dm: add cache target

Add a target that allows a fast device such as an SSD to be used as a
cache for a slower device such as a disk.

A plug-in architecture was chosen so that the decisions about which data
to migrate and when are delegated to interchangeable tunable policy
modules.  The first general purpose module we have developed, called
"mq" (multiqueue), follows in the next patch.  Other modules are
under development.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Heinz Mauelshagen <mauelshagen@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

Documentation/device-mapper/cache.txt

+Introduction
+============
+
+dm-cache is a device mapper target written by Joe Thornber, Heinz
+Mauelshagen, and Mike Snitzer.
+
+It aims to improve performance of a block device (eg, a spindle) by
+dynamically migrating some of its data to a faster, smaller device
+(eg, an SSD).
+
+This device-mapper solution allows us to insert this caching at
+different levels of the dm stack, for instance above the data device for
+a thin-provisioning pool.  Caching solutions that are integrated more
+closely with the virtual memory system should give better performance.
+
+The target reuses the metadata library used in the thin-provisioning
+library.
+
+The decision as to what data to migrate and when is left to a plug-in
+policy module.  Several of these have been written as we experiment,
+and we hope other people will contribute others for specific io
+scenarios (eg. a vm image server).
+
+Glossary
+========
+
+  Migration -  Movement of the primary copy of a logical block from one
+	       device to the other.
+  Promotion -  Migration from slow device to fast device.
+  Demotion  -  Migration from fast device to slow device.
+
+The origin device always contains a copy of the logical block, which
+may be out of date or kept in sync with the copy on the cache device
+(depending on policy).
+
+Design
+======
+
+Sub-devices
+-----------
+
+The target is constructed by passing three devices to it (along with
+other parameters detailed later):
+
+1. An origin device - the big, slow one.
+
+2. A cache device - the small, fast one.
+
+3. A small metadata device - records which blocks are in the cache,
+   which are dirty, and extra hints for use by the policy object.
+   This information could be put on the cache device, but having it
+   separate allows the volume manager to configure it differently,
+   e.g. as a mirror for extra robustness.
+
+Fixed block size
+----------------
+
+The origin is divided up into blocks of a fixed size.  This block size
+is configurable when you first create the cache.  Typically we've been
+using block sizes of 256k - 1024k.
+
+Having a fixed block size simplifies the target a lot.  But it is
+something of a compromise.  For instance, a small part of a block may be
+getting hit a lot, yet the whole block will be promoted to the cache.
+So large block sizes are bad because they waste cache space.  And small
+block sizes are bad because they increase the amount of metadata (both
+in core and on disk).
+
+Writeback/writethrough
+----------------------
+
+The cache has two modes, writeback and writethrough.
+
+If writeback, the default, is selected then a write to a block that is
+cached will go only to the cache and the block will be marked dirty in
+the metadata.
+
+If writethrough is selected then a write to a cached block will not
+complete until it has hit both the origin and cache devices.  Clean
+blocks should remain clean.
+
+A simple cleaner policy is provided, which will clean (write back) all
+dirty blocks in a cache.  Useful for decommissioning a cache.
+
+Migration throttling
+--------------------
+
+Migrating data between the origin and cache device uses bandwidth.
+The user can set a throttle to prevent more than a certain amount of
+migration occuring at any one time.  Currently we're not taking any
+account of normal io traffic going to the devices.  More work needs
+doing here to avoid migrating during those peak io moments.
+
+For the time being, a message "migration_threshold <#sectors>"
+can be used to set the maximum number of sectors being migrated,
+the default being 204800 sectors (or 100MB).
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
+written.  If no such requests are made then commits will occur every
+second.  This means the cache behaves like a physical disk that has a
+write cache (the same is true of the thin-provisioning target).  If
+power is lost you may lose some recent writes.  The metadata should
+always be consistent in spite of any crash.
+
+The 'dirty' state for a cache block changes far too frequently for us
+to keep updating it on the fly.  So we treat it as a hint.  In normal
+operation it will be written when the dm device is suspended.  If the
+system crashes all cache blocks will be assumed dirty when restarted.
+
+Per-block policy hints
+----------------------
+
+Policy plug-ins can store a chunk of data per cache block.  It's up to
+the policy how big this chunk is, but it should be kept small.  Like the
+dirty flags this data is lost if there's a crash so a safe fallback
+value should always be possible.
+
+For instance, the 'mq' policy, which is currently the default policy,
+uses this facility to store the hit count of the cache blocks.  If
+there's a crash this information will be lost, which means the cache
+may be less efficient until those hit counts are regenerated.
+
+Policy hints affect performance, not correctness.
+
+Policy messaging
+----------------
+
+Policies will have different tunables, specific to each one, so we
+need a generic way of getting and setting these.  Device-mapper
+messages are used.  Refer to cache-policies.txt.
+
+Discard bitset resolution
+-------------------------
+
+We can avoid copying data during migration if we know the block has
+been discarded.  A prime example of this is when mkfs discards the
+whole block device.  We store a bitset tracking the discard state of
+blocks.  However, we allow this bitset to have a different block size
+from the cache blocks.  This is because we need to track the discard
+state for all of the origin device (compare with the dirty bitset
+which is just for the smaller cache device).
+
+Target interface
+================
+
+Constructor
+-----------
+
+ cache <metadata dev> <cache dev> <origin dev> <block size>
+       <#feature args> [<feature arg>]*
+       <policy> <#policy args> [policy args]*
+
+ metadata dev    : fast device holding the persistent metadata
+ cache dev	 : fast device holding cached data blocks
+ origin dev	 : slow device holding original data blocks
+ block size      : cache unit size in sectors
+
+ #feature args   : number of feature arguments passed
+ feature args    : writethrough.  (The default is writeback.)
+
+ policy          : the replacement policy to use
+ #policy args    : an even number of arguments corresponding to
+                   key/value pairs passed to the policy
+ policy args     : key/value pairs passed to the policy
+		   E.g. 'sequential_threshold 1024'
+		   See cache-policies.txt for details.
+
+Optional feature arguments are:
+   writethrough  : write through caching that prohibits cache block
+		   content from being different from origin block content.
+		   Without this argument, the default behaviour is to write
+		   back cache block contents later for performance reasons,
+		   so they may differ from the corresponding origin blocks.
+
+A policy called 'default' is always registered.  This is an alias for
+the policy we currently think is giving best all round performance.
+
+As the default policy could vary between kernels, if you are relying on
+the characteristics of a specific policy, always request it by name.
+
+Status
+------
+
+<#used metadata blocks>/<#total metadata blocks> <#read hits> <#read misses>
+<#write hits> <#write misses> <#demotions> <#promotions> <#blocks in cache>
+<#dirty> <#features> <features>* <#core args> <core args>* <#policy args>
+<policy args>*
+
+#used metadata blocks    : Number of metadata blocks used
+#total metadata blocks   : Total number of metadata blocks
+#read hits               : Number of times a READ bio has been mapped
+			     to the cache
+#read misses             : Number of times a READ bio has been mapped
+			     to the origin
+#write hits              : Number of times a WRITE bio has been mapped
+			     to the cache
+#write misses            : Number of times a WRITE bio has been
+			     mapped to the origin
+#demotions               : Number of times a block has been removed
+			     from the cache
+#promotions              : Number of times a block has been moved to
+			     the cache
+#blocks in cache         : Number of blocks resident in the cache
+#dirty                   : Number of blocks in the cache that differ
+			     from the origin
+#feature args            : Number of feature args to follow
+feature args             : 'writethrough' (optional)
+#core args               : Number of core arguments (must be even)
+core args                : Key/value pairs for tuning the core
+			     e.g. migration_threshold
+#policy args             : Number of policy arguments to follow (must be even)
+policy args              : Key/value pairs
+			     e.g. 'sequential_threshold 1024
+
+Messages
+--------
+
+Policies will have different tunables, specific to each one, so we
+need a generic way of getting and setting these.  Device-mapper
+messages are used.  (A sysfs interface would also be possible.)
+
+The message format is:
+
+   <key> <value>
+
+E.g.
+   dmsetup message my_cache 0 sequential_threshold 1024
+
+Examples
+========
+
+The test suite can be found here:
+
+https://github.com/jthornber/thinp-test-suite
+
+dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \
+	/dev/mapper/ssd /dev/mapper/origin 512 1 writeback default 0'
+dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \
+	/dev/mapper/ssd /dev/mapper/origin 1024 1 writeback \
+	mq 4 sequential_threshold 1024 random_threshold 8'

drivers/md/Kconfig

@@ -268,6 +268,19 @@ 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_MIRROR
        tristate "Mirror target"
        depends on BLK_DEV_DM

drivers/md/Makefile

@@ -11,6 +11,7 @@ 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
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
 
@@ -44,6 +45,7 @@ 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
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o

drivers/md/dm-bio-prison.c

@@ -179,6 +179,15 @@ int dm_bio_detain(struct dm_bio_prison *prison,
 }
 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
  */

drivers/md/dm-bio-prison.h

@@ -56,6 +56,17 @@ struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison
 void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
 			     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.
  *

