Merge tag 'dm-3.9-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm

Pull device-mapper update from Alasdair G Kergon:
 "The main addition here is a long-desired target framework to allow an
  SSD to be used as a cache in front of a slower device.  Cache tuning
  is delegated to interchangeable policy modules so these can be
  developed independently of the mechanics needed to shuffle the data
  around.

  Other than that, kcopyd users acquire a throttling parameter, ioctl
  buffer usage gets streamlined, more mempool reliance is reduced and
  there are a few other bug fixes and tidy-ups."

* tag 'dm-3.9-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm: (30 commits)
  dm cache: add cleaner policy
  dm cache: add mq policy
  dm: add cache target
  dm persistent data: add bitset
  dm persistent data: add transactional array
  dm thin: remove cells from stack
  dm bio prison: pass cell memory in
  dm persistent data: add btree_walk
  dm: add target num_write_bios fn
  dm kcopyd: introduce configurable throttling
  dm ioctl: allow message to return data
  dm ioctl: optimize functions without variable params
  dm ioctl: introduce ioctl_flags
  dm: merge io_pool and tio_pool
  dm: remove unused _rq_bio_info_cache
  dm: fix limits initialization when there are no data devices
  dm snapshot: add missing module aliases
  dm persistent data: set some btree fn parms const
  dm: refactor bio cloning
  dm: rename bio cloning functions
  ...

43 files changed, 8407 insertions, 580 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 91a02eeeb319..e30b490055aa 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -210,7 +210,7 @@ config DM_DEBUG
 
 config DM_BUFIO
        tristate
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       depends on BLK_DEV_DM
        ---help---
 	 This interface allows you to do buffered I/O on a device and acts
 	 as a cache, holding recently-read blocks in memory and performing
@@ -218,7 +218,7 @@ config DM_BUFIO
 
 config DM_BIO_PRISON
        tristate
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       depends on BLK_DEV_DM
        ---help---
 	 Some bio locking schemes used by other device-mapper targets
 	 including thin provisioning.
@@ -251,8 +251,8 @@ config DM_SNAPSHOT
          Allow volume managers to take writable snapshots of a device.
 
 config DM_THIN_PROVISIONING
-       tristate "Thin provisioning target (EXPERIMENTAL)"
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       tristate "Thin provisioning target"
+       depends on BLK_DEV_DM
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
@@ -268,6 +268,37 @@ config DM_DEBUG_BLOCK_STACK_TRACING
 
 	  If unsure, say N.
 
+config DM_CACHE
+       tristate "Cache target (EXPERIMENTAL)"
+       depends on BLK_DEV_DM
+       default n
+       select DM_PERSISTENT_DATA
+       select DM_BIO_PRISON
+       ---help---
+         dm-cache attempts to improve performance of a block device by
+         moving frequently used data to a smaller, higher performance
+         device.  Different 'policy' plugins can be used to change the
+         algorithms used to select which blocks are promoted, demoted,
+         cleaned etc.  It supports writeback and writethrough modes.
+
+config DM_CACHE_MQ
+       tristate "MQ Cache Policy (EXPERIMENTAL)"
+       depends on DM_CACHE
+       default y
+       ---help---
+         A cache policy that uses a multiqueue ordered by recent hit
+         count to select which blocks should be promoted and demoted.
+         This is meant to be a general purpose policy.  It prioritises
+         reads over writes.
+
+config DM_CACHE_CLEANER
+       tristate "Cleaner Cache Policy (EXPERIMENTAL)"
+       depends on DM_CACHE
+       default y
+       ---help---
+         A simple cache policy that writes back all data to the
+         origin.  Used when decommissioning a dm-cache.
+
 config DM_MIRROR
        tristate "Mirror target"
        depends on BLK_DEV_DM
@@ -302,8 +333,8 @@ config DM_RAID
 	 in one of the available parity distribution methods.
 
 config DM_LOG_USERSPACE
-	tristate "Mirror userspace logging (EXPERIMENTAL)"
-	depends on DM_MIRROR && EXPERIMENTAL && NET
+	tristate "Mirror userspace logging"
+	depends on DM_MIRROR && NET
 	select CONNECTOR
 	---help---
 	  The userspace logging module provides a mechanism for
@@ -350,8 +381,8 @@ config DM_MULTIPATH_ST
 	  If unsure, say N.
 
