dm persistent data: add transactional array

Add a transactional array.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

3 files changed, 975 insertions, 0 deletions

diff --git a/drivers/md/persistent-data/Makefile b/drivers/md/persistent-data/Makefile
index d8e7cb767c1..ebd8d80d529 100644
--- a/drivers/md/persistent-data/Makefile
+++ b/drivers/md/persistent-data/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_DM_PERSISTENT_DATA) += dm-persistent-data.o
 dm-persistent-data-objs := \
+	dm-array.o \
 	dm-block-manager.o \
 	dm-space-map-common.o \
 	dm-space-map-disk.o \
diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
new file mode 100644
index 00000000000..172147eb1d4
--- /dev/null
+++ b/drivers/md/persistent-data/dm-array.c
@@ -0,0 +1,808 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-array.h"
+#include "dm-space-map.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/export.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "array"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * The array is implemented as a fully populated btree, which points to
+ * blocks that contain the packed values.  This is more space efficient
+ * than just using a btree since we don't store 1 key per value.
+ */
+struct array_block {
+	__le32 csum;
+	__le32 max_entries;
+	__le32 nr_entries;
+	__le32 value_size;
+	__le64 blocknr; /* Block this node is supposed to live in. */
+} __packed;
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Validator methods.  As usual we calculate a checksum, and also write the
+ * block location into the header (paranoia about ssds remapping areas by
+ * mistake).
+ */
+#define CSUM_XOR 595846735
+
+static void array_block_prepare_for_write(struct dm_block_validator *v,
+					  struct dm_block *b,
+					  size_t size_of_block)
+{
+	struct array_block *bh_le = dm_block_data(b);
+
+	bh_le->blocknr = cpu_to_le64(dm_block_location(b));
+	bh_le->csum = cpu_to_le32(dm_bm_checksum(&bh_le->max_entries,
+						 size_of_block - sizeof(__le32),
+						 CSUM_XOR));
+}
+
+static int array_block_check(struct dm_block_validator *v,
+			     struct dm_block *b,
+			     size_t size_of_block)
+{
+	struct array_block *bh_le = dm_block_data(b);
+	__le32 csum_disk;
+
+	if (dm_block_location(b) != le64_to_cpu(bh_le->blocknr)) {
+		DMERR_LIMIT("array_block_check failed: blocknr %llu != wanted %llu",
+			    (unsigned long long) le64_to_cpu(bh_le->blocknr),
+			    (unsigned long long) dm_block_location(b));
+		return -ENOTBLK;
+	}
+
+	csum_disk = cpu_to_le32(dm_bm_checksum(&bh_le->max_entries,
+					       size_of_block - sizeof(__le32),
+					       CSUM_XOR));
+	if (csum_disk != bh_le->csum) {
+		DMERR_LIMIT("array_block_check failed: csum %u != wanted %u",
+			    (unsigned) le32_to_cpu(csum_disk),
+			    (unsigned) le32_to_cpu(bh_le->csum));
+		return -EILSEQ;
+	}
+
+	return 0;
+}
+
+static struct dm_block_validator array_validator = {
+	.name = "array",
+	.prepare_for_write = array_block_prepare_for_write,
+	.check = array_block_check
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Functions for manipulating the array blocks.
+ */
+
+/*
+ * Returns a pointer to a value within an array block.
+ *
+ * index - The index into _this_ specific block.
+ */
+static void *element_at(struct dm_array_info *info, struct array_block *ab,
+			unsigned index)
+{
+	unsigned char *entry = (unsigned char *) (ab + 1);
+
+	entry += index * info->value_type.size;
+
+	return entry;
+}
+
+/*
+ * Utility function that calls one of the value_type methods on every value
+ * in an array block.
+ */
+static void on_entries(struct dm_array_info *info, struct array_block *ab,
+		       void (*fn)(void *, const void *))
+{
+	unsigned i, nr_entries = le32_to_cpu(ab->nr_entries);
+
+	for (i = 0; i < nr_entries; i++)
+		fn(info->value_type.context, element_at(info, ab, i));
+}
+
+/*
+ * Increment every value in an array block.
+ */
+static void inc_ablock_entries(struct dm_array_info *info, struct array_block *ab)
+{
+	struct dm_btree_value_type *vt = &info->value_type;
+
+	if (vt->inc)
+		on_entries(info, ab, vt->inc);
+}
+
+/*
+ * Decrement every value in an array block.
