dm cache: make the 'mq' policy an alias for 'smq'

smq seems to be performing better than the old mq policy in all
situations, as well as using a quarter of the memory.

Make 'mq' an alias for 'smq' when choosing a cache policy.  The tunables
that were present for the old mq are faked, and have no effect.  mq
should be considered deprecated now.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

5 files changed, 87 insertions, 1529 deletions

diff --git a/Documentation/device-mapper/cache-policies.txt b/Documentation/device-mapper/cache-policies.txt
index d9246a32e673..e5062ad18717 100644
--- a/Documentation/device-mapper/cache-policies.txt
+++ b/Documentation/device-mapper/cache-policies.txt
@@ -28,51 +28,16 @@ Overview of supplied cache replacement policies
 multiqueue (mq)
 ---------------
 
-This policy has been deprecated in favor of the smq policy (see below).
+This policy is now an alias for smq (see below).
 
-The multiqueue policy has three sets of 16 queues: one set for entries
-waiting for the cache and another two for those in the cache (a set for
-clean entries and a set for dirty entries).
+The following tunables are accepted, but have no effect:
 
-Cache entries in the queues are aged based on logical time. Entry into
-the cache is based on variable thresholds and queue selection is based
-on hit count on entry. The policy aims to take different cache miss
-costs into account and to adjust to varying load patterns automatically.
-
-Message and constructor argument pairs are:
 	'sequential_threshold <#nr_sequential_ios>'
 	'random_threshold <#nr_random_ios>'
 	'read_promote_adjustment <value>'
 	'write_promote_adjustment <value>'
 	'discard_promote_adjustment <value>'
 
-The sequential threshold indicates the number of contiguous I/Os
-required before a stream is treated as sequential.  Once a stream is
-considered sequential it will bypass the cache.  The random threshold
-is the number of intervening non-contiguous I/Os that must be seen
-before the stream is treated as random again.
-
-The sequential and random thresholds default to 512 and 4 respectively.
-
-Large, sequential I/Os are probably better left on the origin device
-since spindles tend to have good sequential I/O bandwidth.  The
-io_tracker counts contiguous I/Os to try to spot when the I/O is in one
-of these sequential modes.  But there are use-cases for wanting to
-promote sequential blocks to the cache (e.g. fast application startup).
-If sequential threshold is set to 0 the sequential I/O detection is
-disabled and sequential I/O will no longer implicitly bypass the cache.
-Setting the random threshold to 0 does _not_ disable the random I/O
-stream detection.
-
-Internally the mq policy determines a promotion threshold.  If the hit
-count of a block not in the cache goes above this threshold it gets
-promoted to the cache.  The read, write and discard promote adjustment
-tunables allow you to tweak the promotion threshold by adding a small
-value based on the io type.  They default to 4, 8 and 1 respectively.
-If you're trying to quickly warm a new cache device you may wish to
-reduce these to encourage promotion.  Remember to switch them back to
-their defaults after the cache fills though.
-
 Stochastic multiqueue (smq)
 ---------------------------
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 0a2e7273db9e..2ae40913bbc6 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -304,16 +304,6 @@ config DM_CACHE
          algorithms used to select which blocks are promoted, demoted,
          cleaned etc.  It supports writeback and writethrough modes.
 
-config DM_CACHE_MQ
-       tristate "MQ Cache Policy (EXPERIMENTAL)"
-       depends on DM_CACHE
-       default y
-       ---help---
-         A cache policy that uses a multiqueue ordered by recent hit
-         count to select which blocks should be promoted and demoted.
-         This is meant to be a general purpose policy.  It prioritises
-         reads over writes.