 config DM_DELAY
-	tristate "I/O delaying target (EXPERIMENTAL)"
-	depends on BLK_DEV_DM && EXPERIMENTAL
+	tristate "I/O delaying target"
+	depends on BLK_DEV_DM
 	---help---
 	A target that delays reads and/or writes and can send
 	them to different devices.  Useful for testing.
@@ -365,14 +396,14 @@ config DM_UEVENT
 	Generate udev events for DM events.
 
 config DM_FLAKEY
-       tristate "Flakey target (EXPERIMENTAL)"
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       tristate "Flakey target"
+       depends on BLK_DEV_DM
        ---help---
          A target that intermittently fails I/O for debugging purposes.
 
 config DM_VERITY
-	tristate "Verity target support (EXPERIMENTAL)"
-	depends on BLK_DEV_DM && EXPERIMENTAL
+	tristate "Verity target support"
+	depends on BLK_DEV_DM
 	select CRYPTO
 	select CRYPTO_HASH
 	select DM_BUFIO
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 94dce8b49324..7ceeaefc0e95 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -11,6 +11,9 @@ dm-mirror-y	+= dm-raid1.o
 dm-log-userspace-y \
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
+dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
+dm-cache-mq-y   += dm-cache-policy-mq.o
+dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
 
@@ -44,6 +47,9 @@ obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
 obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
+obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
+obj-$(CONFIG_DM_CACHE_MQ)	+= dm-cache-mq.o
+obj-$(CONFIG_DM_CACHE_CLEANER)	+= dm-cache-cleaner.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
diff --git a/drivers/md/dm-bio-prison.c b/drivers/md/dm-bio-prison.c
index d9d3f1c7b662..85f0b7074257 100644
--- a/drivers/md/dm-bio-prison.c
+++ b/drivers/md/dm-bio-prison.c
@@ -14,14 +14,6 @@
 
 /*----------------------------------------------------------------*/
 
-struct dm_bio_prison_cell {
-	struct hlist_node list;
-	struct dm_bio_prison *prison;
-	struct dm_cell_key key;
-	struct bio *holder;
-	struct bio_list bios;
-};
-
 struct dm_bio_prison {
 	spinlock_t lock;
 	mempool_t *cell_pool;
@@ -87,6 +79,19 @@ void dm_bio_prison_destroy(struct dm_bio_prison *prison)
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_destroy);
 
+struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, gfp_t gfp)
+{
+	return mempool_alloc(prison->cell_pool, gfp);
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell);
+
+void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
+			     struct dm_bio_prison_cell *cell)
+{
+	mempool_free(cell, prison->cell_pool);
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell);
+
 static uint32_t hash_key(struct dm_bio_prison *prison, struct dm_cell_key *key)
 {
 	const unsigned long BIG_PRIME = 4294967291UL;
@@ -114,91 +119,95 @@ static struct dm_bio_prison_cell *__search_bucket(struct hlist_head *bucket,
 	return NULL;
 }
 
-/*
- * This may block if a new cell needs allocating.  You must ensure that
- * cells will be unlocked even if the calling thread is blocked.
- *
- * Returns 1 if the cell was already held, 0 if @inmate is the new holder.
- */
-int dm_bio_detain(struct dm_bio_prison *prison, struct dm_cell_key *key,
-		  struct bio *inmate, struct dm_bio_prison_cell **ref)
+static void __setup_new_cell(struct dm_bio_prison *prison,
+			     struct dm_cell_key *key,
+			     struct bio *holder,
+			     uint32_t hash,
+			     struct dm_bio_prison_cell *cell)
 {
-	int r = 1;
-	unsigned long flags;
-	uint32_t hash = hash_key(prison, key);
-	struct dm_bio_prison_cell *cell, *cell2;
-
-	BUG_ON(hash > prison->nr_buckets);
-
-	spin_lock_irqsave(&prison->lock, flags);
-
-	cell = __search_bucket(prison->cells + hash, key);
-	if (cell) {
-		bio_list_add(&cell->bios, inmate);
-		goto out;
-	}
+	memcpy(&cell->key, key, sizeof(cell->key));
+	cell->holder = holder;
+	bio_list_init(&cell->bios);
+	hlist_add_head(&cell->list, prison->cells + hash);
+}
 