+ */
+static void dec_ablock_entries(struct dm_array_info *info, struct array_block *ab)
+{
+	struct dm_btree_value_type *vt = &info->value_type;
+
+	if (vt->dec)
+		on_entries(info, ab, vt->dec);
+}
+
+/*
+ * Each array block can hold this many values.
+ */
+static uint32_t calc_max_entries(size_t value_size, size_t size_of_block)
+{
+	return (size_of_block - sizeof(struct array_block)) / value_size;
+}
+
+/*
+ * Allocate a new array block.  The caller will need to unlock block.
+ */
+static int alloc_ablock(struct dm_array_info *info, size_t size_of_block,
+			uint32_t max_entries,
+			struct dm_block **block, struct array_block **ab)
+{
+	int r;
+
+	r = dm_tm_new_block(info->btree_info.tm, &array_validator, block);
+	if (r)
+		return r;
+
+	(*ab) = dm_block_data(*block);
+	(*ab)->max_entries = cpu_to_le32(max_entries);
+	(*ab)->nr_entries = cpu_to_le32(0);
+	(*ab)->value_size = cpu_to_le32(info->value_type.size);
+
+	return 0;
+}
+
+/*
+ * Pad an array block out with a particular value.  Every instance will
+ * cause an increment of the value_type.  new_nr must always be more than
+ * the current number of entries.
+ */
+static void fill_ablock(struct dm_array_info *info, struct array_block *ab,
+			const void *value, unsigned new_nr)
+{
+	unsigned i;
+	uint32_t nr_entries;
+	struct dm_btree_value_type *vt = &info->value_type;
+
+	BUG_ON(new_nr > le32_to_cpu(ab->max_entries));
+	BUG_ON(new_nr < le32_to_cpu(ab->nr_entries));
+
+	nr_entries = le32_to_cpu(ab->nr_entries);
+	for (i = nr_entries; i < new_nr; i++) {
+		if (vt->inc)
+			vt->inc(vt->context, value);
+		memcpy(element_at(info, ab, i), value, vt->size);
+	}
+	ab->nr_entries = cpu_to_le32(new_nr);
+}
+
+/*
+ * Remove some entries from the back of an array block.  Every value
+ * removed will be decremented.  new_nr must be <= the current number of
+ * entries.
+ */
+static void trim_ablock(struct dm_array_info *info, struct array_block *ab,
+			unsigned new_nr)
+{
+	unsigned i;
+	uint32_t nr_entries;
+	struct dm_btree_value_type *vt = &info->value_type;
+
+	BUG_ON(new_nr > le32_to_cpu(ab->max_entries));
+	BUG_ON(new_nr > le32_to_cpu(ab->nr_entries));
+
+	nr_entries = le32_to_cpu(ab->nr_entries);
+	for (i = nr_entries; i > new_nr; i--)
+		if (vt->dec)
+			vt->dec(vt->context, element_at(info, ab, i - 1));
+	ab->nr_entries = cpu_to_le32(new_nr);
+}
+
+/*
+ * Read locks a block, and coerces it to an array block.  The caller must
+ * unlock 'block' when finished.
+ */
+static int get_ablock(struct dm_array_info *info, dm_block_t b,
+		      struct dm_block **block, struct array_block **ab)
+{
+	int r;
+
+	r = dm_tm_read_lock(info->btree_info.tm, b, &array_validator, block);
+	if (r)
+		return r;
+
+	*ab = dm_block_data(*block);
+	return 0;
+}
+
+/*
+ * Unlocks an array block.
+ */
+static int unlock_ablock(struct dm_array_info *info, struct dm_block *block)
+{
+	return dm_tm_unlock(info->btree_info.tm, block);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Btree manipulation.
+ */
+
+/*
+ * Looks up an array block in the btree, and then read locks it.
+ *
+ * index is the index of the index of the array_block, (ie. the array index
+ * / max_entries).
+ */
+static int lookup_ablock(struct dm_array_info *info, dm_block_t root,
+			 unsigned index, struct dm_block **block,
+			 struct array_block **ab)
+{
+	int r;
+	uint64_t key = index;
+	__le64 block_le;
+
+	r = dm_btree_lookup(&info->btree_info, root, &key, &block_le);
+	if (r)
+		return r;
+
+	return get_ablock(info, le64_to_cpu(block_le), block, ab);
+}
+
+/*
+ * Insert an array block into the btree.  The block is _not_ unlocked.