-
 config DM_CACHE_SMQ
        tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)"
        depends on DM_CACHE
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 62a65764e8e0..52ba8dd82821 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -12,7 +12,6 @@ dm-log-userspace-y \
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
 dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
-dm-cache-mq-y   += dm-cache-policy-mq.o
 dm-cache-smq-y   += dm-cache-policy-smq.o
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
@@ -55,7 +54,6 @@ obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
 obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
-obj-$(CONFIG_DM_CACHE_MQ)	+= dm-cache-mq.o
 obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
 obj-$(CONFIG_DM_CACHE_CLEANER)	+= dm-cache-cleaner.o
 obj-$(CONFIG_DM_ERA)		+= dm-era.o
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
deleted file mode 100644
index ddb26980cd66..000000000000
--- a/drivers/md/dm-cache-policy-mq.c
+++ /dev/null
@@ -1,1473 +0,0 @@
-/*
- * Copyright (C) 2012 Red Hat. All rights reserved.
- *
- * This file is released under the GPL.
- */
-
-#include "dm-cache-policy.h"
-#include "dm.h"
-
-#include <linux/hash.h>
-#include <linux/jiffies.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-#define DM_MSG_PREFIX "cache-policy-mq"
-
-static struct kmem_cache *mq_entry_cache;
-
-/*----------------------------------------------------------------*/
-
-static unsigned next_power(unsigned n, unsigned min)
-{
-	return roundup_pow_of_two(max(n, min));
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Large, sequential ios are probably better left on the origin device since
- * spindles tend to have good bandwidth.
- *
- * The io_tracker tries to spot when the io is in one of these sequential
- * modes.
- *
- * Two thresholds to switch between random and sequential io mode are defaulting
- * as follows and can be adjusted via the constructor and message interfaces.
- */
-#define RANDOM_THRESHOLD_DEFAULT 4
-#define SEQUENTIAL_THRESHOLD_DEFAULT 512
-
-enum io_pattern {
-	PATTERN_SEQUENTIAL,
-	PATTERN_RANDOM
-};
-
-struct io_tracker {
-	enum io_pattern pattern;
-
-	unsigned nr_seq_samples;
-	unsigned nr_rand_samples;
-	unsigned thresholds[2];
-
-	dm_oblock_t last_end_oblock;
-};
-
-static void iot_init(struct io_tracker *t,
-		     int sequential_threshold, int random_threshold)
-{
-	t->pattern = PATTERN_RANDOM;
-	t->nr_seq_samples = 0;
-	t->nr_rand_samples = 0;
-	t->last_end_oblock = 0;
-	t->thresholds[PATTERN_RANDOM] = random_threshold;
-	t->thresholds[PATTERN_SEQUENTIAL] = sequential_threshold;
-}
-
-static enum io_pattern iot_pattern(struct io_tracker *t)
-{
-	return t->pattern;
-}
-
-static void iot_update_stats(struct io_tracker *t, struct bio *bio)
-{
-	if (bio->bi_iter.bi_sector == from_oblock(t->last_end_oblock) + 1)
-		t->nr_seq_samples++;
-	else {
-		/*
-		 * Just one non-sequential IO is enough to reset the
-		 * counters.
-		 */
-		if (t->nr_seq_samples) {
-			t->nr_seq_samples = 0;
-			t->nr_rand_samples = 0;
-		}
-
-		t->nr_rand_samples++;
-	}
-
-	t->last_end_oblock = to_oblock(bio_end_sector(bio) - 1);
-}
-
-static void iot_check_for_pattern_switch(struct io_tracker *t)
-{
-	switch (t->pattern) {
-	case PATTERN_SEQUENTIAL:
-		if (t->nr_rand_samples >= t->thresholds[PATTERN_RANDOM]) {
-			t->pattern = PATTERN_RANDOM;
-			t->nr_seq_samples = t->nr_rand_samples = 0;
-		}
-		break;
-
-	case PATTERN_RANDOM:
-		if (t->nr_seq_samples >= t->thresholds[PATTERN_SEQUENTIAL]) {
-			t->pattern = PATTERN_SEQUENTIAL;
-			t->nr_seq_samples = t->nr_rand_samples = 0;
-		}
-		break;
-	}
-}
-
-static void iot_examine_bio(struct io_tracker *t, struct bio *bio)
-{
-	iot_update_stats(t, bio);
-	iot_check_for_pattern_switch(t);
-}
-
-/*----------------------------------------------------------------*/
-
-
-/*
- * This queue is divided up into different levels.  Allowing us to push
- * entries to the back of any of the levels.  Think of it as a partially
- * sorted queue.