-	/*
-	 * Allocate a new cell
-	 */
-	spin_unlock_irqrestore(&prison->lock, flags);
-	cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO);
-	spin_lock_irqsave(&prison->lock, flags);
+static int __bio_detain(struct dm_bio_prison *prison,
+			struct dm_cell_key *key,
+			struct bio *inmate,
+			struct dm_bio_prison_cell *cell_prealloc,
+			struct dm_bio_prison_cell **cell_result)
+{
+	uint32_t hash = hash_key(prison, key);
+	struct dm_bio_prison_cell *cell;
 
-	/*
-	 * We've been unlocked, so we have to double check that
-	 * nobody else has inserted this cell in the meantime.
-	 */
 	cell = __search_bucket(prison->cells + hash, key);
 	if (cell) {
-		mempool_free(cell2, prison->cell_pool);
-		bio_list_add(&cell->bios, inmate);
-		goto out;
+		if (inmate)
+			bio_list_add(&cell->bios, inmate);
+		*cell_result = cell;
+		return 1;
 	}
 
-	/*
-	 * Use new cell.
-	 */
-	cell = cell2;
-
-	cell->prison = prison;
-	memcpy(&cell->key, key, sizeof(cell->key));
-	cell->holder = inmate;
-	bio_list_init(&cell->bios);
-	hlist_add_head(&cell->list, prison->cells + hash);
+	__setup_new_cell(prison, key, inmate, hash, cell_prealloc);
+	*cell_result = cell_prealloc;
+	return 0;
+}
 
-	r = 0;
+static int bio_detain(struct dm_bio_prison *prison,
+		      struct dm_cell_key *key,
+		      struct bio *inmate,
+		      struct dm_bio_prison_cell *cell_prealloc,
+		      struct dm_bio_prison_cell **cell_result)
+{
+	int r;
+	unsigned long flags;
 
-out:
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result);
 	spin_unlock_irqrestore(&prison->lock, flags);
 
-	*ref = cell;
-
 	return r;
 }
+
+int dm_bio_detain(struct dm_bio_prison *prison,
+		  struct dm_cell_key *key,
+		  struct bio *inmate,
+		  struct dm_bio_prison_cell *cell_prealloc,
+		  struct dm_bio_prison_cell **cell_result)
+{
+	return bio_detain(prison, key, inmate, cell_prealloc, cell_result);
+}
 EXPORT_SYMBOL_GPL(dm_bio_detain);
 
+int dm_get_cell(struct dm_bio_prison *prison,
+		struct dm_cell_key *key,
+		struct dm_bio_prison_cell *cell_prealloc,
+		struct dm_bio_prison_cell **cell_result)
+{
+	return bio_detain(prison, key, NULL, cell_prealloc, cell_result);
+}
+EXPORT_SYMBOL_GPL(dm_get_cell);
+
 /*
  * @inmates must have been initialised prior to this call
  */
-static void __cell_release(struct dm_bio_prison_cell *cell, struct bio_list *inmates)
+static void __cell_release(struct dm_bio_prison_cell *cell,
+			   struct bio_list *inmates)
 {
-	struct dm_bio_prison *prison = cell->prison;
-
 	hlist_del(&cell->list);
 
 	if (inmates) {
-		bio_list_add(inmates, cell->holder);
+		if (cell->holder)
+			bio_list_add(inmates, cell->holder);
 		bio_list_merge(inmates, &cell->bios);
 	}
-
-	mempool_free(cell, prison->cell_pool);
 }
 
-void dm_cell_release(struct dm_bio_prison_cell *cell, struct bio_list *bios)
+void dm_cell_release(struct dm_bio_prison *prison,
+		     struct dm_bio_prison_cell *cell,
+		     struct bio_list *bios)
 {
 	unsigned long flags;
-	struct dm_bio_prison *prison = cell->prison;
 
 	spin_lock_irqsave(&prison->lock, flags);
 	__cell_release(cell, bios);
@@ -209,20 +218,18 @@ EXPORT_SYMBOL_GPL(dm_cell_release);
 /*
  * Sometimes we don't want the holder, just the additional bios.
  */
-static void __cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates)
+static void __cell_release_no_holder(struct dm_bio_prison_cell *cell,
+				     struct bio_list *inmates)
 {
-	struct dm_bio_prison *prison = cell->prison;
-
 	hlist_del(&cell->list);
 	bio_list_merge(inmates, &cell->bios);
-
-	mempool_free(cell, prison->cell_pool);
 }
 
