Merge tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper changes from Mike Snitzer:

 - Fix dm-cache corruption caused by discard_block_size > cache_block_size

 - Fix a lock-inversion detected by LOCKDEP in dm-cache

 - Fix a dangling bio bug in the dm-thinp target's process_deferred_bios
   error path

 - Fix corruption due to non-atomic transaction commit which allowed a
   metadata superblock to be written before all other metadata was
   successfully written -- this is common to all targets that use the
   persistent-data library's transaction manager (dm-thinp, dm-cache and
   dm-era).

 - Various small cleanups in the DM core

 - Add the dm-era target which is useful for keeping track of which
   blocks were written within a user defined period of time called an
   'era'.  Use cases include tracking changed blocks for backup
   software, and partially invalidating the contents of a cache to
   restore cache coherency after rolling back a vendor snapshot.

 - Improve the on-disk layout of multithreaded writes to the
   dm-thin-pool by splitting the pool's deferred bio list to be a
   per-thin device list and then sorting that list using an rb_tree.
   The subsequent read throughput of the data written via multiple
   threads improved by ~70%.

 - Simplify the multipath target's handling of queuing IO by pushing
   requests back to the request queue rather than queueing the IO
   internally.

* tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (24 commits)
  dm cache: fix a lock-inversion
  dm thin: sort the per thin deferred bios using an rb_tree
  dm thin: use per thin device deferred bio lists
  dm thin: simplify pool_is_congested
  dm thin: fix dangling bio in process_deferred_bios error path
  dm mpath: print more useful warnings in multipath_message()
  dm-mpath: do not activate failed paths
  dm mpath: remove extra nesting in map function
  dm mpath: remove map_io()
  dm mpath: reduce memory pressure when requeuing
  dm mpath: remove process_queued_ios()
  dm mpath: push back requests instead of queueing
  dm table: add dm_table_run_md_queue_async
  dm mpath: do not call pg_init when it is already running
  dm: use RCU_INIT_POINTER instead of rcu_assign_pointer in __unbind
  dm: stop using bi_private
  dm: remove dm_get_mapinfo
  dm: make dm_table_alloc_md_mempools static
  dm: take care to copy the space map roots before locking the superblock
  dm transaction manager: fix corruption due to non-atomic transaction commit
  ...

19 files changed, 2233 insertions, 475 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 95ad936e6048..5bdedf6df153 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -285,6 +285,17 @@ config DM_CACHE_CLEANER
          A simple cache policy that writes back all data to the
          origin.  Used when decommissioning a dm-cache.
 
+config DM_ERA
+       tristate "Era target (EXPERIMENTAL)"
+       depends on BLK_DEV_DM
+       default n
+       select DM_PERSISTENT_DATA
+       select DM_BIO_PRISON
+       ---help---
+         dm-era tracks which parts of a block device are written to
+         over time.  Useful for maintaining cache coherency when using
+         vendor snapshots.
+
 config DM_MIRROR
        tristate "Mirror target"
        depends on BLK_DEV_DM
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index f26d83292579..a2da532b1c2b 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -14,6 +14,7 @@ dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
 dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
 dm-cache-mq-y   += dm-cache-policy-mq.o
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
+dm-era-y	+= dm-era-target.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
 
@@ -53,6 +54,7 @@ obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
 obj-$(CONFIG_DM_CACHE_MQ)	+= dm-cache-mq.o
 obj-$(CONFIG_DM_CACHE_CLEANER)	+= dm-cache-cleaner.o
+obj-$(CONFIG_DM_ERA)		+= dm-era.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
diff --git a/drivers/md/dm-cache-block-types.h b/drivers/md/dm-cache-block-types.h
index bed4ad4e1b7c..aac0e2df06be 100644
--- a/drivers/md/dm-cache-block-types.h
+++ b/drivers/md/dm-cache-block-types.h
@@ -19,7 +19,6 @@
 
 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)
 {
@@ -41,14 +40,4 @@ static inline uint32_t from_cblock(dm_cblock_t b)
 	return (__force uint32_t) b;
 }
 