+ */
+static int insert_ablock(struct dm_array_info *info, uint64_t index,
+			 struct dm_block *block, dm_block_t *root)
+{
+	__le64 block_le = cpu_to_le64(dm_block_location(block));
+
+	__dm_bless_for_disk(block_le);
+	return dm_btree_insert(&info->btree_info, *root, &index, &block_le, root);
+}
+
+/*
+ * Looks up an array block in the btree.  Then shadows it, and updates the
+ * btree to point to this new shadow.  'root' is an input/output parameter
+ * for both the current root block, and the new one.
+ */
+static int shadow_ablock(struct dm_array_info *info, dm_block_t *root,
+			 unsigned index, struct dm_block **block,
+			 struct array_block **ab)
+{
+	int r, inc;
+	uint64_t key = index;
+	dm_block_t b;
+	__le64 block_le;
+
+	/*
+	 * lookup
+	 */
+	r = dm_btree_lookup(&info->btree_info, *root, &key, &block_le);
+	if (r)
+		return r;
+	b = le64_to_cpu(block_le);
+
+	/*
+	 * shadow
+	 */
+	r = dm_tm_shadow_block(info->btree_info.tm, b,
+			       &array_validator, block, &inc);
+	if (r)
+		return r;
+
+	*ab = dm_block_data(*block);
+	if (inc)
+		inc_ablock_entries(info, *ab);
+
+	/*
+	 * Reinsert.
+	 *
+	 * The shadow op will often be a noop.  Only insert if it really
+	 * copied data.
+	 */
+	if (dm_block_location(*block) != b)
+		r = insert_ablock(info, index, *block, root);
+
+	return r;
+}
+
+/*
+ * Allocate an new array block, and fill it with some values.
+ */
+static int insert_new_ablock(struct dm_array_info *info, size_t size_of_block,
+			     uint32_t max_entries,
+			     unsigned block_index, uint32_t nr,
+			     const void *value, dm_block_t *root)
+{
+	int r;
+	struct dm_block *block;
+	struct array_block *ab;
+
+	r = alloc_ablock(info, size_of_block, max_entries, &block, &ab);
+	if (r)
+		return r;
+
+	fill_ablock(info, ab, value, nr);
+	r = insert_ablock(info, block_index, block, root);
+	unlock_ablock(info, block);
+
+	return r;
+}
+
+static int insert_full_ablocks(struct dm_array_info *info, size_t size_of_block,
+			       unsigned begin_block, unsigned end_block,
+			       unsigned max_entries, const void *value,
+			       dm_block_t *root)
+{
+	int r = 0;
+
+	for (; !r && begin_block != end_block; begin_block++)
+		r = insert_new_ablock(info, size_of_block, max_entries, begin_block, max_entries, value, root);
+
+	return r;
+}
+
+/*
+ * There are a bunch of functions involved with resizing an array.  This
+ * structure holds information that commonly needed by them.  Purely here
+ * to reduce parameter count.
+ */
+struct resize {
+	/*
+	 * Describes the array.
+	 */
+	struct dm_array_info *info;
+
+	/*
+	 * The current root of the array.  This gets updated.
+	 */
+	dm_block_t root;
+
+	/*
+	 * Metadata block size.  Used to calculate the nr entries in an
+	 * array block.
+	 */
+	size_t size_of_block;
+
+	/*
+	 * Maximum nr entries in an array block.
+	 */
+	unsigned max_entries;
+
+	/*
+	 * nr of completely full blocks in the array.
+	 *
+	 * 'old' refers to before the resize, 'new' after.
+	 */
+	unsigned old_nr_full_blocks, new_nr_full_blocks;
+
+	/*
+	 * Number of entries in the final block.  0 iff only full blocks in
+	 * the array.
+	 */
+	unsigned old_nr_entries_in_last_block, new_nr_entries_in_last_block;
+
+	/*
+	 * The default value used when growing the array.
+	 */
+	const void *value;
+};
+
+/*
+ * Removes a consecutive set of array blocks from the btree.  The values
+ * in block are decremented as a side effect of the btree remove.
+ *
+ * begin_index - the index of the first array block to remove.
+ * end_index - the one-past-the-end value.  ie. this block is not removed.