-void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates)
+void dm_cell_release_no_holder(struct dm_bio_prison *prison,
+			       struct dm_bio_prison_cell *cell,
+			       struct bio_list *inmates)
 {
 	unsigned long flags;
-	struct dm_bio_prison *prison = cell->prison;
 
 	spin_lock_irqsave(&prison->lock, flags);
 	__cell_release_no_holder(cell, inmates);
@@ -230,9 +237,9 @@ void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list
 }
 EXPORT_SYMBOL_GPL(dm_cell_release_no_holder);
 
-void dm_cell_error(struct dm_bio_prison_cell *cell)
+void dm_cell_error(struct dm_bio_prison *prison,
+		   struct dm_bio_prison_cell *cell)
 {
-	struct dm_bio_prison *prison = cell->prison;
 	struct bio_list bios;
 	struct bio *bio;
 	unsigned long flags;
diff --git a/drivers/md/dm-bio-prison.h b/drivers/md/dm-bio-prison.h
index 53d1a7a84e2f..3f833190eadf 100644
--- a/drivers/md/dm-bio-prison.h
+++ b/drivers/md/dm-bio-prison.h
@@ -22,7 +22,6 @@
  * subsequently unlocked the bios become available.
  */
 struct dm_bio_prison;
-struct dm_bio_prison_cell;
 
 /* FIXME: this needs to be more abstract */
 struct dm_cell_key {
@@ -31,21 +30,62 @@ struct dm_cell_key {
 	dm_block_t block;
 };
 
+/*
+ * Treat this as opaque, only in header so callers can manage allocation
+ * themselves.
+ */
+struct dm_bio_prison_cell {
+	struct hlist_node list;
+	struct dm_cell_key key;
+	struct bio *holder;
+	struct bio_list bios;
+};
+
 struct dm_bio_prison *dm_bio_prison_create(unsigned nr_cells);
 void dm_bio_prison_destroy(struct dm_bio_prison *prison);
 
 /*
- * This may block if a new cell needs allocating.  You must ensure that
- * cells will be unlocked even if the calling thread is blocked.
+ * These two functions just wrap a mempool.  This is a transitory step:
+ * Eventually all bio prison clients should manage their own cell memory.
  *
- * Returns 1 if the cell was already held, 0 if @inmate is the new holder.
+ * Like mempool_alloc(), dm_bio_prison_alloc_cell() can only fail if called
+ * in interrupt context or passed GFP_NOWAIT.
  */
-int dm_bio_detain(struct dm_bio_prison *prison, struct dm_cell_key *key,
-		  struct bio *inmate, struct dm_bio_prison_cell **ref);
+struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison,
+						    gfp_t gfp);
+void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
+			     struct dm_bio_prison_cell *cell);
 
-void dm_cell_release(struct dm_bio_prison_cell *cell, struct bio_list *bios);
-void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates);
-void dm_cell_error(struct dm_bio_prison_cell *cell);
+/*
+ * Creates, or retrieves a cell for the given key.
+ *
+ * Returns 1 if pre-existing cell returned, zero if new cell created using
+ * @cell_prealloc.
+ */
+int dm_get_cell(struct dm_bio_prison *prison,
+		struct dm_cell_key *key,
+		struct dm_bio_prison_cell *cell_prealloc,
+		struct dm_bio_prison_cell **cell_result);
+
+/*
+ * An atomic op that combines retrieving a cell, and adding a bio to it.
+ *
+ * Returns 1 if the cell was already held, 0 if @inmate is the new holder.
+ */
+int dm_bio_detain(struct dm_bio_prison *prison,
+		  struct dm_cell_key *key,
+		  struct bio *inmate,
+		  struct dm_bio_prison_cell *cell_prealloc,
+		  struct dm_bio_prison_cell **cell_result);
+
+void dm_cell_release(struct dm_bio_prison *prison,
+		     struct dm_bio_prison_cell *cell,
+		     struct bio_list *bios);
+void dm_cell_release_no_holder(struct dm_bio_prison *prison,
+			       struct dm_bio_prison_cell *cell,
+			       struct bio_list *inmates);
+void dm_cell_error(struct dm_bio_prison *prison,
+		   struct dm_bio_prison_cell *cell);
 