- */
-#define NR_QUEUE_LEVELS 16u
-#define NR_SENTINELS NR_QUEUE_LEVELS * 3
-
-#define WRITEBACK_PERIOD HZ
-
-struct queue {
-	unsigned nr_elts;
-	bool current_writeback_sentinels;
-	unsigned long next_writeback;
-	struct list_head qs[NR_QUEUE_LEVELS];
-	struct list_head sentinels[NR_SENTINELS];
-};
-
-static void queue_init(struct queue *q)
-{
-	unsigned i;
-
-	q->nr_elts = 0;
-	q->current_writeback_sentinels = false;
-	q->next_writeback = 0;
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		INIT_LIST_HEAD(q->qs + i);
-		INIT_LIST_HEAD(q->sentinels + i);
-		INIT_LIST_HEAD(q->sentinels + NR_QUEUE_LEVELS + i);
-		INIT_LIST_HEAD(q->sentinels + (2 * NR_QUEUE_LEVELS) + i);
-	}
-}
-
-static unsigned queue_size(struct queue *q)
-{
-	return q->nr_elts;
-}
-
-static bool queue_empty(struct queue *q)
-{
-	return q->nr_elts == 0;
-}
-
-/*
- * Insert an entry to the back of the given level.
- */
-static void queue_push(struct queue *q, unsigned level, struct list_head *elt)
-{
-	q->nr_elts++;
-	list_add_tail(elt, q->qs + level);
-}
-
-static void queue_remove(struct queue *q, struct list_head *elt)
-{
-	q->nr_elts--;
-	list_del(elt);
-}
-
-static bool is_sentinel(struct queue *q, struct list_head *h)
-{
-	return (h >= q->sentinels) && (h < (q->sentinels + NR_SENTINELS));
-}
-
-/*
- * Gives us the oldest entry of the lowest popoulated level.  If the first
- * level is emptied then we shift down one level.
- */
-static struct list_head *queue_peek(struct queue *q)
-{
-	unsigned level;
-	struct list_head *h;
-
-	for (level = 0; level < NR_QUEUE_LEVELS; level++)
-		list_for_each(h, q->qs + level)
-			if (!is_sentinel(q, h))
-				return h;
-
-	return NULL;
-}
-
-static struct list_head *queue_pop(struct queue *q)
-{
-	struct list_head *r = queue_peek(q);
-
-	if (r) {
-		q->nr_elts--;
-		list_del(r);
-	}
-
-	return r;
-}
-
-/*
- * Pops an entry from a level that is not past a sentinel.
- */
-static struct list_head *queue_pop_old(struct queue *q)
-{
-	unsigned level;
-	struct list_head *h;
-
-	for (level = 0; level < NR_QUEUE_LEVELS; level++)
-		list_for_each(h, q->qs + level) {
-			if (is_sentinel(q, h))
-				break;
-
-			q->nr_elts--;
-			list_del(h);
-			return h;
-		}
-
-	return NULL;
-}
-
-static struct list_head *list_pop(struct list_head *lh)
-{
-	struct list_head *r = lh->next;
-
-	BUG_ON(!r);
-	list_del_init(r);
-
-	return r;
-}
-
-static struct list_head *writeback_sentinel(struct queue *q, unsigned level)
-{
-	if (q->current_writeback_sentinels)
-		return q->sentinels + NR_QUEUE_LEVELS + level;
-	else
-		return q->sentinels + 2 * NR_QUEUE_LEVELS + level;
-}
-
-static void queue_update_writeback_sentinels(struct queue *q)
-{
-	unsigned i;
-	struct list_head *h;
-
-	if (time_after(jiffies, q->next_writeback)) {
-		for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-			h = writeback_sentinel(q, i);
-			list_del(h);
-			list_add_tail(h, q->qs + i);
-		}
-
-		q->next_writeback = jiffies + WRITEBACK_PERIOD;
-		q->current_writeback_sentinels = !q->current_writeback_sentinels;
-	}
-}
-
-/*
- * Sometimes we want to iterate through entries that have been pushed since
- * a certain event.  We use sentinel entries on the queues to delimit these
- * 'tick' events.