-static inline dm_dblock_t to_dblock(dm_block_t b)
-{
-	return (__force dm_dblock_t) b;
-}
-
-static inline dm_block_t from_dblock(dm_dblock_t b)
-{
-	return (__force dm_block_t) b;
-}
-
 #endif /* DM_CACHE_BLOCK_TYPES_H */
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 9ef0752e8a08..4ead4ba60656 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -109,7 +109,7 @@ struct dm_cache_metadata {
 	dm_block_t discard_root;
 
 	sector_t discard_block_size;
-	dm_dblock_t discard_nr_blocks;
+	dm_oblock_t discard_nr_blocks;
 
 	sector_t data_block_size;
 	dm_cblock_t cache_blocks;
@@ -120,6 +120,12 @@ struct dm_cache_metadata {
 	unsigned policy_version[CACHE_POLICY_VERSION_SIZE];
 	size_t policy_hint_size;
 	struct dm_cache_statistics stats;
+
+	/*
+	 * Reading the space map root can fail, so we read it into this
+	 * buffer before the superblock is locked and updated.
+	 */
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 /*-------------------------------------------------------------------
@@ -260,11 +266,31 @@ static void __setup_mapping_info(struct dm_cache_metadata *cmd)
 	}
 }
 
+static int __save_sm_root(struct dm_cache_metadata *cmd)
+{
+	int r;
+	size_t metadata_len;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root,
+			       metadata_len);
+}
+
+static void __copy_sm_root(struct dm_cache_metadata *cmd,
+			   struct cache_disk_superblock *disk_super)
+{
+	memcpy(&disk_super->metadata_space_map_root,
+	       &cmd->metadata_space_map_root,
+	       sizeof(cmd->metadata_space_map_root));
+}
+
 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;
 
@@ -272,12 +298,16 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	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);
+	r = dm_tm_pre_commit(cmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(cmd->tm);
-	if (r < 0)
+	/*
+	 * dm_sm_copy_root() can fail.  So we need to do it before we start
+	 * updating the superblock.
+	 */
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock_zero(cmd, &sblock);
@@ -293,16 +323,13 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
 	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;
+	__copy_sm_root(cmd, disk_super);
 
 	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->discard_nr_blocks = cpu_to_le64(from_oblock(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);
@@ -313,10 +340,6 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	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)
@@ -496,7 +519,7 @@ static void read_superblock_fields(struct dm_cache_metadata *cmd,
 	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->discard_nr_blocks = to_oblock(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));
@@ -530,8 +553,9 @@ static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
 	disk_super = dm_block_data(sblock);
 	update_flags(disk_super, mutator);
 	read_superblock_fields(cmd, disk_super);
+	dm_bm_unlock(sblock);
 
-	return dm_bm_flush_and_unlock(cmd->bm, sblock);
+	return dm_bm_flush(cmd->bm);
 }
 
 static int __begin_transaction(struct dm_cache_metadata *cmd)
@@ -559,7 +583,6 @@ 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;
 
@@ -577,8 +600,8 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
-	if (r < 0)
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock(cmd, &sblock);
@@ -594,7 +617,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	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->discard_nr_blocks = cpu_to_le64(from_oblock(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->policy_version[0] = cpu_to_le32(cmd->policy_version[0]);
@@ -605,13 +628,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	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;
-	}
+	__copy_sm_root(cmd, disk_super);
 
 	return dm_tm_commit(cmd->tm, sblock);
 }
@@ -771,15 +788,15 @@ out:
 
 int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
 				   sector_t discard_block_size,
-				   dm_dblock_t new_nr_entries)
+				   dm_oblock_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),
+			     from_oblock(cmd->discard_nr_blocks),
+			     from_oblock(new_nr_entries),
 			     false, &cmd->discard_root);
 	if (!r) {
 		cmd->discard_block_size = discard_block_size;
@@ -792,28 +809,28 @@ int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
 	return r;
 }
 
-static int __set_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
+static int __set_discard(struct dm_cache_metadata *cmd, dm_oblock_t b)
 {
 	return dm_bitset_set_bit(&cmd->discard_info, cmd->discard_root,
-				 from_dblock(b), &cmd->discard_root);
+				 from_oblock(b), &cmd->discard_root);
 }
 
-static int __clear_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
+static int __clear_discard(struct dm_cache_metadata *cmd, dm_oblock_t b)
 {
 	return dm_bitset_clear_bit(&cmd->discard_info, cmd->discard_root,
-				   from_dblock(b), &cmd->discard_root);
+				   from_oblock(b), &cmd->discard_root);
 }
 