drivers/md/dm-cache-block-types.h

+/*
+ * 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 */

drivers/md/dm-cache-metadata.c

+/*
+ * 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->info, cmd->tm, &vt);
+
+	if (cmd->policy_hint_size) {
+		vt.size = sizeof(__le32);
+		dm_array_info_init(&cmd->hint_info, cmd->tm, &vt);
+	}
+}
+
+static int __write_initial_superblock(struct dm_cache_metadata *cmd)
+{
+	int r;
+	struct dm_block *sblock;
+	size_t metadata_len;
+	struct cache_disk_superblock *disk_super;
+	sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;
+
+	/* FIXME: see if we can lose the max sectors limit */
+	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
+		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	r = dm_tm_pre_commit(cmd->tm);
+	if (r < 0)
+		return r;
+
+	r = superblock_lock_zero(cmd, &sblock);
+	if (r)
+		return r;
+
+	disk_super = dm_block_data(sblock);
+	disk_super->flags = 0;
+	memset(disk_super->uuid, 0, sizeof(disk_super->uuid));
+	disk_super->magic = cpu_to_le64(CACHE_SUPERBLOCK_MAGIC);
+	disk_super->version = cpu_to_le32(CACHE_VERSION);
+	memset(disk_super->policy_name, 0, CACHE_POLICY_NAME_SIZE);
+	disk_super->policy_hint_size = 0;
+
+	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
+			    metadata_len);
+	if (r < 0)
+		goto bad_locked;
+
+	disk_super->mapping_root = cpu_to_le64(cmd->root);
+	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
+	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
+	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
+	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
+	disk_super->metadata_block_size = cpu_to_le32(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	disk_super->data_block_size = cpu_to_le32(cmd->data_block_size);
+	disk_super->cache_blocks = cpu_to_le32(0);
+	memset(disk_super->policy_name, 0, sizeof(disk_super->policy_name));
+
+	disk_super->read_hits = cpu_to_le32(0);
+	disk_super->read_misses = cpu_to_le32(0);
+	disk_super->write_hits = cpu_to_le32(0);
+	disk_super->write_misses = cpu_to_le32(0);
+
+	return dm_tm_commit(cmd->tm, sblock);
+
+bad_locked:
+	dm_bm_unlock(sblock);
+	return r;
+}
+
+static int __format_metadata(struct dm_cache_metadata *cmd)
+{
+	int r;
+
+	r = dm_tm_create_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
+				 &cmd->tm, &cmd->metadata_sm);
+	if (r < 0) {
+		DMERR("tm_create_with_sm failed");
+		return r;
+	}
+
+	__setup_mapping_info(cmd);
+
+	r = dm_array_empty(&cmd->info, &cmd->root);
+	if (r < 0)
+		goto bad;
+
+	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
+
+	r = dm_bitset_empty(&cmd->discard_info, &cmd->discard_root);
+	if (r < 0)
+		goto bad;
+
+	cmd->discard_block_size = 0;
+	cmd->discard_nr_blocks = 0;
+
+	r = __write_initial_superblock(cmd);
+	if (r)
+		goto bad;
+
+	cmd->clean_when_opened = true;
+	return 0;
+
+bad:
+	dm_tm_destroy(cmd->tm);
+	dm_sm_destroy(cmd->metadata_sm);
+
+	return r;
+}
+
+static int __check_incompat_features(struct cache_disk_superblock *disk_super,
+				     struct dm_cache_metadata *cmd)
+{
+	uint32_t features;
+
+	features = le32_to_cpu(disk_super->incompat_flags) & ~DM_CACHE_FEATURE_INCOMPAT_SUPP;
+	if (features) {
+		DMERR("could not access metadata due to unsupported optional features (%lx).",
+		      (unsigned long)features);
+		return -EINVAL;
+	}
+
+	/*
+	 * Check for read-only metadata to skip the following RDWR checks.
+	 */
+	if (get_disk_ro(cmd->bdev->bd_disk))
+		return 0;
+
+	features = le32_to_cpu(disk_super->compat_ro_flags) & ~DM_CACHE_FEATURE_COMPAT_RO_SUPP;
+	if (features) {
+		DMERR("could not access metadata RDWR due to unsupported optional features (%lx).",
+		      (unsigned long)features);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __open_metadata(struct dm_cache_metadata *cmd)
+{
+	int r;
+	struct dm_block *sblock;
+	struct cache_disk_superblock *disk_super;
+	unsigned long sb_flags;
+
+	r = superblock_read_lock(cmd, &sblock);
+	if (r < 0) {
+		DMERR("couldn't read lock superblock");
+		return r;
+	}
+
+	disk_super = dm_block_data(sblock);
+
+	r = __check_incompat_features(disk_super, cmd);
+	if (r < 0)
+		goto bad;
+
+	r = dm_tm_open_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
+			       disk_super->metadata_space_map_root,
+			       sizeof(disk_super->metadata_space_map_root),
+			       &cmd->tm, &cmd->metadata_sm);
+	if (r < 0) {
+		DMERR("tm_open_with_sm failed");
+		goto bad;
+	}
+
+	__setup_mapping_info(cmd);
+	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
+	sb_flags = le32_to_cpu(disk_super->flags);
+	cmd->clean_when_opened = test_bit(CLEAN_SHUTDOWN, &sb_flags);
+	return dm_bm_unlock(sblock);
+
+bad:
+	dm_bm_unlock(sblock);
+	return r;
+}
+
+static int __open_or_format_metadata(struct dm_cache_metadata *cmd,
+				     bool format_device)
+{
+	int r, unformatted;
+
+	r = __superblock_all_zeroes(cmd->bm, &unformatted);
+	if (r)
+		return r;
+
+	if (unformatted)
+		return format_device ? __format_metadata(cmd) : -EPERM;
+
+	return __open_metadata(cmd);
+}
+
+static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
+					    bool may_format_device)
+{
+	int r;
+	cmd->bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE,
+					  CACHE_METADATA_CACHE_SIZE,
+					  CACHE_MAX_CONCURRENT_LOCKS);
+	if (IS_ERR(cmd->bm)) {
+		DMERR("could not create block manager");
+		return PTR_ERR(cmd->bm);
+	}
+
+	r = __open_or_format_metadata(cmd, may_format_device);
+	if (r)
+		dm_block_manager_destroy(cmd->bm);
+
+	return r;
+}
+
+static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd)
+{
+	dm_sm_destroy(cmd->metadata_sm);
+	dm_tm_destroy(cmd->tm);
+	dm_block_manager_destroy(cmd->bm);
+}
+
+typedef unsigned long (*flags_mutator)(unsigned long);
+
+static void update_flags(struct cache_disk_superblock *disk_super,
+			 flags_mutator mutator)
+{
+	uint32_t sb_flags = mutator(le32_to_cpu(disk_super->flags));
+	disk_super->flags = cpu_to_le32(sb_flags);
+}
+
+static unsigned long set_clean_shutdown(unsigned long flags)
+{
+	set_bit(CLEAN_SHUTDOWN, &flags);
+	return flags;
+}
+
+static unsigned long clear_clean_shutdown(unsigned long flags)
+{
+	clear_bit(CLEAN_SHUTDOWN, &flags);
+	return flags;
+}
+
+static void read_superblock_fields(struct dm_cache_metadata *cmd,
+				   struct cache_disk_superblock *disk_super)
+{
+	cmd->root = le64_to_cpu(disk_super->mapping_root);
+	cmd->hint_root = le64_to_cpu(disk_super->hint_root);
+	cmd->discard_root = le64_to_cpu(disk_super->discard_root);
+	cmd->discard_block_size = le64_to_cpu(disk_super->discard_block_size);
+	cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks));
+	cmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
+	cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks));
+	strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
+	cmd->policy_hint_size = le32_to_cpu(disk_super->policy_hint_size);
+
+	cmd->stats.read_hits = le32_to_cpu(disk_super->read_hits);
+	cmd->stats.read_misses = le32_to_cpu(disk_super->read_misses);
+	cmd->stats.write_hits = le32_to_cpu(disk_super->write_hits);
+	cmd->stats.write_misses = le32_to_cpu(disk_super->write_misses);
+
+	cmd->changed = false;
+}
+
+/*
+ * The mutator updates the superblock flags.
+ */
+static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
+				     flags_mutator mutator)
+{
+	int r;
+	struct cache_disk_superblock *disk_super;
+	struct dm_block *sblock;
+
+	r = superblock_lock(cmd, &sblock);
+	if (r)
+		return r;
+
+	disk_super = dm_block_data(sblock);
+	update_flags(disk_super, mutator);
+	read_superblock_fields(cmd, disk_super);
+
+	return dm_bm_flush_and_unlock(cmd->bm, sblock);
+}
+
+static int __begin_transaction(struct dm_cache_metadata *cmd)
+{
+	int r;
+	struct cache_disk_superblock *disk_super;
+	struct dm_block *sblock;
+
+	/*
+	 * We re-read the superblock every time.  Shouldn't need to do this
+	 * really.
+	 */
+	r = superblock_read_lock(cmd, &sblock);
+	if (r)
+		return r;
+
+	disk_super = dm_block_data(sblock);
+	read_superblock_fields(cmd, disk_super);
+	dm_bm_unlock(sblock);
+
+	return 0;
+}
+
+static int __commit_transaction(struct dm_cache_metadata *cmd,
+				flags_mutator mutator)
+{
+	int r;
+	size_t metadata_len;
+	struct cache_disk_superblock *disk_super;
+	struct dm_block *sblock;
+
+	/*
+	 * We need to know if the cache_disk_superblock exceeds a 512-byte sector.
+	 */
+	BUILD_BUG_ON(sizeof(struct cache_disk_superblock) > 512);
+
+	r = dm_bitset_flush(&cmd->discard_info, cmd->discard_root,
+			    &cmd->discard_root);
+	if (r)
+		return r;
+
+	r = dm_tm_pre_commit(cmd->tm);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	r = superblock_lock(cmd, &sblock);
+	if (r)
+		return r;
+
+	disk_super = dm_block_data(sblock);
+
+	if (mutator)
+		update_flags(disk_super, mutator);
+
+	disk_super->mapping_root = cpu_to_le64(cmd->root);
+	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
+	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
+	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
+	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
+	disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks));
+	strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
+
+	disk_super->read_hits = cpu_to_le32(cmd->stats.read_hits);
+	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
+	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
+	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);
+
+	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
+			    metadata_len);
+	if (r < 0) {
+		dm_bm_unlock(sblock);
+		return r;
+	}
+
+	return dm_tm_commit(cmd->tm, sblock);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * The mappings are held in a dm-array that has 64-bit values stored in
+ * little-endian format.  The index is the cblock, the high 48bits of the
+ * value are the oblock and the low 16 bit the flags.
+ */
+#define FLAGS_MASK ((1 << 16) - 1)
+
+static __le64 pack_value(dm_oblock_t block, unsigned flags)
+{
+	uint64_t value = from_oblock(block);
+	value <<= 16;
+	value = value | (flags & FLAGS_MASK);
+	return cpu_to_le64(value);
+}
+
+static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags)
+{
+	uint64_t value = le64_to_cpu(value_le);
+	uint64_t b = value >> 16;
+	*block = to_oblock(b);
+	*flags = value & FLAGS_MASK;
+}
+
+/*----------------------------------------------------------------*/
+
+struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
+						 sector_t data_block_size,
+						 bool may_format_device,
+						 size_t policy_hint_size)
+{
+	int r;
+	struct dm_cache_metadata *cmd;
+
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd) {
+		DMERR("could not allocate metadata struct");
+		return NULL;
+	}
+
+	init_rwsem(&cmd->root_lock);
+	cmd->bdev = bdev;
+	cmd->data_block_size = data_block_size;
+	cmd->cache_blocks = 0;
+	cmd->policy_hint_size = policy_hint_size;
+	cmd->changed = true;
+
+	r = __create_persistent_data_objects(cmd, may_format_device);
+	if (r) {
+		kfree(cmd);
+		return ERR_PTR(r);
+	}
+
+	r = __begin_transaction_flags(cmd, clear_clean_shutdown);
+	if (r < 0) {
+		dm_cache_metadata_close(cmd);
+		return ERR_PTR(r);
+	}
+
+	return cmd;
+}
+
+void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
+{
+	__destroy_persistent_data_objects(cmd);
+	kfree(cmd);
+}
+
+int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
+{
+	int r;
+	__le64 null_mapping = pack_value(0, 0);
+
+	down_write(&cmd->root_lock);
+	__dm_bless_for_disk(&null_mapping);
+	r = dm_array_resize(&cmd->info, cmd->root, from_cblock(cmd->cache_blocks),
+			    from_cblock(new_cache_size),
+			    &null_mapping, &cmd->root);
+	if (!r)
+		cmd->cache_blocks = new_cache_size;
+	cmd->changed = true;
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
+				   sector_t discard_block_size,
+				   dm_dblock_t new_nr_entries)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = dm_bitset_resize(&cmd->discard_info,
+			     cmd->discard_root,
+			     from_dblock(cmd->discard_nr_blocks),
+			     from_dblock(new_nr_entries),
+			     false, &cmd->discard_root);
+	if (!r) {
+		cmd->discard_block_size = discard_block_size;
+		cmd->discard_nr_blocks = new_nr_entries;
+	}
+
+	cmd->changed = true;
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+static int __set_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
+{
+	return dm_bitset_set_bit(&cmd->discard_info, cmd->discard_root,
+				 from_dblock(b), &cmd->discard_root);
+}
+
+static int __clear_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
+{
+	return dm_bitset_clear_bit(&cmd->discard_info, cmd->discard_root,
+				   from_dblock(b), &cmd->discard_root);
+}
+
+static int __is_discarded(struct dm_cache_metadata *cmd, dm_dblock_t b,
+			  bool *is_discarded)
+{
+	return dm_bitset_test_bit(&cmd->discard_info, cmd->discard_root,
+				  from_dblock(b), &cmd->discard_root,
+				  is_discarded);
+}
+
+static int __discard(struct dm_cache_metadata *cmd,
+		     dm_dblock_t dblock, bool discard)
+{
+	int r;
+
+	r = (discard ? __set_discard : __clear_discard)(cmd, dblock);
+	if (r)
+		return r;
+
+	cmd->changed = true;
+	return 0;
+}
+
+int dm_cache_set_discard(struct dm_cache_metadata *cmd,
+			 dm_dblock_t dblock, bool discard)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = __discard(cmd, dblock, discard);
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+static int __load_discards(struct dm_cache_metadata *cmd,
+			   load_discard_fn fn, void *context)
+{
+	int r = 0;
+	dm_block_t b;
+	bool discard;
+
+	for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) {
+		dm_dblock_t dblock = to_dblock(b);
+
+		if (cmd->clean_when_opened) {
+			r = __is_discarded(cmd, dblock, &discard);
+			if (r)
+				return r;
+		} else
+			discard = false;
+
+		r = fn(context, cmd->discard_block_size, dblock, discard);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
+int dm_cache_load_discards(struct dm_cache_metadata *cmd,
+			   load_discard_fn fn, void *context)
+{
+	int r;
+
+	down_read(&cmd->root_lock);
+	r = __load_discards(cmd, fn, context);
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd)
+{
+	dm_cblock_t r;
+
+	down_read(&cmd->root_lock);
+	r = cmd->cache_blocks;
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
+{
+	int r;
+	__le64 value = pack_value(0, 0);
+
+	__dm_bless_for_disk(&value);
+	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
+			       &value, &cmd->root);
+	if (r)
+		return r;
+
+	cmd->changed = true;
+	return 0;
+}
+
+int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = __remove(cmd, cblock);
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+static int __insert(struct dm_cache_metadata *cmd,
+		    dm_cblock_t cblock, dm_oblock_t oblock)
+{
+	int r;
+	__le64 value = pack_value(oblock, M_VALID);
+	__dm_bless_for_disk(&value);
+
+	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
+			       &value, &cmd->root);
+	if (r)
+		return r;
+
+	cmd->changed = true;
+	return 0;
+}
+
+int dm_cache_insert_mapping(struct dm_cache_metadata *cmd,
+			    dm_cblock_t cblock, dm_oblock_t oblock)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = __insert(cmd, cblock, oblock);
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+struct thunk {
+	load_mapping_fn fn;
+	void *context;
+
+	struct dm_cache_metadata *cmd;
+	bool respect_dirty_flags;
+	bool hints_valid;
+};
+
+static bool hints_array_initialized(struct dm_cache_metadata *cmd)
+{
+	return cmd->hint_root && cmd->policy_hint_size;
+}
+
+static bool hints_array_available(struct dm_cache_metadata *cmd,
+				  const char *policy_name)
+{
+	bool policy_names_match = !strncmp(cmd->policy_name, policy_name,
+					   sizeof(cmd->policy_name));
+
+	return cmd->clean_when_opened && policy_names_match &&
+		hints_array_initialized(cmd);
+}
+
+static int __load_mapping(void *context, uint64_t cblock, void *leaf)
+{
+	int r = 0;
+	bool dirty;
+	__le64 value;
+	__le32 hint_value = 0;
+	dm_oblock_t oblock;
+	unsigned flags;
+	struct thunk *thunk = context;
+	struct dm_cache_metadata *cmd = thunk->cmd;
+
+	memcpy(&value, leaf, sizeof(value));
+	unpack_value(value, &oblock, &flags);
+
+	if (flags & M_VALID) {
+		if (thunk->hints_valid) {
+			r = dm_array_get_value(&cmd->hint_info, cmd->hint_root,
+					       cblock, &hint_value);
+			if (r && r != -ENODATA)
+				return r;
+		}
+
+		dirty = thunk->respect_dirty_flags ? (flags & M_DIRTY) : true;
+		r = thunk->fn(thunk->context, oblock, to_cblock(cblock),
+			      dirty, le32_to_cpu(hint_value), thunk->hints_valid);
+	}
+
+	return r;
+}
+
+static int __load_mappings(struct dm_cache_metadata *cmd, const char *policy_name,
+			   load_mapping_fn fn, void *context)
+{
+	struct thunk thunk;
+
+	thunk.fn = fn;
+	thunk.context = context;
+
+	thunk.cmd = cmd;
+	thunk.respect_dirty_flags = cmd->clean_when_opened;
+	thunk.hints_valid = hints_array_available(cmd, policy_name);
+
+	return dm_array_walk(&cmd->info, cmd->root, __load_mapping, &thunk);
+}
+
+int dm_cache_load_mappings(struct dm_cache_metadata *cmd, const char *policy_name,
+			   load_mapping_fn fn, void *context)
+{
+	int r;
+
+	down_read(&cmd->root_lock);
+	r = __load_mappings(cmd, policy_name, fn, context);
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+static int __dump_mapping(void *context, uint64_t cblock, void *leaf)
+{
+	int r = 0;
+	__le64 value;
+	dm_oblock_t oblock;
+	unsigned flags;
+
+	memcpy(&value, leaf, sizeof(value));
+	unpack_value(value, &oblock, &flags);
+
+	return r;
+}
+
+static int __dump_mappings(struct dm_cache_metadata *cmd)
+{
+	return dm_array_walk(&cmd->info, cmd->root, __dump_mapping, NULL);
+}
+
+void dm_cache_dump(struct dm_cache_metadata *cmd)
+{
+	down_read(&cmd->root_lock);
+	__dump_mappings(cmd);
+	up_read(&cmd->root_lock);
+}
+
+int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
+{
+	int r;
+
+	down_read(&cmd->root_lock);
+	r = cmd->changed;
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty)
+{
+	int r;
+	unsigned flags;
+	dm_oblock_t oblock;
+	__le64 value;
+
+	r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(cblock), &value);
+	if (r)
+		return r;
+
+	unpack_value(value, &oblock, &flags);
+
+	if (((flags & M_DIRTY) && dirty) || (!(flags & M_DIRTY) && !dirty))
+		/* nothing to be done */
+		return 0;
+
+	value = pack_value(oblock, flags | (dirty ? M_DIRTY : 0));
+	__dm_bless_for_disk(&value);
+
+	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
+			       &value, &cmd->root);
+	if (r)
+		return r;
+
+	cmd->changed = true;
+	return 0;
+
+}
+
+int dm_cache_set_dirty(struct dm_cache_metadata *cmd,
+		       dm_cblock_t cblock, bool dirty)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = __dirty(cmd, cblock, dirty);
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
+				 struct dm_cache_statistics *stats)
+{
+	down_read(&cmd->root_lock);
+	memcpy(stats, &cmd->stats, sizeof(*stats));
+	up_read(&cmd->root_lock);
+}
+
+void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
+				 struct dm_cache_statistics *stats)
+{
+	down_write(&cmd->root_lock);
+	memcpy(&cmd->stats, stats, sizeof(*stats));
+	up_write(&cmd->root_lock);
+}
+
+int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown)
+{
+	int r;
+	flags_mutator mutator = (clean_shutdown ? set_clean_shutdown :
+				 clear_clean_shutdown);
+
+	down_write(&cmd->root_lock);
+	r = __commit_transaction(cmd, mutator);
+	if (r)
+		goto out;
+
+	r = __begin_transaction(cmd);
+
+out:
+	up_write(&cmd->root_lock);
+	return r;
+}
+
+int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
+					   dm_block_t *result)
+{
+	int r = -EINVAL;
+
+	down_read(&cmd->root_lock);
+	r = dm_sm_get_nr_free(cmd->metadata_sm, result);
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
+				   dm_block_t *result)
+{
+	int r = -EINVAL;
+
+	down_read(&cmd->root_lock);
+	r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
+	up_read(&cmd->root_lock);
+
+	return r;
+}
+
+/*----------------------------------------------------------------*/
+
+static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+{
+	int r;
+	__le32 value;
+	size_t hint_size;
+	const char *policy_name = dm_cache_policy_get_name(policy);
+
+	if (!policy_name[0] ||
+	    (strlen(policy_name) > sizeof(cmd->policy_name) - 1))
+		return -EINVAL;
+
+	if (strcmp(cmd->policy_name, policy_name)) {
+		strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
+
+		hint_size = dm_cache_policy_get_hint_size(policy);
+		if (!hint_size)
+			return 0; /* short-circuit hints initialization */
+		cmd->policy_hint_size = hint_size;
+
+		if (cmd->hint_root) {
+			r = dm_array_del(&cmd->hint_info, cmd->hint_root);
+			if (r)
+				return r;
+		}
+
+		r = dm_array_empty(&cmd->hint_info, &cmd->hint_root);
+		if (r)
+			return r;
+
+		value = cpu_to_le32(0);
+		__dm_bless_for_disk(&value);
+		r = dm_array_resize(&cmd->hint_info, cmd->hint_root, 0,
+				    from_cblock(cmd->cache_blocks),
+				    &value, &cmd->hint_root);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+{
+	int r;
+
+	down_write(&cmd->root_lock);
+	r = begin_hints(cmd, policy);
+	up_write(&cmd->root_lock);
+
+	return r;
+}
+
+static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
+		     uint32_t hint)
+{
+	int r;
+	__le32 value = cpu_to_le32(hint);
+	__dm_bless_for_disk(&value);
+
+	r = dm_array_set_value(&cmd->hint_info, cmd->hint_root,
+			       from_cblock(cblock), &value, &cmd->hint_root);
+	cmd->changed = true;
+
+	return r;
+}
+
+int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
+		       uint32_t hint)
+{
+	int r;
+
+	if (!hints_array_initialized(cmd))
+		return 0;
+
+	down_write(&cmd->root_lock);
+	r = save_hint(cmd, cblock, hint);
+	up_write(&cmd->root_lock);
+
+	return r;
+}

