Merge tag 'for-4.13/dm-changes' of...

Merge tag 'for-4.13/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Add the ability to use select or poll /dev/mapper/control to wait for
   events from multiple DM devices.

 - Convert DM's printk macros over to using pr_<level> macros.

 - Add a big-endian variant of plain64 IV to dm-crypt.

 - Add support for zoned (aka SMR) devices to DM core. DM kcopyd was
   also improved to provide a sequential write feature needed by zoned
   devices.

 - Introduce DM zoned target that provides support for host-managed
   zoned devices, the result dm-zoned device acts as a drive-managed
   interface to the underlying host-managed device.

 - A DM raid fix to avoid using BUG() for error handling.

* tag 'for-4.13/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm zoned: fix overflow when converting zone ID to sectors
  dm raid: stop using BUG() in __rdev_sectors()
  dm zoned: drive-managed zoned block device target
  dm kcopyd: add sequential write feature
  dm linear: add support for zoned block devices
  dm flakey: add support for zoned block devices
  dm: introduce dm_remap_zone_report()
  dm: fix REQ_OP_ZONE_REPORT bio handling
  dm: fix REQ_OP_ZONE_RESET bio handling
  dm table: add zoned block devices validation
  dm: convert DM printk macros to pr_<level> macros
  dm crypt: add big-endian variant of plain64 IV
  dm bio prison: use rb_entry() rather than container_of()
  dm ioctl: report event number in DM_LIST_DEVICES
  dm ioctl: add a new DM_DEV_ARM_POLL ioctl
  dm: add basic support for using the select or poll function

Documentation/device-mapper/dm-zoned.txt

+dm-zoned
+========
+
+The dm-zoned device mapper target exposes a zoned block device (ZBC and
+ZAC compliant devices) as a regular block device without any write
+pattern constraints. In effect, it implements a drive-managed zoned
+block device which hides from the user (a file system or an application
+doing raw block device accesses) the sequential write constraints of
+host-managed zoned block devices and can mitigate the potential
+device-side performance degradation due to excessive random writes on
+host-aware zoned block devices.
+
+For a more detailed description of the zoned block device models and
+their constraints see (for SCSI devices):
+
+http://www.t10.org/drafts.htm#ZBC_Family
+
+and (for ATA devices):
+
+http://www.t13.org/Documents/UploadedDocuments/docs2015/di537r05-Zoned_Device_ATA_Command_Set_ZAC.pdf
+
+The dm-zoned implementation is simple and minimizes system overhead (CPU
+and memory usage as well as storage capacity loss). For a 10TB
+host-managed disk with 256 MB zones, dm-zoned memory usage per disk
+instance is at most 4.5 MB and as little as 5 zones will be used
+internally for storing metadata and performaing reclaim operations.
+
+dm-zoned target devices are formatted and checked using the dmzadm
+utility available at:
+
+https://github.com/hgst/dm-zoned-tools
+
+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.
+
+The zones of the device 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.
+
+2) Data zones: all remaining zones, the vast majority of which will be
+sequential zones used exclusively to store user data. The conventional
+zones of the device may be used also for buffering user random writes.
+Data in these zones may be directly mapped to the conventional zone, but
+later moved to a sequential zone so that the conventional zone can be
+reused for buffering incoming random writes.
+
+dm-zoned exposes a logical device with a sector size of 4096 bytes,
+irrespective of the physical sector size of the backend zoned block
+device being used. This allows reducing the amount of metadata needed to
+manage valid blocks (blocks written).
+
+The on-disk metadata format is as follows:
+
+1) The first block of the first conventional zone found contains the
+super block which describes the on disk amount and position of metadata
+blocks.
+
+2) Following the super block, a set of blocks is used to describe the
+mapping of the logical device blocks. The mapping is done per chunk of
+blocks, with the chunk size equal to the zoned block device size. The
+mapping table is indexed by chunk number and each mapping entry
+indicates the zone number of the device storing the chunk of data. Each
+mapping entry may also indicate if the zone number of a conventional
+zone used to buffer random modification to the data zone.
+
+3) A set of blocks used to store bitmaps indicating the validity of
+blocks in the data zones follows the mapping table. A valid block is
+defined as a block that was written and not discarded. For a buffered
+data chunk, a block is always valid only in the data zone mapping the
+chunk or in the buffer zone of the chunk.
+
+For a logical chunk mapped to a conventional zone, all write operations
+are processed by directly writing to the zone. If the mapping zone is a
+sequential zone, the write operation is processed directly only if the
+write offset within the logical chunk is equal to the write pointer
+offset within of the sequential data zone (i.e. the write operation is
+aligned on the zone write pointer). Otherwise, write operations are
+processed indirectly using a buffer zone. In that case, an unused
+conventional zone is allocated and assigned to the chunk being
+accessed. Writing a block to the buffer zone of a chunk will
+automatically invalidate the same block in the sequential zone mapping
+the chunk. If all blocks of the sequential zone become invalid, the zone
+is freed and the chunk buffer zone becomes the primary zone mapping the
+chunk, resulting in native random write performance similar to a regular
+block device.
+
+Read operations are processed according to the block validity
+information provided by the bitmaps. Valid blocks are read either from
+the sequential zone mapping a chunk, or if the chunk is buffered, from
+the buffer zone assigned. If the accessed chunk has no mapping, or the
+accessed blocks are invalid, the read buffer is zeroed and the read
+operation terminated.
+
+After some time, the limited number of convnetional zones available may
+be exhausted (all used to map chunks or buffer sequential zones) and
+unaligned writes to unbuffered chunks become impossible. To avoid this
+situation, a reclaim process regularly scans used conventional zones and
+tries to reclaim the least recently used zones by copying the valid
+blocks of the buffer zone to a free sequential zone. Once the copy
+completes, the chunk mapping is updated to point to the sequential zone
+and the buffer zone freed for reuse.
+
+Metadata Protection
+===================
+
+To protect metadata against corruption in case of sudden power loss or
+system crash, 2 sets of metadata zones are used. One set, the primary
+set, is used as the main metadata region, while the secondary set is
+used as a staging area. Modified metadata is first written to the
+secondary set and validated by updating the super block in the secondary
+set, a generation counter is used to indicate that this set contains the
+newest metadata. Once this operation completes, in place of metadata
+block updates can be done in the primary metadata set. This ensures that
+one of the set is always consistent (all modifications committed or none
+at all). Flush operations are used as a commit point. Upon reception of
+a flush request, metadata modification activity is temporarily blocked
+(for both incoming BIO processing and reclaim process) and all dirty
+metadata blocks are staged and updated. Normal operation is then
+resumed. Flushing metadata thus only temporarily delays write and
+discard requests. Read requests can be processed concurrently while
+metadata flush is being executed.
+
+Usage
+=====
+
+A zoned block device must first be formatted using the dmzadm tool. This
+will analyze the device zone configuration, determine where to place the
+metadata sets on the device and initialize the metadata sets.
+
+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}`

drivers/md/Kconfig

@@ -521,6 +521,23 @@ config DM_INTEGRITY
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-integrity.
 
+config DM_ZONED
+	tristate "Drive-managed zoned block device target support"
+	depends on BLK_DEV_DM
+	depends on BLK_DEV_ZONED
+	---help---
+	  This device-mapper target takes a host-managed or host-aware zoned
+	  block device and exposes most of its capacity as a regular block
+	  device (drive-managed zoned block device) without any write
+	  constraints. This is mainly intended for use with file systems that
+	  do not natively support zoned block devices but still want to
+	  benefit from the increased capacity offered by SMR disks. Other uses
+	  by applications using raw block devices (for example object stores)
+	  are also possible.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called dm-zoned.
+
 	  If unsure, say N.
 
 endif # MD

drivers/md/Makefile

@@ -20,6 +20,7 @@ dm-era-y	+= dm-era-target.o
 dm-verity-y	+= dm-verity-target.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
+dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
@@ -60,6 +61,7 @@ obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
 obj-$(CONFIG_DM_ERA)		+= dm-era.o
 obj-$(CONFIG_DM_LOG_WRITES)	+= dm-log-writes.o
 obj-$(CONFIG_DM_INTEGRITY)	+= dm-integrity.o
+obj-$(CONFIG_DM_ZONED)		+= dm-zoned.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o

drivers/md/dm-bio-prison-v1.c

@@ -116,7 +116,7 @@ static int __bio_detain(struct dm_bio_prison *prison,
 
 	while (*new) {
 		struct dm_bio_prison_cell *cell =
-			container_of(*new, struct dm_bio_prison_cell, node);
+			rb_entry(*new, struct dm_bio_prison_cell, node);
 
 		r = cmp_keys(key, &cell->key);
 

drivers/md/dm-bio-prison-v2.c

@@ -120,7 +120,7 @@ static bool __find_or_insert(struct dm_bio_prison_v2 *prison,
 
 	while (*new) {
 		struct dm_bio_prison_cell_v2 *cell =
-			container_of(*new, struct dm_bio_prison_cell_v2, node);
+			rb_entry(*new, struct dm_bio_prison_cell_v2, node);
 
 		r = cmp_keys(key, &cell->key);
 

drivers/md/dm-core.h

@@ -147,4 +147,7 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen
 	return !maxlen || strlen(result) + 1 >= maxlen;
 }
 
+extern atomic_t dm_global_event_nr;
+extern wait_queue_head_t dm_global_eventq;
+
 #endif

drivers/md/dm-crypt.c

@@ -246,6 +246,9 @@ static struct crypto_aead *any_tfm_aead(struct crypt_config *cc)
  * plain64: the initial vector is the 64-bit little-endian version of the sector
  *        number, padded with zeros if necessary.
  *
+ * plain64be: the initial vector is the 64-bit big-endian version of the sector
+ *        number, padded with zeros if necessary.
+ *
  * essiv: "encrypted sector|salt initial vector", the sector number is
  *        encrypted with the bulk cipher using a salt as key. The salt
  *        should be derived from the bulk cipher's key via hashing.
@@ -302,6 +305,16 @@ static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv,
 	return 0;
 }
 
+static int crypt_iv_plain64be_gen(struct crypt_config *cc, u8 *iv,
+				  struct dm_crypt_request *dmreq)
+{
+	memset(iv, 0, cc->iv_size);
+	/* iv_size is at least of size u64; usually it is 16 bytes */
+	*(__be64 *)&iv[cc->iv_size - sizeof(u64)] = cpu_to_be64(dmreq->iv_sector);
+
+	return 0;
+}
+
 /* Initialise ESSIV - compute salt but no local memory allocations */
 static int crypt_iv_essiv_init(struct crypt_config *cc)
 {
@@ -835,6 +848,10 @@ static const struct crypt_iv_operations crypt_iv_plain64_ops = {
 	.generator = crypt_iv_plain64_gen
 };
 
+static const struct crypt_iv_operations crypt_iv_plain64be_ops = {
+	.generator = crypt_iv_plain64be_gen
+};
+
 static const struct crypt_iv_operations crypt_iv_essiv_ops = {
 	.ctr       = crypt_iv_essiv_ctr,
 	.dtr       = crypt_iv_essiv_dtr,
@@ -2208,6 +2225,8 @@ static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode)
 		cc->iv_gen_ops = &crypt_iv_plain_ops;
 	else if (strcmp(ivmode, "plain64") == 0)
 		cc->iv_gen_ops = &crypt_iv_plain64_ops;
+	else if (strcmp(ivmode, "plain64be") == 0)
+		cc->iv_gen_ops = &crypt_iv_plain64be_ops;
 	else if (strcmp(ivmode, "essiv") == 0)
 		cc->iv_gen_ops = &crypt_iv_essiv_ops;
 	else if (strcmp(ivmode, "benbi") == 0)
@@ -2987,7 +3006,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 17, 0},
+	.version = {1, 18, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,

drivers/md/dm-flakey.c

@@ -275,7 +275,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	struct flakey_c *fc = ti->private;
 
 	bio->bi_bdev = fc->dev->bdev;
-	if (bio_sectors(bio))
+	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
 		bio->bi_iter.bi_sector =
 			flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -306,6 +306,14 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 	pb->bio_submitted = false;
 
+	/* Do not fail reset zone */
+	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+		goto map_bio;
+
+	/* We need to remap reported zones, so remember the BIO iter */
+	if (bio_op(bio) == REQ_OP_ZONE_REPORT)
+		goto map_bio;
+
 	/* Are we alive ? */
 	elapsed = (jiffies - fc->start_time) / HZ;
 	if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
@@ -364,6 +372,14 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
+	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+		return DM_ENDIO_DONE;
+
+	if (bio_op(bio) == REQ_OP_ZONE_REPORT) {
+		dm_remap_zone_report(ti, bio, fc->start);
+		return DM_ENDIO_DONE;
+	}
+
 	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)) {
@@ -446,7 +462,8 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_
 
 static struct target_type flakey_target = {
 	.name   = "flakey",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
+	.features = DM_TARGET_ZONED_HM,
 	.module = THIS_MODULE,
 	.ctr    = flakey_ctr,
 	.dtr    = flakey_dtr,

drivers/md/dm-ioctl.c

@@ -23,6 +23,14 @@
 #define DM_MSG_PREFIX "ioctl"
 #define DM_DRIVER_EMAIL "dm-devel@redhat.com"
 
+struct dm_file {
+	/*
+	 * poll will wait until the global event number is greater than
+	 * this value.
+	 */
+	volatile unsigned global_event_nr;
+};
+
 /*-----------------------------------------------------------------
  * The ioctl interface needs to be able to look up devices by
  * name or uuid.
@@ -456,9 +464,9 @@ void dm_deferred_remove(void)
  * All the ioctl commands get dispatched to functions with this
  * prototype.
  */
-typedef int (*ioctl_fn)(struct dm_ioctl *param, size_t param_size);
+typedef int (*ioctl_fn)(struct file *filp, struct dm_ioctl *param, size_t param_size);
 
-static int remove_all(struct dm_ioctl *param, size_t param_size)
+static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	dm_hash_remove_all(true, !!(param->flags & DM_DEFERRED_REMOVE), false);
 	param->data_size = 0;
@@ -491,13 +499,14 @@ static void *get_result_buffer(struct dm_ioctl *param, size_t param_size,
 	return ((void *) param) + param->data_start;
 }
 
-static int list_devices(struct dm_ioctl *param, size_t param_size)
+static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	unsigned int i;
 	struct hash_cell *hc;
 	size_t len, needed = 0;
 	struct gendisk *disk;
 	struct dm_name_list *nl, *old_nl = NULL;
+	uint32_t *event_nr;
 
 	down_write(&_hash_lock);
 
@@ -510,6 +519,7 @@ static int list_devices(struct dm_ioctl *param, size_t param_size)
 			needed += sizeof(struct dm_name_list);
 			needed += strlen(hc->name) + 1;
 			needed += ALIGN_MASK;
+			needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK;
 		}
 	}
 
@@ -539,7 +549,9 @@ static int list_devices(struct dm_ioctl *param, size_t param_size)
 			strcpy(nl->name, hc->name);
 
 			old_nl = nl;
-			nl = align_ptr(((void *) ++nl) + strlen(hc->name) + 1);
+			event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1);
+			*event_nr = dm_get_event_nr(hc->md);
+			nl = align_ptr(event_nr + 1);
 		}
 	}
 
@@ -582,7 +594,7 @@ static void list_version_get_info(struct target_type *tt, void *param)
     info->vers = align_ptr(((void *) ++info->vers) + strlen(tt->name) + 1);
 }
 
-static int list_versions(struct dm_ioctl *param, size_t param_size)
+static int list_versions(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	size_t len, needed = 0;
 	struct dm_target_versions *vers;
@@ -724,7 +736,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 	}
 }
 
-static int dev_create(struct dm_ioctl *param, size_t param_size)
+static int dev_create(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r, m = DM_ANY_MINOR;
 	struct mapped_device *md;
@@ -816,7 +828,7 @@ static struct mapped_device *find_device(struct dm_ioctl *param)
 	return md;
 }
 
-static int dev_remove(struct dm_ioctl *param, size_t param_size)
+static int dev_remove(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	struct hash_cell *hc;
 	struct mapped_device *md;
@@ -881,7 +893,7 @@ static int invalid_str(char *str, void *end)
 	return -EINVAL;
 }
 
-static int dev_rename(struct dm_ioctl *param, size_t param_size)
+static int dev_rename(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r;
 	char *new_data = (char *) param + param->data_start;
@@ -911,7 +923,7 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size)
 	return 0;
 }
 
-static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
+static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r = -EINVAL, x;
 	struct mapped_device *md;
@@ -1060,7 +1072,7 @@ static int do_resume(struct dm_ioctl *param)
  * Set or unset the suspension state of a device.
  * If the device already is in the requested state we just return its status.
  */
-static int dev_suspend(struct dm_ioctl *param, size_t param_size)
+static int dev_suspend(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	if (param->flags & DM_SUSPEND_FLAG)
 		return do_suspend(param);
@@ -1072,7 +1084,7 @@ static int dev_suspend(struct dm_ioctl *param, size_t param_size)
  * Copies device info back to user space, used by
  * the create and info ioctls.
  */
-static int dev_status(struct dm_ioctl *param, size_t param_size)
+static int dev_status(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	struct mapped_device *md;
 
@@ -1163,7 +1175,7 @@ static void retrieve_status(struct dm_table *table,
 /*
  * Wait for a device to report an event
  */
-static int dev_wait(struct dm_ioctl *param, size_t param_size)
+static int dev_wait(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r = 0;
 	struct mapped_device *md;
@@ -1200,6 +1212,19 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
 	return r;
 }
 
+/*
+ * Remember the global event number and make it possible to poll
+ * for further events.
+ */
+static int dev_arm_poll(struct file *filp, struct dm_ioctl *param, size_t param_size)
+{
+	struct dm_file *priv = filp->private_data;
+
+	priv->global_event_nr = atomic_read(&dm_global_event_nr);
+
+	return 0;
+}
+
 static inline fmode_t get_mode(struct dm_ioctl *param)
 {
 	fmode_t mode = FMODE_READ | FMODE_WRITE;
@@ -1269,7 +1294,7 @@ static bool is_valid_type(enum dm_queue_mode cur, enum dm_queue_mode new)
 	return false;
 }
 
-static int table_load(struct dm_ioctl *param, size_t param_size)
+static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r;
 	struct hash_cell *hc;
@@ -1356,7 +1381,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 	return r;
 }
 
-static int table_clear(struct dm_ioctl *param, size_t param_size)
+static int table_clear(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	struct hash_cell *hc;
 	struct mapped_device *md;
@@ -1430,7 +1455,7 @@ static void retrieve_deps(struct dm_table *table,
 	param->data_size = param->data_start + needed;
 }
 
-static int table_deps(struct dm_ioctl *param, size_t param_size)
+static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	struct mapped_device *md;
 	struct dm_table *table;
@@ -1456,7 +1481,7 @@ static int table_deps(struct dm_ioctl *param, size_t param_size)
  * Return the status of a device as a text string for each
  * target.
  */
-static int table_status(struct dm_ioctl *param, size_t param_size)
+static int table_status(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	struct mapped_device *md;
 	struct dm_table *table;
@@ -1511,7 +1536,7 @@ static int message_for_md(struct mapped_device *md, unsigned argc, char **argv,
 /*
  * Pass a message to the target that's at the supplied device offset.
  */
-static int target_message(struct dm_ioctl *param, size_t param_size)
+static int target_message(struct file *filp, struct dm_ioctl *param, size_t param_size)
 {
 	int r, argc;
 	char **argv;
@@ -1628,7 +1653,8 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags)
 		{DM_LIST_VERSIONS_CMD, 0, list_versions},
 
 		{DM_TARGET_MSG_CMD, 0, target_message},
-		{DM_DEV_SET_GEOMETRY_CMD, 0, dev_set_geometry}
+		{DM_DEV_SET_GEOMETRY_CMD, 0, dev_set_geometry},
+		{DM_DEV_ARM_POLL, IOCTL_FLAGS_NO_PARAMS, dev_arm_poll},
 	};
 
 	if (unlikely(cmd >= ARRAY_SIZE(_ioctls)))
@@ -1783,7 +1809,7 @@ static int validate_params(uint cmd, struct dm_ioctl *param)
 	return 0;
 }
 
-static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
+static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *user)
 {
 	int r = 0;
 	int ioctl_flags;
@@ -1837,7 +1863,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
 		goto out;
 
 	param->data_size = offsetof(struct dm_ioctl, data);
-	r = fn(param, input_param_size);
+	r = fn(file, param, input_param_size);
 
 	if (unlikely(param->flags & DM_BUFFER_FULL_FLAG) &&
 	    unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS))
@@ -1856,7 +1882,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
 
 static long dm_ctl_ioctl(struct file *file, uint command, ulong u)
 {
-	return (long)ctl_ioctl(command, (struct dm_ioctl __user *)u);
+	return (long)ctl_ioctl(file, command, (struct dm_ioctl __user *)u);
 }
 