-static int __is_discarded(struct dm_cache_metadata *cmd, dm_dblock_t b,
+static int __is_discarded(struct dm_cache_metadata *cmd, dm_oblock_t b,
 			  bool *is_discarded)
 {
 	return dm_bitset_test_bit(&cmd->discard_info, cmd->discard_root,
-				  from_dblock(b), &cmd->discard_root,
+				  from_oblock(b), &cmd->discard_root,
 				  is_discarded);
 }
 
 static int __discard(struct dm_cache_metadata *cmd,
-		     dm_dblock_t dblock, bool discard)
+		     dm_oblock_t dblock, bool discard)
 {
 	int r;
 
@@ -826,7 +843,7 @@ static int __discard(struct dm_cache_metadata *cmd,
 }
 
 int dm_cache_set_discard(struct dm_cache_metadata *cmd,
-			 dm_dblock_t dblock, bool discard)
+			 dm_oblock_t dblock, bool discard)
 {
 	int r;
 
@@ -844,8 +861,8 @@ static int __load_discards(struct dm_cache_metadata *cmd,
 	dm_block_t b;
 	bool discard;
 
-	for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) {
-		dm_dblock_t dblock = to_dblock(b);
+	for (b = 0; b < from_oblock(cmd->discard_nr_blocks); b++) {
+		dm_oblock_t dblock = to_oblock(b);
 
 		if (cmd->clean_when_opened) {
 			r = __is_discarded(cmd, dblock, &discard);
@@ -1228,22 +1245,12 @@ static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po
 	return 0;
 }
 
-int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, uint32_t hint)
 {
+	struct dm_cache_metadata *cmd = context;
+	__le32 value = cpu_to_le32(hint);
 	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,
@@ -1253,16 +1260,25 @@ static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
 	return r;
 }
 
-int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
-		       uint32_t hint)
+static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
 {
 	int r;
 
-	if (!hints_array_initialized(cmd))
-		return 0;
+	r = begin_hints(cmd, policy);
+	if (r) {
+		DMERR("begin_hints failed");
+		return r;
+	}
+
+	return policy_walk_mappings(policy, save_hint, cmd);
+}
+
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+{
+	int r;
 
 	down_write(&cmd->root_lock);
-	r = save_hint(cmd, cblock, hint);
+	r = write_hints(cmd, policy);
 	up_write(&cmd->root_lock);
 
 	return r;
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index cd906f14f98d..cd70a78623a3 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -72,14 +72,14 @@ 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);
+				   dm_oblock_t new_nr_entries);
 
 typedef int (*load_discard_fn)(void *context, sector_t discard_block_size,
-			       dm_dblock_t dblock, bool discarded);
+			       dm_oblock_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_set_discard(struct dm_cache_metadata *cmd, dm_oblock_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);
@@ -128,14 +128,7 @@ void dm_cache_dump(struct dm_cache_metadata *cmd);
  * 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);
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
 
 /*
  * Query method.  Are all the blocks in the cache clean?
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 074b9c8e4cf0..1bf4a71919ec 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -237,9 +237,8 @@ struct cache {
 	/*
 	 * origin_blocks entries, discarded if set.
 	 */
-	dm_dblock_t discard_nr_blocks;
+	dm_oblock_t discard_nr_blocks;
 	unsigned long *discard_bitset;
-	uint32_t discard_block_size; /* a power of 2 times sectors per block */
 
 	/*
 	 * Rather than reconstructing the table line for the status we just
@@ -526,48 +525,33 @@ static dm_block_t block_div(dm_block_t b, uint32_t n)
 	return b;
 }
 
-static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
-{
-	uint32_t discard_blocks = cache->discard_block_size;
-	dm_block_t b = from_oblock(oblock);
-
-	if (!block_size_is_power_of_two(cache))
-		discard_blocks = discard_blocks / cache->sectors_per_block;
-	else
-		discard_blocks >>= cache->sectors_per_block_shift;
-
-	b = block_div(b, discard_blocks);
-
-	return to_dblock(b);
-}
-
-static void set_discard(struct cache *cache, dm_dblock_t b)
+static void set_discard(struct cache *cache, dm_oblock_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);
+	set_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 }
 
-static void clear_discard(struct cache *cache, dm_dblock_t b)
+static void clear_discard(struct cache *cache, dm_oblock_t b)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	clear_bit(from_dblock(b), cache->discard_bitset);
+	clear_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 }
 