drivers/md/dm-cache-metadata.h

+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_CACHE_METADATA_H
+#define DM_CACHE_METADATA_H
+
+#include "dm-cache-block-types.h"
+#include "dm-cache-policy-internal.h"
+
+/*----------------------------------------------------------------*/
+
+#define DM_CACHE_METADATA_BLOCK_SIZE 4096
+
+/* FIXME: remove this restriction */
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about 16k metadata blocks.
+ */
+#define DM_CACHE_METADATA_MAX_SECTORS (255 * (1 << 14) * (DM_CACHE_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+
+/*
+ * A metadata device larger than 16GB triggers a warning.
+ */
+#define DM_CACHE_METADATA_MAX_SECTORS_WARNING (16 * (1024 * 1024 * 1024 >> SECTOR_SHIFT))
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Ext[234]-style compat feature flags.
+ *
+ * A new feature which old metadata will still be compatible with should
+ * define a DM_CACHE_FEATURE_COMPAT_* flag (rarely useful).
+ *
+ * A new feature that is not compatible with old code should define a
+ * DM_CACHE_FEATURE_INCOMPAT_* flag and guard the relevant code with
+ * that flag.
+ *
+ * A new feature that is not compatible with old code accessing the
+ * metadata RDWR should define a DM_CACHE_FEATURE_RO_COMPAT_* flag and
+ * guard the relevant code with that flag.
+ *
+ * As these various flags are defined they should be added to the
+ * following masks.
+ */
+#define DM_CACHE_FEATURE_COMPAT_SUPP	  0UL
+#define DM_CACHE_FEATURE_COMPAT_RO_SUPP	  0UL
+#define DM_CACHE_FEATURE_INCOMPAT_SUPP	  0UL
+
+/*
+ * Reopens or creates a new, empty metadata volume.
+ * Returns an ERR_PTR on failure.
+ */
+struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
+						 sector_t data_block_size,
+						 bool may_format_device,
+						 size_t policy_hint_size);
+
+void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
+
+/*
+ * The metadata needs to know how many cache blocks there are.  We don't
+ * care about the origin, assuming the core target is giving us valid
+ * origin blocks to map to.
+ */
+int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size);
+dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd);
+
+int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
+				   sector_t discard_block_size,
+				   dm_dblock_t new_nr_entries);
+
+typedef int (*load_discard_fn)(void *context, sector_t discard_block_size,
+			       dm_dblock_t dblock, bool discarded);
+int dm_cache_load_discards(struct dm_cache_metadata *cmd,
+			   load_discard_fn fn, void *context);
+
+int dm_cache_set_discard(struct dm_cache_metadata *cmd, dm_dblock_t dblock, bool discard);
+
+int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock);
+int dm_cache_insert_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock, dm_oblock_t oblock);
+int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd);
+
+typedef int (*load_mapping_fn)(void *context, dm_oblock_t oblock,
+			       dm_cblock_t cblock, bool dirty,
+			       uint32_t hint, bool hint_valid);
+int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
+			   const char *policy_name,
+			   load_mapping_fn fn,
+			   void *context);
+
+int dm_cache_set_dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty);
+
+struct dm_cache_statistics {
+	uint32_t read_hits;
+	uint32_t read_misses;
+	uint32_t write_hits;
+	uint32_t write_misses;
+};
+
+void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
+				 struct dm_cache_statistics *stats);
+void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
+				 struct dm_cache_statistics *stats);
+
+int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown);
+
+int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
+					   dm_block_t *result);
+
+int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
+				   dm_block_t *result);
+
+void dm_cache_dump(struct dm_cache_metadata *cmd);
+
+/*
+ * The policy is invited to save a 32bit hint value for every cblock (eg,
+ * for a hit count).  These are stored against the policy name.  If
+ * policies are changed, then hints will be lost.  If the machine crashes,
+ * hints will be lost.
+ *
+ * The hints are indexed by the cblock, but many policies will not
+ * neccessarily have a fast way of accessing efficiently via cblock.  So
+ * rather than querying the policy for each cblock, we let it walk its data
+ * structures and fill in the hints in whatever order it wishes.
+ */
+
+int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
+
+/*
+ * requests hints for every cblock and stores in the metadata device.
+ */
+int dm_cache_save_hint(struct dm_cache_metadata *cmd,
+		       dm_cblock_t cblock, uint32_t hint);
+
+/*----------------------------------------------------------------*/
+
+#endif /* DM_CACHE_METADATA_H */

drivers/md/dm-cache-policy-internal.h

+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_CACHE_POLICY_INTERNAL_H
+#define DM_CACHE_POLICY_INTERNAL_H
+
+#include "dm-cache-policy.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Little inline functions that simplify calling the policy methods.
+ */
+static inline int policy_map(struct dm_cache_policy *p, dm_oblock_t oblock,
+			     bool can_block, bool can_migrate, bool discarded_oblock,
+			     struct bio *bio, struct policy_result *result)
+{
+	return p->map(p, oblock, can_block, can_migrate, discarded_oblock, bio, result);
+}
+
+static inline int policy_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
+{
+	BUG_ON(!p->lookup);
+	return p->lookup(p, oblock, cblock);
+}
+
+static inline void policy_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
+{
+	if (p->set_dirty)
+		p->set_dirty(p, oblock);
+}
+
+static inline void policy_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
+{
+	if (p->clear_dirty)
+		p->clear_dirty(p, oblock);
+}
+
+static inline int policy_load_mapping(struct dm_cache_policy *p,
+				      dm_oblock_t oblock, dm_cblock_t cblock,
+				      uint32_t hint, bool hint_valid)
+{
+	return p->load_mapping(p, oblock, cblock, hint, hint_valid);
+}
+
+static inline int policy_walk_mappings(struct dm_cache_policy *p,
+				      policy_walk_fn fn, void *context)
+{
+	return p->walk_mappings ? p->walk_mappings(p, fn, context) : 0;
+}
+
+static inline int policy_writeback_work(struct dm_cache_policy *p,
+					dm_oblock_t *oblock,
+					dm_cblock_t *cblock)
+{
+	return p->writeback_work ? p->writeback_work(p, oblock, cblock) : -ENOENT;
+}
+
+static inline void policy_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
+{
+	return p->remove_mapping(p, oblock);
+}
+
+static inline void policy_force_mapping(struct dm_cache_policy *p,
+					dm_oblock_t current_oblock, dm_oblock_t new_oblock)
+{
+	return p->force_mapping(p, current_oblock, new_oblock);
+}
+
+static inline dm_cblock_t policy_residency(struct dm_cache_policy *p)
+{
+	return p->residency(p);
+}
+
+static inline void policy_tick(struct dm_cache_policy *p)
+{
+	if (p->tick)
+		return p->tick(p);
+}
+
+static inline int policy_emit_config_values(struct dm_cache_policy *p, char *result, unsigned maxlen)
+{
+	ssize_t sz = 0;
+	if (p->emit_config_values)
+		return p->emit_config_values(p, result, maxlen);
+
+	DMEMIT("0");
+	return 0;
+}
+
+static inline int policy_set_config_value(struct dm_cache_policy *p,
+					  const char *key, const char *value)
+{
+	return p->set_config_value ? p->set_config_value(p, key, value) : -EINVAL;
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Creates a new cache policy given a policy name, a cache size, an origin size and the block size.
+ */
+struct dm_cache_policy *dm_cache_policy_create(const char *name, dm_cblock_t cache_size,
+					       sector_t origin_size, sector_t block_size);
+
+/*
+ * Destroys the policy.  This drops references to the policy module as well
+ * as calling it's destroy method.  So always use this rather than calling
+ * the policy->destroy method directly.
+ */
+void dm_cache_policy_destroy(struct dm_cache_policy *p);
+
+/*
+ * In case we've forgotten.
+ */
+const char *dm_cache_policy_get_name(struct dm_cache_policy *p);
+
+size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p);
+
+/*----------------------------------------------------------------*/
+
+#endif /* DM_CACHE_POLICY_INTERNAL_H */

drivers/md/dm-cache-policy.c

+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-cache-policy-internal.h"
+#include "dm.h"
+
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/*----------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX "cache-policy"
+
+static DEFINE_SPINLOCK(register_lock);
+static LIST_HEAD(register_list);
+
+static struct dm_cache_policy_type *__find_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	list_for_each_entry(t, &register_list, list)
+		if (!strcmp(t->name, name))
+			return t;
+
+	return NULL;
+}
+
+static struct dm_cache_policy_type *__get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t = __find_policy(name);
+
+	if (t && !try_module_get(t->owner)) {
+		DMWARN("couldn't get module %s", name);
+		t = ERR_PTR(-EINVAL);
+	}
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	spin_lock(&register_lock);
+	t = __get_policy_once(name);
+	spin_unlock(&register_lock);
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	if (t)
+		return t;
+
+	request_module("dm-cache-%s", name);
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	return t;
+}
+
+static void put_policy(struct dm_cache_policy_type *t)
+{
+	module_put(t->owner);
+}
+
+int dm_cache_policy_register(struct dm_cache_policy_type *type)
+{
+	int r;
+
+	/* One size fits all for now */
+	if (type->hint_size != 0 && type->hint_size != 4) {
+		DMWARN("hint size must be 0 or 4 but %llu supplied.", (unsigned long long) type->hint_size);
+		return -EINVAL;
+	}
+
+	spin_lock(&register_lock);
+	if (__find_policy(type->name)) {
+		DMWARN("attempt to register policy under duplicate name %s", type->name);
+		r = -EINVAL;
+	} else {
+		list_add(&type->list, &register_list);
+		r = 0;
+	}
+	spin_unlock(&register_lock);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_register);
+
+void dm_cache_policy_unregister(struct dm_cache_policy_type *type)
+{
+	spin_lock(&register_lock);
+	list_del_init(&type->list);
+	spin_unlock(&register_lock);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_unregister);
+
+struct dm_cache_policy *dm_cache_policy_create(const char *name,
+					       dm_cblock_t cache_size,
+					       sector_t origin_size,
+					       sector_t cache_block_size)
+{
+	struct dm_cache_policy *p = NULL;
+	struct dm_cache_policy_type *type;
+
+	type = get_policy(name);
+	if (!type) {
+		DMWARN("unknown policy type");
+		return NULL;
+	}
+
+	p = type->create(cache_size, origin_size, cache_block_size);
+	if (!p) {
+		put_policy(type);
+		return NULL;
+	}
+	p->private = type;
+
+	return p;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_create);
+
+void dm_cache_policy_destroy(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	p->destroy(p);
+	put_policy(t);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_destroy);
+
+const char *dm_cache_policy_get_name(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->name;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_name);
+
+size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->hint_size;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_hint_size);
+
+/*----------------------------------------------------------------*/