- */
-static void queue_tick(struct queue *q)
-{
-	unsigned i;
-
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		list_del(q->sentinels + i);
-		list_add_tail(q->sentinels + i, q->qs + i);
-	}
-}
-
-typedef void (*iter_fn)(struct list_head *, void *);
-static void queue_iterate_tick(struct queue *q, iter_fn fn, void *context)
-{
-	unsigned i;
-	struct list_head *h;
-
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		list_for_each_prev(h, q->qs + i) {
-			if (is_sentinel(q, h))
-				break;
-
-			fn(h, context);
-		}
-	}
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Describes a cache entry.  Used in both the cache and the pre_cache.
- */
-struct entry {
-	struct hlist_node hlist;
-	struct list_head list;
-	dm_oblock_t oblock;
-
-	/*
-	 * FIXME: pack these better
-	 */
-	bool dirty:1;
-	unsigned hit_count;
-};
-
-/*
- * Rather than storing the cblock in an entry, we allocate all entries in
- * an array, and infer the cblock from the entry position.
- *
- * Free entries are linked together into a list.
- */
-struct entry_pool {
-	struct entry *entries, *entries_end;
-	struct list_head free;
-	unsigned nr_allocated;
-};
-
-static int epool_init(struct entry_pool *ep, unsigned nr_entries)
-{
-	unsigned i;
-
-	ep->entries = vzalloc(sizeof(struct entry) * nr_entries);
-	if (!ep->entries)
-		return -ENOMEM;
-
-	ep->entries_end = ep->entries + nr_entries;
-
-	INIT_LIST_HEAD(&ep->free);
-	for (i = 0; i < nr_entries; i++)
-		list_add(&ep->entries[i].list, &ep->free);
-
-	ep->nr_allocated = 0;
-
-	return 0;
-}
-
-static void epool_exit(struct entry_pool *ep)
-{
-	vfree(ep->entries);
-}
-
-static struct entry *alloc_entry(struct entry_pool *ep)
-{
-	struct entry *e;
-
-	if (list_empty(&ep->free))
-		return NULL;
-
-	e = list_entry(list_pop(&ep->free), struct entry, list);
-	INIT_LIST_HEAD(&e->list);
-	INIT_HLIST_NODE(&e->hlist);
-	ep->nr_allocated++;
-
-	return e;
-}
-
-/*
- * This assumes the cblock hasn't already been allocated.
- */
-static struct entry *alloc_particular_entry(struct entry_pool *ep, dm_cblock_t cblock)
-{
-	struct entry *e = ep->entries + from_cblock(cblock);
-
-	list_del_init(&e->list);
-	INIT_HLIST_NODE(&e->hlist);
-	ep->nr_allocated++;
-
-	return e;
-}
-
-static void free_entry(struct entry_pool *ep, struct entry *e)
-{
-	BUG_ON(!ep->nr_allocated);
-	ep->nr_allocated--;
-	INIT_HLIST_NODE(&e->hlist);
-	list_add(&e->list, &ep->free);
-}
-
-/*
- * Returns NULL if the entry is free.