 #ifdef CONFIG_COMPAT
@@ -1868,8 +1894,47 @@ static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u)
 #define dm_compat_ctl_ioctl NULL
 #endif
 
+static int dm_open(struct inode *inode, struct file *filp)
+{
+	int r;
+	struct dm_file *priv;
+
+	r = nonseekable_open(inode, filp);
+	if (unlikely(r))
+		return r;
+
+	priv = filp->private_data = kmalloc(sizeof(struct dm_file), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->global_event_nr = atomic_read(&dm_global_event_nr);
+
+	return 0;
+}
+
+static int dm_release(struct inode *inode, struct file *filp)
+{
+	kfree(filp->private_data);
+	return 0;
+}
+
+static unsigned dm_poll(struct file *filp, poll_table *wait)
+{
+	struct dm_file *priv = filp->private_data;
+	unsigned mask = 0;
+
+	poll_wait(filp, &dm_global_eventq, wait);
+
+	if ((int)(atomic_read(&dm_global_event_nr) - priv->global_event_nr) > 0)
+		mask |= POLLIN;
+
+	return mask;
+}
+
 static const struct file_operations _ctl_fops = {
-	.open = nonseekable_open,
+	.open    = dm_open,
+	.release = dm_release,
+	.poll    = dm_poll,
 	.unlocked_ioctl	 = dm_ctl_ioctl,
 	.compat_ioctl = dm_compat_ctl_ioctl,
 	.owner	 = THIS_MODULE,

drivers/md/dm-kcopyd.c

@@ -356,6 +356,7 @@ struct kcopyd_job {
 	struct mutex lock;
 	atomic_t sub_jobs;
 	sector_t progress;
+	sector_t write_offset;
 
 	struct kcopyd_job *master_job;
 };
@@ -386,6 +387,31 @@ void dm_kcopyd_exit(void)
  * Functions to push and pop a job onto the head of a given job
  * list.
  */
+static struct kcopyd_job *pop_io_job(struct list_head *jobs,
+				     struct dm_kcopyd_client *kc)
+{
+	struct kcopyd_job *job;
+
+	/*
+	 * For I/O jobs, pop any read, any write without sequential write
+	 * constraint and sequential writes that are at the right position.
+	 */
+	list_for_each_entry(job, jobs, list) {
+		if (job->rw == READ || !test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags)) {
+			list_del(&job->list);
+			return job;
+		}
+
+		if (job->write_offset == job->master_job->write_offset) {
+			job->master_job->write_offset += job->source.count;
+			list_del(&job->list);
+			return job;
+		}
+	}
+
+	return NULL;
+}
+
 static struct kcopyd_job *pop(struct list_head *jobs,
 			      struct dm_kcopyd_client *kc)
 {
@@ -395,9 +421,13 @@ static struct kcopyd_job *pop(struct list_head *jobs,
 	spin_lock_irqsave(&kc->job_lock, flags);
 
 	if (!list_empty(jobs)) {
+		if (jobs == &kc->io_jobs)
+			job = pop_io_job(jobs, kc);
+		else {
 			job = list_entry(jobs->next, struct kcopyd_job, list);
 			list_del(&job->list);
 		}
+	}
 	spin_unlock_irqrestore(&kc->job_lock, flags);
 
 	return job;
@@ -506,6 +536,14 @@ static int run_io_job(struct kcopyd_job *job)
 		.client = job->kc->io_client,
 	};
 
+	/*
+	 * If we need to write sequentially and some reads or writes failed,
+	 * no point in continuing.
+	 */
+	if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) &&
+	    job->master_job->write_err)
+		return -EIO;
+
 	io_job_start(job->kc->throttle);
 
 	if (job->rw == READ)
@@ -655,6 +693,7 @@ static void segment_complete(int read_err, unsigned long write_err,
 		int i;
 
 		*sub_job = *job;
+		sub_job->write_offset = progress;
 		sub_job->source.sector += progress;
 		sub_job->source.count = count;
 
@@ -723,6 +762,27 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	job->num_dests = num_dests;
 	memcpy(&job->dests, dests, sizeof(*dests) * num_dests);
 
+	/*
+	 * If one of the destination is a host-managed zoned block device,
+	 * we need to write sequentially. If one of the destination is a
+	 * host-aware device, then leave it to the caller to choose what to do.
+	 */
+	if (!test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags)) {
+		for (i = 0; i < job->num_dests; i++) {
+			if (bdev_zoned_model(dests[i].bdev) == BLK_ZONED_HM) {
+				set_bit(DM_KCOPYD_WRITE_SEQ, &job->flags);
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If we need to write sequentially, errors cannot be ignored.
+	 */
+	if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) &&
+	    test_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags))
+		clear_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags);
+
 	if (from) {
 		job->source = *from;
 		job->pages = NULL;
@@ -746,6 +806,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	job->fn = fn;
 	job->context = context;
 	job->master_job = job;
+	job->write_offset = 0;
 
 	if (job->source.count <= SUB_JOB_SIZE)
 		dispatch_job(job);

drivers/md/dm-linear.c

@@ -89,7 +89,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 	struct linear_c *lc = ti->private;
 
 	bio->bi_bdev = lc->dev->bdev;
-	if (bio_sectors(bio))
+	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
 		bio->bi_iter.bi_sector =
 			linear_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -101,6 +101,17 @@ static int linear_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
+static int linear_end_io(struct dm_target *ti, struct bio *bio,
+			 blk_status_t *error)
+{
+	struct linear_c *lc = ti->private;
+
+	if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT)
+		dm_remap_zone_report(ti, bio, lc->start);
+
+	return DM_ENDIO_DONE;
+}
+
 static void linear_status(struct dm_target *ti, status_type_t type,
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
@@ -161,12 +172,13 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version = {1, 3, 0},
-	.features = DM_TARGET_PASSES_INTEGRITY,
+	.version = {1, 4, 0},
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
 	.dtr    = linear_dtr,
 	.map    = linear_map,
+	.end_io = linear_end_io,
 	.status = linear_status,
 	.prepare_ioctl = linear_prepare_ioctl,
 	.iterate_devices = linear_iterate_devices,

drivers/md/dm-raid.c

@@ -1571,7 +1571,7 @@ static sector_t __rdev_sectors(struct raid_set *rs)
 			return rdev->sectors;
 	}
 
-	BUG(); /* Constructor ensures we got some. */
+	return 0;
 }
 
 /* Calculate the sectors per device and per array used for @rs */
@@ -2941,7 +2941,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	bool resize;
 	struct raid_type *rt;
 	unsigned int num_raid_params, num_raid_devs;
-	sector_t calculated_dev_sectors;
+	sector_t calculated_dev_sectors, rdev_sectors;
 	struct raid_set *rs = NULL;
 	const char *arg;
 	struct rs_layout rs_layout;
@@ -3017,7 +3017,14 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
-	resize = calculated_dev_sectors != __rdev_sectors(rs);
+	rdev_sectors = __rdev_sectors(rs);
+	if (!rdev_sectors) {
+		ti->error = "Invalid rdev size";
+		r = -EINVAL;
+		goto bad;
+	}
+
+	resize = calculated_dev_sectors != rdev_sectors;
 
 	INIT_WORK(&rs->md.event_work, do_table_event);
 	ti->private = rs;

drivers/md/dm-table.c

@@ -319,6 +319,39 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 		return 1;
 	}
 
+	/*
+	 * If the target is mapped to zoned block device(s), check
+	 * that the zones are not partially mapped.
+	 */
+	if (bdev_zoned_model(bdev) != BLK_ZONED_NONE) {
+		unsigned int zone_sectors = bdev_zone_sectors(bdev);
+
+		if (start & (zone_sectors - 1)) {
+			DMWARN("%s: start=%llu not aligned to h/w zone size %u of %s",
+			       dm_device_name(ti->table->md),
+			       (unsigned long long)start,
+			       zone_sectors, bdevname(bdev, b));
+			return 1;
+		}
+
+		/*
+		 * Note: The last zone of a zoned block device may be smaller
+		 * than other zones. So for a target mapping the end of a
+		 * zoned block device with such a zone, len would not be zone
+		 * aligned. We do not allow such last smaller zone to be part
+		 * of the mapping here to ensure that mappings with multiple
+		 * devices do not end up with a smaller zone in the middle of
+		 * the sector range.
+		 */
+		if (len & (zone_sectors - 1)) {
+			DMWARN("%s: len=%llu not aligned to h/w zone size %u of %s",
+			       dm_device_name(ti->table->md),
+			       (unsigned long long)len,
+			       zone_sectors, bdevname(bdev, b));
+			return 1;
+		}
+	}
+
 	if (logical_block_size_sectors <= 1)
 		return 0;
 
@@ -456,6 +489,8 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
 
+	limits->zoned = blk_queue_zoned_model(q);
+
 	return 0;
 }
 
@@ -1346,6 +1381,88 @@ bool dm_table_has_no_data_devices(struct dm_table *table)
 	return true;
 }
 
+static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
+				 sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+	enum blk_zoned_model *zoned_model = data;
+
+	return q && blk_queue_zoned_model(q) == *zoned_model;
+}
+
+static bool dm_table_supports_zoned_model(struct dm_table *t,
+					  enum blk_zoned_model zoned_model)
+{
+	struct dm_target *ti;
+	unsigned i;
+
+	for (i = 0; i < dm_table_get_num_targets(t); i++) {
+		ti = dm_table_get_target(t, i);
+
+		if (zoned_model == BLK_ZONED_HM &&
+		    !dm_target_supports_zoned_hm(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    !ti->type->iterate_devices(ti, device_is_zoned_model, &zoned_model))
+			return false;
+	}
+
+	return true;
+}
+
+static int device_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev,
+				       sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+	unsigned int *zone_sectors = data;
+
+	return q && blk_queue_zone_sectors(q) == *zone_sectors;
+}
+
+static bool dm_table_matches_zone_sectors(struct dm_table *t,
+					  unsigned int zone_sectors)
+{
+	struct dm_target *ti;
+	unsigned i;
+
+	for (i = 0; i < dm_table_get_num_targets(t); i++) {
+		ti = dm_table_get_target(t, i);
+
+		if (!ti->type->iterate_devices ||
+		    !ti->type->iterate_devices(ti, device_matches_zone_sectors, &zone_sectors))
+			return false;
+	}
+
+	return true;
+}
+
+static int validate_hardware_zoned_model(struct dm_table *table,
+					 enum blk_zoned_model zoned_model,
+					 unsigned int zone_sectors)
+{
+	if (zoned_model == BLK_ZONED_NONE)
+		return 0;
+
+	if (!dm_table_supports_zoned_model(table, zoned_model)) {
+		DMERR("%s: zoned model is not consistent across all devices",
+		      dm_device_name(table->md));
+		return -EINVAL;
+	}
+
+	/* Check zone size validity and compatibility */
+	if (!zone_sectors || !is_power_of_2(zone_sectors))
+		return -EINVAL;
+
+	if (!dm_table_matches_zone_sectors(table, zone_sectors)) {
+		DMERR("%s: zone sectors is not consistent across all devices",
+		      dm_device_name(table->md));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * Establish the new table's queue_limits and validate them.
  */
@@ -1355,6 +1472,8 @@ int dm_calculate_queue_limits(struct dm_table *table,
 	struct dm_target *ti;
 	struct queue_limits ti_limits;
 	unsigned i;
+	enum blk_zoned_model zoned_model = BLK_ZONED_NONE;
+	unsigned int zone_sectors = 0;
 
 	blk_set_stacking_limits(limits);
 
@@ -1372,6 +1491,15 @@ int dm_calculate_queue_limits(struct dm_table *table,
 		ti->type->iterate_devices(ti, dm_set_device_limits,
 					  &ti_limits);
 
+		if (zoned_model == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+			/*
+			 * After stacking all limits, validate all devices
+			 * in table support this zoned model and zone sectors.
+			 */
+			zoned_model = ti_limits.zoned;
+			zone_sectors = ti_limits.chunk_sectors;
+		}
+
 		/* Set I/O hints portion of queue limits */
 		if (ti->type->io_hints)
 			ti->type->io_hints(ti, &ti_limits);
@@ -1396,7 +1524,41 @@ int dm_calculate_queue_limits(struct dm_table *table,
 			       dm_device_name(table->md),
 			       (unsigned long long) ti->begin,
 			       (unsigned long long) ti->len);
+
+		/*
+		 * FIXME: this should likely be moved to blk_stack_limits(), would
+		 * also eliminate limits->zoned stacking hack in dm_set_device_limits()
+		 */
+		if (limits->zoned == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+			/*
+			 * By default, the stacked limits zoned model is set to
+			 * BLK_ZONED_NONE in blk_set_stacking_limits(). Update
+			 * this model using the first target model reported
+			 * that is not BLK_ZONED_NONE. This will be either the
+			 * first target device zoned model or the model reported
+			 * by the target .io_hints.
+			 */
+			limits->zoned = ti_limits.zoned;
 		}
+	}
+
+	/*
+	 * Verify that the zoned model and zone sectors, as determined before
+	 * any .io_hints override, are the same across all devices in the table.
+	 * - this is especially relevant if .io_hints is emulating a disk-managed
+	 *   zoned model (aka BLK_ZONED_NONE) on host-managed zoned block devices.
+	 * BUT...
+	 */
+	if (limits->zoned != BLK_ZONED_NONE) {
+		/*
+		 * ...IF the above limits stacking determined a zoned model
+		 * validate that all of the table's devices conform to it.
+		 */
+		zoned_model = limits->zoned;
+		zone_sectors = limits->chunk_sectors;
+	}
+	if (validate_hardware_zoned_model(table, zoned_model, zone_sectors))
+		return -EINVAL;
 