-static bool is_discarded(struct cache *cache, dm_dblock_t b)
+static bool is_discarded(struct cache *cache, dm_oblock_t b)
 {
 	int r;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	r = test_bit(from_dblock(b), cache->discard_bitset);
+	r = test_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	return r;
@@ -579,8 +563,7 @@ static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
-		     cache->discard_bitset);
+	r = test_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	return r;
@@ -705,7 +688,7 @@ static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
 	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));
+		clear_discard(cache, oblock);
 }
 
 static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
@@ -715,7 +698,7 @@ static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
 	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));
+		clear_discard(cache, oblock);
 	}
 }
 
@@ -1288,14 +1271,14 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
 static void process_discard_bio(struct cache *cache, struct bio *bio)
 {
 	dm_block_t start_block = dm_sector_div_up(bio->bi_iter.bi_sector,
-						  cache->discard_block_size);
+						  cache->sectors_per_block);
 	dm_block_t end_block = bio_end_sector(bio);
 	dm_block_t b;
 
-	end_block = block_div(end_block, cache->discard_block_size);
+	end_block = block_div(end_block, cache->sectors_per_block);
 
 	for (b = start_block; b < end_block; b++)
-		set_discard(cache, to_dblock(b));
+		set_discard(cache, to_oblock(b));
 
 	bio_endio(bio, 0);
 }
@@ -2171,35 +2154,6 @@ static int create_cache_policy(struct cache *cache, struct cache_args *ca,
 	return 0;
 }
 
-/*
- * 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
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2321,16 +2275,13 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	}
 	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));
+	cache->discard_nr_blocks = cache->origin_blocks;
+	cache->discard_bitset = alloc_bitset(from_oblock(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));
+	clear_bitset(cache->discard_bitset, from_oblock(cache->discard_nr_blocks));
 
 	cache->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle);
 	if (IS_ERR(cache->copier)) {
@@ -2614,16 +2565,16 @@ 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);
+	r = dm_cache_discard_bitset_resize(cache->cmd, cache->sectors_per_block,
+					   cache->origin_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)));
+	for (i = 0; i < from_oblock(cache->discard_nr_blocks); i++) {
+		r = dm_cache_set_discard(cache->cmd, to_oblock(i),
+					 is_discarded(cache, to_oblock(i)));
 		if (r)
 			return r;
 	}
@@ -2631,30 +2582,6 @@ static int write_discard_bitset(struct cache *cache)
 	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
  */
@@ -2672,7 +2599,7 @@ static bool sync_metadata(struct cache *cache)
 
 	save_stats(cache);
 
-	r3 = write_hints(cache);
+	r3 = dm_cache_write_hints(cache->cmd, cache->policy);
 	if (r3)
 		DMERR("could not write hints");
 
@@ -2720,16 +2647,14 @@ static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
 }
 
 static int load_discard(void *context, sector_t discard_block_size,
-			dm_dblock_t dblock, bool discard)
+			dm_oblock_t oblock, bool discard)
 {
 	struct cache *cache = context;
 
-	/* FIXME: handle mis-matched block size */
-
 	if (discard)
-		set_discard(cache, dblock);
+		set_discard(cache, oblock);
 	else
-		clear_discard(cache, dblock);
+		clear_discard(cache, oblock);
 
 	return 0;
 }
@@ -3120,8 +3045,8 @@ 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;
+	limits->max_discard_sectors = cache->sectors_per_block;
+	limits->discard_granularity = cache->sectors_per_block << SECTOR_SHIFT;
 }
 