+ */
+static int drop_blocks(struct resize *resize, unsigned begin_index,
+		       unsigned end_index)
+{
+	int r;
+
+	while (begin_index != end_index) {
+		uint64_t key = begin_index++;
+		r = dm_btree_remove(&resize->info->btree_info, resize->root,
+				    &key, &resize->root);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+/*
+ * Calculates how many blocks are needed for the array.
+ */
+static unsigned total_nr_blocks_needed(unsigned nr_full_blocks,
+				       unsigned nr_entries_in_last_block)
+{
+	return nr_full_blocks + (nr_entries_in_last_block ? 1 : 0);
+}
+
+/*
+ * Shrink an array.
+ */
+static int shrink(struct resize *resize)
+{
+	int r;
+	unsigned begin, end;
+	struct dm_block *block;
+	struct array_block *ab;
+
+	/*
+	 * Lose some blocks from the back?
+	 */
+	if (resize->new_nr_full_blocks < resize->old_nr_full_blocks) {
+		begin = total_nr_blocks_needed(resize->new_nr_full_blocks,
+					       resize->new_nr_entries_in_last_block);
+		end = total_nr_blocks_needed(resize->old_nr_full_blocks,
+					     resize->old_nr_entries_in_last_block);
+
+		r = drop_blocks(resize, begin, end);
+		if (r)
+			return r;
+	}
+
+	/*
+	 * Trim the new tail block
+	 */
+	if (resize->new_nr_entries_in_last_block) {
+		r = shadow_ablock(resize->info, &resize->root,
+				  resize->new_nr_full_blocks, &block, &ab);
+		if (r)
+			return r;
+
+		trim_ablock(resize->info, ab, resize->new_nr_entries_in_last_block);
+		unlock_ablock(resize->info, block);
+	}
+
+	return 0;
+}
+
+/*
+ * Grow an array.
+ */
+static int grow_extend_tail_block(struct resize *resize, uint32_t new_nr_entries)
+{
+	int r;
+	struct dm_block *block;
+	struct array_block *ab;
+
+	r = shadow_ablock(resize->info, &resize->root,
+			  resize->old_nr_full_blocks, &block, &ab);
+	if (r)
+		return r;
+
+	fill_ablock(resize->info, ab, resize->value, new_nr_entries);
+	unlock_ablock(resize->info, block);
+
+	return r;
+}
+
+static int grow_add_tail_block(struct resize *resize)
+{
+	return insert_new_ablock(resize->info, resize->size_of_block,
+				 resize->max_entries,
+				 resize->new_nr_full_blocks,
+				 resize->new_nr_entries_in_last_block,
+				 resize->value, &resize->root);
+}
+
+static int grow_needs_more_blocks(struct resize *resize)
+{
+	int r;
+
+	if (resize->old_nr_entries_in_last_block > 0) {
+		r = grow_extend_tail_block(resize, resize->max_entries);
+		if (r)
+			return r;
+	}
+
+	r = insert_full_ablocks(resize->info, resize->size_of_block,
+				resize->old_nr_full_blocks,
+				resize->new_nr_full_blocks,
+				resize->max_entries, resize->value,
+				&resize->root);
+	if (r)
+		return r;
+
+	if (resize->new_nr_entries_in_last_block)
+		r = grow_add_tail_block(resize);
+
+	return r;
+}
+
+static int grow(struct resize *resize)
+{
+	if (resize->new_nr_full_blocks > resize->old_nr_full_blocks)
+		return grow_needs_more_blocks(resize);
+
+	else if (resize->old_nr_entries_in_last_block)
+		return grow_extend_tail_block(resize, resize->new_nr_entries_in_last_block);
+
+	else
+		return grow_add_tail_block(resize);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * These are the value_type functions for the btree elements, which point
+ * to array blocks.
+ */
+static void block_inc(void *context, const void *value)
+{
+	__le64 block_le;
+	struct dm_array_info *info = context;
+
+	memcpy(&block_le, value, sizeof(block_le));
+	dm_tm_inc(info->btree_info.tm, le64_to_cpu(block_le));
+}
+
+static void block_dec(void *context, const void *value)
+{
+	int r;
+	uint64_t b;
+	__le64 block_le;
+	uint32_t ref_count;
+	struct dm_block *block;
+	struct array_block *ab;
+	struct dm_array_info *info = context;
+
+	memcpy(&block_le, value, sizeof(block_le));
+	b = le64_to_cpu(block_le);
+
+	r = dm_tm_ref(info->btree_info.tm, b, &ref_count);
+	if (r) {
+		DMERR_LIMIT("couldn't get reference count for block %llu",
+			    (unsigned long long) b);
+		return;
+	}
+
+	if (ref_count == 1) {
+		/*
+		 * We're about to drop the last reference to this ablock.