drivers/md/dm-cache-policy.h

+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_CACHE_POLICY_H
+#define DM_CACHE_POLICY_H
+
+#include "dm-cache-block-types.h"
+
+#include <linux/device-mapper.h>
+
+/*----------------------------------------------------------------*/
+
+/* FIXME: make it clear which methods are optional.  Get debug policy to
+ * double check this at start.
+ */
+
+/*
+ * The cache policy makes the important decisions about which blocks get to
+ * live on the faster cache device.
+ *
+ * When the core target has to remap a bio it calls the 'map' method of the
+ * policy.  This returns an instruction telling the core target what to do.
+ *
+ * POLICY_HIT:
+ *   That block is in the cache.  Remap to the cache and carry on.
+ *
+ * POLICY_MISS:
+ *   This block is on the origin device.  Remap and carry on.
+ *
+ * POLICY_NEW:
+ *   This block is currently on the origin device, but the policy wants to
+ *   move it.  The core should:
+ *
+ *   - hold any further io to this origin block
+ *   - copy the origin to the given cache block
+ *   - release all the held blocks
+ *   - remap the original block to the cache
+ *
+ * POLICY_REPLACE:
+ *   This block is currently on the origin device.  The policy wants to
+ *   move it to the cache, with the added complication that the destination
+ *   cache block needs a writeback first.  The core should:
+ *
+ *   - hold any further io to this origin block
+ *   - hold any further io to the origin block that's being written back
+ *   - writeback
+ *   - copy new block to cache
+ *   - release held blocks
+ *   - remap bio to cache and reissue.
+ *
+ * Should the core run into trouble while processing a POLICY_NEW or
+ * POLICY_REPLACE instruction it will roll back the policies mapping using
+ * remove_mapping() or force_mapping().  These methods must not fail.  This
+ * approach avoids having transactional semantics in the policy (ie, the
+ * core informing the policy when a migration is complete), and hence makes
+ * it easier to write new policies.
+ *
+ * In general policy methods should never block, except in the case of the
+ * map function when can_migrate is set.  So be careful to implement using
+ * bounded, preallocated memory.
+ */
+enum policy_operation {
+	POLICY_HIT,
+	POLICY_MISS,
+	POLICY_NEW,
+	POLICY_REPLACE
+};
+
+/*
+ * This is the instruction passed back to the core target.
+ */
+struct policy_result {
+	enum policy_operation op;
+	dm_oblock_t old_oblock;	/* POLICY_REPLACE */
+	dm_cblock_t cblock;	/* POLICY_HIT, POLICY_NEW, POLICY_REPLACE */
+};
+
+typedef int (*policy_walk_fn)(void *context, dm_cblock_t cblock,
+			      dm_oblock_t oblock, uint32_t hint);
+
+/*
+ * The cache policy object.  Just a bunch of methods.  It is envisaged that
+ * this structure will be embedded in a bigger, policy specific structure
+ * (ie. use container_of()).
+ */
+struct dm_cache_policy {
+
+	/*
+	 * FIXME: make it clear which methods are optional, and which may
+	 * block.
+	 */
+
+	/*
+	 * Destroys this object.
+	 */
+	void (*destroy)(struct dm_cache_policy *p);
+
+	/*
+	 * See large comment above.
+	 *
+	 * oblock      - the origin block we're interested in.
+	 *
+	 * can_block - indicates whether the current thread is allowed to
+	 *             block.  -EWOULDBLOCK returned if it can't and would.
+	 *
+	 * can_migrate - gives permission for POLICY_NEW or POLICY_REPLACE
+	 *               instructions.  If denied and the policy would have
+	 *               returned one of these instructions it should
+	 *               return -EWOULDBLOCK.
+	 *
+	 * discarded_oblock - indicates whether the whole origin block is
+	 *               in a discarded state (FIXME: better to tell the
+	 *               policy about this sooner, so it can recycle that
+	 *               cache block if it wants.)
+	 * bio         - the bio that triggered this call.
+	 * result      - gets filled in with the instruction.
+	 *
+	 * May only return 0, or -EWOULDBLOCK (if !can_migrate)
+	 */
+	int (*map)(struct dm_cache_policy *p, dm_oblock_t oblock,
+		   bool can_block, bool can_migrate, bool discarded_oblock,
+		   struct bio *bio, struct policy_result *result);
+
+	/*
+	 * Sometimes we want to see if a block is in the cache, without
+	 * triggering any update of stats.  (ie. it's not a real hit).
+	 *
+	 * Must not block.
+	 *
+	 * Returns 1 iff in cache, 0 iff not, < 0 on error (-EWOULDBLOCK
+	 * would be typical).
+	 */
+	int (*lookup)(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock);
+
+	/*
+	 * oblock must be a mapped block.  Must not block.
+	 */
+	void (*set_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock);
+	void (*clear_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock);
+
+	/*
+	 * Called when a cache target is first created.  Used to load a
+	 * mapping from the metadata device into the policy.
+	 */
+	int (*load_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock,
+			    dm_cblock_t cblock, uint32_t hint, bool hint_valid);
+
+	int (*walk_mappings)(struct dm_cache_policy *p, policy_walk_fn fn,
+			     void *context);
+
+	/*
+	 * Override functions used on the error paths of the core target.
+	 * They must succeed.
+	 */
+	void (*remove_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock);
+	void (*force_mapping)(struct dm_cache_policy *p, dm_oblock_t current_oblock,
+			      dm_oblock_t new_oblock);
+
+	int (*writeback_work)(struct dm_cache_policy *p, dm_oblock_t *oblock, dm_cblock_t *cblock);
+
+
+	/*
+	 * How full is the cache?
+	 */
+	dm_cblock_t (*residency)(struct dm_cache_policy *p);
+
+	/*
+	 * Because of where we sit in the block layer, we can be asked to
+	 * map a lot of little bios that are all in the same block (no
+	 * queue merging has occurred).  To stop the policy being fooled by
+	 * these the core target sends regular tick() calls to the policy.
+	 * The policy should only count an entry as hit once per tick.
+	 */
+	void (*tick)(struct dm_cache_policy *p);
+
+	/*
+	 * Configuration.
+	 */
+	int (*emit_config_values)(struct dm_cache_policy *p,
+				  char *result, unsigned maxlen);
+	int (*set_config_value)(struct dm_cache_policy *p,
+				const char *key, const char *value);
+
+	/*
+	 * Book keeping ptr for the policy register, not for general use.
+	 */
+	void *private;
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * We maintain a little register of the different policy types.
+ */
+#define CACHE_POLICY_NAME_SIZE 16
+
+struct dm_cache_policy_type {
+	/* For use by the register code only. */
+	struct list_head list;
+
+	/*
+	 * Policy writers should fill in these fields.  The name field is
+	 * what gets passed on the target line to select your policy.
+	 */
+	char name[CACHE_POLICY_NAME_SIZE];
+
+	/*
+	 * Policies may store a hint for each each cache block.
+	 * Currently the size of this hint must be 0 or 4 bytes but we
+	 * expect to relax this in future.
+	 */
+	size_t hint_size;
+
+	struct module *owner;
+	struct dm_cache_policy *(*create)(dm_cblock_t cache_size,
+					  sector_t origin_size,
+					  sector_t block_size);
+};
+
+int dm_cache_policy_register(struct dm_cache_policy_type *type);
+void dm_cache_policy_unregister(struct dm_cache_policy_type *type);
+
+/*----------------------------------------------------------------*/
+
+#endif	/* DM_CACHE_POLICY_H */