 /*----------------------------------------------------------------*/
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 93205e32a004..3c955e10a618 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1192,7 +1192,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers);
 int dm_bufio_issue_flush(struct dm_bufio_client *c)
 {
 	struct dm_io_request io_req = {
-		.bi_rw = REQ_FLUSH,
+		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = c->dm_io,
diff --git a/drivers/md/dm-cache-block-types.h b/drivers/md/dm-cache-block-types.h
new file mode 100644
index 000000000000..bed4ad4e1b7c
--- /dev/null
+++ b/drivers/md/dm-cache-block-types.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_CACHE_BLOCK_TYPES_H
+#define DM_CACHE_BLOCK_TYPES_H
+
+#include "persistent-data/dm-block-manager.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * It's helpful to get sparse to differentiate between indexes into the
+ * origin device, indexes into the cache device, and indexes into the
+ * discard bitset.
+ */
+
+typedef dm_block_t __bitwise__ dm_oblock_t;
+typedef uint32_t __bitwise__ dm_cblock_t;
+typedef dm_block_t __bitwise__ dm_dblock_t;
+
+static inline dm_oblock_t to_oblock(dm_block_t b)
+{
+	return (__force dm_oblock_t) b;
+}
+
+static inline dm_block_t from_oblock(dm_oblock_t b)
+{
+	return (__force dm_block_t) b;
+}
+
+static inline dm_cblock_t to_cblock(uint32_t b)
+{
+	return (__force dm_cblock_t) b;
+}
+
+static inline uint32_t from_cblock(dm_cblock_t b)
+{
+	return (__force uint32_t) b;
+}
+
+static inline dm_dblock_t to_dblock(dm_block_t b)
+{
+	return (__force dm_dblock_t) b;
+}
+
+static inline dm_block_t from_dblock(dm_dblock_t b)
+{
+	return (__force dm_block_t) b;
+}
+
+#endif /* DM_CACHE_BLOCK_TYPES_H */
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
new file mode 100644
index 000000000000..fbd3625f2748
--- /dev/null
+++ b/drivers/md/dm-cache-metadata.c
@@ -0,0 +1,1146 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-cache-metadata.h"
+
+#include "persistent-data/dm-array.h"
+#include "persistent-data/dm-bitset.h"
+#include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-disk.h"
+#include "persistent-data/dm-transaction-manager.h"
+
+#include <linux/device-mapper.h>
+
+/*----------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX   "cache metadata"
+
+#define CACHE_SUPERBLOCK_MAGIC 06142003
+#define CACHE_SUPERBLOCK_LOCATION 0
+#define CACHE_VERSION 1
+#define CACHE_METADATA_CACHE_SIZE 64
+
+/*
+ *  3 for btree insert +
+ *  2 for btree lookup used within space map
+ */
+#define CACHE_MAX_CONCURRENT_LOCKS 5
+#define SPACE_MAP_ROOT_SIZE 128
+
+enum superblock_flag_bits {
+	/* for spotting crashes that would invalidate the dirty bitset */
+	CLEAN_SHUTDOWN,
+};
+
+/*
+ * Each mapping from cache block -> origin block carries a set of flags.
+ */
+enum mapping_bits {
+	/*
+	 * A valid mapping.  Because we're using an array we clear this
+	 * flag for an non existant mapping.
+	 */
+	M_VALID = 1,
+
+	/*
+	 * The data on the cache is different from that on the origin.
+	 */
+	M_DIRTY = 2
+};
+
+struct cache_disk_superblock {
+	__le32 csum;
+	__le32 flags;
+	__le64 blocknr;
+
+	__u8 uuid[16];
+	__le64 magic;
+	__le32 version;
+
+	__u8 policy_name[CACHE_POLICY_NAME_SIZE];
+	__le32 policy_hint_size;
+
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
+	__le64 mapping_root;
+	__le64 hint_root;
+
+	__le64 discard_root;
+	__le64 discard_block_size;
+	__le64 discard_nr_blocks;
+
+	__le32 data_block_size;
+	__le32 metadata_block_size;
+	__le32 cache_blocks;
+
+	__le32 compat_flags;
+	__le32 compat_ro_flags;
+	__le32 incompat_flags;
+
+	__le32 read_hits;
+	__le32 read_misses;
+	__le32 write_hits;
+	__le32 write_misses;
+} __packed;
+
+struct dm_cache_metadata {
+	struct block_device *bdev;
+	struct dm_block_manager *bm;
+	struct dm_space_map *metadata_sm;