- */
-static struct entry *epool_find(struct entry_pool *ep, dm_cblock_t cblock)
-{
-	struct entry *e = ep->entries + from_cblock(cblock);
-	return !hlist_unhashed(&e->hlist) ? e : NULL;
-}
-
-static bool epool_empty(struct entry_pool *ep)
-{
-	return list_empty(&ep->free);
-}
-
-static bool in_pool(struct entry_pool *ep, struct entry *e)
-{
-	return e >= ep->entries && e < ep->entries_end;
-}
-
-static dm_cblock_t infer_cblock(struct entry_pool *ep, struct entry *e)
-{
-	return to_cblock(e - ep->entries);
-}
-
-/*----------------------------------------------------------------*/
-
-struct mq_policy {
-	struct dm_cache_policy policy;
-
-	/* protects everything */
-	struct mutex lock;
-	dm_cblock_t cache_size;
-	struct io_tracker tracker;
-
-	/*
-	 * Entries come from two pools, one of pre-cache entries, and one
-	 * for the cache proper.
-	 */
-	struct entry_pool pre_cache_pool;
-	struct entry_pool cache_pool;
-
-	/*
-	 * We maintain three queues of entries.  The cache proper,
-	 * consisting of a clean and dirty queue, contains the currently
-	 * active mappings.  Whereas the pre_cache tracks blocks that
-	 * are being hit frequently and potential candidates for promotion
-	 * to the cache.
-	 */
-	struct queue pre_cache;
-	struct queue cache_clean;
-	struct queue cache_dirty;
-
-	/*
-	 * Keeps track of time, incremented by the core.  We use this to
-	 * avoid attributing multiple hits within the same tick.
-	 *
-	 * Access to tick_protected should be done with the spin lock held.
-	 * It's copied to tick at the start of the map function (within the
-	 * mutex).
-	 */
-	spinlock_t tick_lock;
-	unsigned tick_protected;
-	unsigned tick;
-
-	/*
-	 * A count of the number of times the map function has been called
-	 * and found an entry in the pre_cache or cache.  Currently used to
-	 * calculate the generation.
-	 */
-	unsigned hit_count;
-
-	/*
-	 * A generation is a longish period that is used to trigger some
-	 * book keeping effects.  eg, decrementing hit counts on entries.
-	 * This is needed to allow the cache to evolve as io patterns
-	 * change.
-	 */
-	unsigned generation;
-	unsigned generation_period; /* in lookups (will probably change) */
-
-	unsigned discard_promote_adjustment;
-	unsigned read_promote_adjustment;
-	unsigned write_promote_adjustment;
-
-	/*
-	 * The hash table allows us to quickly find an entry by origin
-	 * block.  Both pre_cache and cache entries are in here.
-	 */
-	unsigned nr_buckets;
-	dm_block_t hash_bits;
-	struct hlist_head *table;
-};
-
-#define DEFAULT_DISCARD_PROMOTE_ADJUSTMENT 1
-#define DEFAULT_READ_PROMOTE_ADJUSTMENT 4
-#define DEFAULT_WRITE_PROMOTE_ADJUSTMENT 8
-#define DISCOURAGE_DEMOTING_DIRTY_THRESHOLD 128
-
-/*----------------------------------------------------------------*/
-
-/*
- * Simple hash table implementation.  Should replace with the standard hash
- * table that's making its way upstream.
- */
-static void hash_insert(struct mq_policy *mq, struct entry *e)
-{
-	unsigned h = hash_64(from_oblock(e->oblock), mq->hash_bits);
-
-	hlist_add_head(&e->hlist, mq->table + h);
-}
-
-static struct entry *hash_lookup(struct mq_policy *mq, dm_oblock_t oblock)
-{
-	unsigned h = hash_64(from_oblock(oblock), mq->hash_bits);
-	struct hlist_head *bucket = mq->table + h;
-	struct entry *e;
-
-	hlist_for_each_entry(e, bucket, hlist)
-		if (e->oblock == oblock) {
-			hlist_del(&e->hlist);
-			hlist_add_head(&e->hlist, bucket);
-			return e;
-		}
-
-	return NULL;
-}
-
-static void hash_remove(struct entry *e)
-{
-	hlist_del(&e->hlist);
-}
-
-/*----------------------------------------------------------------*/
-
-static bool any_free_cblocks(struct mq_policy *mq)
-{
-	return !epool_empty(&mq->cache_pool);
-}
-
-static bool any_clean_cblocks(struct mq_policy *mq)
-{
-	return !queue_empty(&mq->cache_clean);
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Now we get to the meat of the policy.  This section deals with deciding
- * when to to add entries to the pre_cache and cache, and move between
- * them.
