable to allocate the zoned device descriptors";
+		kfree(dmz);
+		return -ENOMEM;
+	}
 	ti->private = dmz;
 
 	/* Get the target zoned block device */
-	ret = dmz_get_zoned_device(ti, argv[0]);
+	ret = dmz_get_zoned_device(ti, argv[0], 0, argc);
+	if (ret)
+		goto err;
+
+	if (argc == 2) {
+		ret = dmz_get_zoned_device(ti, argv[1], 1, argc);
+		if (ret) {
+			dmz_put_zoned_device(ti);
+			goto err;
+		}
+	}
+	ret = dmz_fixup_devices(ti);
 	if (ret) {
-		dmz->ddev = NULL;
+		dmz_put_zoned_device(ti);
 		goto err;
 	}
 
 	/* 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";
@@ -867,6 +934,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 err_dev:
 	dmz_put_zoned_device(ti);
 err:
+	kfree(dmz->dev);
 	kfree(dmz);
 
 	return ret;
@@ -897,6 +965,7 @@ static void dmz_dtr(struct dm_target *ti)
 
 	mutex_destroy(&dmz->chunk_lock);
 
+	kfree(dmz->dev);
 	kfree(dmz);
 }
 
@@ -971,10 +1040,17 @@ 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 & ~(dmz_zone_nr_sectors(dmz->metadata) - 1);
-
-	return fn(ti, dmz->ddev, 0, capacity, data);
+	unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata);
+	sector_t capacity;
+	int r;
+
+	capacity = dmz->dev[0].capacity & ~(zone_nr_sectors - 1);
+	r = fn(ti, dmz->ddev[0], 0, capacity, data);
+	if (!r && dmz->ddev[1]) {
+		capacity = dmz->dev[1].capacity & ~(zone_nr_sectors - 1);
+		r = fn(ti, dmz->ddev[1], 0, capacity, data);
+	}
+	return r;
 }
 
 static void dmz_status(struct dm_target *ti, status_type_t type,
@@ -984,6 +1060,7 @@ static void dmz_status(struct dm_target *ti, status_type_t type,
 	struct dmz_target *dmz = ti->private;
 	ssize_t sz = 0;
 	char buf[BDEVNAME_SIZE];
+	struct dmz_dev *dev;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -995,8 +1072,14 @@ static void dmz_status(struct dm_target *ti, status_type_t type,
 		       dmz_nr_seq_zones(dmz->metadata));
 		break;
 	case STATUSTYPE_TABLE:
-		format_dev_t(buf, dmz->dev->bdev->bd_dev);
+		dev = &dmz->dev[0];
+		format_dev_t(buf, dev->bdev->bd_dev);
 		DMEMIT("%s", buf);
+		if (dmz->dev[1].bdev) {
+			dev = &dmz->dev[1];
+			format_dev_t(buf, dev->bdev->bd_dev);
+			DMEMIT(" %s", buf);
+		}
 		break;
 	}
 	return;
@@ -1018,7 +1101,7 @@ static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv,
 
 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,

drivers/md/dm-zoned.h

@@ -52,10 +52,12 @@ struct dmz_dev {
 	struct block_device	*bdev;
 
 	char			name[BDEVNAME_SIZE];
+	uuid_t			uuid;
 
 	sector_t		capacity;
 
 	unsigned int		nr_zones;
+	unsigned int		zone_offset;
 
 	unsigned int		flags;
 
@@ -69,6 +71,7 @@ struct dmz_dev {
 /* Device flags. */
 #define DMZ_BDEV_DYING		(1 << 0)
 #define DMZ_CHECK_BDEV		(2 << 0)
+#define DMZ_BDEV_REGULAR	(4 << 0)
 
 /*
  * Zone descriptor.
@@ -163,8 +166,8 @@ struct dmz_reclaim;
 /*
  * Functions defined in dm-zoned-metadata.c
  */
-int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **zmd,
-		     const char *devname);
+int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
+		     struct dmz_metadata **zmd, const char *devname);
 void dmz_dtr_metadata(struct dmz_metadata *zmd);
 int dmz_resume_metadata(struct dmz_metadata *zmd);