drivers/md/dm-cache-target.c

+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm.h"
+#include "dm-bio-prison.h"
+#include "dm-cache-metadata.h"
+
+#include <linux/dm-io.h>
+#include <linux/dm-kcopyd.h>
+#include <linux/init.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#define DM_MSG_PREFIX "cache"
+
+DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(cache_copy_throttle,
+	"A percentage of time allocated for copying to and/or from cache");
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Glossary:
+ *
+ * oblock: index of an origin block
+ * cblock: index of a cache block
+ * promotion: movement of a block from origin to cache
+ * demotion: movement of a block from cache to origin
+ * migration: movement of a block between the origin and cache device,
+ *	      either direction
+ */
+
+/*----------------------------------------------------------------*/
+
+static size_t bitset_size_in_bytes(unsigned nr_entries)
+{
+	return sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG);
+}
+
+static unsigned long *alloc_bitset(unsigned nr_entries)
+{
+	size_t s = bitset_size_in_bytes(nr_entries);
+	return vzalloc(s);
+}
+
+static void clear_bitset(void *bitset, unsigned nr_entries)
+{
+	size_t s = bitset_size_in_bytes(nr_entries);
+	memset(bitset, 0, s);
+}
+
+static void free_bitset(unsigned long *bits)
+{
+	vfree(bits);
+}
+
+/*----------------------------------------------------------------*/
+
+#define PRISON_CELLS 1024
+#define MIGRATION_POOL_SIZE 128
+#define COMMIT_PERIOD HZ
+#define MIGRATION_COUNT_WINDOW 10
+
+/*
+ * The block size of the device holding cache data must be >= 32KB
+ */
+#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (32 * 1024 >> SECTOR_SHIFT)
+
+/*
+ * FIXME: the cache is read/write for the time being.
+ */
+enum cache_mode {
+	CM_WRITE,		/* metadata may be changed */
+	CM_READ_ONLY,		/* metadata may not be changed */
+};
+
+struct cache_features {
+	enum cache_mode mode;
+	bool write_through:1;
+};
+
+struct cache_stats {
+	atomic_t read_hit;
+	atomic_t read_miss;
+	atomic_t write_hit;
+	atomic_t write_miss;
+	atomic_t demotion;
+	atomic_t promotion;
+	atomic_t copies_avoided;
+	atomic_t cache_cell_clash;
+	atomic_t commit_count;
+	atomic_t discard_count;
+};
+
+struct cache {
+	struct dm_target *ti;
+	struct dm_target_callbacks callbacks;
+
+	/*
+	 * Metadata is written to this device.
+	 */
+	struct dm_dev *metadata_dev;
+
+	/*
+	 * The slower of the two data devices.  Typically a spindle.
+	 */
+	struct dm_dev *origin_dev;
+
+	/*
+	 * The faster of the two data devices.  Typically an SSD.
+	 */
+	struct dm_dev *cache_dev;
+
+	/*
+	 * Cache features such as write-through.
+	 */
+	struct cache_features features;
+
+	/*
+	 * Size of the origin device in _complete_ blocks and native sectors.
+	 */
+	dm_oblock_t origin_blocks;
+	sector_t origin_sectors;
+
+	/*
+	 * Size of the cache device in blocks.
+	 */
+	dm_cblock_t cache_size;
+
+	/*
+	 * Fields for converting from sectors to blocks.
+	 */
+	uint32_t sectors_per_block;
+	int sectors_per_block_shift;
+
+	struct dm_cache_metadata *cmd;
+
+	spinlock_t lock;
+	struct bio_list deferred_bios;
+	struct bio_list deferred_flush_bios;
+	struct list_head quiesced_migrations;
+	struct list_head completed_migrations;
+	struct list_head need_commit_migrations;
+	sector_t migration_threshold;
+	atomic_t nr_migrations;
+	wait_queue_head_t migration_wait;
+
+	/*
+	 * cache_size entries, dirty if set
+	 */
+	dm_cblock_t nr_dirty;
+	unsigned long *dirty_bitset;
+
+	/*
+	 * origin_blocks entries, discarded if set.
+	 */
+	sector_t discard_block_size; /* a power of 2 times sectors per block */
+	dm_dblock_t discard_nr_blocks;
+	unsigned long *discard_bitset;
+
+	struct dm_kcopyd_client *copier;
+	struct workqueue_struct *wq;
+	struct work_struct worker;
+
+	struct delayed_work waker;
+	unsigned long last_commit_jiffies;
+
+	struct dm_bio_prison *prison;
+	struct dm_deferred_set *all_io_ds;
+
+	mempool_t *migration_pool;
+	struct dm_cache_migration *next_migration;
+
+	struct dm_cache_policy *policy;
+	unsigned policy_nr_args;
+
+	bool need_tick_bio:1;
+	bool sized:1;
+	bool quiescing:1;
+	bool commit_requested:1;
+	bool loaded_mappings:1;
+	bool loaded_discards:1;
+
+	struct cache_stats stats;
+
+	/*
+	 * Rather than reconstructing the table line for the status we just
+	 * save it and regurgitate.
+	 */
+	unsigned nr_ctr_args;
+	const char **ctr_args;
+};
+
+struct per_bio_data {
+	bool tick:1;
+	unsigned req_nr:2;
+	struct dm_deferred_entry *all_io_entry;
+};
+
+struct dm_cache_migration {
+	struct list_head list;
+	struct cache *cache;
+
+	unsigned long start_jiffies;
+	dm_oblock_t old_oblock;
+	dm_oblock_t new_oblock;
+	dm_cblock_t cblock;
+
+	bool err:1;
+	bool writeback:1;
+	bool demote:1;
+	bool promote:1;
+
+	struct dm_bio_prison_cell *old_ocell;
+	struct dm_bio_prison_cell *new_ocell;
+};
+
+/*
+ * Processing a bio in the worker thread may require these memory
+ * allocations.  We prealloc to avoid deadlocks (the same worker thread
+ * frees them back to the mempool).
+ */
+struct prealloc {
+	struct dm_cache_migration *mg;
+	struct dm_bio_prison_cell *cell1;
+	struct dm_bio_prison_cell *cell2;
+};
+
+static void wake_worker(struct cache *cache)
+{
+	queue_work(cache->wq, &cache->worker);
+}
+
+/*----------------------------------------------------------------*/
+
+static struct dm_bio_prison_cell *alloc_prison_cell(struct cache *cache)
+{
+	/* FIXME: change to use a local slab. */
+	return dm_bio_prison_alloc_cell(cache->prison, GFP_NOWAIT);
+}
+
+static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cell)
+{
+	dm_bio_prison_free_cell(cache->prison, cell);
+}
+
+static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
+{
+	if (!p->mg) {
+		p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+		if (!p->mg)
+			return -ENOMEM;
+	}
+
+	if (!p->cell1) {
+		p->cell1 = alloc_prison_cell(cache);
+		if (!p->cell1)
+			return -ENOMEM;
+	}
+
+	if (!p->cell2) {
+		p->cell2 = alloc_prison_cell(cache);
+		if (!p->cell2)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void prealloc_free_structs(struct cache *cache, struct prealloc *p)
+{
+	if (p->cell2)
+		free_prison_cell(cache, p->cell2);
+
+	if (p->cell1)
+		free_prison_cell(cache, p->cell1);
+
+	if (p->mg)
+		mempool_free(p->mg, cache->migration_pool);
+}
+
+static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p)
+{
+	struct dm_cache_migration *mg = p->mg;
+
+	BUG_ON(!mg);
+	p->mg = NULL;
+
+	return mg;
+}
+
+/*
+ * You must have a cell within the prealloc struct to return.  If not this
+ * function will BUG() rather than returning NULL.
+ */
+static struct dm_bio_prison_cell *prealloc_get_cell(struct prealloc *p)
+{
+	struct dm_bio_prison_cell *r = NULL;
+
+	if (p->cell1) {
+		r = p->cell1;
+		p->cell1 = NULL;
+
+	} else if (p->cell2) {
+		r = p->cell2;
+		p->cell2 = NULL;
+	} else
+		BUG();
+
+	return r;
+}
+
+/*
+ * You can't have more than two cells in a prealloc struct.  BUG() will be
+ * called if you try and overfill.
+ */
+static void prealloc_put_cell(struct prealloc *p, struct dm_bio_prison_cell *cell)
+{
+	if (!p->cell2)
+		p->cell2 = cell;
+
+	else if (!p->cell1)
+		p->cell1 = cell;
+
+	else
+		BUG();
+}
+
+/*----------------------------------------------------------------*/
+
+static void build_key(dm_oblock_t oblock, struct dm_cell_key *key)
+{
+	key->virtual = 0;
+	key->dev = 0;
+	key->block = from_oblock(oblock);
+}
+
+/*
+ * The caller hands in a preallocated cell, and a free function for it.
+ * The cell will be freed if there's an error, or if it wasn't used because
+ * a cell with that key already exists.
+ */
+typedef void (*cell_free_fn)(void *context, struct dm_bio_prison_cell *cell);
+
+static int bio_detain(struct cache *cache, dm_oblock_t oblock,
+		      struct bio *bio, struct dm_bio_prison_cell *cell_prealloc,
+		      cell_free_fn free_fn, void *free_context,
+		      struct dm_bio_prison_cell **cell_result)
+{
+	int r;
+	struct dm_cell_key key;
+
+	build_key(oblock, &key);
+	r = dm_bio_detain(cache->prison, &key, bio, cell_prealloc, cell_result);
+	if (r)
+		free_fn(free_context, cell_prealloc);
+
+	return r;
+}
+
+static int get_cell(struct cache *cache,
+		    dm_oblock_t oblock,
+		    struct prealloc *structs,
+		    struct dm_bio_prison_cell **cell_result)
+{
+	int r;
+	struct dm_cell_key key;
+	struct dm_bio_prison_cell *cell_prealloc;
+
+	cell_prealloc = prealloc_get_cell(structs);
+
+	build_key(oblock, &key);
+	r = dm_get_cell(cache->prison, &key, cell_prealloc, cell_result);
+	if (r)
+		prealloc_put_cell(structs, cell_prealloc);
+
+	return r;
+}
+
+ /*----------------------------------------------------------------*/
+
+static bool is_dirty(struct cache *cache, dm_cblock_t b)
+{
+	return test_bit(from_cblock(b), cache->dirty_bitset);
+}
+
+static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
+{
+	if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) {
+		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1);
+		policy_set_dirty(cache->policy, oblock);
+	}
+}
+
+static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
+{
+	if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) {
+		policy_clear_dirty(cache->policy, oblock);
+		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1);
+		if (!from_cblock(cache->nr_dirty))
+			dm_table_event(cache->ti->table);
+	}
+}
+
+/*----------------------------------------------------------------*/
+static bool block_size_is_power_of_two(struct cache *cache)
+{
+	return cache->sectors_per_block_shift >= 0;
+}
+
+static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
+{
+	sector_t discard_blocks = cache->discard_block_size;
+	dm_block_t b = from_oblock(oblock);
+
+	if (!block_size_is_power_of_two(cache))
+		(void) sector_div(discard_blocks, cache->sectors_per_block);
+	else
+		discard_blocks >>= cache->sectors_per_block_shift;
+
+	(void) sector_div(b, discard_blocks);
+
+	return to_dblock(b);
+}
+
+static void set_discard(struct cache *cache, dm_dblock_t b)
+{
+	unsigned long flags;
+
+	atomic_inc(&cache->stats.discard_count);
+
+	spin_lock_irqsave(&cache->lock, flags);
+	set_bit(from_dblock(b), cache->discard_bitset);
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static void clear_discard(struct cache *cache, dm_dblock_t b)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	clear_bit(from_dblock(b), cache->discard_bitset);
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static bool is_discarded(struct cache *cache, dm_dblock_t b)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	r = test_bit(from_dblock(b), cache->discard_bitset);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return r;
+}
+
+static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
+		     cache->discard_bitset);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return r;
+}
+
+/*----------------------------------------------------------------*/
+
+static void load_stats(struct cache *cache)
+{
+	struct dm_cache_statistics stats;
+
+	dm_cache_metadata_get_stats(cache->cmd, &stats);
+	atomic_set(&cache->stats.read_hit, stats.read_hits);
+	atomic_set(&cache->stats.read_miss, stats.read_misses);
+	atomic_set(&cache->stats.write_hit, stats.write_hits);
+	atomic_set(&cache->stats.write_miss, stats.write_misses);
+}
+
+static void save_stats(struct cache *cache)
+{
+	struct dm_cache_statistics stats;
+
+	stats.read_hits = atomic_read(&cache->stats.read_hit);
+	stats.read_misses = atomic_read(&cache->stats.read_miss);
+	stats.write_hits = atomic_read(&cache->stats.write_hit);
+	stats.write_misses = atomic_read(&cache->stats.write_miss);
+
+	dm_cache_metadata_set_stats(cache->cmd, &stats);
+}
+
+/*----------------------------------------------------------------
+ * Per bio data
+ *--------------------------------------------------------------*/
+static struct per_bio_data *get_per_bio_data(struct bio *bio)
+{
+	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
+	BUG_ON(!pb);
+	return pb;
+}
+
+static struct per_bio_data *init_per_bio_data(struct bio *bio)
+{
+	struct per_bio_data *pb = get_per_bio_data(bio);
+
+	pb->tick = false;
+	pb->req_nr = dm_bio_get_target_bio_nr(bio);
+	pb->all_io_entry = NULL;
+
+	return pb;
+}
+
+/*----------------------------------------------------------------
+ * Remapping
+ *--------------------------------------------------------------*/
+static void remap_to_origin(struct cache *cache, struct bio *bio)
+{
+	bio->bi_bdev = cache->origin_dev->bdev;
+}
+
+static void remap_to_cache(struct cache *cache, struct bio *bio,
+			   dm_cblock_t cblock)
+{
+	sector_t bi_sector = bio->bi_sector;
+
+	bio->bi_bdev = cache->cache_dev->bdev;
+	if (!block_size_is_power_of_two(cache))
+		bio->bi_sector = (from_cblock(cblock) * cache->sectors_per_block) +
+				sector_div(bi_sector, cache->sectors_per_block);
+	else
+		bio->bi_sector = (from_cblock(cblock) << cache->sectors_per_block_shift) |
+				(bi_sector & (cache->sectors_per_block - 1));
+}
+
+static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
+{
+	unsigned long flags;
+	struct per_bio_data *pb = get_per_bio_data(bio);
+
+	spin_lock_irqsave(&cache->lock, flags);
+	if (cache->need_tick_bio &&
+	    !(bio->bi_rw & (REQ_FUA | REQ_FLUSH | REQ_DISCARD))) {
+		pb->tick = true;
+		cache->need_tick_bio = false;
+	}
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
+				  dm_oblock_t oblock)
+{
+	check_if_tick_bio_needed(cache, bio);
+	remap_to_origin(cache, bio);
+	if (bio_data_dir(bio) == WRITE)
+		clear_discard(cache, oblock_to_dblock(cache, oblock));
+}
+
+static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
+				 dm_oblock_t oblock, dm_cblock_t cblock)
+{
+	remap_to_cache(cache, bio, cblock);
+	if (bio_data_dir(bio) == WRITE) {
+		set_dirty(cache, oblock, cblock);
+		clear_discard(cache, oblock_to_dblock(cache, oblock));
+	}
+}
+
+static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
+{
+	sector_t block_nr = bio->bi_sector;
+
+	if (!block_size_is_power_of_two(cache))
+		(void) sector_div(block_nr, cache->sectors_per_block);
+	else
+		block_nr >>= cache->sectors_per_block_shift;
+
+	return to_oblock(block_nr);
+}
+
+static int bio_triggers_commit(struct cache *cache, struct bio *bio)
+{
+	return bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+}
+
+static void issue(struct cache *cache, struct bio *bio)
+{
+	unsigned long flags;
+
+	if (!bio_triggers_commit(cache, bio)) {
+		generic_make_request(bio);
+		return;
+	}
+
+	/*
+	 * Batch together any bios that trigger commits and then issue a
+	 * single commit for them in do_worker().
+	 */
+	spin_lock_irqsave(&cache->lock, flags);
+	cache->commit_requested = true;
+	bio_list_add(&cache->deferred_flush_bios, bio);
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+/*----------------------------------------------------------------
+ * Migration processing
+ *
+ * Migration covers moving data from the origin device to the cache, or
+ * vice versa.
+ *--------------------------------------------------------------*/
+static void free_migration(struct dm_cache_migration *mg)
+{
+	mempool_free(mg, mg->cache->migration_pool);
+}
+
+static void inc_nr_migrations(struct cache *cache)
+{
+	atomic_inc(&cache->nr_migrations);
+}
+
+static void dec_nr_migrations(struct cache *cache)
+{
+	atomic_dec(&cache->nr_migrations);
+
+	/*
+	 * Wake the worker in case we're suspending the target.
+	 */
+	wake_up(&cache->migration_wait);
+}
+
+static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
+			 bool holder)
+{
+	(holder ? dm_cell_release : dm_cell_release_no_holder)
+		(cache->prison, cell, &cache->deferred_bios);
+	free_prison_cell(cache, cell);
+}
+
+static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
+		       bool holder)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	__cell_defer(cache, cell, holder);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wake_worker(cache);
+}
+
+static void cleanup_migration(struct dm_cache_migration *mg)
+{
+	dec_nr_migrations(mg->cache);
+	free_migration(mg);
+}
+
+static void migration_failure(struct dm_cache_migration *mg)
+{
+	struct cache *cache = mg->cache;
+
+	if (mg->writeback) {
+		DMWARN_LIMIT("writeback failed; couldn't copy block");
+		set_dirty(cache, mg->old_oblock, mg->cblock);
+		cell_defer(cache, mg->old_ocell, false);