- */
-
-/*
- * The queue level is based on the log2 of the hit count.
- */
-static unsigned queue_level(struct entry *e)
-{
-	return min((unsigned) ilog2(e->hit_count), NR_QUEUE_LEVELS - 1u);
-}
-
-static bool in_cache(struct mq_policy *mq, struct entry *e)
-{
-	return in_pool(&mq->cache_pool, e);
-}
-
-/*
- * Inserts the entry into the pre_cache or the cache.  Ensures the cache
- * block is marked as allocated if necc.  Inserts into the hash table.
- * Sets the tick which records when the entry was last moved about.
- */
-static void push(struct mq_policy *mq, struct entry *e)
-{
-	hash_insert(mq, e);
-
-	if (in_cache(mq, e))
-		queue_push(e->dirty ? &mq->cache_dirty : &mq->cache_clean,
-			   queue_level(e), &e->list);
-	else
-		queue_push(&mq->pre_cache, queue_level(e), &e->list);
-}
-
-/*
- * Removes an entry from pre_cache or cache.  Removes from the hash table.
- */
-static void del(struct mq_policy *mq, struct entry *e)
-{
-	if (in_cache(mq, e))
-		queue_remove(e->dirty ? &mq->cache_dirty : &mq->cache_clean, &e->list);
-	else
-		queue_remove(&mq->pre_cache, &e->list);
-
-	hash_remove(e);
-}
-
-/*
- * Like del, except it removes the first entry in the queue (ie. the least
- * recently used).
- */
-static struct entry *pop(struct mq_policy *mq, struct queue *q)
-{
-	struct entry *e;
-	struct list_head *h = queue_pop(q);
-
-	if (!h)
-		return NULL;
-
-	e = container_of(h, struct entry, list);
-	hash_remove(e);
-
-	return e;
-}
-
-static struct entry *pop_old(struct mq_policy *mq, struct queue *q)
-{
-	struct entry *e;
-	struct list_head *h = queue_pop_old(q);
-
-	if (!h)
-		return NULL;
-
-	e = container_of(h, struct entry, list);
-	hash_remove(e);
-
-	return e;
-}
-
-static struct entry *peek(struct queue *q)
-{
-	struct list_head *h = queue_peek(q);
-	return h ? container_of(h, struct entry, list) : NULL;
-}
-
-/*
- * The promotion threshold is adjusted every generation.  As are the counts
- * of the entries.
- *
- * At the moment the threshold is taken by averaging the hit counts of some
- * of the entries in the cache (the first 20 entries across all levels in
- * ascending order, giving preference to the clean entries at each level).
- *
- * We can be much cleverer than this though.  For example, each promotion
- * could bump up the threshold helping to prevent churn.  Much more to do
- * here.