 	return validate_hardware_logical_block_alignment(table, limits);
 }

drivers/md/dm-zoned-metadata.c

+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-zoned.h"
+
+#include <linux/module.h>
+#include <linux/crc32.h>
+
+#define	DM_MSG_PREFIX		"zoned metadata"
+
+/*
+ * Metadata version.
+ */
+#define DMZ_META_VER	1
+
+/*
+ * On-disk super block magic.
+ */
+#define DMZ_MAGIC	((((unsigned int)('D')) << 24) | \
+			 (((unsigned int)('Z')) << 16) | \
+			 (((unsigned int)('B')) <<  8) | \
+			 ((unsigned int)('D')))
+
+/*
+ * On disk super block.
+ * This uses only 512 B but uses on disk a full 4KB block. This block is
+ * followed on disk by the mapping table of chunks to zones and the bitmap
+ * blocks indicating zone block validity.
+ * The overall resulting metadata format is:
+ *    (1) Super block (1 block)
+ *    (2) Chunk mapping table (nr_map_blocks)
+ *    (3) Bitmap blocks (nr_bitmap_blocks)
+ * All metadata blocks are stored in conventional zones, starting from the
+ * the first conventional zone found on disk.
+ */
+struct dmz_super {
+	/* Magic number */
+	__le32		magic;			/*   4 */
+
+	/* Metadata version number */
+	__le32		version;		/*   8 */
+
+	/* Generation number */
+	__le64		gen;			/*  16 */
+
+	/* This block number */
+	__le64		sb_block;		/*  24 */
+
+	/* The number of metadata blocks, including this super block */
+	__le32		nr_meta_blocks;		/*  28 */
+
+	/* The number of sequential zones reserved for reclaim */
+	__le32		nr_reserved_seq;	/*  32 */
+
+	/* The number of entries in the mapping table */
+	__le32		nr_chunks;		/*  36 */
+
+	/* The number of blocks used for the chunk mapping table */
+	__le32		nr_map_blocks;		/*  40 */
+
+	/* The number of blocks used for the block bitmaps */
+	__le32		nr_bitmap_blocks;	/*  44 */
+
+	/* Checksum */
+	__le32		crc;			/*  48 */
+
+	/* Padding to full 512B sector */
+	u8		reserved[464];		/* 512 */
+};
+
+/*
+ * Chunk mapping entry: entries are indexed by chunk number
+ * and give the zone ID (dzone_id) mapping the chunk on disk.
+ * This zone may be sequential or random. If it is a sequential
+ * zone, a second zone (bzone_id) used as a write buffer may
+ * also be specified. This second zone will always be a randomly
+ * writeable zone.
+ */
+struct dmz_map {
+	__le32			dzone_id;
+	__le32			bzone_id;
+};
+
+/*
+ * Chunk mapping table metadata: 512 8-bytes entries per 4KB block.
+ */
+#define DMZ_MAP_ENTRIES		(DMZ_BLOCK_SIZE / sizeof(struct dmz_map))
+#define DMZ_MAP_ENTRIES_SHIFT	(ilog2(DMZ_MAP_ENTRIES))
+#define DMZ_MAP_ENTRIES_MASK	(DMZ_MAP_ENTRIES - 1)
+#define DMZ_MAP_UNMAPPED	UINT_MAX
+
+/*
+ * Meta data block descriptor (for cached metadata blocks).
+ */
+struct dmz_mblock {
+	struct rb_node		node;
+	struct list_head	link;
+	sector_t		no;
+	atomic_t		ref;
+	unsigned long		state;
+	struct page		*page;
+	void			*data;
+};
+
+/*
+ * Metadata block state flags.
+ */
+enum {
+	DMZ_META_DIRTY,
+	DMZ_META_READING,
+	DMZ_META_WRITING,
+	DMZ_META_ERROR,
+};
+
+/*
+ * Super block information (one per metadata set).
+ */
+struct dmz_sb {
+	sector_t		block;
+	struct dmz_mblock	*mblk;
+	struct dmz_super	*sb;
+};
+
+/*
+ * In-memory metadata.
+ */
+struct dmz_metadata {
+	struct dmz_dev		*dev;
+
+	sector_t		zone_bitmap_size;
+	unsigned int		zone_nr_bitmap_blocks;
+
+	unsigned int		nr_bitmap_blocks;
+	unsigned int		nr_map_blocks;
+
+	unsigned int		nr_useable_zones;
+	unsigned int		nr_meta_blocks;
+	unsigned int		nr_meta_zones;
+	unsigned int		nr_data_zones;
+	unsigned int		nr_rnd_zones;
+	unsigned int		nr_reserved_seq;
+	unsigned int		nr_chunks;
+
+	/* Zone information array */
+	struct dm_zone		*zones;
+
+	struct dm_zone		*sb_zone;
+	struct dmz_sb		sb[2];
+	unsigned int		mblk_primary;
+	u64			sb_gen;
+	unsigned int		min_nr_mblks;
+	unsigned int		max_nr_mblks;
+	atomic_t		nr_mblks;
+	struct rw_semaphore	mblk_sem;
+	struct mutex		mblk_flush_lock;
+	spinlock_t		mblk_lock;
+	struct rb_root		mblk_rbtree;
+	struct list_head	mblk_lru_list;
+	struct list_head	mblk_dirty_list;
+	struct shrinker		mblk_shrinker;
+
+	/* 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;
+
+	atomic_t		nr_reserved_seq_zones;
+	struct list_head	reserved_seq_zones_list;
+
+	wait_queue_head_t	free_wq;
+};
+
+/*
+ * Various accessors
+ */
+unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	return ((unsigned int)(zone - zmd->zones));
+}
+
+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;
+}
+
+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 dmz_nr_chunks(struct dmz_metadata *zmd)
+{
+	return zmd->nr_chunks;
+}
+
+unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd)
+{
+	return zmd->nr_rnd;
+}
+
+unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd)
+{
+	return atomic_read(&zmd->unmap_nr_rnd);
+}
+
+/*
+ * Lock/unlock mapping table.
+ * The map lock also protects all the zone lists.
+ */
+void dmz_lock_map(struct dmz_metadata *zmd)
+{
+	mutex_lock(&zmd->map_lock);
+}
+
+void dmz_unlock_map(struct dmz_metadata *zmd)
+{
+	mutex_unlock(&zmd->map_lock);
+}
+
+/*
+ * Lock/unlock metadata access. This is a "read" lock on a semaphore
+ * that prevents metadata flush from running while metadata are being
+ * modified. The actual metadata write mutual exclusion is achieved with
+ * the map lock and zone styate management (active and reclaim state are
+ * mutually exclusive).
+ */
+void dmz_lock_metadata(struct dmz_metadata *zmd)
+{
+	down_read(&zmd->mblk_sem);
+}
+
+void dmz_unlock_metadata(struct dmz_metadata *zmd)
+{
+	up_read(&zmd->mblk_sem);
+}
+
+/*
+ * Lock/unlock flush: prevent concurrent executions
+ * of dmz_flush_metadata as well as metadata modification in reclaim
+ * while flush is being executed.
+ */
+void dmz_lock_flush(struct dmz_metadata *zmd)
+{
+	mutex_lock(&zmd->mblk_flush_lock);
+}
+
+void dmz_unlock_flush(struct dmz_metadata *zmd)
+{
+	mutex_unlock(&zmd->mblk_flush_lock);
+}
+
+/*
+ * Allocate a metadata block.
+ */
+static struct dmz_mblock *dmz_alloc_mblock(struct dmz_metadata *zmd,
+					   sector_t mblk_no)
+{
+	struct dmz_mblock *mblk = NULL;
+
+	/* See if we can reuse cached blocks */
+	if (zmd->max_nr_mblks && atomic_read(&zmd->nr_mblks) > zmd->max_nr_mblks) {
+		spin_lock(&zmd->mblk_lock);
+		mblk = list_first_entry_or_null(&zmd->mblk_lru_list,
+						struct dmz_mblock, link);
+		if (mblk) {
+			list_del_init(&mblk->link);
+			rb_erase(&mblk->node, &zmd->mblk_rbtree);
+			mblk->no = mblk_no;
+		}
+		spin_unlock(&zmd->mblk_lock);
+		if (mblk)
+			return mblk;
+	}
+
+	/* Allocate a new block */
+	mblk = kmalloc(sizeof(struct dmz_mblock), GFP_NOIO);
+	if (!mblk)
+		return NULL;
+
+	mblk->page = alloc_page(GFP_NOIO);
+	if (!mblk->page) {
+		kfree(mblk);
+		return NULL;
+	}
+
+	RB_CLEAR_NODE(&mblk->node);
+	INIT_LIST_HEAD(&mblk->link);
+	atomic_set(&mblk->ref, 0);
+	mblk->state = 0;
+	mblk->no = mblk_no;
+	mblk->data = page_address(mblk->page);
+
+	atomic_inc(&zmd->nr_mblks);
+
+	return mblk;
+}
+
+/*
+ * Free a metadata block.
+ */
+static void dmz_free_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
+{
+	__free_pages(mblk->page, 0);
+	kfree(mblk);
+
+	atomic_dec(&zmd->nr_mblks);
+}
+
+/*
+ * Insert a metadata block in the rbtree.
+ */
+static void dmz_insert_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
+{
+	struct rb_root *root = &zmd->mblk_rbtree;
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct dmz_mblock *b;
+
+	/* Figure out where to put the new node */
+	while (*new) {
+		b = container_of(*new, struct dmz_mblock, node);
+		parent = *new;
+		new = (b->no < mblk->no) ? &((*new)->rb_left) : &((*new)->rb_right);
+	}
+
+	/* Add new node and rebalance tree */
+	rb_link_node(&mblk->node, parent, new);
+	rb_insert_color(&mblk->node, root);
+}
+
+/*
+ * Lookup a metadata block in the rbtree.
+ */
+static struct dmz_mblock *dmz_lookup_mblock(struct dmz_metadata *zmd,
+					    sector_t mblk_no)
+{
+	struct rb_root *root = &zmd->mblk_rbtree;
+	struct rb_node *node = root->rb_node;
+	struct dmz_mblock *mblk;
+
+	while (node) {
+		mblk = container_of(node, struct dmz_mblock, node);
+		if (mblk->no == mblk_no)
+			return mblk;
+		node = (mblk->no < mblk_no) ? node->rb_left : node->rb_right;
+	}
+
+	return NULL;
+}
+
+/*
+ * Metadata block BIO end callback.
+ */
+static void dmz_mblock_bio_end_io(struct bio *bio)
+{
+	struct dmz_mblock *mblk = bio->bi_private;
+	int flag;
+
+	if (bio->bi_status)
+		set_bit(DMZ_META_ERROR, &mblk->state);
+
+	if (bio_op(bio) == REQ_OP_WRITE)
+		flag = DMZ_META_WRITING;
+	else
+		flag = DMZ_META_READING;
+
+	clear_bit_unlock(flag, &mblk->state);
+	smp_mb__after_atomic();
+	wake_up_bit(&mblk->state, flag);
+
+	bio_put(bio);
+}
+
+/*
+ * Read a metadata block from disk.
+ */
+static struct dmz_mblock *dmz_fetch_mblock(struct dmz_metadata *zmd,
+					   sector_t mblk_no)
+{
+	struct dmz_mblock *mblk;
+	sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no;
+	struct bio *bio;
+
+	/* Get block and insert it */
+	mblk = dmz_alloc_mblock(zmd, mblk_no);
+	if (!mblk)
+		return NULL;
+
+	spin_lock(&zmd->mblk_lock);
+	atomic_inc(&mblk->ref);
+	set_bit(DMZ_META_READING, &mblk->state);
+	dmz_insert_mblock(zmd, mblk);
+	spin_unlock(&zmd->mblk_lock);
+
+	bio = bio_alloc(GFP_NOIO, 1);
+	if (!bio) {
+		dmz_free_mblock(zmd, mblk);
+		return NULL;
+	}
+
+	bio->bi_iter.bi_sector = dmz_blk2sect(block);
+	bio->bi_bdev = zmd->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);
+	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
+	submit_bio(bio);
+
+	return mblk;
+}
+
+/*
+ * Free metadata blocks.
+ */
+static unsigned long dmz_shrink_mblock_cache(struct dmz_metadata *zmd,
+					     unsigned long limit)
+{
+	struct dmz_mblock *mblk;
+	unsigned long count = 0;
+
+	if (!zmd->max_nr_mblks)
+		return 0;
+
+	while (!list_empty(&zmd->mblk_lru_list) &&
+	       atomic_read(&zmd->nr_mblks) > zmd->min_nr_mblks &&
+	       count < limit) {
+		mblk = list_first_entry(&zmd->mblk_lru_list,
+					struct dmz_mblock, link);
+		list_del_init(&mblk->link);
+		rb_erase(&mblk->node, &zmd->mblk_rbtree);
+		dmz_free_mblock(zmd, mblk);
+		count++;
+	}
+
+	return count;
+}
+
+/*
+ * For mblock shrinker: get the number of unused metadata blocks in the cache.
+ */
+static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink,
+					       struct shrink_control *sc)
+{
+	struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+
+	return atomic_read(&zmd->nr_mblks);
+}
+
+/*
+ * For mblock shrinker: scan unused metadata blocks and shrink the cache.
+ */
+static unsigned long dmz_mblock_shrinker_scan(struct shrinker *shrink,
+					      struct shrink_control *sc)
+{
+	struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+	unsigned long count;
+
+	spin_lock(&zmd->mblk_lock);
+	count = dmz_shrink_mblock_cache(zmd, sc->nr_to_scan);
+	spin_unlock(&zmd->mblk_lock);
+
+	return count ? count : SHRINK_STOP;
+}
+
+/*
+ * Release a metadata block.
+ */
+static void dmz_release_mblock(struct dmz_metadata *zmd,
+			       struct dmz_mblock *mblk)
+{
+
+	if (!mblk)
+		return;
+
+	spin_lock(&zmd->mblk_lock);
+
+	if (atomic_dec_and_test(&mblk->ref)) {
+		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
+			rb_erase(&mblk->node, &zmd->mblk_rbtree);
+			dmz_free_mblock(zmd, mblk);
+		} else if (!test_bit(DMZ_META_DIRTY, &mblk->state)) {
+			list_add_tail(&mblk->link, &zmd->mblk_lru_list);
+			dmz_shrink_mblock_cache(zmd, 1);
+		}
+	}
+
+	spin_unlock(&zmd->mblk_lock);
+}
+
+/*
+ * Get a metadata block from the rbtree. If the block
+ * is not present, read it from disk.
+ */
+static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
+					 sector_t mblk_no)
+{
+	struct dmz_mblock *mblk;
+
+	/* Check rbtree */
+	spin_lock(&zmd->mblk_lock);
+	mblk = dmz_lookup_mblock(zmd, mblk_no);
+	if (mblk) {
+		/* Cache hit: remove block from LRU list */
+		if (atomic_inc_return(&mblk->ref) == 1 &&
+		    !test_bit(DMZ_META_DIRTY, &mblk->state))
+			list_del_init(&mblk->link);
+	}
+	spin_unlock(&zmd->mblk_lock);
+
+	if (!mblk) {
+		/* Cache miss: read the block from disk */
+		mblk = dmz_fetch_mblock(zmd, mblk_no);
+		if (!mblk)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	/* Wait for on-going read I/O and check for error */
+	wait_on_bit_io(&mblk->state, DMZ_META_READING,
+		       TASK_UNINTERRUPTIBLE);
+	if (test_bit(DMZ_META_ERROR, &mblk->state)) {
+		dmz_release_mblock(zmd, mblk);
+		return ERR_PTR(-EIO);
+	}
+
+	return mblk;
+}
+
+/*
+ * Mark a metadata block dirty.
+ */
+static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
+{
+	spin_lock(&zmd->mblk_lock);
+	if (!test_and_set_bit(DMZ_META_DIRTY, &mblk->state))
+		list_add_tail(&mblk->link, &zmd->mblk_dirty_list);
+	spin_unlock(&zmd->mblk_lock);
+}
+
+/*
+ * Issue a metadata block write BIO.
+ */
+static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
+			     unsigned int set)
+{
+	sector_t block = zmd->sb[set].block + mblk->no;
+	struct bio *bio;
+
+	bio = bio_alloc(GFP_NOIO, 1);
+	if (!bio) {
+		set_bit(DMZ_META_ERROR, &mblk->state);
+		return;
+	}
+
+	set_bit(DMZ_META_WRITING, &mblk->state);
+
+	bio->bi_iter.bi_sector = dmz_blk2sect(block);
+	bio->bi_bdev = zmd->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);
+	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
+	submit_bio(bio);
+}
+
+/*
+ * Read/write a metadata block.
+ */
+static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
+			  struct page *page)
+{
+	struct bio *bio;
+	int ret;
+
+	bio = bio_alloc(GFP_NOIO, 1);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_iter.bi_sector = dmz_blk2sect(block);
+	bio->bi_bdev = zmd->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);
+
+	return ret;
+}
+
+/*
+ * Write super block of the specified metadata set.
+ */
+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;
+	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->gen = cpu_to_le64(sb_gen);
+
+	sb->sb_block = cpu_to_le64(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);
+
+	sb->nr_map_blocks = cpu_to_le32(zmd->nr_map_blocks);
+	sb->nr_bitmap_blocks = cpu_to_le32(zmd->nr_bitmap_blocks);
+
+	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);
+	if (ret == 0)
+		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_KERNEL, NULL);
+
+	return ret;
+}
+
+/*
+ * Write dirty metadata blocks to the specified set.
+ */
+static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
+				   struct list_head *write_list,
+				   unsigned int set)
+{
+	struct dmz_mblock *mblk;
+	struct blk_plug plug;
+	int ret = 0;
+
+	/* Issue writes */
+	blk_start_plug(&plug);
+	list_for_each_entry(mblk, write_list, link)
+		dmz_write_mblock(zmd, mblk, set);
+	blk_finish_plug(&plug);
+
+	/* Wait for completion */
+	list_for_each_entry(mblk, write_list, link) {
+		wait_on_bit_io(&mblk->state, DMZ_META_WRITING,
+			       TASK_UNINTERRUPTIBLE);
+		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
+			clear_bit(DMZ_META_ERROR, &mblk->state);
+			ret = -EIO;
+		}
+	}
+
+	/* Flush drive cache (this will also sync data) */
+	if (ret == 0)
+		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_KERNEL, NULL);
+
+	return ret;
+}
+
+/*
+ * Log dirty metadata blocks.
+ */
+static int dmz_log_dirty_mblocks(struct dmz_metadata *zmd,
+				 struct list_head *write_list)
+{
+	unsigned int log_set = zmd->mblk_primary ^ 0x1;
+	int ret;
+
+	/* Write dirty blocks to the log */
+	ret = dmz_write_dirty_mblocks(zmd, write_list, log_set);
+	if (ret)
+		return ret;
+
+	/*
+	 * No error so far: now validate the log by updating the
+	 * log index super block generation.
+	 */
+	ret = dmz_write_sb(zmd, log_set);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Flush dirty metadata blocks.
+ */
+int dmz_flush_metadata(struct dmz_metadata *zmd)
+{
+	struct dmz_mblock *mblk;
+	struct list_head write_list;
+	int ret;
+
+	if (WARN_ON(!zmd))
+		return 0;
+
+	INIT_LIST_HEAD(&write_list);
+
+	/*
+	 * Make sure that metadata blocks are stable before logging: take
+	 * the write lock on the metadata semaphore to prevent target BIOs
+	 * from modifying metadata.
+	 */
+	down_write(&zmd->mblk_sem);
+
+	/*
+	 * This is called from the target flush work and reclaim work.
+	 * Concurrent execution is not allowed.
+	 */
+	dmz_lock_flush(zmd);
+
+	/* Get dirty blocks */
+	spin_lock(&zmd->mblk_lock);
+	list_splice_init(&zmd->mblk_dirty_list, &write_list);
+	spin_unlock(&zmd->mblk_lock);
+
+	/* 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_KERNEL, NULL);
+		goto out;
+	}
+
+	/*
+	 * The primary metadata set is still clean. Keep it this way until
+	 * all updates are successful in the secondary set. That is, use
+	 * the secondary set as a log.
+	 */
+	ret = dmz_log_dirty_mblocks(zmd, &write_list);
+	if (ret)
+		goto out;
+
+	/*
+	 * The log is on disk. It is now safe to update in place
+	 * in the primary metadata set.
+	 */
+	ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary);
+	if (ret)
+		goto out;
+
+	ret = dmz_write_sb(zmd, zmd->mblk_primary);
+	if (ret)
+		goto out;
+
+	while (!list_empty(&write_list)) {
+		mblk = list_first_entry(&write_list, struct dmz_mblock, link);
+		list_del_init(&mblk->link);
+
+		spin_lock(&zmd->mblk_lock);
+		clear_bit(DMZ_META_DIRTY, &mblk->state);
+		if (atomic_read(&mblk->ref) == 0)
+			list_add_tail(&mblk->link, &zmd->mblk_lru_list);
+		spin_unlock(&zmd->mblk_lock);
+	}
+
+	zmd->sb_gen++;
+out:
+	if (ret && !list_empty(&write_list)) {
+		spin_lock(&zmd->mblk_lock);
+		list_splice(&write_list, &zmd->mblk_dirty_list);
+		spin_unlock(&zmd->mblk_lock);
+	}
+
+	dmz_unlock_flush(zmd);
+	up_write(&zmd->mblk_sem);
+
+	return ret;
+}
+
+/*
+ * Check super block.
+ */
+static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb)
+{
+	unsigned int nr_meta_zones, nr_data_zones;
+	struct dmz_dev *dev = zmd->dev;
+	u32 crc, stored_crc;
+	u64 gen;
+
+	gen = le64_to_cpu(sb->gen);
+	stored_crc = le32_to_cpu(sb->crc);
+	sb->crc = 0;
+	crc = crc32_le(gen, (unsigned char *)sb, DMZ_BLOCK_SIZE);
+	if (crc != stored_crc) {
+		dmz_dev_err(dev, "Invalid checksum (needed 0x%08x, got 0x%08x)",
+			    crc, stored_crc);
+		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;
+	}
+
+	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;
+	}
+
+	nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + dev->zone_nr_blocks - 1)
+		>> dev->zone_nr_blocks_shift;
+	if (!nr_meta_zones ||
+	    nr_meta_zones >= zmd->nr_rnd_zones) {
+		dmz_dev_err(dev, "Invalid number of metadata blocks");
+		return -ENXIO;
+	}
+
+	if (!le32_to_cpu(sb->nr_reserved_seq) ||
+	    le32_to_cpu(sb->nr_reserved_seq) >= (zmd->nr_useable_zones - nr_meta_zones)) {
+		dmz_dev_err(dev, "Invalid number of reserved sequential zones");
+		return -ENXIO;
+	}
+
+	nr_data_zones = zmd->nr_useable_zones -
+		(nr_meta_zones * 2 + le32_to_cpu(sb->nr_reserved_seq));
+	if (le32_to_cpu(sb->nr_chunks) > nr_data_zones) {
+		dmz_dev_err(dev, "Invalid number of chunks %u / %u",
+			    le32_to_cpu(sb->nr_chunks), nr_data_zones);
+		return -ENXIO;
+	}
+
+	/* OK */
+	zmd->nr_meta_blocks = le32_to_cpu(sb->nr_meta_blocks);
+	zmd->nr_reserved_seq = le32_to_cpu(sb->nr_reserved_seq);
+	zmd->nr_chunks = le32_to_cpu(sb->nr_chunks);
+	zmd->nr_map_blocks = le32_to_cpu(sb->nr_map_blocks);
+	zmd->nr_bitmap_blocks = le32_to_cpu(sb->nr_bitmap_blocks);
+	zmd->nr_meta_zones = nr_meta_zones;
+	zmd->nr_data_zones = nr_data_zones;
+
+	return 0;
+}
+
+/*
+ * Read the first or second super block from disk.
+ */
+static int dmz_read_sb(struct dmz_metadata *zmd, unsigned int set)
+{
+	return dmz_rdwr_block(zmd, REQ_OP_READ, zmd->sb[set].block,
+			      zmd->sb[set].mblk->page);
+}
+
+/*
+ * Determine the position of the secondary super blocks on disk.
+ * This is used only if a corruption of the primary super block
+ * is detected.
+ */
+static int dmz_lookup_secondary_sb(struct dmz_metadata *zmd)
+{
+	unsigned int zone_nr_blocks = zmd->dev->zone_nr_blocks;
+	struct dmz_mblock *mblk;
+	int i;
+
+	/* Allocate a block */
+	mblk = dmz_alloc_mblock(zmd, 0);
+	if (!mblk)
+		return -ENOMEM;
+