 static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
@@ -3145,7 +3070,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
new file mode 100644
index 000000000000..414dad4cb49b
--- /dev/null
+++ b/drivers/md/dm-era-target.c
@@ -0,0 +1,1746 @@
+#include "dm.h"
+#include "persistent-data/dm-transaction-manager.h"
+#include "persistent-data/dm-bitset.h"
+#include "persistent-data/dm-space-map.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 "era"
+
+#define SUPERBLOCK_LOCATION 0
+#define SUPERBLOCK_MAGIC 2126579579
+#define SUPERBLOCK_CSUM_XOR 146538381
+#define MIN_ERA_VERSION 1
+#define MAX_ERA_VERSION 1
+#define INVALID_WRITESET_ROOT SUPERBLOCK_LOCATION
+#define MIN_BLOCK_SIZE 8
+
+/*----------------------------------------------------------------
+ * Writeset
+ *--------------------------------------------------------------*/
+struct writeset_metadata {
+	uint32_t nr_bits;
+	dm_block_t root;
+};
+
+struct writeset {
+	struct writeset_metadata md;
+
+	/*
+	 * An in core copy of the bits to save constantly doing look ups on
+	 * disk.
+	 */
+	unsigned long *bits;
+};
+
+/*
+ * This does not free off the on disk bitset as this will normally be done
+ * after digesting into the era array.
+ */
+static void writeset_free(struct writeset *ws)
+{
+	vfree(ws->bits);
+}
+
+static int setup_on_disk_bitset(struct dm_disk_bitset *info,
+				unsigned nr_bits, dm_block_t *root)
+{
+	int r;
+
+	r = dm_bitset_empty(info, root);
+	if (r)
+		return r;
+
+	return dm_bitset_resize(info, *root, 0, nr_bits, false, root);
+}
+
+static size_t bitset_size(unsigned nr_bits)
+{
+	return sizeof(unsigned long) * dm_div_up(nr_bits, BITS_PER_LONG);
+}
+
+/*
+ * Allocates memory for the in core bitset.
+ */
+static int writeset_alloc(struct writeset *ws, dm_block_t nr_blocks)
+{
+	ws->md.nr_bits = nr_blocks;
+	ws->md.root = INVALID_WRITESET_ROOT;
+	ws->bits = vzalloc(bitset_size(nr_blocks));
+	if (!ws->bits) {
+		DMERR("%s: couldn't allocate in memory bitset", __func__);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/*
+ * Wipes the in-core bitset, and creates a new on disk bitset.
+ */
+static int writeset_init(struct dm_disk_bitset *info, struct writeset *ws)
+{
+	int r;
+
+	memset(ws->bits, 0, bitset_size(ws->md.nr_bits));
+
+	r = setup_on_disk_bitset(info, ws->md.nr_bits, &ws->md.root);
+	if (r) {
+		DMERR("%s: setup_on_disk_bitset failed", __func__);
+		return r;
+	}
+
+	return 0;
+}
+
+static bool writeset_marked(struct writeset *ws, dm_block_t block)
+{
+	return test_bit(block, ws->bits);
+}
+
+static int writeset_marked_on_disk(struct dm_disk_bitset *info,
+				   struct writeset_metadata *m, dm_block_t block,
+				   bool *result)
+{
+	dm_block_t old = m->root;
+
+	/*
+	 * The bitset was flushed when it was archived, so we know there'll
+	 * be no change to the root.
+	 */
+	int r = dm_bitset_test_bit(info, m->root, block, &m->root, result);
+	if (r) {
+		DMERR("%s: dm_bitset_test_bit failed", __func__);
+		return r;
+	}
+
+	BUG_ON(m->root != old);
+
+	return r;
+}
+
+/*
+ * Returns < 0 on error, 0 if the bit wasn't previously set, 1 if it was.
+ */
+static int writeset_test_and_set(struct dm_disk_bitset *info,
+				 struct writeset *ws, uint32_t block)
+{
+	int r;
+
+	if (!test_and_set_bit(block, ws->bits)) {
+		r = dm_bitset_set_bit(info, ws->md.root, block, &ws->md.root);
+		if (r) {
+			/* FIXME: fail mode */
+			return r;
+		}
+
+		return 0;
+	}
+
+	return 1;
+}
+
+/*----------------------------------------------------------------
+ * On disk metadata layout
+ *--------------------------------------------------------------*/
+#define SPACE_MAP_ROOT_SIZE 128
+#define UUID_LEN 16
+
+struct writeset_disk {
+	__le32 nr_bits;
+	__le64 root;
+} __packed;
+
+struct superblock_disk {
+	__le32 csum;
+	__le32 flags;
+	__le64 blocknr;
+
+	__u8 uuid[UUID_LEN];
+	__le64 magic;
+	__le32 version;
+
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
+
+	__le32 data_block_size;
+	__le32 metadata_block_size;
+	__le32 nr_blocks;
+
+	__le32 current_era;
+	struct writeset_disk current_writeset;
+
+	/*
+	 * Only these two fields are valid within the metadata snapshot.
+	 */
+	__le64 writeset_tree_root;
+	__le64 era_array_root;
+
+	__le64 metadata_snap;
+} __packed;
+
+/*----------------------------------------------------------------
+ * Superblock validation
+ *--------------------------------------------------------------*/
+static void sb_prepare_for_write(struct dm_block_validator *v,
+				 struct dm_block *b,
+				 size_t sb_block_size)
+{
+	struct superblock_disk *disk = dm_block_data(b);