- */
-
-#define MAX_TO_AVERAGE 20
-
-static void check_generation(struct mq_policy *mq)
-{
-	unsigned total = 0, nr = 0, count = 0, level;
-	struct list_head *head;
-	struct entry *e;
-
-	if ((mq->hit_count >= mq->generation_period) && (epool_empty(&mq->cache_pool))) {
-		mq->hit_count = 0;
-		mq->generation++;
-
-		for (level = 0; level < NR_QUEUE_LEVELS && count < MAX_TO_AVERAGE; level++) {
-			head = mq->cache_clean.qs + level;
-			list_for_each_entry(e, head, list) {
-				nr++;
-				total += e->hit_count;
-
-				if (++count >= MAX_TO_AVERAGE)
-					break;
-			}
-
-			head = mq->cache_dirty.qs + level;
-			list_for_each_entry(e, head, list) {
-				nr++;
-				total += e->hit_count;
-
-				if (++count >= MAX_TO_AVERAGE)
-					break;
-			}
-		}
-	}
-}
-
-/*
- * Whenever we use an entry we bump up it's hit counter, and push it to the
- * back to it's current level.
- */
-static void requeue(struct mq_policy *mq, struct entry *e)
-{
-	check_generation(mq);
-	del(mq, e);
-	push(mq, e);
-}
-
-/*
- * Demote the least recently used entry from the cache to the pre_cache.
- * Returns the new cache entry to use, and the old origin block it was
- * mapped to.
- *
- * We drop the hit count on the demoted entry back to 1 to stop it bouncing
- * straight back into the cache if it's subsequently hit.  There are
- * various options here, and more experimentation would be good:
- *
- * - just forget about the demoted entry completely (ie. don't insert it
-     into the pre_cache).
- * - divide the hit count rather that setting to some hard coded value.
- * - set the hit count to a hard coded value other than 1, eg, is it better
- *   if it goes in at level 2?
- */
-static int demote_cblock(struct mq_policy *mq,
-			 struct policy_locker *locker, dm_oblock_t *oblock)
-{
-	struct entry *demoted = peek(&mq->cache_clean);
-
-	if (!demoted)
-		/*
-		 * We could get a block from mq->cache_dirty, but that
-		 * would add extra latency to the triggering bio as it
-		 * waits for the writeback.  Better to not promote this
-		 * time and hope there's a clean block next time this block
-		 * is hit.
-		 */
-		return -ENOSPC;
-
-	if (locker->fn(locker, demoted->oblock))
-		/*
-		 * We couldn't lock the demoted block.
-		 */
-		return -EBUSY;
-
-	del(mq, demoted);
-	*oblock = demoted->oblock;
-	free_entry(&mq->cache_pool, demoted);
-
-	/*
-	 * We used to put the demoted block into the pre-cache, but I think
-	 * it's simpler to just let it work it's way up from zero again.
-	 * Stops blocks flickering in and out of the cache.
-	 */
-
-	return 0;
-}
-
-/*
- * Entries in the pre_cache whose hit count passes the promotion
- * threshold move to the cache proper.  Working out the correct
- * value for the promotion_threshold is crucial to this policy.
- */
-static unsigned promote_threshold(struct mq_policy *mq)
-{
-	struct entry *e;
-
-	if (any_free_cblocks(mq))
-		return 0;
-
-	e = peek(&mq->cache_clean);
-	if (e)
-		return e->hit_count;
-
-	e = peek(&mq->cache_dirty);
-	if (e)
-		return e->hit_count + DISCOURAGE_DEMOTING_DIRTY_THRESHOLD;
-
-	/* This should never happen */
-	return 0;
-}
-
-/*
- * We modify the basic promotion_threshold depending on the specific io.
- *
- * If the origin block has been discarded then there's no cost to copy it
- * to the cache.
- *
- * We bias towards reads, since they can be demoted at no cost if they
- * haven't been dirtied.
- */
-static unsigned adjusted_promote_threshold(struct mq_policy *mq,
-					   bool discarded_oblock, int data_dir)
-{
-	if (data_dir == READ)
-		return promote_threshold(mq) + mq->read_promote_adjustment;
-
-	if (discarded_oblock && (any_free_cblocks(mq) || any_clean_cblocks(mq))) {
-		/*
-		 * We don't need to do any copying at all, so give this a
-		 * very low threshold.