+		 * So we need to decrement the ref count of the contents.
+		 */
+		r = get_ablock(info, b, &block, &ab);
+		if (r) {
+			DMERR_LIMIT("couldn't get array block %llu",
+				    (unsigned long long) b);
+			return;
+		}
+
+		dec_ablock_entries(info, ab);
+		unlock_ablock(info, block);
+	}
+
+	dm_tm_dec(info->btree_info.tm, b);
+}
+
+static int block_equal(void *context, const void *value1, const void *value2)
+{
+	return !memcmp(value1, value2, sizeof(__le64));
+}
+
+/*----------------------------------------------------------------*/
+
+void dm_array_info_init(struct dm_array_info *info,
+			struct dm_transaction_manager *tm,
+			struct dm_btree_value_type *vt)
+{
+	struct dm_btree_value_type *bvt = &info->btree_info.value_type;
+
+	memcpy(&info->value_type, vt, sizeof(info->value_type));
+	info->btree_info.tm = tm;
+	info->btree_info.levels = 1;
+
+	bvt->context = info;
+	bvt->size = sizeof(__le64);
+	bvt->inc = block_inc;
+	bvt->dec = block_dec;
+	bvt->equal = block_equal;
+}
+EXPORT_SYMBOL_GPL(dm_array_info_init);
+
+int dm_array_empty(struct dm_array_info *info, dm_block_t *root)
+{
+	return dm_btree_empty(&info->btree_info, root);
+}
+EXPORT_SYMBOL_GPL(dm_array_empty);
+
+static int array_resize(struct dm_array_info *info, dm_block_t root,
+			uint32_t old_size, uint32_t new_size,
+			const void *value, dm_block_t *new_root)
+{
+	int r;
+	struct resize resize;
+
+	if (old_size == new_size)
+		return 0;
+
+	resize.info = info;
+	resize.root = root;
+	resize.size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
+	resize.max_entries = calc_max_entries(info->value_type.size,
+					      resize.size_of_block);
+
+	resize.old_nr_full_blocks = old_size / resize.max_entries;
+	resize.old_nr_entries_in_last_block = old_size % resize.max_entries;
+	resize.new_nr_full_blocks = new_size / resize.max_entries;
+	resize.new_nr_entries_in_last_block = new_size % resize.max_entries;
+	resize.value = value;
+
+	r = ((new_size > old_size) ? grow : shrink)(&resize);
+	if (r)
+		return r;
+
+	*new_root = resize.root;
+	return 0;
+}
+
+int dm_array_resize(struct dm_array_info *info, dm_block_t root,
+		    uint32_t old_size, uint32_t new_size,
+		    const void *value, dm_block_t *new_root)
+		    __dm_written_to_disk(value)
+{
+	int r = array_resize(info, root, old_size, new_size, value, new_root);
+	__dm_unbless_for_disk(value);
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_array_resize);
+
+int dm_array_del(struct dm_array_info *info, dm_block_t root)
+{
+	return dm_btree_del(&info->btree_info, root);
+}
+EXPORT_SYMBOL_GPL(dm_array_del);
+
+int dm_array_get_value(struct dm_array_info *info, dm_block_t root,
+		       uint32_t index, void *value_le)
+{
+	int r;
+	struct dm_block *block;
+	struct array_block *ab;
+	size_t size_of_block;
+	unsigned entry, max_entries;
+
+	size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
+	max_entries = calc_max_entries(info->value_type.size, size_of_block);
+
+	r = lookup_ablock(info, root, index / max_entries, &block, &ab);
+	if (r)
+		return r;
+
+	entry = index % max_entries;
+	if (entry >= le32_to_cpu(ab->nr_entries))
+		r = -ENODATA;
+	else
+		memcpy(value_le, element_at(info, ab, entry),
+		       info->value_type.size);
+
+	unlock_ablock(info, block);
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_array_get_value);
+
+static int array_set_value(struct dm_array_info *info, dm_block_t root,
+			   uint32_t index, const void *value, dm_block_t *new_root)
+{
+	int r;
+	struct dm_block *block;
+	struct array_block *ab;
+	size_t size_of_block;
+	unsigned max_entries;
+	unsigned entry;
+	void *old_value;
+	struct dm_btree_value_type *vt = &info->value_type;
+