+	zmd->sb[1].mblk = mblk;
+	zmd->sb[1].sb = mblk->data;
+
+	/* 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)
+			break;
+		if (le32_to_cpu(zmd->sb[1].sb->magic) == DMZ_MAGIC)
+			return 0;
+		zmd->sb[1].block += zone_nr_blocks;
+	}
+
+	dmz_free_mblock(zmd, mblk);
+	zmd->sb[1].mblk = NULL;
+
+	return -EIO;
+}
+
+/*
+ * Read the first or second super block from disk.
+ */
+static int dmz_get_sb(struct dmz_metadata *zmd, unsigned int set)
+{
+	struct dmz_mblock *mblk;
+	int ret;
+
+	/* Allocate a block */
+	mblk = dmz_alloc_mblock(zmd, 0);
+	if (!mblk)
+		return -ENOMEM;
+
+	zmd->sb[set].mblk = mblk;
+	zmd->sb[set].sb = mblk->data;
+
+	/* Read super block */
+	ret = dmz_read_sb(zmd, set);
+	if (ret) {
+		dmz_free_mblock(zmd, mblk);
+		zmd->sb[set].mblk = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Recover a metadata set.
+ */
+static int dmz_recover_mblocks(struct dmz_metadata *zmd, unsigned int dst_set)
+{
+	unsigned int src_set = dst_set ^ 0x1;
+	struct page *page;
+	int i, ret;
+
+	dmz_dev_warn(zmd->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);
+	}
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	/* Copy metadata blocks */
+	for (i = 1; i < zmd->nr_meta_blocks; i++) {
+		ret = dmz_rdwr_block(zmd, REQ_OP_READ,
+				     zmd->sb[src_set].block + i, page);
+		if (ret)
+			goto out;
+		ret = dmz_rdwr_block(zmd, REQ_OP_WRITE,
+				     zmd->sb[dst_set].block + i, page);
+		if (ret)
+			goto out;
+	}
+
+	/* Finalize with the super block */
+	if (!zmd->sb[dst_set].mblk) {
+		zmd->sb[dst_set].mblk = dmz_alloc_mblock(zmd, 0);
+		if (!zmd->sb[dst_set].mblk) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		zmd->sb[dst_set].sb = zmd->sb[dst_set].mblk->data;
+	}
+
+	ret = dmz_write_sb(zmd, dst_set);
+out:
+	__free_pages(page, 0);
+
+	return ret;
+}
+
+/*
+ * Get super block from disk.
+ */
+static int dmz_load_sb(struct dmz_metadata *zmd)
+{
+	bool sb_good[2] = {false, false};
+	u64 sb_gen[2] = {0, 0};
+	int ret;
+
+	/* Read and check the primary super block */
+	zmd->sb[0].block = dmz_start_block(zmd, zmd->sb_zone);
+	ret = dmz_get_sb(zmd, 0);
+	if (ret) {
+		dmz_dev_err(zmd->dev, "Read primary super block failed");
+		return ret;
+	}
+
+	ret = dmz_check_sb(zmd, zmd->sb[0].sb);
+
+	/* 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);
+	} else
+		ret = dmz_lookup_secondary_sb(zmd);
+
+	if (ret) {
+		dmz_dev_err(zmd->dev, "Read secondary super block failed");
+		return ret;
+	}
+
+	ret = dmz_check_sb(zmd, zmd->sb[1].sb);
+	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");
+		return -EIO;
+	}
+
+	if (sb_good[0])
+		sb_gen[0] = le64_to_cpu(zmd->sb[0].sb->gen);
+	else
+		ret = dmz_recover_mblocks(zmd, 0);
+
+	if (sb_good[1])
+		sb_gen[1] = le64_to_cpu(zmd->sb[1].sb->gen);
+	else
+		ret = dmz_recover_mblocks(zmd, 1);
+
+	if (ret) {
+		dmz_dev_err(zmd->dev, "Recovery failed");
+		return -EIO;
+	}
+
+	if (sb_gen[0] >= sb_gen[1]) {
+		zmd->sb_gen = sb_gen[0];
+		zmd->mblk_primary = 0;
+	} else {
+		zmd->sb_gen = sb_gen[1];
+		zmd->mblk_primary = 1;
+	}
+
+	dmz_dev_debug(zmd->dev, "Using super block %u (gen %llu)",
+		      zmd->mblk_primary, zmd->sb_gen);
+
+	return 0;
+}
+
+/*
+ * Initialize a zone descriptor.
+ */
+static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
+			 struct blk_zone *blkz)
+{
+	struct dmz_dev *dev = zmd->dev;
+
+	/* Ignore the eventual last runt (smaller) zone */
+	if (blkz->len != dev->zone_nr_sectors) {
+		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;
+
+	if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		set_bit(DMZ_RND, &zone->flags);
+		zmd->nr_rnd_zones++;
+	} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
+		   blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
+		set_bit(DMZ_SEQ, &zone->flags);
+	} else
+		return -ENXIO;
+
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
+
+	if (dmz_is_rnd(zone))
+		zone->wp_block = 0;
+	else
+		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
+
+	if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) {
+		zmd->nr_useable_zones++;
+		if (dmz_is_rnd(zone)) {
+			zmd->nr_rnd_zones++;
+			if (!zmd->sb_zone) {
+				/* Super block zone */
+				zmd->sb_zone = zone;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Free zones descriptors.
+ */
+static void dmz_drop_zones(struct dmz_metadata *zmd)
+{
+	kfree(zmd->zones);
+	zmd->zones = NULL;
+}
+
+/*
+ * The size of a zone report in number of zones.
+ * This results in 4096*64B=256KB report zones commands.
+ */
+#define DMZ_REPORT_NR_ZONES	4096
+
+/*
+ * Allocate and initialize zone descriptors using the zone
+ * information from disk.
+ */
+static int dmz_init_zones(struct dmz_metadata *zmd)
+{
+	struct dmz_dev *dev = zmd->dev;
+	struct dm_zone *zone;
+	struct blk_zone *blkz;
+	unsigned int nr_blkz;
+	sector_t sector = 0;
+	int i, ret = 0;
+
+	/* Init */
+	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
+	zmd->zone_nr_bitmap_blocks = zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT;
+
+	/* Allocate zone array */
+	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
+	if (!zmd->zones)
+		return -ENOMEM;
+
+	dmz_dev_info(dev, "Using %zu B for zone information",
+		     sizeof(struct dm_zone) * dev->nr_zones);
+
+	/* Get zone information */
+	nr_blkz = DMZ_REPORT_NR_ZONES;
+	blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!blkz) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * 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.
+	 */
+	zone = zmd->zones;
+	while (sector < dev->capacity) {
+		/* Get zone information */
+		nr_blkz = DMZ_REPORT_NR_ZONES;
+		ret = blkdev_report_zones(dev->bdev, sector, blkz,
+					  &nr_blkz, GFP_KERNEL);
+		if (ret) {
+			dmz_dev_err(dev, "Report zones failed %d", ret);
+			goto out;
+		}
+
+		/* Process report */
+		for (i = 0; i < nr_blkz; i++) {
+			ret = dmz_init_zone(zmd, zone, &blkz[i]);
+			if (ret)
+				goto out;
+			sector += dev->zone_nr_sectors;
+			zone++;
+		}
+	}
+
+	/* The entire zone configuration of the disk should now be known */
+	if (sector < dev->capacity) {
+		dmz_dev_err(dev, "Failed to get correct zone information");
+		ret = -ENXIO;
+	}
+out:
+	kfree(blkz);
+	if (ret)
+		dmz_drop_zones(zmd);
+
+	return ret;
+}
+
+/*
+ * Update a zone information.
+ */
+static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	unsigned int nr_blkz = 1;
+	struct blk_zone blkz;
+	int ret;
+
+	/* Get zone information from disk */
+	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
+				  &blkz, &nr_blkz, GFP_KERNEL);
+	if (ret) {
+		dmz_dev_err(zmd->dev, "Get zone %u report failed",
+			    dmz_id(zmd, zone));
+		return ret;
+	}
+
+	clear_bit(DMZ_OFFLINE, &zone->flags);
+	clear_bit(DMZ_READ_ONLY, &zone->flags);
+	if (blkz.cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz.cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
+
+	if (dmz_is_seq(zone))
+		zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start);
+	else
+		zone->wp_block = 0;
+
+	return 0;
+}
+
+/*
+ * Check a zone write pointer position when the zone is marked
+ * with the sequential write error flag.
+ */
+static int dmz_handle_seq_write_err(struct dmz_metadata *zmd,
+				    struct dm_zone *zone)
+{
+	unsigned int wp = 0;
+	int ret;
+
+	wp = zone->wp_block;
+	ret = dmz_update_zone(zmd, zone);
+	if (ret)
+		return ret;
+
+	dmz_dev_warn(zmd->dev, "Processing zone %u write error (zone wp %u/%u)",
+		     dmz_id(zmd, zone), zone->wp_block, wp);
+
+	if (zone->wp_block < wp) {
+		dmz_invalidate_blocks(zmd, zone, zone->wp_block,
+				      wp - zone->wp_block);
+	}
+
+	return 0;
+}
+
+static struct dm_zone *dmz_get(struct dmz_metadata *zmd, unsigned int zone_id)
+{
+	return &zmd->zones[zone_id];
+}
+
+/*
+ * Reset a zone write pointer.
+ */
+static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	int ret;
+
+	/*
+	 * Ignore offline zones, read only zones,
+	 * and conventional zones.
+	 */
+	if (dmz_is_offline(zone) ||
+	    dmz_is_readonly(zone) ||
+	    dmz_is_rnd(zone))
+		return 0;
+
+	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
+		struct dmz_dev *dev = zmd->dev;
+
+		ret = blkdev_reset_zones(dev->bdev,
+					 dmz_start_sect(zmd, zone),
+					 dev->zone_nr_sectors, GFP_KERNEL);
+		if (ret) {
+			dmz_dev_err(dev, "Reset zone %u failed %d",
+				    dmz_id(zmd, zone), ret);
+			return ret;
+		}
+	}
+
+	/* Clear write error bit and rewind write pointer position */
+	clear_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
+	zone->wp_block = 0;
+
+	return 0;
+}
+
+static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone);
+
+/*
+ * Initialize chunk mapping.
+ */
+static int dmz_load_mapping(struct dmz_metadata *zmd)
+{
+	struct dmz_dev *dev = zmd->dev;
+	struct dm_zone *dzone, *bzone;
+	struct dmz_mblock *dmap_mblk = NULL;
+	struct dmz_map *dmap;
+	unsigned int i = 0, e = 0, chunk = 0;
+	unsigned int dzone_id;
+	unsigned int bzone_id;
+
+	/* Metadata block array for the chunk mapping table */
+	zmd->map_mblk = kcalloc(zmd->nr_map_blocks,
+				sizeof(struct dmz_mblk *), GFP_KERNEL);
+	if (!zmd->map_mblk)
+		return -ENOMEM;
+
+	/* Get chunk mapping table blocks and initialize zone mapping */
+	while (chunk < zmd->nr_chunks) {
+		if (!dmap_mblk) {
+			/* Get mapping block */
+			dmap_mblk = dmz_get_mblock(zmd, i + 1);
+			if (IS_ERR(dmap_mblk))
+				return PTR_ERR(dmap_mblk);
+			zmd->map_mblk[i] = dmap_mblk;
+			dmap = (struct dmz_map *) dmap_mblk->data;
+			i++;
+			e = 0;
+		}
+
+		/* Check data zone */
+		dzone_id = le32_to_cpu(dmap[e].dzone_id);
+		if (dzone_id == DMZ_MAP_UNMAPPED)
+			goto next;
+
+		if (dzone_id >= dev->nr_zones) {
+			dmz_dev_err(dev, "Chunk %u mapping: invalid data zone ID %u",
+				    chunk, dzone_id);
+			return -EIO;
+		}
+
+		dzone = dmz_get(zmd, dzone_id);
+		set_bit(DMZ_DATA, &dzone->flags);
+		dzone->chunk = chunk;
+		dmz_get_zone_weight(zmd, dzone);
+
+		if (dmz_is_rnd(dzone))
+			list_add_tail(&dzone->link, &zmd->map_rnd_list);
+		else
+			list_add_tail(&dzone->link, &zmd->map_seq_list);
+
+		/* Check buffer zone */
+		bzone_id = le32_to_cpu(dmap[e].bzone_id);
+		if (bzone_id == DMZ_MAP_UNMAPPED)
+			goto next;
+
+		if (bzone_id >= dev->nr_zones) {
+			dmz_dev_err(dev, "Chunk %u mapping: invalid buffer zone ID %u",
+				    chunk, bzone_id);
+			return -EIO;
+		}
+
+		bzone = dmz_get(zmd, bzone_id);
+		if (!dmz_is_rnd(bzone)) {
+			dmz_dev_err(dev, "Chunk %u mapping: invalid buffer zone %u",
+				    chunk, bzone_id);
+			return -EIO;
+		}
+
+		set_bit(DMZ_DATA, &bzone->flags);
+		set_bit(DMZ_BUF, &bzone->flags);
+		bzone->chunk = chunk;
+		bzone->bzone = dzone;
+		dzone->bzone = bzone;
+		dmz_get_zone_weight(zmd, bzone);
+		list_add_tail(&bzone->link, &zmd->map_rnd_list);
+next:
+		chunk++;
+		e++;
+		if (e >= DMZ_MAP_ENTRIES)
+			dmap_mblk = NULL;
+	}
+
+	/*
+	 * At this point, only meta zones and mapped data zones were
+	 * fully initialized. All remaining zones are unmapped data
+	 * zones. Finish initializing those here.
+	 */
+	for (i = 0; i < dev->nr_zones; i++) {
+		dzone = dmz_get(zmd, i);
+		if (dmz_is_meta(dzone))
+			continue;
+
+		if (dmz_is_rnd(dzone))
+			zmd->nr_rnd++;
+		else
+			zmd->nr_seq++;
+
+		if (dmz_is_data(dzone)) {
+			/* Already initialized */
+			continue;
+		}
+
+		/* Unmapped data zone */
+		set_bit(DMZ_DATA, &dzone->flags);
+		dzone->chunk = DMZ_MAP_UNMAPPED;
+		if (dmz_is_rnd(dzone)) {
+			list_add_tail(&dzone->link, &zmd->unmap_rnd_list);
+			atomic_inc(&zmd->unmap_nr_rnd);
+		} else if (atomic_read(&zmd->nr_reserved_seq_zones) < zmd->nr_reserved_seq) {
+			list_add_tail(&dzone->link, &zmd->reserved_seq_zones_list);
+			atomic_inc(&zmd->nr_reserved_seq_zones);
+			zmd->nr_seq--;
+		} else {
+			list_add_tail(&dzone->link, &zmd->unmap_seq_list);
+			atomic_inc(&zmd->unmap_nr_seq);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Set a data chunk mapping.
+ */
+static void dmz_set_chunk_mapping(struct dmz_metadata *zmd, unsigned int chunk,
+				  unsigned int dzone_id, unsigned int bzone_id)
+{
+	struct dmz_mblock *dmap_mblk = zmd->map_mblk[chunk >> DMZ_MAP_ENTRIES_SHIFT];
+	struct dmz_map *dmap = (struct dmz_map *) dmap_mblk->data;
+	int map_idx = chunk & DMZ_MAP_ENTRIES_MASK;
+
+	dmap[map_idx].dzone_id = cpu_to_le32(dzone_id);
+	dmap[map_idx].bzone_id = cpu_to_le32(bzone_id);
+	dmz_dirty_mblock(zmd, dmap_mblk);
+}
+
+/*
+ * The list of mapped zones is maintained in LRU order.
+ * This rotates a zone at the end of its map list.
+ */
+static void __dmz_lru_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	if (list_empty(&zone->link))
+		return;
+
+	list_del_init(&zone->link);
+	if (dmz_is_seq(zone)) {
+		/* LRU rotate sequential zone */
+		list_add_tail(&zone->link, &zmd->map_seq_list);
+	} else {
+		/* LRU rotate random zone */
+		list_add_tail(&zone->link, &zmd->map_rnd_list);
+	}
+}
+
+/*
+ * The list of mapped random zones is maintained
+ * in LRU order. This rotates a zone at the end of the list.
+ */
+static void dmz_lru_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	__dmz_lru_zone(zmd, zone);
+	if (zone->bzone)
+		__dmz_lru_zone(zmd, zone->bzone);
+}
+
+/*
+ * Wait for any zone to be freed.
+ */
+static void dmz_wait_for_free_zones(struct dmz_metadata *zmd)
+{
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(&zmd->free_wq, &wait, TASK_UNINTERRUPTIBLE);
+	dmz_unlock_map(zmd);
+	dmz_unlock_metadata(zmd);
+
+	io_schedule_timeout(HZ);
+
+	dmz_lock_metadata(zmd);
+	dmz_lock_map(zmd);
+	finish_wait(&zmd->free_wq, &wait);
+}
+
+/*
+ * Lock a zone for reclaim (set the zone RECLAIM bit).
+ * Returns false if the zone cannot be locked or if it is already locked
+ * and 1 otherwise.
+ */
+int dmz_lock_zone_reclaim(struct dm_zone *zone)
+{
+	/* Active zones cannot be reclaimed */
+	if (dmz_is_active(zone))
+		return 0;
+
+	return !test_and_set_bit(DMZ_RECLAIM, &zone->flags);
+}
+
+/*
+ * Clear a zone reclaim flag.
+ */
+void dmz_unlock_zone_reclaim(struct dm_zone *zone)
+{
+	WARN_ON(dmz_is_active(zone));
+	WARN_ON(!dmz_in_reclaim(zone));
+
+	clear_bit_unlock(DMZ_RECLAIM, &zone->flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&zone->flags, DMZ_RECLAIM);
+}
+
+/*
+ * Wait for a zone reclaim to complete.
+ */
+static void dmz_wait_for_reclaim(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	dmz_unlock_map(zmd);
+	dmz_unlock_metadata(zmd);
+	wait_on_bit_timeout(&zone->flags, DMZ_RECLAIM, TASK_UNINTERRUPTIBLE, HZ);
+	dmz_lock_metadata(zmd);
+	dmz_lock_map(zmd);
+}
+
+/*
+ * Select a random write zone for reclaim.
+ */
+static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd)
+{
+	struct dm_zone *dzone = NULL;
+	struct dm_zone *zone;
+
+	if (list_empty(&zmd->map_rnd_list))
+		return NULL;
+
+	list_for_each_entry(zone, &zmd->map_rnd_list, link) {
+		if (dmz_is_buf(zone))
+			dzone = zone->bzone;
+		else
+			dzone = zone;
+		if (dmz_lock_zone_reclaim(dzone))
+			return dzone;
+	}
+
+	return NULL;
+}
+
+/*
+ * Select a buffered sequential zone for reclaim.
+ */
+static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
+{
+	struct dm_zone *zone;
+
+	if (list_empty(&zmd->map_seq_list))
+		return NULL;
+
+	list_for_each_entry(zone, &zmd->map_seq_list, link) {
+		if (!zone->bzone)
+			continue;
+		if (dmz_lock_zone_reclaim(zone))
+			return zone;
+	}
+
+	return NULL;
+}
+
+/*
+ * Select a zone for reclaim.
+ */
+struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd)
+{
+	struct dm_zone *zone;
+
+	/*
+	 * Search for a zone candidate to reclaim: 2 cases are possible.
+	 * (1) There is no free sequential zones. Then a random data zone
+	 *     cannot be reclaimed. So choose a sequential zone to reclaim so
+	 *     that afterward a random zone can be reclaimed.
+	 * (2) At least one free sequential zone is available, then choose
+	 *     the oldest random zone (data or buffer) that can be locked.
+	 */
+	dmz_lock_map(zmd);
+	if (list_empty(&zmd->reserved_seq_zones_list))
+		zone = dmz_get_seq_zone_for_reclaim(zmd);
+	else
+		zone = dmz_get_rnd_zone_for_reclaim(zmd);
+	dmz_unlock_map(zmd);
+
+	return zone;
+}
+
+/*
+ * Activate a zone (increment its reference count).
+ */
+void dmz_activate_zone(struct dm_zone *zone)
+{
+	set_bit(DMZ_ACTIVE, &zone->flags);
+	atomic_inc(&zone->refcount);
+}
+
+/*
+ * Deactivate a zone. This decrement the zone reference counter
+ * and clears the active state of the zone once the count reaches 0,
+ * indicating that all BIOs to the zone have completed. Returns
+ * true if the zone was deactivated.
+ */
+void dmz_deactivate_zone(struct dm_zone *zone)
+{
+	if (atomic_dec_and_test(&zone->refcount)) {
+		WARN_ON(!test_bit(DMZ_ACTIVE, &zone->flags));
+		clear_bit_unlock(DMZ_ACTIVE, &zone->flags);
+		smp_mb__after_atomic();
+	}
+}
+
+/*
+ * Get the zone mapping a chunk, if the chunk is mapped already.
+ * If no mapping exist and the operation is WRITE, a zone is
+ * allocated and used to map the chunk.
+ * The zone returned will be set to the active state.
+ */
+struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd, unsigned int chunk, int op)
+{
+	struct dmz_mblock *dmap_mblk = zmd->map_mblk[chunk >> DMZ_MAP_ENTRIES_SHIFT];
+	struct dmz_map *dmap = (struct dmz_map *) dmap_mblk->data;
+	int dmap_idx = chunk & DMZ_MAP_ENTRIES_MASK;
+	unsigned int dzone_id;
+	struct dm_zone *dzone = NULL;
+	int ret = 0;
+
+	dmz_lock_map(zmd);
+again:
+	/* Get the chunk mapping */
+	dzone_id = le32_to_cpu(dmap[dmap_idx].dzone_id);
+	if (dzone_id == DMZ_MAP_UNMAPPED) {
+		/*
+		 * Read or discard in unmapped chunks are fine. But for
+		 * writes, we need a mapping, so get one.
+		 */
+		if (op != REQ_OP_WRITE)
+			goto out;
+
+		/* Alloate a random zone */
+		dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
+		if (!dzone) {
+			dmz_wait_for_free_zones(zmd);
+			goto again;
+		}
+
+		dmz_map_zone(zmd, dzone, chunk);
+
+	} else {
+		/* The chunk is already mapped: get the mapping zone */
+		dzone = dmz_get(zmd, dzone_id);
+		if (dzone->chunk != chunk) {
+			dzone = ERR_PTR(-EIO);
+			goto out;
+		}
+
+		/* Repair write pointer if the sequential dzone has error */
+		if (dmz_seq_write_err(dzone)) {
+			ret = dmz_handle_seq_write_err(zmd, dzone);
+			if (ret) {
+				dzone = ERR_PTR(-EIO);
+				goto out;
+			}
+			clear_bit(DMZ_SEQ_WRITE_ERR, &dzone->flags);
+		}
+	}
+
+	/*
+	 * If the zone is being reclaimed, the chunk mapping may change
+	 * to a different zone. So wait for reclaim and retry. Otherwise,
+	 * activate the zone (this will prevent reclaim from touching it).
+	 */
+	if (dmz_in_reclaim(dzone)) {
+		dmz_wait_for_reclaim(zmd, dzone);
+		goto again;
+	}
+	dmz_activate_zone(dzone);
+	dmz_lru_zone(zmd, dzone);
+out:
+	dmz_unlock_map(zmd);
+
+	return dzone;
+}
+
+/*
+ * Write and discard change the block validity of data zones and their buffer
+ * zones. Check here that valid blocks are still present. If all blocks are
+ * invalid, the zones can be unmapped on the fly without waiting for reclaim
+ * to do it.
+ */
+void dmz_put_chunk_mapping(struct dmz_metadata *zmd, struct dm_zone *dzone)
+{
+	struct dm_zone *bzone;
+
+	dmz_lock_map(zmd);
+
+	bzone = dzone->bzone;
+	if (bzone) {
+		if (dmz_weight(bzone))
+			dmz_lru_zone(zmd, bzone);
+		else {
+			/* Empty buffer zone: reclaim it */
+			dmz_unmap_zone(zmd, bzone);
+			dmz_free_zone(zmd, bzone);
+			bzone = NULL;
+		}
+	}
+
+	/* Deactivate the data zone */
+	dmz_deactivate_zone(dzone);
+	if (dmz_is_active(dzone) || bzone || dmz_weight(dzone))
+		dmz_lru_zone(zmd, dzone);
+	else {
+		/* Unbuffered inactive empty data zone: reclaim it */
+		dmz_unmap_zone(zmd, dzone);
+		dmz_free_zone(zmd, dzone);
+	}
+
+	dmz_unlock_map(zmd);
+}
+
+/*
+ * Allocate and map a random zone to buffer a chunk
+ * already mapped to a sequential zone.
+ */
+struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd,
+				     struct dm_zone *dzone)
+{
+	struct dm_zone *bzone;
+
+	dmz_lock_map(zmd);
+again:
+	bzone = dzone->bzone;
+	if (bzone)
+		goto out;
+
+	/* Alloate a random zone */
+	bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