+
+	} else if (mg->demote) {
+		DMWARN_LIMIT("demotion failed; couldn't copy block");
+		policy_force_mapping(cache->policy, mg->new_oblock, mg->old_oblock);
+
+		cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1);
+		if (mg->promote)
+			cell_defer(cache, mg->new_ocell, 1);
+	} else {
+		DMWARN_LIMIT("promotion failed; couldn't copy block");
+		policy_remove_mapping(cache->policy, mg->new_oblock);
+		cell_defer(cache, mg->new_ocell, 1);
+	}
+
+	cleanup_migration(mg);
+}
+
+static void migration_success_pre_commit(struct dm_cache_migration *mg)
+{
+	unsigned long flags;
+	struct cache *cache = mg->cache;
+
+	if (mg->writeback) {
+		cell_defer(cache, mg->old_ocell, false);
+		clear_dirty(cache, mg->old_oblock, mg->cblock);
+		cleanup_migration(mg);
+		return;
+
+	} else if (mg->demote) {
+		if (dm_cache_remove_mapping(cache->cmd, mg->cblock)) {
+			DMWARN_LIMIT("demotion failed; couldn't update on disk metadata");
+			policy_force_mapping(cache->policy, mg->new_oblock,
+					     mg->old_oblock);
+			if (mg->promote)
+				cell_defer(cache, mg->new_ocell, true);
+			cleanup_migration(mg);
+			return;
+		}
+	} else {
+		if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) {
+			DMWARN_LIMIT("promotion failed; couldn't update on disk metadata");
+			policy_remove_mapping(cache->policy, mg->new_oblock);
+			cleanup_migration(mg);
+			return;
+		}
+	}
+
+	spin_lock_irqsave(&cache->lock, flags);
+	list_add_tail(&mg->list, &cache->need_commit_migrations);
+	cache->commit_requested = true;
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static void migration_success_post_commit(struct dm_cache_migration *mg)
+{
+	unsigned long flags;
+	struct cache *cache = mg->cache;
+
+	if (mg->writeback) {
+		DMWARN("writeback unexpectedly triggered commit");
+		return;
+
+	} else if (mg->demote) {
+		cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1);
+
+		if (mg->promote) {
+			mg->demote = false;
+
+			spin_lock_irqsave(&cache->lock, flags);
+			list_add_tail(&mg->list, &cache->quiesced_migrations);
+			spin_unlock_irqrestore(&cache->lock, flags);
+
+		} else
+			cleanup_migration(mg);
+
+	} else {
+		cell_defer(cache, mg->new_ocell, true);
+		clear_dirty(cache, mg->new_oblock, mg->cblock);
+		cleanup_migration(mg);
+	}
+}
+
+static void copy_complete(int read_err, unsigned long write_err, void *context)
+{
+	unsigned long flags;
+	struct dm_cache_migration *mg = (struct dm_cache_migration *) context;
+	struct cache *cache = mg->cache;
+
+	if (read_err || write_err)
+		mg->err = true;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	list_add_tail(&mg->list, &cache->completed_migrations);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wake_worker(cache);
+}
+
+static void issue_copy_real(struct dm_cache_migration *mg)
+{
+	int r;
+	struct dm_io_region o_region, c_region;
+	struct cache *cache = mg->cache;
+
+	o_region.bdev = cache->origin_dev->bdev;
+	o_region.count = cache->sectors_per_block;
+
+	c_region.bdev = cache->cache_dev->bdev;
+	c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+	c_region.count = cache->sectors_per_block;
+
+	if (mg->writeback || mg->demote) {
+		/* demote */
+		o_region.sector = from_oblock(mg->old_oblock) * cache->sectors_per_block;
+		r = dm_kcopyd_copy(cache->copier, &c_region, 1, &o_region, 0, copy_complete, mg);
+	} else {
+		/* promote */
+		o_region.sector = from_oblock(mg->new_oblock) * cache->sectors_per_block;
+		r = dm_kcopyd_copy(cache->copier, &o_region, 1, &c_region, 0, copy_complete, mg);
+	}
+
+	if (r < 0)
+		migration_failure(mg);
+}
+
+static void avoid_copy(struct dm_cache_migration *mg)
+{
+	atomic_inc(&mg->cache->stats.copies_avoided);
+	migration_success_pre_commit(mg);
+}
+
+static void issue_copy(struct dm_cache_migration *mg)
+{
+	bool avoid;
+	struct cache *cache = mg->cache;
+
+	if (mg->writeback || mg->demote)
+		avoid = !is_dirty(cache, mg->cblock) ||
+			is_discarded_oblock(cache, mg->old_oblock);
+	else
+		avoid = is_discarded_oblock(cache, mg->new_oblock);
+
+	avoid ? avoid_copy(mg) : issue_copy_real(mg);
+}
+
+static void complete_migration(struct dm_cache_migration *mg)
+{
+	if (mg->err)
+		migration_failure(mg);
+	else
+		migration_success_pre_commit(mg);
+}
+
+static void process_migrations(struct cache *cache, struct list_head *head,
+			       void (*fn)(struct dm_cache_migration *))
+{
+	unsigned long flags;
+	struct list_head list;
+	struct dm_cache_migration *mg, *tmp;
+
+	INIT_LIST_HEAD(&list);
+	spin_lock_irqsave(&cache->lock, flags);
+	list_splice_init(head, &list);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	list_for_each_entry_safe(mg, tmp, &list, list)
+		fn(mg);
+}
+
+static void __queue_quiesced_migration(struct dm_cache_migration *mg)
+{
+	list_add_tail(&mg->list, &mg->cache->quiesced_migrations);
+}
+
+static void queue_quiesced_migration(struct dm_cache_migration *mg)
+{
+	unsigned long flags;
+	struct cache *cache = mg->cache;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	__queue_quiesced_migration(mg);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wake_worker(cache);
+}
+
+static void queue_quiesced_migrations(struct cache *cache, struct list_head *work)
+{
+	unsigned long flags;
+	struct dm_cache_migration *mg, *tmp;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	list_for_each_entry_safe(mg, tmp, work, list)
+		__queue_quiesced_migration(mg);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wake_worker(cache);
+}
+
+static void check_for_quiesced_migrations(struct cache *cache,
+					  struct per_bio_data *pb)
+{
+	struct list_head work;
+
+	if (!pb->all_io_entry)
+		return;
+
+	INIT_LIST_HEAD(&work);
+	if (pb->all_io_entry)
+		dm_deferred_entry_dec(pb->all_io_entry, &work);
+
+	if (!list_empty(&work))
+		queue_quiesced_migrations(cache, &work);
+}
+
+static void quiesce_migration(struct dm_cache_migration *mg)
+{
+	if (!dm_deferred_set_add_work(mg->cache->all_io_ds, &mg->list))
+		queue_quiesced_migration(mg);
+}
+
+static void promote(struct cache *cache, struct prealloc *structs,
+		    dm_oblock_t oblock, dm_cblock_t cblock,
+		    struct dm_bio_prison_cell *cell)
+{
+	struct dm_cache_migration *mg = prealloc_get_migration(structs);
+
+	mg->err = false;
+	mg->writeback = false;
+	mg->demote = false;
+	mg->promote = true;
+	mg->cache = cache;
+	mg->new_oblock = oblock;
+	mg->cblock = cblock;
+	mg->old_ocell = NULL;
+	mg->new_ocell = cell;
+	mg->start_jiffies = jiffies;
+
+	inc_nr_migrations(cache);
+	quiesce_migration(mg);
+}
+
+static void writeback(struct cache *cache, struct prealloc *structs,
+		      dm_oblock_t oblock, dm_cblock_t cblock,
+		      struct dm_bio_prison_cell *cell)
+{
+	struct dm_cache_migration *mg = prealloc_get_migration(structs);
+
+	mg->err = false;
+	mg->writeback = true;
+	mg->demote = false;
+	mg->promote = false;
+	mg->cache = cache;
+	mg->old_oblock = oblock;
+	mg->cblock = cblock;
+	mg->old_ocell = cell;
+	mg->new_ocell = NULL;
+	mg->start_jiffies = jiffies;
+
+	inc_nr_migrations(cache);
+	quiesce_migration(mg);
+}
+
+static void demote_then_promote(struct cache *cache, struct prealloc *structs,
+				dm_oblock_t old_oblock, dm_oblock_t new_oblock,
+				dm_cblock_t cblock,
+				struct dm_bio_prison_cell *old_ocell,
+				struct dm_bio_prison_cell *new_ocell)
+{
+	struct dm_cache_migration *mg = prealloc_get_migration(structs);
+
+	mg->err = false;
+	mg->writeback = false;
+	mg->demote = true;
+	mg->promote = true;
+	mg->cache = cache;
+	mg->old_oblock = old_oblock;
+	mg->new_oblock = new_oblock;
+	mg->cblock = cblock;
+	mg->old_ocell = old_ocell;
+	mg->new_ocell = new_ocell;
+	mg->start_jiffies = jiffies;
+
+	inc_nr_migrations(cache);
+	quiesce_migration(mg);
+}
+
+/*----------------------------------------------------------------
+ * bio processing
+ *--------------------------------------------------------------*/
+static void defer_bio(struct cache *cache, struct bio *bio)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	bio_list_add(&cache->deferred_bios, bio);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	wake_worker(cache);
+}
+
+static void process_flush_bio(struct cache *cache, struct bio *bio)
+{
+	struct per_bio_data *pb = get_per_bio_data(bio);
+
+	BUG_ON(bio->bi_size);
+	if (!pb->req_nr)
+		remap_to_origin(cache, bio);
+	else
+		remap_to_cache(cache, bio, 0);
+
+	issue(cache, bio);
+}
+
+/*
+ * People generally discard large parts of a device, eg, the whole device
+ * when formatting.  Splitting these large discards up into cache block
+ * sized ios and then quiescing (always neccessary for discard) takes too
+ * long.
+ *
+ * We keep it simple, and allow any size of discard to come in, and just
+ * mark off blocks on the discard bitset.  No passdown occurs!
+ *
+ * To implement passdown we need to change the bio_prison such that a cell
+ * can have a key that spans many blocks.
+ */
+static void process_discard_bio(struct cache *cache, struct bio *bio)
+{
+	dm_block_t start_block = dm_sector_div_up(bio->bi_sector,
+						  cache->discard_block_size);
+	dm_block_t end_block = bio->bi_sector + bio_sectors(bio);
+	dm_block_t b;
+
+	(void) sector_div(end_block, cache->discard_block_size);
+
+	for (b = start_block; b < end_block; b++)
+		set_discard(cache, to_dblock(b));
+
+	bio_endio(bio, 0);
+}
+
+static bool spare_migration_bandwidth(struct cache *cache)
+{
+	sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) *
+		cache->sectors_per_block;
+	return current_volume < cache->migration_threshold;
+}
+
+static bool is_writethrough_io(struct cache *cache, struct bio *bio,
+			       dm_cblock_t cblock)
+{
+	return bio_data_dir(bio) == WRITE &&
+		cache->features.write_through && !is_dirty(cache, cblock);
+}
+
+static void inc_hit_counter(struct cache *cache, struct bio *bio)
+{
+	atomic_inc(bio_data_dir(bio) == READ ?
+		   &cache->stats.read_hit : &cache->stats.write_hit);
+}
+
+static void inc_miss_counter(struct cache *cache, struct bio *bio)
+{
+	atomic_inc(bio_data_dir(bio) == READ ?
+		   &cache->stats.read_miss : &cache->stats.write_miss);
+}
+
+static void process_bio(struct cache *cache, struct prealloc *structs,
+			struct bio *bio)
+{
+	int r;
+	bool release_cell = true;
+	dm_oblock_t block = get_bio_block(cache, bio);
+	struct dm_bio_prison_cell *cell_prealloc, *old_ocell, *new_ocell;
+	struct policy_result lookup_result;
+	struct per_bio_data *pb = get_per_bio_data(bio);
+	bool discarded_block = is_discarded_oblock(cache, block);
+	bool can_migrate = discarded_block || spare_migration_bandwidth(cache);
+
+	/*
+	 * Check to see if that block is currently migrating.
+	 */
+	cell_prealloc = prealloc_get_cell(structs);
+	r = bio_detain(cache, block, bio, cell_prealloc,
+		       (cell_free_fn) prealloc_put_cell,
+		       structs, &new_ocell);
+	if (r > 0)
+		return;
+
+	r = policy_map(cache->policy, block, true, can_migrate, discarded_block,
+		       bio, &lookup_result);
+
+	if (r == -EWOULDBLOCK)
+		/* migration has been denied */
+		lookup_result.op = POLICY_MISS;
+
+	switch (lookup_result.op) {
+	case POLICY_HIT:
+		inc_hit_counter(cache, bio);
+		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
+
+		if (is_writethrough_io(cache, bio, lookup_result.cblock)) {
+			/*
+			 * No need to mark anything dirty in write through mode.
+			 */
+			pb->req_nr == 0 ?
+				remap_to_cache(cache, bio, lookup_result.cblock) :
+				remap_to_origin_clear_discard(cache, bio, block);
+		} else
+			remap_to_cache_dirty(cache, bio, block, lookup_result.cblock);
+
+		issue(cache, bio);
+		break;
+
+	case POLICY_MISS:
+		inc_miss_counter(cache, bio);
+		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
+
+		if (pb->req_nr != 0) {
+			/*
+			 * This is a duplicate writethrough io that is no
+			 * longer needed because the block has been demoted.
+			 */
+			bio_endio(bio, 0);
+		} else {
+			remap_to_origin_clear_discard(cache, bio, block);
+			issue(cache, bio);
+		}
+		break;
+
+	case POLICY_NEW:
+		atomic_inc(&cache->stats.promotion);
+		promote(cache, structs, block, lookup_result.cblock, new_ocell);
+		release_cell = false;
+		break;
+
+	case POLICY_REPLACE:
+		cell_prealloc = prealloc_get_cell(structs);
+		r = bio_detain(cache, lookup_result.old_oblock, bio, cell_prealloc,
+			       (cell_free_fn) prealloc_put_cell,
+			       structs, &old_ocell);
+		if (r > 0) {
+			/*
+			 * We have to be careful to avoid lock inversion of
+			 * the cells.  So we back off, and wait for the
+			 * old_ocell to become free.
+			 */
+			policy_force_mapping(cache->policy, block,
+					     lookup_result.old_oblock);
+			atomic_inc(&cache->stats.cache_cell_clash);
+			break;
+		}
+		atomic_inc(&cache->stats.demotion);
+		atomic_inc(&cache->stats.promotion);
+
+		demote_then_promote(cache, structs, lookup_result.old_oblock,
+				    block, lookup_result.cblock,
+				    old_ocell, new_ocell);
+		release_cell = false;
+		break;
+
+	default:
+		DMERR_LIMIT("%s: erroring bio, unknown policy op: %u", __func__,
+			    (unsigned) lookup_result.op);
+		bio_io_error(bio);
+	}
+
+	if (release_cell)
+		cell_defer(cache, new_ocell, false);
+}
+
+static int need_commit_due_to_time(struct cache *cache)
+{
+	return jiffies < cache->last_commit_jiffies ||
+	       jiffies > cache->last_commit_jiffies + COMMIT_PERIOD;
+}
+
+static int commit_if_needed(struct cache *cache)
+{
+	if (dm_cache_changed_this_transaction(cache->cmd) &&
+	    (cache->commit_requested || need_commit_due_to_time(cache))) {
+		atomic_inc(&cache->stats.commit_count);
+		cache->last_commit_jiffies = jiffies;
+		cache->commit_requested = false;
+		return dm_cache_commit(cache->cmd, false);
+	}
+
+	return 0;
+}
+
+static void process_deferred_bios(struct cache *cache)
+{
+	unsigned long flags;
+	struct bio_list bios;
+	struct bio *bio;
+	struct prealloc structs;
+
+	memset(&structs, 0, sizeof(structs));
+	bio_list_init(&bios);
+
+	spin_lock_irqsave(&cache->lock, flags);
+	bio_list_merge(&bios, &cache->deferred_bios);
+	bio_list_init(&cache->deferred_bios);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	while (!bio_list_empty(&bios)) {
+		/*
+		 * If we've got no free migration structs, and processing
+		 * this bio might require one, we pause until there are some
+		 * prepared mappings to process.
+		 */
+		if (prealloc_data_structs(cache, &structs)) {
+			spin_lock_irqsave(&cache->lock, flags);
+			bio_list_merge(&cache->deferred_bios, &bios);
+			spin_unlock_irqrestore(&cache->lock, flags);
+			break;
+		}
+
+		bio = bio_list_pop(&bios);
+
+		if (bio->bi_rw & REQ_FLUSH)
+			process_flush_bio(cache, bio);
+		else if (bio->bi_rw & REQ_DISCARD)
+			process_discard_bio(cache, bio);
+		else
+			process_bio(cache, &structs, bio);
+	}
+
+	prealloc_free_structs(cache, &structs);
+}
+
+static void process_deferred_flush_bios(struct cache *cache, bool submit_bios)
+{
+	unsigned long flags;
+	struct bio_list bios;
+	struct bio *bio;
+
+	bio_list_init(&bios);
+
+	spin_lock_irqsave(&cache->lock, flags);
+	bio_list_merge(&bios, &cache->deferred_flush_bios);
+	bio_list_init(&cache->deferred_flush_bios);
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	while ((bio = bio_list_pop(&bios)))
+		submit_bios ? generic_make_request(bio) : bio_io_error(bio);
+}
+
+static void writeback_some_dirty_blocks(struct cache *cache)
+{
+	int r = 0;
+	dm_oblock_t oblock;
+	dm_cblock_t cblock;
+	struct prealloc structs;
+	struct dm_bio_prison_cell *old_ocell;
+
+	memset(&structs, 0, sizeof(structs));
+
+	while (spare_migration_bandwidth(cache)) {
+		if (prealloc_data_structs(cache, &structs))
+			break;
+
+		r = policy_writeback_work(cache->policy, &oblock, &cblock);
+		if (r)
+			break;
+
+		r = get_cell(cache, oblock, &structs, &old_ocell);
+		if (r) {
+			policy_set_dirty(cache->policy, oblock);
+			break;
+		}
+
+		writeback(cache, &structs, oblock, cblock, old_ocell);
+	}
+
+	prealloc_free_structs(cache, &structs);
+}
+
+/*----------------------------------------------------------------
+ * Main worker loop
+ *--------------------------------------------------------------*/
+static void start_quiescing(struct cache *cache)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	cache->quiescing = 1;
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static void stop_quiescing(struct cache *cache)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	cache->quiescing = 0;