+	size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
+	max_entries = calc_max_entries(info->value_type.size, size_of_block);
+
+	r = shadow_ablock(info, &root, index / max_entries, &block, &ab);
+	if (r)
+		return r;
+	*new_root = root;
+
+	entry = index % max_entries;
+	if (entry >= le32_to_cpu(ab->nr_entries)) {
+		r = -ENODATA;
+		goto out;
+	}
+
+	old_value = element_at(info, ab, entry);
+	if (vt->dec &&
+	    (!vt->equal || !vt->equal(vt->context, old_value, value))) {
+		vt->dec(vt->context, old_value);
+		if (vt->inc)
+			vt->inc(vt->context, value);
+	}
+
+	memcpy(old_value, value, info->value_type.size);
+
+out:
+	unlock_ablock(info, block);
+	return r;
+}
+
+int dm_array_set_value(struct dm_array_info *info, dm_block_t root,
+		 uint32_t index, const void *value, dm_block_t *new_root)
+		 __dm_written_to_disk(value)
+{
+	int r;
+
+	r = array_set_value(info, root, index, value, new_root);
+	__dm_unbless_for_disk(value);
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_array_set_value);
+
+struct walk_info {
+	struct dm_array_info *info;
+	int (*fn)(void *context, uint64_t key, void *leaf);
+	void *context;
+};
+
+static int walk_ablock(void *context, uint64_t *keys, void *leaf)
+{
+	struct walk_info *wi = context;
+
+	int r;
+	unsigned i;
+	__le64 block_le;
+	unsigned nr_entries, max_entries;
+	struct dm_block *block;
+	struct array_block *ab;
+
+	memcpy(&block_le, leaf, sizeof(block_le));
+	r = get_ablock(wi->info, le64_to_cpu(block_le), &block, &ab);
+	if (r)
+		return r;
+
+	max_entries = le32_to_cpu(ab->max_entries);
+	nr_entries = le32_to_cpu(ab->nr_entries);
+	for (i = 0; i < nr_entries; i++) {
+		r = wi->fn(wi->context, keys[0] * max_entries + i,
+			   element_at(wi->info, ab, i));
+
+		if (r)
+			break;
+	}
+
+	unlock_ablock(wi->info, block);
+	return r;
+}
+
+int dm_array_walk(struct dm_array_info *info, dm_block_t root,
+		  int (*fn)(void *, uint64_t key, void *leaf),
+		  void *context)
+{
+	struct walk_info wi;
+
+	wi.info = info;
+	wi.fn = fn;
+	wi.context = context;
+
+	return dm_btree_walk(&info->btree_info, root, walk_ablock, &wi);
+}
+EXPORT_SYMBOL_GPL(dm_array_walk);
+
+/*----------------------------------------------------------------*/
diff --git a/drivers/md/persistent-data/dm-array.h b/drivers/md/persistent-data/dm-array.h
new file mode 100644
index 00000000000..ea177d6fa58
--- /dev/null
+++ b/drivers/md/persistent-data/dm-array.h
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+#ifndef _LINUX_DM_ARRAY_H
+#define _LINUX_DM_ARRAY_H
+
+#include "dm-btree.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * The dm-array is a persistent version of an array.  It packs the data
+ * more efficiently than a btree which will result in less disk space use,
+ * and a performance boost.  The element get and set operations are still
+ * O(ln(n)), but with a much smaller constant.
+ *
+ * The value type structure is reused from the btree type to support proper
+ * reference counting of values.
+ *
+ * The arrays implicitly know their length, and bounds are checked for
+ * lookups and updated.  It doesn't store this in an accessible place
+ * because it would waste a whole metadata block.  Make sure you store the
+ * size along with the array root in your encompassing data.
+ *
+ * Array entries are indexed via an unsigned integer starting from zero.
+ * Arrays are not sparse; if you resize an array to have 'n' entries then
+ * 'n - 1' will be the last valid index.
+ *
+ * Typical use:
+ *
+ * a) initialise a dm_array_info structure.  This describes the array
+ *    values and ties it into a specific transaction manager.  It holds no
+ *    instance data; the same info can be used for many similar arrays if
+ *    you wish.