+	if (!bzone) {
+		dmz_wait_for_free_zones(zmd);
+		goto again;
+	}
+
+	/* Update the chunk mapping */
+	dmz_set_chunk_mapping(zmd, dzone->chunk, dmz_id(zmd, dzone),
+			      dmz_id(zmd, bzone));
+
+	set_bit(DMZ_BUF, &bzone->flags);
+	bzone->chunk = dzone->chunk;
+	bzone->bzone = dzone;
+	dzone->bzone = bzone;
+	list_add_tail(&bzone->link, &zmd->map_rnd_list);
+out:
+	dmz_unlock_map(zmd);
+
+	return bzone;
+}
+
+/*
+ * Get an unmapped (free) zone.
+ * This must be called with the mapping lock held.
+ */
+struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags)
+{
+	struct list_head *list;
+	struct dm_zone *zone;
+
+	if (flags & DMZ_ALLOC_RND)
+		list = &zmd->unmap_rnd_list;
+	else
+		list = &zmd->unmap_seq_list;
+again:
+	if (list_empty(list)) {
+		/*
+		 * No free zone: if this is for reclaim, allow using the
+		 * reserved sequential zones.
+		 */
+		if (!(flags & DMZ_ALLOC_RECLAIM) ||
+		    list_empty(&zmd->reserved_seq_zones_list))
+			return NULL;
+
+		zone = list_first_entry(&zmd->reserved_seq_zones_list,
+					struct dm_zone, link);
+		list_del_init(&zone->link);
+		atomic_dec(&zmd->nr_reserved_seq_zones);
+		return zone;
+	}
+
+	zone = list_first_entry(list, struct dm_zone, link);
+	list_del_init(&zone->link);
+
+	if (dmz_is_rnd(zone))
+		atomic_dec(&zmd->unmap_nr_rnd);
+	else
+		atomic_dec(&zmd->unmap_nr_seq);
+
+	if (dmz_is_offline(zone)) {
+		dmz_dev_warn(zmd->dev, "Zone %u is offline", dmz_id(zmd, zone));
+		zone = NULL;
+		goto again;
+	}
+
+	return zone;
+}
+
+/*
+ * Free a zone.
+ * This must be called with the mapping lock held.
+ */
+void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	/* If this is a sequential zone, reset it */
+	if (dmz_is_seq(zone))
+		dmz_reset_zone(zmd, zone);
+
+	/* Return the zone to its type unmap list */
+	if (dmz_is_rnd(zone)) {
+		list_add_tail(&zone->link, &zmd->unmap_rnd_list);
+		atomic_inc(&zmd->unmap_nr_rnd);
+	} else if (atomic_read(&zmd->nr_reserved_seq_zones) <
+		   zmd->nr_reserved_seq) {
+		list_add_tail(&zone->link, &zmd->reserved_seq_zones_list);
+		atomic_inc(&zmd->nr_reserved_seq_zones);
+	} else {
+		list_add_tail(&zone->link, &zmd->unmap_seq_list);
+		atomic_inc(&zmd->unmap_nr_seq);
+	}
+
+	wake_up_all(&zmd->free_wq);
+}
+
+/*
+ * Map a chunk to a zone.
+ * This must be called with the mapping lock held.
+ */
+void dmz_map_zone(struct dmz_metadata *zmd, struct dm_zone *dzone,
+		  unsigned int chunk)
+{
+	/* Set the chunk mapping */
+	dmz_set_chunk_mapping(zmd, chunk, dmz_id(zmd, dzone),
+			      DMZ_MAP_UNMAPPED);
+	dzone->chunk = chunk;
+	if (dmz_is_rnd(dzone))
+		list_add_tail(&dzone->link, &zmd->map_rnd_list);
+	else
+		list_add_tail(&dzone->link, &zmd->map_seq_list);
+}
+
+/*
+ * Unmap a zone.
+ * This must be called with the mapping lock held.
+ */
+void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	unsigned int chunk = zone->chunk;
+	unsigned int dzone_id;
+
+	if (chunk == DMZ_MAP_UNMAPPED) {
+		/* Already unmapped */
+		return;
+	}
+
+	if (test_and_clear_bit(DMZ_BUF, &zone->flags)) {
+		/*
+		 * Unmapping the chunk buffer zone: clear only
+		 * the chunk buffer mapping
+		 */
+		dzone_id = dmz_id(zmd, zone->bzone);
+		zone->bzone->bzone = NULL;
+		zone->bzone = NULL;
+
+	} else {
+		/*
+		 * Unmapping the chunk data zone: the zone must
+		 * not be buffered.
+		 */
+		if (WARN_ON(zone->bzone)) {
+			zone->bzone->bzone = NULL;
+			zone->bzone = NULL;
+		}
+		dzone_id = DMZ_MAP_UNMAPPED;
+	}
+
+	dmz_set_chunk_mapping(zmd, chunk, dzone_id, DMZ_MAP_UNMAPPED);
+
+	zone->chunk = DMZ_MAP_UNMAPPED;
+	list_del_init(&zone->link);
+}
+
+/*
+ * Set @nr_bits bits in @bitmap starting from @bit.
+ * Return the number of bits changed from 0 to 1.
+ */
+static unsigned int dmz_set_bits(unsigned long *bitmap,
+				 unsigned int bit, unsigned int nr_bits)
+{
+	unsigned long *addr;
+	unsigned int end = bit + nr_bits;
+	unsigned int n = 0;
+
+	while (bit < end) {
+		if (((bit & (BITS_PER_LONG - 1)) == 0) &&
+		    ((end - bit) >= BITS_PER_LONG)) {
+			/* Try to set the whole word at once */
+			addr = bitmap + BIT_WORD(bit);
+			if (*addr == 0) {
+				*addr = ULONG_MAX;
+				n += BITS_PER_LONG;
+				bit += BITS_PER_LONG;
+				continue;
+			}
+		}
+
+		if (!test_and_set_bit(bit, bitmap))
+			n++;
+		bit++;
+	}
+
+	return n;
+}
+
+/*
+ * Get the bitmap block storing the bit for chunk_block in zone.
+ */
+static struct dmz_mblock *dmz_get_bitmap(struct dmz_metadata *zmd,
+					 struct dm_zone *zone,
+					 sector_t chunk_block)
+{
+	sector_t bitmap_block = 1 + zmd->nr_map_blocks +
+		(sector_t)(dmz_id(zmd, zone) * zmd->zone_nr_bitmap_blocks) +
+		(chunk_block >> DMZ_BLOCK_SHIFT_BITS);
+
+	return dmz_get_mblock(zmd, bitmap_block);
+}
+
+/*
+ * Copy the valid blocks bitmap of from_zone to the bitmap of to_zone.
+ */
+int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+			  struct dm_zone *to_zone)
+{
+	struct dmz_mblock *from_mblk, *to_mblk;
+	sector_t chunk_block = 0;
+
+	/* Get the zones bitmap blocks */
+	while (chunk_block < zmd->dev->zone_nr_blocks) {
+		from_mblk = dmz_get_bitmap(zmd, from_zone, chunk_block);
+		if (IS_ERR(from_mblk))
+			return PTR_ERR(from_mblk);
+		to_mblk = dmz_get_bitmap(zmd, to_zone, chunk_block);
+		if (IS_ERR(to_mblk)) {
+			dmz_release_mblock(zmd, from_mblk);
+			return PTR_ERR(to_mblk);
+		}
+
+		memcpy(to_mblk->data, from_mblk->data, DMZ_BLOCK_SIZE);
+		dmz_dirty_mblock(zmd, to_mblk);
+
+		dmz_release_mblock(zmd, to_mblk);
+		dmz_release_mblock(zmd, from_mblk);
+
+		chunk_block += DMZ_BLOCK_SIZE_BITS;
+	}
+
+	to_zone->weight = from_zone->weight;
+
+	return 0;
+}
+
+/*
+ * Merge the valid blocks bitmap of from_zone into the bitmap of to_zone,
+ * starting from chunk_block.
+ */
+int dmz_merge_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+			   struct dm_zone *to_zone, sector_t chunk_block)
+{
+	unsigned int nr_blocks;
+	int ret;
+
+	/* Get the zones bitmap blocks */
+	while (chunk_block < zmd->dev->zone_nr_blocks) {
+		/* Get a valid region from the source zone */
+		ret = dmz_first_valid_block(zmd, from_zone, &chunk_block);
+		if (ret <= 0)
+			return ret;
+
+		nr_blocks = ret;
+		ret = dmz_validate_blocks(zmd, to_zone, chunk_block, nr_blocks);
+		if (ret)
+			return ret;
+
+		chunk_block += nr_blocks;
+	}
+
+	return 0;
+}
+
+/*
+ * Validate all the blocks in the range [block..block+nr_blocks-1].
+ */
+int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+			sector_t chunk_block, unsigned int nr_blocks)
+{
+	unsigned int count, bit, nr_bits;
+	unsigned int zone_nr_blocks = zmd->dev->zone_nr_blocks;
+	struct dmz_mblock *mblk;
+	unsigned int n = 0;
+
+	dmz_dev_debug(zmd->dev, "=> VALIDATE zone %u, block %llu, %u blocks",
+		      dmz_id(zmd, zone), (unsigned long long)chunk_block,
+		      nr_blocks);
+
+	WARN_ON(chunk_block + nr_blocks > zone_nr_blocks);
+
+	while (nr_blocks) {
+		/* Get bitmap block */
+		mblk = dmz_get_bitmap(zmd, zone, chunk_block);
+		if (IS_ERR(mblk))
+			return PTR_ERR(mblk);
+
+		/* Set bits */
+		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
+		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+
+		count = dmz_set_bits((unsigned long *)mblk->data, bit, nr_bits);
+		if (count) {
+			dmz_dirty_mblock(zmd, mblk);
+			n += count;
+		}
+		dmz_release_mblock(zmd, mblk);
+
+		nr_blocks -= nr_bits;
+		chunk_block += nr_bits;
+	}
+
+	if (likely(zone->weight + n <= zone_nr_blocks))
+		zone->weight += n;
+	else {
+		dmz_dev_warn(zmd->dev, "Zone %u: weight %u should be <= %u",
+			     dmz_id(zmd, zone), zone->weight,
+			     zone_nr_blocks - n);
+		zone->weight = zone_nr_blocks;
+	}
+
+	return 0;
+}
+
+/*
+ * Clear nr_bits bits in bitmap starting from bit.
+ * Return the number of bits cleared.
+ */
+static int dmz_clear_bits(unsigned long *bitmap, int bit, int nr_bits)
+{
+	unsigned long *addr;
+	int end = bit + nr_bits;
+	int n = 0;
+
+	while (bit < end) {
+		if (((bit & (BITS_PER_LONG - 1)) == 0) &&
+		    ((end - bit) >= BITS_PER_LONG)) {
+			/* Try to clear whole word at once */
+			addr = bitmap + BIT_WORD(bit);
+			if (*addr == ULONG_MAX) {
+				*addr = 0;
+				n += BITS_PER_LONG;
+				bit += BITS_PER_LONG;
+				continue;
+			}
+		}
+
+		if (test_and_clear_bit(bit, bitmap))
+			n++;
+		bit++;
+	}
+
+	return n;
+}
+
+/*
+ * Invalidate all the blocks in the range [block..block+nr_blocks-1].
+ */
+int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+			  sector_t chunk_block, unsigned int nr_blocks)
+{
+	unsigned int count, bit, nr_bits;
+	struct dmz_mblock *mblk;
+	unsigned int n = 0;
+
+	dmz_dev_debug(zmd->dev, "=> INVALIDATE zone %u, block %llu, %u blocks",
+		      dmz_id(zmd, zone), (u64)chunk_block, nr_blocks);
+
+	WARN_ON(chunk_block + nr_blocks > zmd->dev->zone_nr_blocks);
+
+	while (nr_blocks) {
+		/* Get bitmap block */
+		mblk = dmz_get_bitmap(zmd, zone, chunk_block);
+		if (IS_ERR(mblk))
+			return PTR_ERR(mblk);
+
+		/* Clear bits */
+		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
+		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+
+		count = dmz_clear_bits((unsigned long *)mblk->data,
+				       bit, nr_bits);
+		if (count) {
+			dmz_dirty_mblock(zmd, mblk);
+			n += count;
+		}
+		dmz_release_mblock(zmd, mblk);
+
+		nr_blocks -= nr_bits;
+		chunk_block += nr_bits;
+	}
+
+	if (zone->weight >= n)
+		zone->weight -= n;
+	else {
+		dmz_dev_warn(zmd->dev, "Zone %u: weight %u should be >= %u",
+			     dmz_id(zmd, zone), zone->weight, n);
+		zone->weight = 0;
+	}
+
+	return 0;
+}
+
+/*
+ * Get a block bit value.
+ */
+static int dmz_test_block(struct dmz_metadata *zmd, struct dm_zone *zone,
+			  sector_t chunk_block)
+{
+	struct dmz_mblock *mblk;
+	int ret;
+
+	WARN_ON(chunk_block >= zmd->dev->zone_nr_blocks);
+
+	/* Get bitmap block */
+	mblk = dmz_get_bitmap(zmd, zone, chunk_block);
+	if (IS_ERR(mblk))
+		return PTR_ERR(mblk);
+
+	/* Get offset */
+	ret = test_bit(chunk_block & DMZ_BLOCK_MASK_BITS,
+		       (unsigned long *) mblk->data) != 0;
+
+	dmz_release_mblock(zmd, mblk);
+
+	return ret;
+}
+
+/*
+ * Return the number of blocks from chunk_block to the first block with a bit
+ * value specified by set. Search at most nr_blocks blocks from chunk_block.
+ */
+static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
+				 sector_t chunk_block, unsigned int nr_blocks,
+				 int set)
+{
+	struct dmz_mblock *mblk;
+	unsigned int bit, set_bit, nr_bits;
+	unsigned long *bitmap;
+	int n = 0;
+
+	WARN_ON(chunk_block + nr_blocks > zmd->dev->zone_nr_blocks);
+
+	while (nr_blocks) {
+		/* Get bitmap block */
+		mblk = dmz_get_bitmap(zmd, zone, chunk_block);
+		if (IS_ERR(mblk))
+			return PTR_ERR(mblk);
+
+		/* Get offset */
+		bitmap = (unsigned long *) mblk->data;
+		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
+		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		if (set)
+			set_bit = find_next_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+		else
+			set_bit = find_next_zero_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+		dmz_release_mblock(zmd, mblk);
+
+		n += set_bit - bit;
+		if (set_bit < DMZ_BLOCK_SIZE_BITS)
+			break;
+
+		nr_blocks -= nr_bits;
+		chunk_block += nr_bits;
+	}
+
+	return n;
+}
+
+/*
+ * Test if chunk_block is valid. If it is, the number of consecutive
+ * valid blocks from chunk_block will be returned.
+ */
+int dmz_block_valid(struct dmz_metadata *zmd, struct dm_zone *zone,
+		    sector_t chunk_block)
+{
+	int valid;
+
+	valid = dmz_test_block(zmd, zone, chunk_block);
+	if (valid <= 0)
+		return valid;
+
+	/* The block is valid: get the number of valid blocks from block */
+	return dmz_to_next_set_block(zmd, zone, chunk_block,
+				     zmd->dev->zone_nr_blocks - chunk_block, 0);
+}
+
+/*
+ * Find the first valid block from @chunk_block in @zone.
+ * If such a block is found, its number is returned using
+ * @chunk_block and the total number of valid blocks from @chunk_block
+ * is returned.
+ */
+int dmz_first_valid_block(struct dmz_metadata *zmd, struct dm_zone *zone,
+			  sector_t *chunk_block)
+{
+	sector_t start_block = *chunk_block;
+	int ret;
+
+	ret = dmz_to_next_set_block(zmd, zone, start_block,
+				    zmd->dev->zone_nr_blocks - start_block, 1);
+	if (ret < 0)
+		return ret;
+
+	start_block += ret;
+	*chunk_block = start_block;
+
+	return dmz_to_next_set_block(zmd, zone, start_block,
+				     zmd->dev->zone_nr_blocks - start_block, 0);
+}
+
+/*
+ * Count the number of bits set starting from bit up to bit + nr_bits - 1.
+ */
+static int dmz_count_bits(void *bitmap, int bit, int nr_bits)
+{
+	unsigned long *addr;
+	int end = bit + nr_bits;
+	int n = 0;
+
+	while (bit < end) {
+		if (((bit & (BITS_PER_LONG - 1)) == 0) &&
+		    ((end - bit) >= BITS_PER_LONG)) {
+			addr = (unsigned long *)bitmap + BIT_WORD(bit);
+			if (*addr == ULONG_MAX) {
+				n += BITS_PER_LONG;
+				bit += BITS_PER_LONG;
+				continue;
+			}
+		}
+
+		if (test_bit(bit, bitmap))
+			n++;
+		bit++;
+	}
+
+	return n;
+}
+
+/*
+ * Get a zone weight.
+ */
+static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone)
+{
+	struct dmz_mblock *mblk;
+	sector_t chunk_block = 0;
+	unsigned int bit, nr_bits;
+	unsigned int nr_blocks = zmd->dev->zone_nr_blocks;
+	void *bitmap;
+	int n = 0;
+
+	while (nr_blocks) {
+		/* Get bitmap block */
+		mblk = dmz_get_bitmap(zmd, zone, chunk_block);
+		if (IS_ERR(mblk)) {
+			n = 0;
+			break;
+		}
+
+		/* Count bits in this block */
+		bitmap = mblk->data;
+		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
+		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		n += dmz_count_bits(bitmap, bit, nr_bits);
+
+		dmz_release_mblock(zmd, mblk);
+
+		nr_blocks -= nr_bits;
+		chunk_block += nr_bits;
+	}
+
+	zone->weight = n;
+}
+
+/*
+ * Cleanup the zoned metadata resources.
+ */
+static void dmz_cleanup_metadata(struct dmz_metadata *zmd)
+{
+	struct rb_root *root;
+	struct dmz_mblock *mblk, *next;
+	int i;
+
+	/* Release zone mapping resources */
+	if (zmd->map_mblk) {
+		for (i = 0; i < zmd->nr_map_blocks; i++)
+			dmz_release_mblock(zmd, zmd->map_mblk[i]);
+		kfree(zmd->map_mblk);
+		zmd->map_mblk = NULL;
+	}
+
+	/* Release super blocks */
+	for (i = 0; i < 2; i++) {
+		if (zmd->sb[i].mblk) {
+			dmz_free_mblock(zmd, zmd->sb[i].mblk);
+			zmd->sb[i].mblk = NULL;
+		}
+	}
+
+	/* Free cached blocks */
+	while (!list_empty(&zmd->mblk_dirty_list)) {
+		mblk = list_first_entry(&zmd->mblk_dirty_list,
+					struct dmz_mblock, link);
+		dmz_dev_warn(zmd->dev, "mblock %llu still in dirty list (ref %u)",
+			     (u64)mblk->no, atomic_read(&mblk->ref));
+		list_del_init(&mblk->link);
+		rb_erase(&mblk->node, &zmd->mblk_rbtree);
+		dmz_free_mblock(zmd, mblk);
+	}
+
+	while (!list_empty(&zmd->mblk_lru_list)) {
+		mblk = list_first_entry(&zmd->mblk_lru_list,
+					struct dmz_mblock, link);
+		list_del_init(&mblk->link);
+		rb_erase(&mblk->node, &zmd->mblk_rbtree);
+		dmz_free_mblock(zmd, mblk);
+	}
+
+	/* Sanity checks: the mblock rbtree should now be empty */
+	root = &zmd->mblk_rbtree;
+	rbtree_postorder_for_each_entry_safe(mblk, next, root, node) {
+		dmz_dev_warn(zmd->dev, "mblock %llu ref %u still in rbtree",
+			     (u64)mblk->no, atomic_read(&mblk->ref));
+		atomic_set(&mblk->ref, 0);
+		dmz_free_mblock(zmd, mblk);
+	}
+
+	/* Free the zone descriptors */
+	dmz_drop_zones(zmd);
+}
+
+/*
+ * Initialize the zoned metadata.
+ */
+int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata)
+{
+	struct dmz_metadata *zmd;
+	unsigned int i, zid;
+	struct dm_zone *zone;
+	int ret;
+
+	zmd = kzalloc(sizeof(struct dmz_metadata), GFP_KERNEL);
+	if (!zmd)
+		return -ENOMEM;
+
+	zmd->dev = dev;
+	zmd->mblk_rbtree = RB_ROOT;
+	init_rwsem(&zmd->mblk_sem);
+	mutex_init(&zmd->mblk_flush_lock);
+	spin_lock_init(&zmd->mblk_lock);
+	INIT_LIST_HEAD(&zmd->mblk_lru_list);
+	INIT_LIST_HEAD(&zmd->mblk_dirty_list);
+
+	mutex_init(&zmd->map_lock);
+	atomic_set(&zmd->unmap_nr_rnd, 0);
+	INIT_LIST_HEAD(&zmd->unmap_rnd_list);
+	INIT_LIST_HEAD(&zmd->map_rnd_list);
+
+	atomic_set(&zmd->unmap_nr_seq, 0);
+	INIT_LIST_HEAD(&zmd->unmap_seq_list);
+	INIT_LIST_HEAD(&zmd->map_seq_list);
+
+	atomic_set(&zmd->nr_reserved_seq_zones, 0);
+	INIT_LIST_HEAD(&zmd->reserved_seq_zones_list);
+
+	init_waitqueue_head(&zmd->free_wq);
+
+	/* Initialize zone descriptors */
+	ret = dmz_init_zones(zmd);
+	if (ret)
+		goto err;
+
+	/* Get super block */
+	ret = dmz_load_sb(zmd);
+	if (ret)
+		goto err;
+
+	/* Set metadata zones starting from sb_zone */
+	zid = dmz_id(zmd, zmd->sb_zone);
+	for (i = 0; i < zmd->nr_meta_zones << 1; i++) {
+		zone = dmz_get(zmd, zid + i);
+		if (!dmz_is_rnd(zone))
+			goto err;
+		set_bit(DMZ_META, &zone->flags);
+	}
+
+	/* Load mapping table */
+	ret = dmz_load_mapping(zmd);
+	if (ret)
+		goto err;
+
+	/*
+	 * Cache size boundaries: allow at least 2 super blocks, the chunk map
+	 * blocks and enough blocks to be able to cache the bitmap blocks of
+	 * up to 16 zones when idle (min_nr_mblks). Otherwise, if busy, allow
+	 * the cache to add 512 more metadata blocks.
+	 */
+	zmd->min_nr_mblks = 2 + zmd->nr_map_blocks + zmd->zone_nr_bitmap_blocks * 16;
+	zmd->max_nr_mblks = zmd->min_nr_mblks + 512;
+	zmd->mblk_shrinker.count_objects = dmz_mblock_shrinker_count;
+	zmd->mblk_shrinker.scan_objects = dmz_mblock_shrinker_scan;
+	zmd->mblk_shrinker.seeks = DEFAULT_SEEKS;
+
+	/* Metadata cache shrinker */
+	ret = register_shrinker(&zmd->mblk_shrinker);
+	if (ret) {
+		dmz_dev_err(dev, "Register metadata cache shrinker failed");
+		goto err;
+	}
+
+	dmz_dev_info(dev, "Host-%s zoned block device",
+		     bdev_zoned_model(dev->bdev) == BLK_ZONED_HA ?
+		     "aware" : "managed");
+	dmz_dev_info(dev, "  %llu 512-byte logical sectors",
+		     (u64)dev->capacity);
+	dmz_dev_info(dev, "  %u zones of %llu 512-byte logical sectors",
+		     dev->nr_zones, (u64)dev->zone_nr_sectors);
+	dmz_dev_info(dev, "  %u metadata zones",
+		     zmd->nr_meta_zones * 2);
+	dmz_dev_info(dev, "  %u data zones for %u chunks",
+		     zmd->nr_data_zones, zmd->nr_chunks);
+	dmz_dev_info(dev, "    %u random zones (%u unmapped)",
+		     zmd->nr_rnd, atomic_read(&zmd->unmap_nr_rnd));
+	dmz_dev_info(dev, "    %u sequential zones (%u unmapped)",
+		     zmd->nr_seq, atomic_read(&zmd->unmap_nr_seq));
+	dmz_dev_info(dev, "  %u reserved sequential data zones",
+		     zmd->nr_reserved_seq);
+
+	dmz_dev_debug(dev, "Format:");
+	dmz_dev_debug(dev, "%u metadata blocks per set (%u max cache)",
+		      zmd->nr_meta_blocks, zmd->max_nr_mblks);
+	dmz_dev_debug(dev, "  %u data zone mapping blocks",
+		      zmd->nr_map_blocks);
+	dmz_dev_debug(dev, "  %u bitmap blocks",
+		      zmd->nr_bitmap_blocks);
+
+	*metadata = zmd;
+
+	return 0;
+err:
+	dmz_cleanup_metadata(zmd);
+	kfree(zmd);
+	*metadata = NULL;
+
+	return ret;
+}
+
+/*
+ * Cleanup the zoned metadata resources.
+ */
+void dmz_dtr_metadata(struct dmz_metadata *zmd)
+{
+	unregister_shrinker(&zmd->mblk_shrinker);
+	dmz_cleanup_metadata(zmd);
+	kfree(zmd);
+}
+
+/*
+ * Check zone information on resume.
+ */
+int dmz_resume_metadata(struct dmz_metadata *zmd)
+{
+	struct dmz_dev *dev = zmd->dev;
+	struct dm_zone *zone;
+	sector_t wp_block;
+	unsigned int i;
+	int ret;
+
+	/* Check zones */
+	for (i = 0; i < dev->nr_zones; i++) {
+		zone = dmz_get(zmd, i);
+		if (!zone) {
+			dmz_dev_err(dev, "Unable to get zone %u", i);
+			return -EIO;
+		}
+
+		wp_block = zone->wp_block;
+
+		ret = dmz_update_zone(zmd, zone);
+		if (ret) {
+			dmz_dev_err(dev, "Broken zone %u", i);
+			return ret;
+		}
+
+		if (dmz_is_offline(zone)) {
+			dmz_dev_warn(dev, "Zone %u is offline", i);
+			continue;
+		}
+
+		/* Check write pointer */
+		if (!dmz_is_seq(zone))
+			zone->wp_block = 0;
+		else if (zone->wp_block != wp_block) {
+			dmz_dev_err(dev, "Zone %u: Invalid wp (%llu / %llu)",
+				    i, (u64)zone->wp_block, (u64)wp_block);
+			zone->wp_block = wp_block;
+			dmz_invalidate_blocks(zmd, zone, zone->wp_block,
+					      dev->zone_nr_blocks - zone->wp_block);
+		}
+	}
+
+	return 0;
+}