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+
+static bool is_quiescing(struct cache *cache)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+	r = cache->quiescing;
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return r;
+}
+
+static void wait_for_migrations(struct cache *cache)
+{
+	wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations));
+}
+
+static void stop_worker(struct cache *cache)
+{
+	cancel_delayed_work(&cache->waker);
+	flush_workqueue(cache->wq);
+}
+
+static void requeue_deferred_io(struct cache *cache)
+{
+	struct bio *bio;
+	struct bio_list bios;
+
+	bio_list_init(&bios);
+	bio_list_merge(&bios, &cache->deferred_bios);
+	bio_list_init(&cache->deferred_bios);
+
+	while ((bio = bio_list_pop(&bios)))
+		bio_endio(bio, DM_ENDIO_REQUEUE);
+}
+
+static int more_work(struct cache *cache)
+{
+	if (is_quiescing(cache))
+		return !list_empty(&cache->quiesced_migrations) ||
+			!list_empty(&cache->completed_migrations) ||
+			!list_empty(&cache->need_commit_migrations);
+	else
+		return !bio_list_empty(&cache->deferred_bios) ||
+			!bio_list_empty(&cache->deferred_flush_bios) ||
+			!list_empty(&cache->quiesced_migrations) ||
+			!list_empty(&cache->completed_migrations) ||
+			!list_empty(&cache->need_commit_migrations);
+}
+
+static void do_worker(struct work_struct *ws)
+{
+	struct cache *cache = container_of(ws, struct cache, worker);
+
+	do {
+		if (!is_quiescing(cache))
+			process_deferred_bios(cache);
+
+		process_migrations(cache, &cache->quiesced_migrations, issue_copy);
+		process_migrations(cache, &cache->completed_migrations, complete_migration);
+
+		writeback_some_dirty_blocks(cache);
+
+		if (commit_if_needed(cache)) {
+			process_deferred_flush_bios(cache, false);
+
+			/*
+			 * FIXME: rollback metadata or just go into a
+			 * failure mode and error everything
+			 */
+		} else {
+			process_deferred_flush_bios(cache, true);
+			process_migrations(cache, &cache->need_commit_migrations,
+					   migration_success_post_commit);
+		}
+	} while (more_work(cache));
+}
+
+/*
+ * We want to commit periodically so that not too much
+ * unwritten metadata builds up.
+ */
+static void do_waker(struct work_struct *ws)
+{
+	struct cache *cache = container_of(to_delayed_work(ws), struct cache, waker);
+	wake_worker(cache);
+	queue_delayed_work(cache->wq, &cache->waker, COMMIT_PERIOD);
+}
+
+/*----------------------------------------------------------------*/
+
+static int is_congested(struct dm_dev *dev, int bdi_bits)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+	return bdi_congested(&q->backing_dev_info, bdi_bits);
+}
+
+static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
+{
+	struct cache *cache = container_of(cb, struct cache, callbacks);
+
+	return is_congested(cache->origin_dev, bdi_bits) ||
+		is_congested(cache->cache_dev, bdi_bits);
+}
+
+/*----------------------------------------------------------------
+ * Target methods
+ *--------------------------------------------------------------*/
+
+/*
+ * This function gets called on the error paths of the constructor, so we
+ * have to cope with a partially initialised struct.
+ */
+static void destroy(struct cache *cache)
+{
+	unsigned i;
+
+	if (cache->next_migration)
+		mempool_free(cache->next_migration, cache->migration_pool);
+
+	if (cache->migration_pool)
+		mempool_destroy(cache->migration_pool);
+
+	if (cache->all_io_ds)
+		dm_deferred_set_destroy(cache->all_io_ds);
+
+	if (cache->prison)
+		dm_bio_prison_destroy(cache->prison);
+
+	if (cache->wq)
+		destroy_workqueue(cache->wq);
+
+	if (cache->dirty_bitset)
+		free_bitset(cache->dirty_bitset);
+
+	if (cache->discard_bitset)
+		free_bitset(cache->discard_bitset);
+
+	if (cache->copier)
+		dm_kcopyd_client_destroy(cache->copier);
+
+	if (cache->cmd)
+		dm_cache_metadata_close(cache->cmd);
+
+	if (cache->metadata_dev)
+		dm_put_device(cache->ti, cache->metadata_dev);
+
+	if (cache->origin_dev)
+		dm_put_device(cache->ti, cache->origin_dev);
+
+	if (cache->cache_dev)
+		dm_put_device(cache->ti, cache->cache_dev);
+
+	if (cache->policy)
+		dm_cache_policy_destroy(cache->policy);
+
+	for (i = 0; i < cache->nr_ctr_args ; i++)
+		kfree(cache->ctr_args[i]);
+	kfree(cache->ctr_args);
+
+	kfree(cache);
+}
+
+static void cache_dtr(struct dm_target *ti)
+{
+	struct cache *cache = ti->private;
+
+	destroy(cache);
+}
+
+static sector_t get_dev_size(struct dm_dev *dev)
+{
+	return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Construct a cache device mapping.
+ *
+ * cache <metadata dev> <cache dev> <origin dev> <block size>
+ *       <#feature args> [<feature arg>]*
+ *       <policy> <#policy args> [<policy arg>]*
+ *
+ * metadata dev    : fast device holding the persistent metadata
+ * cache dev	   : fast device holding cached data blocks
+ * origin dev	   : slow device holding original data blocks
+ * block size	   : cache unit size in sectors
+ *
+ * #feature args   : number of feature arguments passed
+ * feature args    : writethrough.  (The default is writeback.)
+ *
+ * policy	   : the replacement policy to use
+ * #policy args    : an even number of policy arguments corresponding
+ *		     to key/value pairs passed to the policy
+ * policy args	   : key/value pairs passed to the policy
+ *		     E.g. 'sequential_threshold 1024'
+ *		     See cache-policies.txt for details.
+ *
+ * Optional feature arguments are:
+ *   writethrough  : write through caching that prohibits cache block
+ *		     content from being different from origin block content.
+ *		     Without this argument, the default behaviour is to write
+ *		     back cache block contents later for performance reasons,
+ *		     so they may differ from the corresponding origin blocks.
+ */
+struct cache_args {
+	struct dm_target *ti;
+
+	struct dm_dev *metadata_dev;
+
+	struct dm_dev *cache_dev;
+	sector_t cache_sectors;
+
+	struct dm_dev *origin_dev;
+	sector_t origin_sectors;
+
+	uint32_t block_size;
+
+	const char *policy_name;
+	int policy_argc;
+	const char **policy_argv;
+
+	struct cache_features features;
+};
+
+static void destroy_cache_args(struct cache_args *ca)
+{
+	if (ca->metadata_dev)
+		dm_put_device(ca->ti, ca->metadata_dev);
+
+	if (ca->cache_dev)
+		dm_put_device(ca->ti, ca->cache_dev);
+
+	if (ca->origin_dev)
+		dm_put_device(ca->ti, ca->origin_dev);
+
+	kfree(ca);
+}
+
+static bool at_least_one_arg(struct dm_arg_set *as, char **error)
+{
+	if (!as->argc) {
+		*error = "Insufficient args";
+		return false;
+	}
+
+	return true;
+}
+
+static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as,
+			      char **error)
+{
+	int r;
+	sector_t metadata_dev_size;
+	char b[BDEVNAME_SIZE];
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+			  &ca->metadata_dev);
+	if (r) {
+		*error = "Error opening metadata device";
+		return r;
+	}
+
+	metadata_dev_size = get_dev_size(ca->metadata_dev);
+	if (metadata_dev_size > DM_CACHE_METADATA_MAX_SECTORS_WARNING)
+		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
+		       bdevname(ca->metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS);
+
+	return 0;
+}
+
+static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as,
+			   char **error)
+{
+	int r;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+			  &ca->cache_dev);
+	if (r) {
+		*error = "Error opening cache device";
+		return r;
+	}
+	ca->cache_sectors = get_dev_size(ca->cache_dev);
+
+	return 0;
+}
+
+static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as,
+			    char **error)
+{
+	int r;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+			  &ca->origin_dev);
+	if (r) {
+		*error = "Error opening origin device";
+		return r;
+	}
+
+	ca->origin_sectors = get_dev_size(ca->origin_dev);
+	if (ca->ti->len > ca->origin_sectors) {
+		*error = "Device size larger than cached device";
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int parse_block_size(struct cache_args *ca, struct dm_arg_set *as,
+			    char **error)
+{
+	unsigned long tmp;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	if (kstrtoul(dm_shift_arg(as), 10, &tmp) || !tmp ||
+	    tmp < DATA_DEV_BLOCK_SIZE_MIN_SECTORS ||
+	    tmp & (DATA_DEV_BLOCK_SIZE_MIN_SECTORS - 1)) {
+		*error = "Invalid data block size";
+		return -EINVAL;
+	}
+
+	if (tmp > ca->cache_sectors) {
+		*error = "Data block size is larger than the cache device";
+		return -EINVAL;
+	}
+
+	ca->block_size = tmp;
+
+	return 0;
+}
+
+static void init_features(struct cache_features *cf)
+{
+	cf->mode = CM_WRITE;
+	cf->write_through = false;
+}
+
+static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
+			  char **error)
+{
+	static struct dm_arg _args[] = {
+		{0, 1, "Invalid number of cache feature arguments"},
+	};
+
+	int r;
+	unsigned argc;
+	const char *arg;
+	struct cache_features *cf = &ca->features;
+
+	init_features(cf);
+
+	r = dm_read_arg_group(_args, as, &argc, error);
+	if (r)
+		return -EINVAL;
+
+	while (argc--) {
+		arg = dm_shift_arg(as);
+
+		if (!strcasecmp(arg, "writeback"))
+			cf->write_through = false;
+
+		else if (!strcasecmp(arg, "writethrough"))
+			cf->write_through = true;
+
+		else {
+			*error = "Unrecognised cache feature requested";
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int parse_policy(struct cache_args *ca, struct dm_arg_set *as,
+			char **error)
+{
+	static struct dm_arg _args[] = {
+		{0, 1024, "Invalid number of policy arguments"},
+	};
+
+	int r;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	ca->policy_name = dm_shift_arg(as);
+
+	r = dm_read_arg_group(_args, as, &ca->policy_argc, error);
+	if (r)
+		return -EINVAL;
+
+	ca->policy_argv = (const char **)as->argv;
+	dm_consume_args(as, ca->policy_argc);
+
+	return 0;
+}
+
+static int parse_cache_args(struct cache_args *ca, int argc, char **argv,
+			    char **error)
+{
+	int r;
+	struct dm_arg_set as;
+
+	as.argc = argc;
+	as.argv = argv;
+
+	r = parse_metadata_dev(ca, &as, error);
+	if (r)
+		return r;
+
+	r = parse_cache_dev(ca, &as, error);
+	if (r)
+		return r;
+
+	r = parse_origin_dev(ca, &as, error);
+	if (r)
+		return r;
+
+	r = parse_block_size(ca, &as, error);
+	if (r)
+		return r;
+
+	r = parse_features(ca, &as, error);
+	if (r)
+		return r;
+
+	r = parse_policy(ca, &as, error);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+/*----------------------------------------------------------------*/
+
+static struct kmem_cache *migration_cache;
+
+static int set_config_values(struct dm_cache_policy *p, int argc, const char **argv)
+{
+	int r = 0;
+
+	if (argc & 1) {
+		DMWARN("Odd number of policy arguments given but they should be <key> <value> pairs.");
+		return -EINVAL;
+	}
+
+	while (argc) {
+		r = policy_set_config_value(p, argv[0], argv[1]);
+		if (r) {
+			DMWARN("policy_set_config_value failed: key = '%s', value = '%s'",
+			       argv[0], argv[1]);
+			return r;
+		}
+
+		argc -= 2;
+		argv += 2;
+	}
+
+	return r;
+}
+
+static int create_cache_policy(struct cache *cache, struct cache_args *ca,
+			       char **error)
+{
+	int r;
+
+	cache->policy =	dm_cache_policy_create(ca->policy_name,
+					       cache->cache_size,
+					       cache->origin_sectors,
+					       cache->sectors_per_block);
+	if (!cache->policy) {
+		*error = "Error creating cache's policy";
+		return -ENOMEM;
+	}
+
+	r = set_config_values(cache->policy, ca->policy_argc, ca->policy_argv);
+	if (r)
+		dm_cache_policy_destroy(cache->policy);
+
+	return r;
+}
+
+/*
+ * We want the discard block size to be a power of two, at least the size
+ * of the cache block size, and have no more than 2^14 discard blocks
+ * across the origin.
+ */
+#define MAX_DISCARD_BLOCKS (1 << 14)
+
+static bool too_many_discard_blocks(sector_t discard_block_size,
+				    sector_t origin_size)
+{
+	(void) sector_div(origin_size, discard_block_size);
+
+	return origin_size > MAX_DISCARD_BLOCKS;
+}
+
+static sector_t calculate_discard_block_size(sector_t cache_block_size,
+					     sector_t origin_size)
+{
+	sector_t discard_block_size;
+
+	discard_block_size = roundup_pow_of_two(cache_block_size);
+
+	if (origin_size)
+		while (too_many_discard_blocks(discard_block_size, origin_size))
+			discard_block_size *= 2;
+
+	return discard_block_size;
+}
+
+#define DEFAULT_MIGRATION_THRESHOLD (2048 * 100)
+
+static unsigned cache_num_write_bios(struct dm_target *ti, struct bio *bio);
+
+static int cache_create(struct cache_args *ca, struct cache **result)
+{
+	int r = 0;
+	char **error = &ca->ti->error;
+	struct cache *cache;
+	struct dm_target *ti = ca->ti;
+	dm_block_t origin_blocks;
+	struct dm_cache_metadata *cmd;
+	bool may_format = ca->features.mode == CM_WRITE;
+
+	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+	if (!cache)
+		return -ENOMEM;
+
+	cache->ti = ca->ti;
+	ti->private = cache;
+	ti->per_bio_data_size = sizeof(struct per_bio_data);
+	ti->num_flush_bios = 2;
+	ti->flush_supported = true;
+
+	ti->num_discard_bios = 1;
+	ti->discards_supported = true;
+	ti->discard_zeroes_data_unsupported = true;
+
+	memcpy(&cache->features, &ca->features, sizeof(cache->features));
+
+	if (cache->features.write_through)
+		ti->num_write_bios = cache_num_write_bios;
+
+	cache->callbacks.congested_fn = cache_is_congested;
+	dm_table_add_target_callbacks(ti->table, &cache->callbacks);
+
+	cache->metadata_dev = ca->metadata_dev;
+	cache->origin_dev = ca->origin_dev;
+	cache->cache_dev = ca->cache_dev;
+
+	ca->metadata_dev = ca->origin_dev = ca->cache_dev = NULL;
+
+	/* FIXME: factor out this whole section */
+	origin_blocks = cache->origin_sectors = ca->origin_sectors;
+	(void) sector_div(origin_blocks, ca->block_size);
+	cache->origin_blocks = to_oblock(origin_blocks);
+
+	cache->sectors_per_block = ca->block_size;
+	if (dm_set_target_max_io_len(ti, cache->sectors_per_block)) {
+		r = -EINVAL;
+		goto bad;
+	}
+
+	if (ca->block_size & (ca->block_size - 1)) {
+		dm_block_t cache_size = ca->cache_sectors;
+
+		cache->sectors_per_block_shift = -1;
+		(void) sector_div(cache_size, ca->block_size);
+		cache->cache_size = to_cblock(cache_size);
+	} else {
+		cache->sectors_per_block_shift = __ffs(ca->block_size);
+		cache->cache_size = to_cblock(ca->cache_sectors >> cache->sectors_per_block_shift);
+	}
+
+	r = create_cache_policy(cache, ca, error);
+	if (r)
+		goto bad;
+	cache->policy_nr_args = ca->policy_argc;
+
+	cmd = dm_cache_metadata_open(cache->metadata_dev->bdev,
+				     ca->block_size, may_format,
+				     dm_cache_policy_get_hint_size(cache->policy));
+	if (IS_ERR(cmd)) {
+		*error = "Error creating metadata object";
+		r = PTR_ERR(cmd);
+		goto bad;
+	}
+	cache->cmd = cmd;
+
+	spin_lock_init(&cache->lock);
+	bio_list_init(&cache->deferred_bios);
+	bio_list_init(&cache->deferred_flush_bios);
+	INIT_LIST_HEAD(&cache->quiesced_migrations);
+	INIT_LIST_HEAD(&cache->completed_migrations);
+	INIT_LIST_HEAD(&cache->need_commit_migrations);
+	cache->migration_threshold = DEFAULT_MIGRATION_THRESHOLD;
+	atomic_set(&cache->nr_migrations, 0);
+	init_waitqueue_head(&cache->migration_wait);
+
+	cache->nr_dirty = 0;
+	cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
+	if (!cache->dirty_bitset) {
+		*error = "could not allocate dirty bitset";
+		goto bad;
+	}
+	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));
+
+	cache->discard_block_size =
+		calculate_discard_block_size(cache->sectors_per_block,
+					     cache->origin_sectors);
+	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
+	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
+	if (!cache->discard_bitset) {
+		*error = "could not allocate discard bitset";
+		goto bad;
+	}
+	clear_bitset(cache->discard_bitset, from_dblock(cache->discard_nr_blocks));
+
+	cache->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle);
+	if (IS_ERR(cache->copier)) {
+		*error = "could not create kcopyd client";
+		r = PTR_ERR(cache->copier);
+		goto bad;
+	}
+
+	cache->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM);
+	if (!cache->wq) {
+		*error = "could not create workqueue for metadata object";
+		goto bad;
+	}
+	INIT_WORK(&cache->worker, do_worker);
+	INIT_DELAYED_WORK(&cache->waker, do_waker);
+	cache->last_commit_jiffies = jiffies;
+
+	cache->prison = dm_bio_prison_create(PRISON_CELLS);
+	if (!cache->prison) {
+		*error = "could not create bio prison";
+		goto bad;
+	}
+
