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-bio-record.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);
}

/*----------------------------------------------------------------*/

/*
 * There are a couple of places where we let a bio run, but want to do some
 * work before calling its endio function.  We do this by temporarily
 * changing the endio fn.
 */
struct dm_hook_info {
	bio_end_io_t *bi_end_io;
	void *bi_private;
};

static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio,
			bio_end_io_t *bi_end_io, void *bi_private)
{
	h->bi_end_io = bio->bi_end_io;
	h->bi_private = bio->bi_private;

	bio->bi_end_io = bi_end_io;
	bio->bi_private = bi_private;
}

static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
{
	bio->bi_end_io = h->bi_end_io;
	bio->bi_private = h->bi_private;
}

/*----------------------------------------------------------------*/

#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
 * between 32KB and 1GB.
 */
#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (32 * 1024 >> SECTOR_SHIFT)
#define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT)

/*
 * FIXME: the cache is read/write for the time being.
 */
enum cache_metadata_mode {
	CM_WRITE,		/* metadata may be changed */
	CM_READ_ONLY,		/* metadata may not be changed */
};

enum cache_io_mode {
	/*
	 * Data is written to cached blocks only.  These blocks are marked
	 * dirty.  If you lose the cache device you will lose data.
	 * Potential performance increase for both reads and writes.
	 */
	CM_IO_WRITEBACK,

	/*
	 * Data is written to both cache and origin.  Blocks are never
	 * dirty.  Potential performance benfit for reads only.
	 */
	CM_IO_WRITETHROUGH,

	/*
	 * A degraded mode useful for various cache coherency situations
	 * (eg, rolling back snapshots).  Reads and writes always go to the
	 * origin.  If a write goes to a cached oblock, then the cache
	 * block is invalidated.
	 */
	CM_IO_PASSTHROUGH
};

struct cache_features {
	enum cache_metadata_mode mode;
	enum cache_io_mode io_mode;
};

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;

	struct dm_cache_metadata *cmd;

	/*
	 * 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;

	/*
	 * 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;

	spinlock_t lock;
	struct bio_list deferred_bios;
	struct bio_list deferred_flush_bios;
	struct bio_list deferred_writethrough_bios;
	struct list_head quiesced_migrations;
	struct list_head completed_migrations;
	struct list_head need_commit_migrations;
	sector_t migration_threshold;
	wait_queue_head_t migration_wait;
	atomic_t nr_migrations;

	wait_queue_head_t quiescing_wait;
	atomic_t quiescing;
	atomic_t quiescing_ack;

	/*
	 * cache_size entries, dirty if set
	 */
	dm_cblock_t nr_dirty;
	unsigned long *dirty_bitset;

	/*
	 * origin_blocks entries, discarded if set.
	 */
	dm_dblock_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
	 * save it and regurgitate.
	 */
	unsigned nr_ctr_args;
	const char **ctr_args;

	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 commit_requested:1;
	bool loaded_mappings:1;
	bool loaded_discards:1;

	/*
	 * Cache features such as write-through.
	 */
	struct cache_features features;

	struct cache_stats stats;
};

struct per_bio_data {
	bool tick:1;
	unsigned req_nr:2;
	struct dm_deferred_entry *all_io_entry;

	/*
	 * writethrough fields.  These MUST remain at the end of this
	 * structure and the 'cache' member must be the first as it
	 * is used to determine the offset of the writethrough fields.
	 */
	struct cache *cache;
	dm_cblock_t cblock;
	struct dm_hook_info hook_info;
	struct dm_bio_details bio_details;
};

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;
	bool requeue_holder: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;
}

/* gcc on ARM generates spurious references to __udivdi3 and __umoddi3 */
#if defined(CONFIG_ARM) && __GNUC__ == 4 && __GNUC_MINOR__ <= 6
__always_inline
#endif
static dm_block_t block_div(dm_block_t b, uint32_t n)
{
	do_div(b, 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)
{
	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
 *--------------------------------------------------------------*/