drivers/md/dm-zoned-reclaim.c

+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-zoned.h"
+
+#include <linux/module.h>
+
+#define	DM_MSG_PREFIX		"zoned reclaim"
+
+struct dmz_reclaim {
+	struct dmz_metadata     *metadata;
+	struct dmz_dev		*dev;
+
+	struct delayed_work	work;
+	struct workqueue_struct *wq;
+
+	struct dm_kcopyd_client	*kc;
+	struct dm_kcopyd_throttle kc_throttle;
+	int			kc_err;
+
+	unsigned long		flags;
+
+	/* Last target access time */
+	unsigned long		atime;
+};
+
+/*
+ * Reclaim state flags.
+ */
+enum {
+	DMZ_RECLAIM_KCOPY,
+};
+
+/*
+ * Number of seconds of target BIO inactivity to consider the target idle.
+ */
+#define DMZ_IDLE_PERIOD		(10UL * HZ)
+
+/*
+ * Percentage of unmapped (free) random zones below which reclaim starts
+ * even if the target is busy.
+ */
+#define DMZ_RECLAIM_LOW_UNMAP_RND	30
+
+/*
+ * Percentage of unmapped (free) random zones above which reclaim will
+ * stop if the target is busy.
+ */
+#define DMZ_RECLAIM_HIGH_UNMAP_RND	50
+
+/*
+ * Align a sequential zone write pointer to chunk_block.
+ */
+static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
+				sector_t block)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	sector_t wp_block = zone->wp_block;
+	unsigned int nr_blocks;
+	int ret;
+
+	if (wp_block == block)
+		return 0;
+
+	if (wp_block > block)
+		return -EIO;
+
+	/*
+	 * Zeroout the space between the write
+	 * pointer and the requested position.
+	 */
+	nr_blocks = block - wp_block;
+	ret = blkdev_issue_zeroout(zrc->dev->bdev,
+				   dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block),
+				   dmz_blk2sect(nr_blocks), GFP_NOFS, false);
+	if (ret) {
+		dmz_dev_err(zrc->dev,
+			    "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
+			    dmz_id(zmd, zone), (unsigned long long)wp_block,
+			    (unsigned long long)block, nr_blocks, ret);
+		return ret;
+	}
+
+	zone->wp_block = block;
+
+	return 0;
+}
+
+/*
+ * dm_kcopyd_copy end notification.
+ */
+static void dmz_reclaim_kcopy_end(int read_err, unsigned long write_err,
+				  void *context)
+{
+	struct dmz_reclaim *zrc = context;
+
+	if (read_err || write_err)
+		zrc->kc_err = -EIO;
+	else
+		zrc->kc_err = 0;
+
+	clear_bit_unlock(DMZ_RECLAIM_KCOPY, &zrc->flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&zrc->flags, DMZ_RECLAIM_KCOPY);
+}
+
+/*
+ * Copy valid blocks of src_zone into dst_zone.
+ */
+static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
+			    struct dm_zone *src_zone, struct dm_zone *dst_zone)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	struct dmz_dev *dev = zrc->dev;
+	struct dm_io_region src, dst;
+	sector_t block = 0, end_block;
+	sector_t nr_blocks;
+	sector_t src_zone_block;
+	sector_t dst_zone_block;
+	unsigned long flags = 0;
+	int ret;
+
+	if (dmz_is_seq(src_zone))
+		end_block = src_zone->wp_block;
+	else
+		end_block = dev->zone_nr_blocks;
+	src_zone_block = dmz_start_block(zmd, src_zone);
+	dst_zone_block = dmz_start_block(zmd, dst_zone);
+
+	if (dmz_is_seq(dst_zone))
+		set_bit(DM_KCOPYD_WRITE_SEQ, &flags);
+
+	while (block < end_block) {
+		/* Get a valid region from the source zone */
+		ret = dmz_first_valid_block(zmd, src_zone, &block);
+		if (ret <= 0)
+			return ret;
+		nr_blocks = ret;
+
+		/*
+		 * If we are writing in a sequential zone, we must make sure
+		 * that writes are sequential. So Zeroout any eventual hole
+		 * between writes.
+		 */
+		if (dmz_is_seq(dst_zone)) {
+			ret = dmz_reclaim_align_wp(zrc, dst_zone, block);
+			if (ret)
+				return ret;
+		}
+
+		src.bdev = dev->bdev;
+		src.sector = dmz_blk2sect(src_zone_block + block);
+		src.count = dmz_blk2sect(nr_blocks);
+
+		dst.bdev = dev->bdev;
+		dst.sector = dmz_blk2sect(dst_zone_block + block);
+		dst.count = src.count;
+
+		/* Copy the valid region */
+		set_bit(DMZ_RECLAIM_KCOPY, &zrc->flags);
+		ret = dm_kcopyd_copy(zrc->kc, &src, 1, &dst, flags,
+				     dmz_reclaim_kcopy_end, zrc);
+		if (ret)
+			return ret;
+
+		/* Wait for copy to complete */
+		wait_on_bit_io(&zrc->flags, DMZ_RECLAIM_KCOPY,
+			       TASK_UNINTERRUPTIBLE);
+		if (zrc->kc_err)
+			return zrc->kc_err;
+
+		block += nr_blocks;
+		if (dmz_is_seq(dst_zone))
+			dst_zone->wp_block = block;
+	}
+
+	return 0;
+}
+
+/*
+ * Move valid blocks of dzone buffer zone into dzone (after its write pointer)
+ * and free the buffer zone.
+ */
+static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	struct dm_zone *bzone = dzone->bzone;
+	sector_t chunk_block = dzone->wp_block;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)",
+		      dzone->chunk, dmz_id(zmd, bzone), dmz_weight(bzone),
+		      dmz_id(zmd, dzone), dmz_weight(dzone));
+
+	/* Flush data zone into the buffer zone */
+	ret = dmz_reclaim_copy(zrc, bzone, dzone);
+	if (ret < 0)
+		return ret;
+
+	dmz_lock_flush(zmd);
+
+	/* Validate copied blocks */
+	ret = dmz_merge_valid_blocks(zmd, bzone, dzone, chunk_block);
+	if (ret == 0) {
+		/* Free the buffer zone */
+		dmz_invalidate_blocks(zmd, bzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, bzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, bzone);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Merge valid blocks of dzone into its buffer zone and free dzone.
+ */
+static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	unsigned int chunk = dzone->chunk;
+	struct dm_zone *bzone = dzone->bzone;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret = 0;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)",
+		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
+		      dmz_id(zmd, bzone), dmz_weight(bzone));
+
+	/* Flush data zone into the buffer zone */
+	ret = dmz_reclaim_copy(zrc, dzone, bzone);
+	if (ret < 0)
+		return ret;
+
+	dmz_lock_flush(zmd);
+
+	/* Validate copied blocks */
+	ret = dmz_merge_valid_blocks(zmd, dzone, bzone, 0);
+	if (ret == 0) {
+		/*
+		 * Free the data zone and remap the chunk to
+		 * the buffer zone.
+		 */
+		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, bzone);
+		dmz_unmap_zone(zmd, dzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, dzone);
+		dmz_map_zone(zmd, bzone, chunk);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Move valid blocks of the random data zone dzone into a free sequential zone.
+ * Once blocks are moved, remap the zone chunk to the sequential zone.
+ */
+static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	unsigned int chunk = dzone->chunk;
+	struct dm_zone *szone = NULL;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret;
+
+	/* Get a free sequential zone */
+	dmz_lock_map(zmd);
+	szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM);
+	dmz_unlock_map(zmd);
+	if (!szone)
+		return -ENOSPC;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move rnd zone %u (weight %u) to seq zone %u",
+		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
+		      dmz_id(zmd, szone));
+
+	/* Flush the random data zone into the sequential zone */
+	ret = dmz_reclaim_copy(zrc, dzone, szone);
+
+	dmz_lock_flush(zmd);
+
+	if (ret == 0) {
+		/* Validate copied blocks */
+		ret = dmz_copy_valid_blocks(zmd, dzone, szone);
+	}
+	if (ret) {
+		/* Free the sequential zone */
+		dmz_lock_map(zmd);
+		dmz_free_zone(zmd, szone);
+		dmz_unlock_map(zmd);
+	} else {
+		/* Free the data zone and remap the chunk */
+		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, dzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, dzone);
+		dmz_map_zone(zmd, szone, chunk);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Reclaim an empty zone.
+ */
+static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+
+	dmz_lock_flush(zmd);
+	dmz_lock_map(zmd);
+	dmz_unmap_zone(zmd, dzone);
+	dmz_unlock_zone_reclaim(dzone);
+	dmz_free_zone(zmd, dzone);
+	dmz_unlock_map(zmd);
+	dmz_unlock_flush(zmd);
+}
+
+/*
+ * Find a candidate zone for reclaim and process it.
+ */
+static void dmz_reclaim(struct dmz_reclaim *zrc)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	struct dm_zone *dzone;
+	struct dm_zone *rzone;
+	unsigned long start;
+	int ret;
+
+	/* Get a data zone */
+	dzone = dmz_get_zone_for_reclaim(zmd);
+	if (!dzone)
+		return;
+
+	start = jiffies;
+
+	if (dmz_is_rnd(dzone)) {
+		if (!dmz_weight(dzone)) {
+			/* Empty zone */
+			dmz_reclaim_empty(zrc, dzone);
+			ret = 0;
+		} else {
+			/*
+			 * Reclaim the random data zone by moving its
+			 * valid data blocks to a free sequential zone.
+			 */
+			ret = dmz_reclaim_rnd_data(zrc, dzone);
+		}
+		rzone = dzone;
+
+	} else {
+		struct dm_zone *bzone = dzone->bzone;
+		sector_t chunk_block = 0;
+
+		ret = dmz_first_valid_block(zmd, bzone, &chunk_block);
+		if (ret < 0)
+			goto out;
+
+		if (ret == 0 || chunk_block >= dzone->wp_block) {
+			/*
+			 * The buffer zone is empty or its valid blocks are
+			 * after the data zone write pointer.
+			 */
+			ret = dmz_reclaim_buf(zrc, dzone);
+			rzone = bzone;
+		} else {
+			/*
+			 * Reclaim the data zone by merging it into the
+			 * buffer zone so that the buffer zone itself can
+			 * be later reclaimed.
+			 */
+			ret = dmz_reclaim_seq_data(zrc, dzone);
+			rzone = dzone;
+		}
+	}
+out:
+	if (ret) {
+		dmz_unlock_zone_reclaim(dzone);
+		return;
+	}
+
+	(void) dmz_flush_metadata(zrc->metadata);
+
+	dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms",
+		      dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start));
+}
+
+/*
+ * Test if the target device is idle.
+ */
+static inline int dmz_target_idle(struct dmz_reclaim *zrc)
+{
+	return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
+}
+
+/*
+ * Test if reclaim is necessary.
+ */
+static bool dmz_should_reclaim(struct dmz_reclaim *zrc)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	unsigned int nr_rnd = dmz_nr_rnd_zones(zmd);
+	unsigned int nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
+	unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+
+	/* Reclaim when idle */
+	if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd)
+		return true;
+
+	/* If there are still plenty of random zones, do not reclaim */
+	if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND)
+		return false;
+
+	/*
+	 * If the percentage of unmappped random zones is low,
+	 * reclaim even if the target is busy.
+	 */
+	return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
+}
+
+/*
+ * Reclaim work function.
+ */
+static void dmz_reclaim_work(struct work_struct *work)
+{
+	struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
+	struct dmz_metadata *zmd = zrc->metadata;
+	unsigned int nr_rnd, nr_unmap_rnd;
+	unsigned int p_unmap_rnd;
+
+	if (!dmz_should_reclaim(zrc)) {
+		mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
+		return;
+	}
+
+	/*
+	 * We need to start reclaiming random zones: set up zone copy
+	 * throttling to either go fast if we are very low on random zones
+	 * and slower if there are still some free random zones to avoid
+	 * as much as possible to negatively impact the user workload.
+	 */
+	nr_rnd = dmz_nr_rnd_zones(zmd);
+	nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
+	p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+	if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) {
+		/* Idle or very low percentage: go fast */
+		zrc->kc_throttle.throttle = 100;
+	} else {
+		/* Busy but we still have some random zone: throttle */
+		zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2);
+	}
+
+	dmz_dev_debug(zrc->dev,
+		      "Reclaim (%u): %s, %u%% free rnd zones (%u/%u)",
+		      zrc->kc_throttle.throttle,
+		      (dmz_target_idle(zrc) ? "Idle" : "Busy"),
+		      p_unmap_rnd, nr_unmap_rnd, nr_rnd);
+
+	dmz_reclaim(zrc);
+
+	dmz_schedule_reclaim(zrc);
+}
+
+/*
+ * Initialize reclaim.
+ */
+int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
+		    struct dmz_reclaim **reclaim)
+{
+	struct dmz_reclaim *zrc;
+	int ret;
+
+	zrc = kzalloc(sizeof(struct dmz_reclaim), GFP_KERNEL);
+	if (!zrc)
+		return -ENOMEM;
+
+	zrc->dev = dev;
+	zrc->metadata = zmd;
+	zrc->atime = jiffies;
+
+	/* Reclaim kcopyd client */
+	zrc->kc = dm_kcopyd_client_create(&zrc->kc_throttle);
+	if (IS_ERR(zrc->kc)) {
+		ret = PTR_ERR(zrc->kc);
+		zrc->kc = NULL;
+		goto err;
+	}
+
+	/* Reclaim work */
+	INIT_DELAYED_WORK(&zrc->work, dmz_reclaim_work);
+	zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s", WQ_MEM_RECLAIM,
+					  dev->name);
+	if (!zrc->wq) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	*reclaim = zrc;
+	queue_delayed_work(zrc->wq, &zrc->work, 0);
+
+	return 0;
+err:
+	if (zrc->kc)
+		dm_kcopyd_client_destroy(zrc->kc);
+	kfree(zrc);
+
+	return ret;
+}
+
+/*
+ * Terminate reclaim.
+ */
+void dmz_dtr_reclaim(struct dmz_reclaim *zrc)
+{
+	cancel_delayed_work_sync(&zrc->work);
+	destroy_workqueue(zrc->wq);
+	dm_kcopyd_client_destroy(zrc->kc);
+	kfree(zrc);
+}
+
+/*
+ * Suspend reclaim.
+ */
+void dmz_suspend_reclaim(struct dmz_reclaim *zrc)
+{
+	cancel_delayed_work_sync(&zrc->work);
+}
+
+/*
+ * Resume reclaim.
+ */
+void dmz_resume_reclaim(struct dmz_reclaim *zrc)
+{
+	queue_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
+}
+
+/*
+ * BIO accounting.
+ */
+void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc)
+{
+	zrc->atime = jiffies;
+}
+
+/*
+ * Start reclaim if necessary.
+ */
+void dmz_schedule_reclaim(struct dmz_reclaim *zrc)
+{
+	if (dmz_should_reclaim(zrc))
+		mod_delayed_work(zrc->wq, &zrc->work, 0);
+}
+