+	struct dm_transaction_manager *tm;
+
+	struct dm_array_info info;
+	struct dm_array_info hint_info;
+	struct dm_disk_bitset discard_info;
+
+	struct rw_semaphore root_lock;
+	dm_block_t root;
+	dm_block_t hint_root;
+	dm_block_t discard_root;
+
+	sector_t discard_block_size;
+	dm_dblock_t discard_nr_blocks;
+
+	sector_t data_block_size;
+	dm_cblock_t cache_blocks;
+	bool changed:1;
+	bool clean_when_opened:1;
+
+	char policy_name[CACHE_POLICY_NAME_SIZE];
+	size_t policy_hint_size;
+	struct dm_cache_statistics stats;
+};
+
+/*-------------------------------------------------------------------
+ * superblock validator
+ *-----------------------------------------------------------------*/
+
+#define SUPERBLOCK_CSUM_XOR 9031977
+
+static void sb_prepare_for_write(struct dm_block_validator *v,
+				 struct dm_block *b,
+				 size_t sb_block_size)
+{
+	struct cache_disk_superblock *disk_super = dm_block_data(b);
+
+	disk_super->blocknr = cpu_to_le64(dm_block_location(b));
+	disk_super->csum = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
+						      sb_block_size - sizeof(__le32),
+						      SUPERBLOCK_CSUM_XOR));
+}
+
+static int sb_check(struct dm_block_validator *v,
+		    struct dm_block *b,
+		    size_t sb_block_size)
+{
+	struct cache_disk_superblock *disk_super = dm_block_data(b);
+	__le32 csum_le;
+
+	if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) {
+		DMERR("sb_check failed: blocknr %llu: wanted %llu",
+		      le64_to_cpu(disk_super->blocknr),
+		      (unsigned long long)dm_block_location(b));
+		return -ENOTBLK;
+	}
+
+	if (le64_to_cpu(disk_super->magic) != CACHE_SUPERBLOCK_MAGIC) {
+		DMERR("sb_check failed: magic %llu: wanted %llu",
+		      le64_to_cpu(disk_super->magic),
+		      (unsigned long long)CACHE_SUPERBLOCK_MAGIC);
+		return -EILSEQ;
+	}
+
+	csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
+					     sb_block_size - sizeof(__le32),
+					     SUPERBLOCK_CSUM_XOR));
+	if (csum_le != disk_super->csum) {
+		DMERR("sb_check failed: csum %u: wanted %u",
+		      le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
+		return -EILSEQ;
+	}
+
+	return 0;
+}
+
+static struct dm_block_validator sb_validator = {
+	.name = "superblock",
+	.prepare_for_write = sb_prepare_for_write,
+	.check = sb_check
+};
+
+/*----------------------------------------------------------------*/
+
+static int superblock_read_lock(struct dm_cache_metadata *cmd,
+				struct dm_block **sblock)
+{
+	return dm_bm_read_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
+			       &sb_validator, sblock);
+}
+
+static int superblock_lock_zero(struct dm_cache_metadata *cmd,
+				struct dm_block **sblock)
+{
+	return dm_bm_write_lock_zero(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
+				     &sb_validator, sblock);
+}
+
+static int superblock_lock(struct dm_cache_metadata *cmd,
+			   struct dm_block **sblock)
+{
+	return dm_bm_write_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
+				&sb_validator, sblock);
+}
+
+/*----------------------------------------------------------------*/
+
+static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result)
+{
+	int r;
+	unsigned i;
+	struct dm_block *b;
+	__le64 *data_le, zero = cpu_to_le64(0);
+	unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64);
+
+	/*
+	 * We can't use a validator here - it may be all zeroes.
+	 */
+	r = dm_bm_read_lock(bm, CACHE_SUPERBLOCK_LOCATION, NULL, &b);
+	if (r)
+		return r;
+
+	data_le = dm_block_data(b);
+	*result = 1;
+	for (i = 0; i < sb_block_size; i++) {
+		if (data_le[i] != zero) {
+			*result = 0;
+			break;
+		}
+	}
+
+	return dm_bm_unlock(b);
+}
+
+static void __setup_mapping_info(struct dm_cache_metadata *cmd)
+{
+	struct dm_btree_value_type vt;
+
+	vt.context = NULL;
+	vt.size = sizeof(__le64);
+	vt.inc = NULL;
+	vt.dec = NULL;
+	vt.equal = NULL;
+	dm_array_info_init(&cmd-&