/*
 * If using writeback, leave out struct per_bio_data's writethrough fields.
 */
#define PB_DATA_SIZE_WB (offsetof(struct per_bio_data, cache))
#define PB_DATA_SIZE_WT (sizeof(struct per_bio_data))

static bool writethrough_mode(struct cache_features *f)
{
	return f->io_mode == CM_IO_WRITETHROUGH;
}

static bool writeback_mode(struct cache_features *f)
{
	return f->io_mode == CM_IO_WRITEBACK;
}

static bool passthrough_mode(struct cache_features *f)
{
	return f->io_mode == CM_IO_PASSTHROUGH;
}

static size_t get_per_bio_data_size(struct cache *cache)
{
	return writethrough_mode(&cache->features) ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB;
}

static struct per_bio_data *get_per_bio_data(struct bio *bio, size_t data_size)
{
	struct per_bio_data *pb = dm_per_bio_data(bio, data_size);
	BUG_ON(!pb);
	return pb;
}

static struct per_bio_data *init_per_bio_data(struct bio *bio, size_t data_size)
{
	struct per_bio_data *pb = get_per_bio_data(bio, data_size);

	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;
	size_t pb_data_size = get_per_bio_data_size(cache);
	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);

	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)
{
	check_if_tick_bio_needed(cache, 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));
	}
}

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);
}

static void defer_writethrough_bio(struct cache *cache, struct bio *bio)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_add(&cache->deferred_writethrough_bios, bio);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void writethrough_endio(struct bio *bio, int err)
{
	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);

	dm_unhook_bio(&pb->hook_info, bio);

	if (err) {
		bio_endio(bio, err);
		return;
	}

	dm_bio_restore(&pb->bio_details, bio);
	remap_to_cache(pb->cache, bio, pb->cblock);

	/*
	 * We can't issue this bio directly, since we're in interrupt
	 * context.  So it gets put on a bio list for processing by the
	 * worker thread.
	 */
	defer_writethrough_bio(pb->cache, bio);
}

/*
 * When running in writethrough mode we need to send writes to clean blocks
 * to both the cache and origin devices.  In future we'd like to clone the
 * bio and send them in parallel, but for now we're doing them in
 * series as this is easier.
 */
static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio,
				       dm_oblock_t oblock, dm_cblock_t cblock)
{
	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);

	pb->cache = cache;
	pb->cblock = cblock;
	dm_hook_bio(&pb->hook_info, bio, writethrough_endio, NULL);
	dm_bio_record(&pb->bio_details, bio);

	remap_to_origin_clear_discard(pb->cache, bio, oblock);
}

/*----------------------------------------------------------------
 * 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)
{
	struct cache *cache = mg->cache;
	free_migration(mg);
	dec_nr_migrations(cache);
}

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 ? false : true);
		if (mg->promote)
			cell_defer(cache, mg->new_ocell, true);
	} else {
		DMWARN_LIMIT("promotion failed; couldn't copy block");
		policy_remove_mapping(cache->policy, mg->new_oblock);
		cell_defer(cache, mg->new_ocell, true);
	}

	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 ? false : true);

		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 {
		if (mg->requeue_holder)
			cell_defer(cache, mg->new_ocell, true);
		else {
			bio_endio(mg->new_ocell->holder, 0);
			cell_defer(cache, mg->new_ocell, false);
		}
		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) {
		DMERR_LIMIT("issuing migration failed");
		migration_failure(mg);
	}
}

static void overwrite_endio(struct bio *bio, int err)
{
	struct dm_cache_migration *mg = bio->bi_private;
	struct cache *cache = mg->cache;
	size_t pb_data_size = get_per_bio_data_size(cache);
	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
	unsigned long flags;

	if (err)
		mg->err = true;

	spin_lock_irqsave(&cache->lock, flags);
	list_add_tail(&mg->list, &cache->completed_migrations);
	dm_unhook_bio(&pb->hook_info, bio);
	mg->requeue_holder = false;
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void issue_overwrite(struct dm_cache_migration *mg, struct bio *bio)
{
	size_t pb_data_size = get_per_bio_data_size(mg->cache);
	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);

	dm_hook_bio(&pb->hook_info, bio, overwrite_endio, mg);
	remap_to_cache_dirty(mg->cache, bio, mg->new_oblock, mg->cblock);
	generic_make_request(bio);
}

static bool bio_writes_complete_block(struct cache *cache, struct bio *bio)
{
	return (bio_data_dir(bio) == WRITE) &&
		(bio->bi_size == (cache->sectors_per_block << SECTOR_SHIFT));