drivers/md/dm-zoned-target.c

+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-zoned.h"
+
+#include <linux/module.h>
+
+#define	DM_MSG_PREFIX		"zoned"
+
+#define DMZ_MIN_BIOS		8192
+
+/*
+ * Zone BIO context.
+ */
+struct dmz_bioctx {
+	struct dmz_target	*target;
+	struct dm_zone		*zone;
+	struct bio		*bio;
+	atomic_t		ref;
+	blk_status_t		status;
+};
+
+/*
+ * Chunk work descriptor.
+ */
+struct dm_chunk_work {
+	struct work_struct	work;
+	atomic_t		refcount;
+	struct dmz_target	*target;
+	unsigned int		chunk;
+	struct bio_list		bio_list;
+};
+
+/*
+ * Target descriptor.
+ */
+struct dmz_target {
+	struct dm_dev		*ddev;
+
+	unsigned long		flags;
+
+	/* Zoned block device information */
+	struct dmz_dev		*dev;
+
+	/* For metadata handling */
+	struct dmz_metadata     *metadata;
+
+	/* For reclaim */
+	struct dmz_reclaim	*reclaim;
+
+	/* For chunk work */
+	struct mutex		chunk_lock;
+	struct radix_tree_root	chunk_rxtree;
+	struct workqueue_struct *chunk_wq;
+
+	/* For cloned BIOs to zones */
+	struct bio_set		*bio_set;
+
+	/* For flush */
+	spinlock_t		flush_lock;
+	struct bio_list		flush_list;
+	struct delayed_work	flush_work;
+	struct workqueue_struct *flush_wq;
+};
+
+/*
+ * Flush intervals (seconds).
+ */
+#define DMZ_FLUSH_PERIOD	(10 * HZ)
+
+/*
+ * Target BIO completion.
+ */
+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));
+
+	if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK)
+		bioctx->status = status;
+	bio_endio(bio);
+}
+
+/*
+ * Partial clone read BIO completion callback. This terminates the
+ * target BIO when there are no more references to its context.
+ */
+static void dmz_read_bio_end_io(struct bio *bio)
+{
+	struct dmz_bioctx *bioctx = bio->bi_private;
+	blk_status_t status = bio->bi_status;
+
+	bio_put(bio);
+	dmz_bio_endio(bioctx->bio, status);
+}
+
+/*
+ * Issue a BIO to a zone. The BIO may only partially process the
+ * original target BIO.
+ */
+static int dmz_submit_read_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));
+	sector_t sector;
+	struct bio *clone;
+
+	/* BIO remap sector */
+	sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
+
+	/* If the read is not partial, there is no need to clone the BIO */
+	if (nr_blocks == dmz_bio_blocks(bio)) {
+		/* Setup and submit the BIO */
+		bio->bi_iter.bi_sector = sector;
+		atomic_inc(&bioctx->ref);
+		generic_make_request(bio);
+		return 0;
+	}
+
+	/* Partial BIO: we need to clone the BIO */
+	clone = bio_clone_fast(bio, GFP_NOIO, dmz->bio_set);
+	if (!clone)
+		return -ENOMEM;
+
+	/* Setup the clone */
+	clone->bi_iter.bi_sector = sector;
+	clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT;
+	clone->bi_end_io = dmz_read_bio_end_io;
+	clone->bi_private = bioctx;
+
+	bio_advance(bio, clone->bi_iter.bi_size);
+
+	/* Submit the clone */
+	atomic_inc(&bioctx->ref);
+	generic_make_request(clone);
+
+	return 0;
+}
+
+/*
+ * Zero out pages of discarded blocks accessed by a read BIO.
+ */
+static void dmz_handle_read_zero(struct dmz_target *dmz, struct bio *bio,
+				 sector_t chunk_block, unsigned int nr_blocks)
+{
+	unsigned int size = nr_blocks << DMZ_BLOCK_SHIFT;
+
+	/* Clear nr_blocks */
+	swap(bio->bi_iter.bi_size, size);
+	zero_fill_bio(bio);
+	swap(bio->bi_iter.bi_size, size);
+
+	bio_advance(bio, size);
+}
+
+/*
+ * Process a read 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));
+	unsigned int nr_blocks = dmz_bio_blocks(bio);
+	sector_t end_block = chunk_block + nr_blocks;
+	struct dm_zone *rzone, *bzone;
+	int ret;
+
+	/* Read into unmapped chunks need only zeroing the BIO buffer */
+	if (!zone) {
+		zero_fill_bio(bio);
+		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);
+
+	/* 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) {
+			/* Test block validity in the data zone */
+			ret = dmz_block_valid(dmz->metadata, zone, chunk_block);
+			if (ret < 0)
+				return ret;
+			if (ret > 0) {
+				/* Read data zone blocks */
+				nr_blocks = ret;
+				rzone = zone;
+			}
+		}
+
+		/*
+		 * No valid blocks found in the data zone.
+		 * Check the buffer zone, if there is one.
+		 */
+		if (!nr_blocks && bzone) {
+			ret = dmz_block_valid(dmz->metadata, bzone, chunk_block);
+			if (ret < 0)
+				return ret;
+			if (ret > 0) {
+				/* Read buffer zone blocks */
+				nr_blocks = ret;
+				rzone = bzone;
+			}
+		}
+
+		if (nr_blocks) {
+			/* Valid blocks found: read them */
+			nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block);
+			ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks);
+			if (ret)
+				return ret;
+			chunk_block += nr_blocks;
+		} else {
+			/* No valid block: zeroout the current BIO block */
+			dmz_handle_read_zero(dmz, bio, chunk_block, 1);
+			chunk_block++;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Issue a write BIO to a zone.
+ */
+static void dmz_submit_write_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));
+
+	/* Setup and submit the BIO */
+	bio->bi_bdev = dmz->dev->bdev;
+	bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
+	atomic_inc(&bioctx->ref);
+	generic_make_request(bio);
+
+	if (dmz_is_seq(zone))
+		zone->wp_block += nr_blocks;
+}
+
+/*
+ * Write blocks directly in a data zone, at the write pointer.
+ * If a buffer zone is assigned, invalidate the blocks written
+ * in place.
+ */
+static int dmz_handle_direct_write(struct dmz_target *dmz,
+				   struct dm_zone *zone, struct bio *bio,
+				   sector_t chunk_block,
+				   unsigned int nr_blocks)
+{
+	struct dmz_metadata *zmd = dmz->metadata;
+	struct dm_zone *bzone = zone->bzone;
+	int ret;
+
+	if (dmz_is_readonly(zone))
+		return -EROFS;
+
+	/* Submit write */
+	dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks);
+
+	/*
+	 * Validate the blocks in the data zone and invalidate
+	 * in the buffer zone, if there is one.
+	 */
+	ret = dmz_validate_blocks(zmd, zone, chunk_block, nr_blocks);
+	if (ret == 0 && bzone)
+		ret = dmz_invalidate_blocks(zmd, bzone, chunk_block, nr_blocks);
+
+	return ret;
+}
+
+/*
+ * Write blocks in the buffer zone of @zone.
+ * If no buffer zone is assigned yet, get one.
+ * Called with @zone write locked.
+ */
+static int dmz_handle_buffered_write(struct dmz_target *dmz,
+				     struct dm_zone *zone, struct bio *bio,
+				     sector_t chunk_block,
+				     unsigned int nr_blocks)
+{
+	struct dmz_metadata *zmd = dmz->metadata;
+	struct dm_zone *bzone;
+	int ret;
+
+	/* Get the buffer zone. One will be allocated if needed */
+	bzone = dmz_get_chunk_buffer(zmd, zone);
+	if (!bzone)
+		return -ENOSPC;
+
+	if (dmz_is_readonly(bzone))
+		return -EROFS;
+
+	/* Submit write */
+	dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks);
+
+	/*
+	 * Validate the blocks in the buffer zone
+	 * and invalidate in the data zone.
+	 */
+	ret = dmz_validate_blocks(zmd, bzone, chunk_block, nr_blocks);
+	if (ret == 0 && chunk_block < zone->wp_block)
+		ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks);
+
+	return ret;
+}
+
+/*
+ * Process a write BIO.
+ */
+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));
+	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);
+
+	if (dmz_is_rnd(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);
+	}
+
+	/*
+	 * This is an unaligned write in a sequential zone:
+	 * use buffered write.
+	 */
+	return dmz_handle_buffered_write(dmz, zone, bio, chunk_block, nr_blocks);
+}
+
+/*
+ * Process a discard BIO.
+ */
+static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone,
+			      struct bio *bio)
+{
+	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);
+	int ret = 0;
+
+	/* For unmapped chunks, there is nothing to do */
+	if (!zone)
+		return 0;
+
+	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);
+
+	/*
+	 * Invalidate blocks in the data zone and its
+	 * buffer zone if one is mapped.
+	 */
+	if (dmz_is_rnd(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,
+					    chunk_block, nr_blocks);
+	return ret;
+}
+
+/*
+ * Process a BIO.
+ */
+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_metadata *zmd = dmz->metadata;
+	struct dm_zone *zone;
+	int 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);
+
+	dmz_lock_metadata(zmd);
+
+	/*
+	 * 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),
+				     bio_op(bio));
+	if (IS_ERR(zone)) {
+		ret = PTR_ERR(zone);
+		goto out;
+	}
+
+	/* Process the BIO */
+	if (zone) {
+		dmz_activate_zone(zone);
+		bioctx->zone = zone;
+	}
+
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+		ret = dmz_handle_read(dmz, zone, bio);
+		break;
+	case REQ_OP_WRITE:
+		ret = dmz_handle_write(dmz, zone, bio);
+		break;
+	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
+		ret = dmz_handle_discard(dmz, zone, bio);
+		break;
+	default:
+		dmz_dev_err(dmz->dev, "Unsupported BIO operation 0x%x",
+			    bio_op(bio));
+		ret = -EIO;
+	}
+
+	/*
+	 * Release the chunk mapping. This will check that the mapping
+	 * is still valid, that is, that the zone used still has valid blocks.
+	 */
+	if (zone)
+		dmz_put_chunk_mapping(zmd, zone);
+out:
+	dmz_bio_endio(bio, errno_to_blk_status(ret));
+
+	dmz_unlock_metadata(zmd);
+}
+
+/*
+ * Increment a chunk reference counter.
+ */
+static inline void dmz_get_chunk_work(struct dm_chunk_work *cw)
+{
+	atomic_inc(&cw->refcount);
+}
+
+/*
+ * Decrement a chunk work reference count and
+ * free it if it becomes 0.
+ */
+static void dmz_put_chunk_work(struct dm_chunk_work *cw)
+{
+	if (atomic_dec_and_test(&cw->refcount)) {
+		WARN_ON(!bio_list_empty(&cw->bio_list));
+		radix_tree_delete(&cw->target->chunk_rxtree, cw->chunk);
+		kfree(cw);
+	}
+}
+
+/*
+ * Chunk BIO work function.
+ */
+static void dmz_chunk_work(struct work_struct *work)
+{
+	struct dm_chunk_work *cw = container_of(work, struct dm_chunk_work, work);
+	struct dmz_target *dmz = cw->target;
+	struct bio *bio;
+
+	mutex_lock(&dmz->chunk_lock);
+
+	/* Process the chunk BIOs */
+	while ((bio = bio_list_pop(&cw->bio_list))) {
+		mutex_unlock(&dmz->chunk_lock);
+		dmz_handle_bio(dmz, cw, bio);
+		mutex_lock(&dmz->chunk_lock);
+		dmz_put_chunk_work(cw);
+	}
+
+	/* Queueing the work incremented the work refcount */
+	dmz_put_chunk_work(cw);
+
+	mutex_unlock(&dmz->chunk_lock);
+}
+
+/*
+ * Flush work.
+ */
+static void dmz_flush_work(struct work_struct *work)
+{
+	struct dmz_target *dmz = container_of(work, struct dmz_target, flush_work.work);
+	struct bio *bio;
+	int ret;
+
+	/* Flush dirty metadata blocks */
+	ret = dmz_flush_metadata(dmz->metadata);
+
+	/* Process queued flush requests */
+	while (1) {
+		spin_lock(&dmz->flush_lock);
+		bio = bio_list_pop(&dmz->flush_list);
+		spin_unlock(&dmz->flush_lock);
+
+		if (!bio)
+			break;
+
+		dmz_bio_endio(bio, errno_to_blk_status(ret));
+	}
+
+	queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
+}
+
+/*
+ * Get a chunk work and start it to process a new BIO.
+ * If the BIO chunk has no work yet, create one.
+ */
+static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
+{
+	unsigned int chunk = dmz_bio_chunk(dmz->dev, bio);
+	struct dm_chunk_work *cw;
+
+	mutex_lock(&dmz->chunk_lock);
+
+	/* Get the BIO chunk work. If one is not active yet, create one */
+	cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
+	if (!cw) {
+		int ret;
+
+		/* Create a new chunk work */
+		cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOFS);
+		if (!cw)
+			goto out;
+
+		INIT_WORK(&cw->work, dmz_chunk_work);
+		atomic_set(&cw->refcount, 0);
+		cw->target = dmz;
+		cw->chunk = chunk;
+		bio_list_init(&cw->bio_list);
+
+		ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw);
+		if (unlikely(ret)) {
+			kfree(cw);
+			cw = NULL;
+			goto out;
+		}
+	}
+
+	bio_list_add(&cw->bio_list, bio);
+	dmz_get_chunk_work(cw);
+
+	if (queue_work(dmz->chunk_wq, &cw->work))
+		dmz_get_chunk_work(cw);
+out:
+	mutex_unlock(&dmz->chunk_lock);
+}
+
+/*
+ * Process a new BIO.
+ */
+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_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;
+
+	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->bi_bdev = dev->bdev;
+
+	if (!nr_sectors && (bio_op(bio) != REQ_OP_FLUSH) && (bio_op(bio) != REQ_OP_WRITE))
+		return DM_MAPIO_REMAPPED;
+
+	/* The BIO should be block aligned */
+	if ((nr_sectors & DMZ_BLOCK_SECTORS_MASK) || (sector & DMZ_BLOCK_SECTORS_MASK))
+		return DM_MAPIO_KILL;
+
+	/* Initialize the BIO context */
+	bioctx->target = dmz;
+	bioctx->zone = NULL;
+	bioctx->bio = bio;
+	atomic_set(&bioctx->ref, 1);
+	bioctx->status = BLK_STS_OK;
+
+	/* Set the BIO pending in the flush list */
+	if (bio_op(bio) == REQ_OP_FLUSH || (!nr_sectors && bio_op(bio) == REQ_OP_WRITE)) {
+		spin_lock(&dmz->flush_lock);
+		bio_list_add(&dmz->flush_list, bio);
+		spin_unlock(&dmz->flush_lock);
+		mod_delayed_work(dmz->flush_wq, &dmz->flush_work, 0);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	/* 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);
+
+	/* Now ready to handle this BIO */
+	dmz_reclaim_bio_acc(dmz->reclaim);
+	dmz_queue_chunk_work(dmz, bio);
+
+	return DM_MAPIO_SUBMITTED;
+}
+
+/*
+ * Completed target BIO processing.
+ */
+static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error)
+{
+	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
+
+	if (bioctx->status == BLK_STS_OK && *error)
+		bioctx->status = *error;
+
+	if (!atomic_dec_and_test(&bioctx->ref))
+		return DM_ENDIO_INCOMPLETE;
+
+	/* Done */
+	bio->bi_status = bioctx->status;
+
+	if (bioctx->zone) {
+		struct dm_zone *zone = bioctx->zone;
+
+		if (*error && bio_op(bio) == REQ_OP_WRITE) {
+			if (dmz_is_seq(zone))
+				set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
+		}
+		dmz_deactivate_zone(zone);
+	}
+
+	return DM_ENDIO_DONE;
+}
+
+/*
+ * Get zoned device information.
+ */
+static int dmz_get_zoned_device(struct dm_target *ti, char *path)
+{
+	struct dmz_target *dmz = ti->private;
+	struct request_queue *q;
+	struct dmz_dev *dev;
+	int ret;
+
+	/* Get the target device */
+	ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &dmz->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;
+	}
+
+	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;
+		goto err;
+	}
+
+	dev->capacity = i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+	if (ti->begin || (ti->len != dev->capacity)) {
+		ti->error = "Partial mapping not supported";
+		ret = -EINVAL;
+		goto err;
+	}
+
+	q = bdev_get_queue(dev->bdev);
+	dev->zone_nr_sectors = q->limits.chunk_sectors;
+	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 = (dev->capacity + dev->zone_nr_sectors - 1)
+		>> dev->zone_nr_sectors_shift;
+
+	dmz->dev = dev;
+
+	return 0;
+err:
+	dm_put_device(ti, dmz->ddev);
+	kfree(dev);
+
+	return ret;
+}
+
+/*
+ * Cleanup zoned device information.
+ */
+static void dmz_put_zoned_device(struct dm_target *ti)
+{
+	struct dmz_target *dmz = ti->private;
+
+	dm_put_device(ti, dmz->ddev);
+	kfree(dmz->dev);
+	dmz->dev = NULL;
+}
+
+/*
+ * Setup target.
+ */
+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) {
+		ti->error = "Invalid argument count";
+		return -EINVAL;
+	}
+
+	/* Allocate and initialize the target descriptor */
+	dmz = kzalloc(sizeof(struct dmz_target), GFP_KERNEL);
+	if (!dmz) {
+		ti->error = "Unable to allocate the zoned target descriptor";
+		return -ENOMEM;
+	}
+	ti->private = dmz;
+
+	/* Get the target zoned block device */
+	ret = dmz_get_zoned_device(ti, argv[0]);
+	if (ret) {
+		dmz->ddev = NULL;
+		goto err;
+	}
+
+	/* Initialize metadata */
+	dev = dmz->dev;
+	ret = dmz_ctr_metadata(dev, &dmz->metadata);
+	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->num_flush_bios = 1;
+	ti->num_discard_bios = 1;
+	ti->num_write_zeroes_bios = 1;
+	ti->per_io_data_size = sizeof(struct dmz_bioctx);
+	ti->flush_supported = true;
+	ti->discards_supported = true;
+	ti->split_discard_bios = 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;
+
+	/* Zone BIO */
+	dmz->bio_set = bioset_create(DMZ_MIN_BIOS, 0, 0);
+	if (!dmz->bio_set) {
+		ti->error = "Create BIO set failed";
+		ret = -ENOMEM;
+		goto err_meta;
+	}
+
+	/* Chunk BIO work */
+	mutex_init(&dmz->chunk_lock);
+	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOFS);
+	dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
+					0, dev->name);
+	if (!dmz->chunk_wq) {
+		ti->error = "Create chunk workqueue failed";
+		ret = -ENOMEM;
+		goto err_bio;
+	}
+
+	/* Flush work */
+	spin_lock_init(&dmz->flush_lock);
+	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);
+	if (!dmz->flush_wq) {
+		ti->error = "Create flush workqueue failed";
+		ret = -ENOMEM;
+		goto err_cwq;
+	}
+	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;
+	}
+
+	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));
+
+	return 0;
+err_fwq:
+	destroy_workqueue(dmz->flush_wq);
+err_cwq:
+	destroy_workqueue(dmz->chunk_wq);
+err_bio:
+	bioset_free(dmz->bio_set);
+err_meta:
+	dmz_dtr_metadata(dmz->metadata);
+err_dev:
+	dmz_put_zoned_device(ti);
+err:
+	kfree(dmz);
+
+	return ret;
+}
+
+/*
+ * Cleanup target.
+ */
+static void dmz_dtr(struct dm_target *ti)
+{
+	struct dmz_target *dmz = ti->private;
+
+	flush_workqueue(dmz->chunk_wq);
+	destroy_workqueue(dmz->chunk_wq);
+
+	dmz_dtr_reclaim(dmz->reclaim);
+
+	cancel_delayed_work_sync(&dmz->flush_work);
+	destroy_workqueue(dmz->flush_wq);
+
+	(void) dmz_flush_metadata(dmz->metadata);
+
+	dmz_dtr_metadata(dmz->metadata);
+
+	bioset_free(dmz->bio_set);
+
+	dmz_put_zoned_device(ti);
+
+	kfree(dmz);
+}
+
+/*
+ * Setup target request queue limits.
+ */
+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;
+
+	limits->logical_block_size = DMZ_BLOCK_SIZE;
+	limits->physical_block_size = DMZ_BLOCK_SIZE;
+
+	blk_limits_io_min(limits, DMZ_BLOCK_SIZE);
+	blk_limits_io_opt(limits, DMZ_BLOCK_SIZE);
+
+	limits->discard_alignment = DMZ_BLOCK_SIZE;
+	limits->discard_granularity = DMZ_BLOCK_SIZE;
+	limits->max_discard_sectors = chunk_sectors;
+	limits->max_hw_discard_sectors = chunk_sectors;
+	limits->max_write_zeroes_sectors = chunk_sectors;
+
+	/* FS hint to try to align to the device zone size */
+	limits->chunk_sectors = chunk_sectors;
+	limits->max_sectors = chunk_sectors;
+
+	/* We are exposing a drive-managed zoned block device */
+	limits->zoned = BLK_ZONED_NONE;
+}
+
+/*
+ * Pass on ioctl to the backend device.
+ */
+static int dmz_prepare_ioctl(struct dm_target *ti,
+			     struct block_device **bdev, fmode_t *mode)
+{
+	struct dmz_target *dmz = ti->private;
+
+	*bdev = dmz->dev->bdev;
+
+	return 0;
+}
+
+/*
+ * Stop works on suspend.
+ */
+static void dmz_suspend(struct dm_target *ti)
+{
+	struct dmz_target *dmz = ti->private;
+
+	flush_workqueue(dmz->chunk_wq);
+	dmz_suspend_reclaim(dmz->reclaim);
+	cancel_delayed_work_sync(&dmz->flush_work);
+}
+
+/*
+ * Restart works on resume or if suspend failed.
+ */
+static void dmz_resume(struct dm_target *ti)
+{
+	struct dmz_target *dmz = ti->private;
+
+	queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
+	dmz_resume_reclaim(dmz->reclaim);
+}
+
+static int dmz_iterate_devices(struct dm_target *ti,
+			       iterate_devices_callout_fn fn, void *data)
+{
+	struct dmz_target *dmz = ti->private;
+
+	return fn(ti, dmz->ddev, 0, dmz->dev->capacity, data);
+}
+
+static struct target_type dmz_type = {
+	.name		 = "zoned",
+	.version	 = {1, 0, 0},
+	.features	 = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
+	.module		 = THIS_MODULE,
+	.ctr		 = dmz_ctr,
+	.dtr		 = dmz_dtr,
+	.map		 = dmz_map,
+	.end_io		 = dmz_end_io,
+	.io_hints	 = dmz_io_hints,
+	.prepare_ioctl	 = dmz_prepare_ioctl,
+	.postsuspend	 = dmz_suspend,
+	.resume		 = dmz_resume,
+	.iterate_devices = dmz_iterate_devices,
+};
+
+static int __init dmz_init(void)
+{
+	return dm_register_target(&dmz_type);
+}
+
+static void __exit dmz_exit(void)
+{
+	dm_unregister_target(&dmz_type);
+}
+
+module_init(dmz_init);
+module_exit(dmz_exit);
+
+MODULE_DESCRIPTION(DM_NAME " target for zoned block devices");
+MODULE_AUTHOR("Damien Le Moal <damien.lemoal@wdc.com>");
+MODULE_LICENSE("GPL");