+	cache->all_io_ds = dm_deferred_set_create();
+	if (!cache->all_io_ds) {
+		*error = "could not create all_io deferred set";
+		goto bad;
+	}
+
+	cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE,
+							 migration_cache);
+	if (!cache->migration_pool) {
+		*error = "Error creating cache's migration mempool";
+		goto bad;
+	}
+
+	cache->next_migration = NULL;
+
+	cache->need_tick_bio = true;
+	cache->sized = false;
+	cache->quiescing = false;
+	cache->commit_requested = false;
+	cache->loaded_mappings = false;
+	cache->loaded_discards = false;
+
+	load_stats(cache);
+
+	atomic_set(&cache->stats.demotion, 0);
+	atomic_set(&cache->stats.promotion, 0);
+	atomic_set(&cache->stats.copies_avoided, 0);
+	atomic_set(&cache->stats.cache_cell_clash, 0);
+	atomic_set(&cache->stats.commit_count, 0);
+	atomic_set(&cache->stats.discard_count, 0);
+
+	*result = cache;
+	return 0;
+
+bad:
+	destroy(cache);
+	return r;
+}
+
+static int copy_ctr_args(struct cache *cache, int argc, const char **argv)
+{
+	unsigned i;
+	const char **copy;
+
+	copy = kcalloc(argc, sizeof(*copy), GFP_KERNEL);
+	if (!copy)
+		return -ENOMEM;
+	for (i = 0; i < argc; i++) {
+		copy[i] = kstrdup(argv[i], GFP_KERNEL);
+		if (!copy[i]) {
+			while (i--)
+				kfree(copy[i]);
+			kfree(copy);
+			return -ENOMEM;
+		}
+	}
+
+	cache->nr_ctr_args = argc;
+	cache->ctr_args = copy;
+
+	return 0;
+}
+
+static int cache_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+	int r = -EINVAL;
+	struct cache_args *ca;
+	struct cache *cache = NULL;
+
+	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	if (!ca) {
+		ti->error = "Error allocating memory for cache";
+		return -ENOMEM;
+	}
+	ca->ti = ti;
+
+	r = parse_cache_args(ca, argc, argv, &ti->error);
+	if (r)
+		goto out;
+
+	r = cache_create(ca, &cache);
+
+	r = copy_ctr_args(cache, argc - 3, (const char **)argv + 3);
+	if (r) {
+		destroy(cache);
+		goto out;
+	}
+
+	ti->private = cache;
+
+out:
+	destroy_cache_args(ca);
+	return r;
+}
+
+static unsigned cache_num_write_bios(struct dm_target *ti, struct bio *bio)
+{
+	int r;
+	struct cache *cache = ti->private;
+	dm_oblock_t block = get_bio_block(cache, bio);
+	dm_cblock_t cblock;
+
+	r = policy_lookup(cache->policy, block, &cblock);
+	if (r < 0)
+		return 2;	/* assume the worst */
+
+	return (!r && !is_dirty(cache, cblock)) ? 2 : 1;
+}
+
+static int cache_map(struct dm_target *ti, struct bio *bio)
+{
+	struct cache *cache = ti->private;
+
+	int r;
+	dm_oblock_t block = get_bio_block(cache, bio);
+	bool can_migrate = false;
+	bool discarded_block;
+	struct dm_bio_prison_cell *cell;
+	struct policy_result lookup_result;
+	struct per_bio_data *pb;
+
+	if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+		/*
+		 * This can only occur if the io goes to a partial block at
+		 * the end of the origin device.  We don't cache these.
+		 * Just remap to the origin and carry on.
+		 */
+		remap_to_origin_clear_discard(cache, bio, block);
+		return DM_MAPIO_REMAPPED;
+	}
+
+	pb = init_per_bio_data(bio);
+
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
+		defer_bio(cache, bio);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	/*
+	 * Check to see if that block is currently migrating.
+	 */
+	cell = alloc_prison_cell(cache);
+	if (!cell) {
+		defer_bio(cache, bio);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	r = bio_detain(cache, block, bio, cell,
+		       (cell_free_fn) free_prison_cell,
+		       cache, &cell);
+	if (r) {
+		if (r < 0)
+			defer_bio(cache, bio);
+
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	discarded_block = is_discarded_oblock(cache, block);
+
+	r = policy_map(cache->policy, block, false, can_migrate, discarded_block,
+		       bio, &lookup_result);
+	if (r == -EWOULDBLOCK) {
+		cell_defer(cache, cell, true);
+		return DM_MAPIO_SUBMITTED;
+
+	} else if (r) {
+		DMERR_LIMIT("Unexpected return from cache replacement policy: %d", r);
+		bio_io_error(bio);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	switch (lookup_result.op) {
+	case POLICY_HIT:
+		inc_hit_counter(cache, bio);
+		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
+
+		if (is_writethrough_io(cache, bio, lookup_result.cblock)) {
+			/*
+			 * No need to mark anything dirty in write through mode.
+			 */
+			pb->req_nr == 0 ?
+				remap_to_cache(cache, bio, lookup_result.cblock) :
+				remap_to_origin_clear_discard(cache, bio, block);
+			cell_defer(cache, cell, false);
+		} else {
+			remap_to_cache_dirty(cache, bio, block, lookup_result.cblock);
+			cell_defer(cache, cell, false);
+		}
+		break;
+
+	case POLICY_MISS:
+		inc_miss_counter(cache, bio);
+		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
+
+		if (pb->req_nr != 0) {
+			/*
+			 * This is a duplicate writethrough io that is no
+			 * longer needed because the block has been demoted.
+			 */
+			bio_endio(bio, 0);
+			cell_defer(cache, cell, false);
+			return DM_MAPIO_SUBMITTED;
+		} else {
+			remap_to_origin_clear_discard(cache, bio, block);
+			cell_defer(cache, cell, false);
+		}
+		break;
+
+	default:
+		DMERR_LIMIT("%s: erroring bio: unknown policy op: %u", __func__,
+			    (unsigned) lookup_result.op);
+		bio_io_error(bio);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	return DM_MAPIO_REMAPPED;
+}
+
+static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
+{
+	struct cache *cache = ti->private;
+	unsigned long flags;
+	struct per_bio_data *pb = get_per_bio_data(bio);
+
+	if (pb->tick) {
+		policy_tick(cache->policy);
+
+		spin_lock_irqsave(&cache->lock, flags);
+		cache->need_tick_bio = true;
+		spin_unlock_irqrestore(&cache->lock, flags);
+	}
+
+	check_for_quiesced_migrations(cache, pb);
+
+	return 0;
+}
+
+static int write_dirty_bitset(struct cache *cache)
+{
+	unsigned i, r;
+
+	for (i = 0; i < from_cblock(cache->cache_size); i++) {
+		r = dm_cache_set_dirty(cache->cmd, to_cblock(i),
+				       is_dirty(cache, to_cblock(i)));
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+static int write_discard_bitset(struct cache *cache)
+{
+	unsigned i, r;
+
+	r = dm_cache_discard_bitset_resize(cache->cmd, cache->discard_block_size,
+					   cache->discard_nr_blocks);
+	if (r) {
+		DMERR("could not resize on-disk discard bitset");
+		return r;
+	}
+
+	for (i = 0; i < from_dblock(cache->discard_nr_blocks); i++) {
+		r = dm_cache_set_discard(cache->cmd, to_dblock(i),
+					 is_discarded(cache, to_dblock(i)));
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock,
+		     uint32_t hint)
+{
+	struct cache *cache = context;
+	return dm_cache_save_hint(cache->cmd, cblock, hint);
+}
+
+static int write_hints(struct cache *cache)
+{
+	int r;
+
+	r = dm_cache_begin_hints(cache->cmd, cache->policy);
+	if (r) {
+		DMERR("dm_cache_begin_hints failed");
+		return r;
+	}
+
+	r = policy_walk_mappings(cache->policy, save_hint, cache);
+	if (r)
+		DMERR("policy_walk_mappings failed");
+
+	return r;
+}
+
+/*
+ * returns true on success
+ */
+static bool sync_metadata(struct cache *cache)
+{
+	int r1, r2, r3, r4;
+
+	r1 = write_dirty_bitset(cache);
+	if (r1)
+		DMERR("could not write dirty bitset");
+
+	r2 = write_discard_bitset(cache);
+	if (r2)
+		DMERR("could not write discard bitset");
+
+	save_stats(cache);
+
+	r3 = write_hints(cache);
+	if (r3)
+		DMERR("could not write hints");
+
+	/*
+	 * If writing the above metadata failed, we still commit, but don't
+	 * set the clean shutdown flag.  This will effectively force every
+	 * dirty bit to be set on reload.
+	 */
+	r4 = dm_cache_commit(cache->cmd, !r1 && !r2 && !r3);
+	if (r4)
+		DMERR("could not write cache metadata.  Data loss may occur.");
+
+	return !r1 && !r2 && !r3 && !r4;
+}
+
+static void cache_postsuspend(struct dm_target *ti)
+{
+	struct cache *cache = ti->private;
+
+	start_quiescing(cache);
+	wait_for_migrations(cache);
+	stop_worker(cache);
+	requeue_deferred_io(cache);
+	stop_quiescing(cache);
+
+	(void) sync_metadata(cache);
+}
+
+static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
+			bool dirty, uint32_t hint, bool hint_valid)
+{
+	int r;
+	struct cache *cache = context;
+
+	r = policy_load_mapping(cache->policy, oblock, cblock, hint, hint_valid);
+	if (r)
+		return r;
+
+	if (dirty)
+		set_dirty(cache, oblock, cblock);
+	else
+		clear_dirty(cache, oblock, cblock);
+
+	return 0;
+}
+
+static int load_discard(void *context, sector_t discard_block_size,
+			dm_dblock_t dblock, bool discard)
+{
+	struct cache *cache = context;
+
+	/* FIXME: handle mis-matched block size */
+
+	if (discard)
+		set_discard(cache, dblock);
+	else
+		clear_discard(cache, dblock);
+
+	return 0;
+}
+
+static int cache_preresume(struct dm_target *ti)
+{
+	int r = 0;
+	struct cache *cache = ti->private;
+	sector_t actual_cache_size = get_dev_size(cache->cache_dev);
+	(void) sector_div(actual_cache_size, cache->sectors_per_block);
+
+	/*
+	 * Check to see if the cache has resized.
+	 */
+	if (from_cblock(cache->cache_size) != actual_cache_size || !cache->sized) {
+		cache->cache_size = to_cblock(actual_cache_size);
+
+		r = dm_cache_resize(cache->cmd, cache->cache_size);
+		if (r) {
+			DMERR("could not resize cache metadata");
+			return r;
+		}
+
+		cache->sized = true;
+	}
+
+	if (!cache->loaded_mappings) {
+		r = dm_cache_load_mappings(cache->cmd,
+					   dm_cache_policy_get_name(cache->policy),
+					   load_mapping, cache);
+		if (r) {
+			DMERR("could not load cache mappings");
+			return r;
+		}
+
+		cache->loaded_mappings = true;
+	}
+
+	if (!cache->loaded_discards) {
+		r = dm_cache_load_discards(cache->cmd, load_discard, cache);
+		if (r) {
+			DMERR("could not load origin discards");
+			return r;
+		}
+
+		cache->loaded_discards = true;
+	}
+
+	return r;
+}
+
+static void cache_resume(struct dm_target *ti)
+{
+	struct cache *cache = ti->private;
+
+	cache->need_tick_bio = true;
+	do_waker(&cache->waker.work);
+}
+
+/*
+ * Status format:
+ *
+ * <#used metadata blocks>/<#total metadata blocks>
+ * <#read hits> <#read misses> <#write hits> <#write misses>
+ * <#demotions> <#promotions> <#blocks in cache> <#dirty>
+ * <#features> <features>*
+ * <#core args> <core args>
+ * <#policy args> <policy args>*
+ */
+static void cache_status(struct dm_target *ti, status_type_t type,
+			 unsigned status_flags, char *result, unsigned maxlen)
+{
+	int r = 0;
+	unsigned i;
+	ssize_t sz = 0;
+	dm_block_t nr_free_blocks_metadata = 0;
+	dm_block_t nr_blocks_metadata = 0;
+	char buf[BDEVNAME_SIZE];
+	struct cache *cache = ti->private;
+	dm_cblock_t residency;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		/* Commit to ensure statistics aren't out-of-date */
+		if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) {
+			r = dm_cache_commit(cache->cmd, false);
+			if (r)
+				DMERR("could not commit metadata for accurate status");
+		}
+
+		r = dm_cache_get_free_metadata_block_count(cache->cmd,
+							   &nr_free_blocks_metadata);
+		if (r) {
+			DMERR("could not get metadata free block count");
+			goto err;
+		}
+
+		r = dm_cache_get_metadata_dev_size(cache->cmd, &nr_blocks_metadata);
+		if (r) {
+			DMERR("could not get metadata device size");
+			goto err;
+		}
+
+		residency = policy_residency(cache->policy);
+
+		DMEMIT("%llu/%llu %u %u %u %u %u %u %llu %u ",
+		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
+		       (unsigned long long)nr_blocks_metadata,
+		       (unsigned) atomic_read(&cache->stats.read_hit),
+		       (unsigned) atomic_read(&cache->stats.read_miss),
+		       (unsigned) atomic_read(&cache->stats.write_hit),
+		       (unsigned) atomic_read(&cache->stats.write_miss),
+		       (unsigned) atomic_read(&cache->stats.demotion),
+		       (unsigned) atomic_read(&cache->stats.promotion),
+		       (unsigned long long) from_cblock(residency),
+		       cache->nr_dirty);
+
+		if (cache->features.write_through)
+			DMEMIT("1 writethrough ");
+		else
+			DMEMIT("0 ");
+
+		DMEMIT("2 migration_threshold %llu ", (unsigned long long) cache->migration_threshold);
+		if (sz < maxlen) {
+			r = policy_emit_config_values(cache->policy, result + sz, maxlen - sz);
+			if (r)
+				DMERR("policy_emit_config_values returned %d", r);
+		}
+
+		break;
+
+	case STATUSTYPE_TABLE:
+		format_dev_t(buf, cache->metadata_dev->bdev->bd_dev);
+		DMEMIT("%s ", buf);
+		format_dev_t(buf, cache->cache_dev->bdev->bd_dev);
+		DMEMIT("%s ", buf);
+		format_dev_t(buf, cache->origin_dev->bdev->bd_dev);
+		DMEMIT("%s", buf);
+
+		for (i = 0; i < cache->nr_ctr_args - 1; i++)
+			DMEMIT(" %s", cache->ctr_args[i]);
+		if (cache->nr_ctr_args)
+			DMEMIT(" %s", cache->ctr_args[cache->nr_ctr_args - 1]);
+	}
+
+	return;
+
+err:
+	DMEMIT("Error");
+}
+
+#define NOT_CORE_OPTION 1
+
+static int process_config_option(struct cache *cache, char **argv)
+{
+	unsigned long tmp;
+
+	if (!strcasecmp(argv[0], "migration_threshold")) {
+		if (kstrtoul(argv[1], 10, &tmp))
+			return -EINVAL;
+
+		cache->migration_threshold = tmp;
+		return 0;
+	}
+
+	return NOT_CORE_OPTION;
+}
+
+/*
+ * Supports <key> <value>.
+ *
+ * The key migration_threshold is supported by the cache target core.
+ */
+static int cache_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+	int r;
+	struct cache *cache = ti->private;
+
+	if (argc != 2)
+		return -EINVAL;
+
+	r = process_config_option(cache, argv);
+	if (r == NOT_CORE_OPTION)
+		return policy_set_config_value(cache->policy, argv[0], argv[1]);
+
+	return r;
+}
+
+static int cache_iterate_devices(struct dm_target *ti,
+				 iterate_devices_callout_fn fn, void *data)
+{
+	int r = 0;
+	struct cache *cache = ti->private;
+
+	r = fn(ti, cache->cache_dev, 0, get_dev_size(cache->cache_dev), data);
+	if (!r)
+		r = fn(ti, cache->origin_dev, 0, ti->len, data);
+
+	return r;
+}
+
+/*
+ * We assume I/O is going to the origin (which is the volume
+ * more likely to have restrictions e.g. by being striped).
+ * (Looking up the exact location of the data would be expensive
+ * and could always be out of date by the time the bio is submitted.)
+ */
+static int cache_bvec_merge(struct dm_target *ti,
+			    struct bvec_merge_data *bvm,
+			    struct bio_vec *biovec, int max_size)
+{
+	struct cache *cache = ti->private;
+	struct request_queue *q = bdev_get_queue(cache->origin_dev->bdev);
+
+	if (!q->merge_bvec_fn)
+		return max_size;
+
+	bvm->bi_bdev = cache->origin_dev->bdev;
+	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
+}
+
+static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
+{
+	/*
+	 * FIXME: these limits may be incompatible with the cache device
+	 */
+	limits->max_discard_sectors = cache->discard_block_size * 1024;
+	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
+}
+
+static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	struct cache *cache = ti->private;
+
+	blk_limits_io_min(limits, 0);
+	blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT);
+	set_discard_limits(cache, limits);
+}
+
+/*----------------------------------------------------------------*/
+
+static struct target_type cache_target = {
+	.name = "cache",
+	.version = {1, 0, 0},
+	.module = THIS_MODULE,
+	.ctr = cache_ctr,
+	.dtr = cache_dtr,
+	.map = cache_map,
+	.end_io = cache_end_io,
+	.postsuspend = cache_postsuspend,
+	.preresume = cache_preresume,
+	.resume = cache_resume,
+	.status = cache_status,
+	.message = cache_message,
+	.iterate_devices = cache_iterate_devices,
+	.merge = cache_bvec_merge,
+	.io_hints = cache_io_hints,
+};
+
+static int __init dm_cache_init(void)
+{
+	int r;
+
+	r = dm_register_target(&cache_target);
+	if (r) {
+		DMERR("cache target registration failed: %d", r);
+		return r;
+	}
+
+	migration_cache = KMEM_CACHE(dm_cache_migration, 0);
+	if (!migration_cache) {
+		dm_unregister_target(&cache_target);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void __exit dm_cache_exit(void)
+{
+	dm_unregister_target(&cache_target);
+	kmem_cache_destroy(migration_cache);
+}
+
+module_init(dm_cache_init);
+module_exit(dm_cache_exit);
+
+MODULE_DESCRIPTION(DM_NAME " cache target");
+MODULE_AUTHOR("Joe Thornber <ejt@redhat.com>");
+MODULE_LICENSE("GPL");

drivers/md/persistent-data/dm-block-manager.c

@@ -613,6 +613,7 @@ int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
 
 	return dm_bufio_write_dirty_buffers(bm->bufio);
 }
+EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
 
 void dm_bm_set_read_only(struct dm_block_manager *bm)
 {