+ *
+ * b) Get yourself a root.  The root is the index of a block of data on the
+ *    disk that holds a particular instance of an array.  You may have a
+ *    pre existing root in your metadata that you wish to use, or you may
+ *    want to create a brand new, empty array with dm_array_empty().
+ *
+ * Like the other data structures in this library, dm_array objects are
+ * immutable between transactions.  Update functions will return you the
+ * root for a _new_ array.  If you've incremented the old root, via
+ * dm_tm_inc(), before calling the update function you may continue to use
+ * it in parallel with the new root.
+ *
+ * c) resize an array with dm_array_resize().
+ *
+ * d) Get a value from the array with dm_array_get_value().
+ *
+ * e) Set a value in the array with dm_array_set_value().
+ *
+ * f) Walk an array of values in index order with dm_array_walk().  More
+ *    efficient than making many calls to dm_array_get_value().
+ *
+ * g) Destroy the array with dm_array_del().  This tells the transaction
+ *    manager that you're no longer using this data structure so it can
+ *    recycle it's blocks.  (dm_array_dec() would be a better name for it,
+ *    but del is in keeping with dm_btree_del()).
+ */
+
+/*
+ * Describes an array.  Don't initialise this structure yourself, use the
+ * init function below.
+ */
+struct dm_array_info {
+	struct dm_transaction_manager *tm;
+	struct dm_btree_value_type value_type;
+	struct dm_btree_info btree_info;
+};
+
+/*
+ * Sets up a dm_array_info structure.  You don't need to do anything with
+ * this structure when you finish using it.
+ *
+ * info - the structure being filled in.
+ * tm   - the transaction manager that should supervise this structure.
+ * vt   - describes the leaf values.
+ */
+void dm_array_info_init(struct dm_array_info *info,
+			struct dm_transaction_manager *tm,
+			struct dm_btree_value_type *vt);
+
+/*
+ * Create an empty, zero length array.
+ *
+ * info - describes the array
+ * root - on success this will be filled out with the root block
+ */
+int dm_array_empty(struct dm_array_info *info, dm_block_t *root);
+
+/*
+ * Resizes the array.
+ *
+ * info - describes the array
+ * root - the root block of the array on disk
+ * old_size - the caller is responsible for remembering the size of
+ *            the array
+ * new_size - can be bigger or smaller than old_size
+ * value - if we're growing the array the new entries will have this value
+ * new_root - on success, points to the new root block
+ *
+ * If growing the inc function for 'value' will be called the appropriate
+ * number of times.  So if the caller is holding a reference they may want
+ * to drop it.
+ */
+int dm_array_resize(struct dm_array_info *info, dm_block_t root,
+		    uint32_t old_size, uint32_t new_size,
+		    const void *value, dm_block_t *new_root)
+	__dm_written_to_disk(value);
+
+/*
+ * Frees a whole array.  The value_type's decrement operation will be called
+ * for all values in the array
+ */
+int dm_array_del(struct dm_array_info *info, dm_block_t root);
+
+/*
+ * Lookup a value in the array
+ *
+ * info - describes the array
+ * root - root block of the array
+ * index - array index
+ * value - the value to be read.  Will be in on-disk format of course.
+ *
+ * -ENODATA will be returned if the index is out of bounds.
+ */
+int dm_array_get_value(struct dm_array_info *info, dm_block_t root,
+		       uint32_t index, void *value);
+
+/*
+ * Set an entry in the array.
+ *
+ * info - describes the array
+ * root - root block of the array
+ * index - array index
+ * value - value to be written to disk.  Make sure you confirm the value is
+ *         in on-disk format with__dm_bless_for_disk() before calling.
+ * new_root - the new root block
+ *
+ * The old value being overwritten will be decremented, the new value
+ * incremented.
+ *
+ * -ENODATA will be returned if the index is out of bounds.
+ */
+int dm_array_set_value(struct dm_array_info *info, dm_block_t root,
+		       uint32_t index, const void *value, dm_block_t *new_root)
+	__dm_written_to_disk(value);
+
+/*
+ * Walk through all the entries in an array.
+ *
+ * info - describes the array
+ * root - root block of the array
+ * fn - called back for every element
+ * context - passed to the callback
+ */
+int dm_array_walk(struct dm_array_info *info, dm_block_t root,
+		  int (*fn)(void *context, uint64_t key, void *leaf),
+		  void *context);
+
+/*----------------------------------------------------------------*/
+
+#endif	/* _LINUX_DM_ARRAY_H */