drivers/md/dm-zoned.h

+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_ZONED_H
+#define DM_ZONED_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/device-mapper.h>
+#include <linux/dm-kcopyd.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/radix-tree.h>
+#include <linux/shrinker.h>
+
+/*
+ * dm-zoned creates block devices with 4KB blocks, always.
+ */
+#define DMZ_BLOCK_SHIFT		12
+#define DMZ_BLOCK_SIZE		(1 << DMZ_BLOCK_SHIFT)
+#define DMZ_BLOCK_MASK		(DMZ_BLOCK_SIZE - 1)
+
+#define DMZ_BLOCK_SHIFT_BITS	(DMZ_BLOCK_SHIFT + 3)
+#define DMZ_BLOCK_SIZE_BITS	(1 << DMZ_BLOCK_SHIFT_BITS)
+#define DMZ_BLOCK_MASK_BITS	(DMZ_BLOCK_SIZE_BITS - 1)
+
+#define DMZ_BLOCK_SECTORS_SHIFT	(DMZ_BLOCK_SHIFT - SECTOR_SHIFT)
+#define DMZ_BLOCK_SECTORS	(DMZ_BLOCK_SIZE >> SECTOR_SHIFT)
+#define DMZ_BLOCK_SECTORS_MASK	(DMZ_BLOCK_SECTORS - 1)
+
+/*
+ * 4KB block <-> 512B sector conversion.
+ */
+#define dmz_blk2sect(b)		((sector_t)(b) << DMZ_BLOCK_SECTORS_SHIFT)
+#define dmz_sect2blk(s)		((sector_t)(s) >> DMZ_BLOCK_SECTORS_SHIFT)
+
+#define dmz_bio_block(bio)	dmz_sect2blk((bio)->bi_iter.bi_sector)
+#define dmz_bio_blocks(bio)	dmz_sect2blk(bio_sectors(bio))
+
+/*
+ * Zoned block device information.
+ */
+struct dmz_dev {
+	struct block_device	*bdev;
+
+	char			name[BDEVNAME_SIZE];
+
+	sector_t		capacity;
+
+	unsigned int		nr_zones;
+
+	sector_t		zone_nr_sectors;
+	unsigned int		zone_nr_sectors_shift;
+
+	sector_t		zone_nr_blocks;
+	sector_t		zone_nr_blocks_shift;
+};
+
+#define dmz_bio_chunk(dev, bio)	((bio)->bi_iter.bi_sector >> \
+				 (dev)->zone_nr_sectors_shift)
+#define dmz_chunk_block(dev, b)	((b) & ((dev)->zone_nr_blocks - 1))
+
+/*
+ * Zone descriptor.
+ */
+struct dm_zone {
+	/* For listing the zone depending on its state */
+	struct list_head	link;
+
+	/* Zone type and state */
+	unsigned long		flags;
+
+	/* Zone activation reference count */
+	atomic_t		refcount;
+
+	/* Zone write pointer block (relative to the zone start block) */
+	unsigned int		wp_block;
+
+	/* Zone weight (number of valid blocks in the zone) */
+	unsigned int		weight;
+
+	/* The chunk that the zone maps */
+	unsigned int		chunk;
+
+	/*
+	 * For a sequential data zone, pointer to the random zone
+	 * used as a buffer for processing unaligned writes.
+	 * For a buffer zone, this points back to the data zone.
+	 */
+	struct dm_zone		*bzone;
+};
+
+/*
+ * Zone flags.
+ */
+enum {
+	/* Zone write type */
+	DMZ_RND,
+	DMZ_SEQ,
+
+	/* Zone critical condition */
+	DMZ_OFFLINE,
+	DMZ_READ_ONLY,
+
+	/* How the zone is being used */
+	DMZ_META,
+	DMZ_DATA,
+	DMZ_BUF,
+
+	/* Zone internal state */
+	DMZ_ACTIVE,
+	DMZ_RECLAIM,
+	DMZ_SEQ_WRITE_ERR,
+};
+
+/*
+ * Zone data accessors.
+ */
+#define dmz_is_rnd(z)		test_bit(DMZ_RND, &(z)->flags)
+#define dmz_is_seq(z)		test_bit(DMZ_SEQ, &(z)->flags)
+#define dmz_is_empty(z)		((z)->wp_block == 0)
+#define dmz_is_offline(z)	test_bit(DMZ_OFFLINE, &(z)->flags)
+#define dmz_is_readonly(z)	test_bit(DMZ_READ_ONLY, &(z)->flags)
+#define dmz_is_active(z)	test_bit(DMZ_ACTIVE, &(z)->flags)
+#define dmz_in_reclaim(z)	test_bit(DMZ_RECLAIM, &(z)->flags)
+#define dmz_seq_write_err(z)	test_bit(DMZ_SEQ_WRITE_ERR, &(z)->flags)
+
+#define dmz_is_meta(z)		test_bit(DMZ_META, &(z)->flags)
+#define dmz_is_buf(z)		test_bit(DMZ_BUF, &(z)->flags)
+#define dmz_is_data(z)		test_bit(DMZ_DATA, &(z)->flags)
+
+#define dmz_weight(z)		((z)->weight)
+
+/*
+ * Message functions.
+ */
+#define dmz_dev_info(dev, format, args...)	\
+	DMINFO("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_err(dev, format, args...)	\
+	DMERR("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_warn(dev, format, args...)	\
+	DMWARN("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_debug(dev, format, args...)	\
+	DMDEBUG("(%s): " format, (dev)->name, ## args)
+
+struct dmz_metadata;
+struct dmz_reclaim;
+
+/*
+ * Functions defined in dm-zoned-metadata.c
+ */
+int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **zmd);
+void dmz_dtr_metadata(struct dmz_metadata *zmd);
+int dmz_resume_metadata(struct dmz_metadata *zmd);
+
+void dmz_lock_map(struct dmz_metadata *zmd);
+void dmz_unlock_map(struct dmz_metadata *zmd);
+void dmz_lock_metadata(struct dmz_metadata *zmd);
+void dmz_unlock_metadata(struct dmz_metadata *zmd);
+void dmz_lock_flush(struct dmz_metadata *zmd);
+void dmz_unlock_flush(struct dmz_metadata *zmd);
+int dmz_flush_metadata(struct dmz_metadata *zmd);
+
+unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone);
+sector_t dmz_start_sect(struct dmz_metadata *zmd, struct dm_zone *zone);
+sector_t dmz_start_block(struct dmz_metadata *zmd, struct dm_zone *zone);
+unsigned int dmz_nr_chunks(struct dmz_metadata *zmd);
+
+#define DMZ_ALLOC_RND		0x01
+#define DMZ_ALLOC_RECLAIM	0x02
+
+struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags);
+void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone);
+
+void dmz_map_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
+		  unsigned int chunk);
+void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone);
+unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd);
+unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd);
+
+void dmz_activate_zone(struct dm_zone *zone);
+void dmz_deactivate_zone(struct dm_zone *zone);
+
+int dmz_lock_zone_reclaim(struct dm_zone *zone);
+void dmz_unlock_zone_reclaim(struct dm_zone *zone);
+struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd);
+
+struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd,
+				      unsigned int chunk, int op);
+void dmz_put_chunk_mapping(struct dmz_metadata *zmd, struct dm_zone *zone);
+struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd,
+				     struct dm_zone *dzone);
+
+int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+			sector_t chunk_block, unsigned int nr_blocks);
+int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+			  sector_t chunk_block, unsigned int nr_blocks);
+int dmz_block_valid(struct dmz_metadata *zmd, struct dm_zone *zone,
+		    sector_t chunk_block);
+int dmz_first_valid_block(struct dmz_metadata *zmd, struct dm_zone *zone,
+			  sector_t *chunk_block);
+int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+			  struct dm_zone *to_zone);
+int dmz_merge_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+			   struct dm_zone *to_zone, sector_t chunk_block);
+
+/*
+ * Functions defined in dm-zoned-reclaim.c
+ */
+int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
+		    struct dmz_reclaim **zrc);
+void dmz_dtr_reclaim(struct dmz_reclaim *zrc);
+void dmz_suspend_reclaim(struct dmz_reclaim *zrc);
+void dmz_resume_reclaim(struct dmz_reclaim *zrc);
+void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc);
+void dmz_schedule_reclaim(struct dmz_reclaim *zrc);
+
+#endif /* DM_ZONED_H */

drivers/md/dm.c

@@ -58,6 +58,9 @@ static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 
 static struct workqueue_struct *deferred_remove_workqueue;
 
+atomic_t dm_global_event_nr = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq);
+
 /*
  * One of these is allocated per bio.
  */
@@ -1009,6 +1012,85 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
+/*
+ * The zone descriptors obtained with a zone report indicate
+ * zone positions within the target device. The zone descriptors
+ * must be remapped to match their position within the dm device.
+ * A target may call dm_remap_zone_report after completion of a
+ * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained
+ * from the target device mapping to the dm device.
+ */
+void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
+	struct bio *report_bio = tio->io->bio;
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct blk_zone *zone;
+	unsigned int nr_rep = 0;
+	unsigned int ofst;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+
+	if (bio->bi_status)
+		return;
+
+	/*
+	 * Remap the start sector of the reported zones. For sequential zones,
+	 * also remap the write pointer position.
+	 */
+	bio_for_each_segment(bvec, report_bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		/* Remember the report header in the first page */
+		if (!hdr) {
+			hdr = addr;
+			ofst = sizeof(struct blk_zone_report_hdr);
+		} else
+			ofst = 0;
+
+		/* Set zones start sector */
+		while (hdr->nr_zones && ofst < bvec.bv_len) {
+			zone = addr + ofst;
+			if (zone->start >= start + ti->len) {
+				hdr->nr_zones = 0;
+				break;
+			}
+			zone->start = zone->start + ti->begin - start;
+			if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+				if (zone->cond == BLK_ZONE_COND_FULL)
+					zone->wp = zone->start + zone->len;
+				else if (zone->cond == BLK_ZONE_COND_EMPTY)
+					zone->wp = zone->start;
+				else
+					zone->wp = zone->wp + ti->begin - start;
+			}
+			ofst += sizeof(struct blk_zone);
+			hdr->nr_zones--;
+			nr_rep++;
+		}
+
+		if (addr != hdr)
+			kunmap_atomic(addr);
+
+		if (!hdr->nr_zones)
+			break;
+	}
+
+	if (hdr) {
+		hdr->nr_zones = nr_rep;
+		kunmap_atomic(hdr);
+	}
+
+	bio_advance(report_bio, report_bio->bi_iter.bi_size);
+
+#else /* !CONFIG_BLK_DEV_ZONED */
+	bio->bi_status = BLK_STS_NOTSUPP;
+#endif
+}
+EXPORT_SYMBOL_GPL(dm_remap_zone_report);
+
 /*
  * Flush current->bio_list when the target map method blocks.
  * This fixes deadlocks in snapshot and possibly in other targets.
@@ -1149,6 +1231,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 			return r;
 	}
 
+	if (bio_op(bio) != REQ_OP_ZONE_REPORT)
 		bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
 	clone->bi_iter.bi_size = to_bytes(len);
 
@@ -1338,7 +1421,11 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	if (!dm_target_is_valid(ti))
 		return -EIO;
 
-	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
+	if (bio_op(bio) == REQ_OP_ZONE_REPORT)
+		len = ci->sector_count;
+	else
+		len = min_t(sector_t, max_io_len(ci->sector, ti),
+			    ci->sector_count);
 
 	r = __clone_and_map_data_bio(ci, ti, ci->sector, &len);
 	if (r < 0)
@@ -1381,6 +1468,10 @@ static void __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
+	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
+		ci.bio = bio;
+		ci.sector_count = 0;
+		error = __split_and_process_non_flush(&ci);
 	} else {
 		ci.bio = bio;
 		ci.sector_count = bio_sectors(bio);
@@ -1759,7 +1850,9 @@ static void event_callback(void *context)
 	dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj);
 
 	atomic_inc(&md->event_nr);
+	atomic_inc(&dm_global_event_nr);
 	wake_up(&md->eventq);
+	wake_up(&dm_global_eventq);
 }
 
 /*

include/linux/device-mapper.h

@@ -237,6 +237,12 @@ typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio)
 #define DM_TARGET_PASSES_INTEGRITY	0x00000020
 #define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY)
 
+/*
+ * Indicates that a target supports host-managed zoned block devices.
+ */
+#define DM_TARGET_ZONED_HM		0x00000040
+#define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM)
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;
@@ -444,6 +450,8 @@ struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
+void dm_remap_zone_report(struct dm_target *ti, struct bio *bio,
+			  sector_t start);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
@@ -543,48 +551,41 @@ extern struct ratelimit_state dm_ratelimit_state;
 #define dm_ratelimit()	0
 #endif
 
-#define DMCRIT(f, arg...) \
-	printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
+#define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n"
 
-#define DMERR(f, arg...) \
-	printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
-#define DMERR_LIMIT(f, arg...) \
-	do { \
+#define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__)
+
+#define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__)
+#define DMERR_LIMIT(fmt, ...)						\
+do {									\
 	if (dm_ratelimit())						\
-			printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \
-			       f "\n", ## arg); \
-	} while (0)
-
-#define DMWARN(f, arg...) \
-	printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
-#define DMWARN_LIMIT(f, arg...) \
-	do { \
+		DMERR(fmt, ##__VA_ARGS__);				\
+} while (0)
+
+#define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__)
+#define DMWARN_LIMIT(fmt, ...)						\
+do {									\
 	if (dm_ratelimit())						\
-			printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \
-			       f "\n", ## arg); \
-	} while (0)
-
-#define DMINFO(f, arg...) \
-	printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
-#define DMINFO_LIMIT(f, arg...) \
-	do { \
+		DMWARN(fmt, ##__VA_ARGS__);				\
+} while (0)
+
+#define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__)
+#define DMINFO_LIMIT(fmt, ...)						\
+do {									\
 	if (dm_ratelimit())						\
-			printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \
-			       "\n", ## arg); \
-	} while (0)
+		DMINFO(fmt, ##__VA_ARGS__);				\
+} while (0)
 
 #ifdef CONFIG_DM_DEBUG
-#  define DMDEBUG(f, arg...) \
-	printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg)
-#  define DMDEBUG_LIMIT(f, arg...) \
-	do { \
+#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__)
+#define DMDEBUG_LIMIT(fmt, ...)						\
+do {									\
 	if (dm_ratelimit())						\
-			printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \
-			       "\n", ## arg); \
-	} while (0)
+		DMDEBUG(fmt, ##__VA_ARGS__);				\
+} while (0)
 #else
-#  define DMDEBUG(f, arg...) do {} while (0)
-#  define DMDEBUG_LIMIT(f, arg...) do {} while (0)
+#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
+#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define DMEMIT(x...) sz += ((sz >= maxlen) ? \

include/linux/dm-kcopyd.h

@@ -20,6 +20,7 @@
 #define DM_KCOPYD_MAX_REGIONS 8
 
 #define DM_KCOPYD_IGNORE_ERROR 1
+#define DM_KCOPYD_WRITE_SEQ    2
 
 struct dm_kcopyd_throttle {
 	unsigned throttle;

include/uapi/linux/dm-ioctl.h

@@ -240,7 +240,8 @@ enum {
 	/* Added later */
 	DM_LIST_VERSIONS_CMD,
 	DM_TARGET_MSG_CMD,
-	DM_DEV_SET_GEOMETRY_CMD
+	DM_DEV_SET_GEOMETRY_CMD,
+	DM_DEV_ARM_POLL_CMD,
 };
 
 #define DM_IOCTL 0xfd
@@ -255,6 +256,7 @@ enum {
 #define DM_DEV_SUSPEND   _IOWR(DM_IOCTL, DM_DEV_SUSPEND_CMD, struct dm_ioctl)
 #define DM_DEV_STATUS    _IOWR(DM_IOCTL, DM_DEV_STATUS_CMD, struct dm_ioctl)
 #define DM_DEV_WAIT      _IOWR(DM_IOCTL, DM_DEV_WAIT_CMD, struct dm_ioctl)
+#define DM_DEV_ARM_POLL  _IOWR(DM_IOCTL, DM_DEV_ARM_POLL_CMD, struct dm_ioctl)
 
 #define DM_TABLE_LOAD    _IOWR(DM_IOCTL, DM_TABLE_LOAD_CMD, struct dm_ioctl)
 #define DM_TABLE_CLEAR   _IOWR(DM_IOCTL, DM_TABLE_CLEAR_CMD, struct dm_ioctl)