-		 */
-		return mq->discard_promote_adjustment;
-	}
-
-	return promote_threshold(mq) + mq->write_promote_adjustment;
-}
-
-static bool should_promote(struct mq_policy *mq, struct entry *e,
-			   bool discarded_oblock, int data_dir)
-{
-	return e->hit_count >=
-		adjusted_promote_threshold(mq, discarded_oblock, data_dir);
-}
-
-static int cache_entry_found(struct mq_policy *mq,
-			     struct entry *e,
-			     struct policy_result *result)
-{
-	requeue(mq, e);
-
-	if (in_cache(mq, e)) {
-		result->op = POLICY_HIT;
-		result->cblock = infer_cblock(&mq->cache_pool, e);
-	}
-
-	return 0;
-}
-
-/*
- * Moves an entry from the pre_cache to the cache.  The main work is
- * finding which cache block to use.
- */
-static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
-			      struct policy_locker *locker,
-			      struct policy_result *result)
-{
-	int r;
-	struct entry *new_e;
-
-	/* Ensure there's a free cblock in the cache */
-	if (epool_empty(&mq->cache_pool)) {
-		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, locker, &result->old_oblock);
-		if (r) {
-			result->op = POLICY_MISS;
-			return 0;
-		}
-
-	} else
-		result->op = POLICY_NEW;
-
-	new_e = alloc_entry(&mq->cache_pool);
-	BUG_ON(!new_e);
-
-	new_e->oblock = e->oblock;
-	new_e->dirty = false;
-	new_e->hit_count = e->hit_count;
-
-	del(mq, e);
-	free_entry(&mq->pre_cache_pool, e);
-	push(mq, new_e);
-
-	result->cblock = infer_cblock(&mq->cache_pool, new_e);
-
-	return 0;
-}
-
-static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
-				 bool can_migrate, bool discarded_oblock,
-				 int data_dir, struct policy_locker *locker,
-				 struct policy_result *result)
-{
-	int r = 0;
-
-	if (!should_promote(mq, e, discarded_oblock, data_dir)) {
-		requeue(mq, e);
-		result->op = POLICY_MISS;
-
-	} else if (!can_migrate)
-		r = -EWOULDBLOCK;
-
-	else {
-		requeue(mq, e);
-		r = pre_cache_to_cache(mq, e, locker, result);
-	}
-
-	return r;
-}
-
-static void insert_in_pre_cache(struct mq_policy *mq,
-				dm_oblock_t oblock)
-{
-	struct entry *e = alloc_entry(&mq->pre_cache_pool);
-
-	if (!e)
-		/*
-		 * There's no spare entry structure, so we grab the least
-		 * used one from the pre_cache.
-		 */
-		e = pop(mq, &mq->pre_cache);
-
-	if (unlikely(!e)) {
-		DMWARN("couldn't pop from pre cache");
-		return;
-	}
-
-	e->dirty = false;
-	e->oblock = oblock;
-	e->hit_count = 1;
-	push(mq, e);
-}
-
-static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
-			    struct policy_locker *locker,
-			    struct policy_result *result)
-{
-	int r;
-	struct entry *e;
-
-	if (epool_empty(&mq->cache_pool)) {
-		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, locker, &result->old_oblock);
-		if (unlikely(r)) {
-			result->op = POLICY_MISS;
-			insert_in_pre_cache(mq, oblock);
-			return;
-		}
-
-		/*
-		 * This will always succeed, since we've just demoted.
-		 */
-		e = alloc_entry(&mq->cache_pool);
-		BUG_ON(!e);
-
-	} else {
-		e = alloc_entry(&mq->cache_pool);
-		result->op = POLICY_NEW;
-	}
-
-	e->oblock = oblock;
-	e->dirty = false;
-	e->hit_count = 1;
-	push(mq, e);
-
-	result->cblock = infer_cblock(&mq->cache_pool, e);
-}
-
-static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
-			  bool can_migrate, bool discarded_oblock,
-			  int data_dir, struct policy_locker *locker,
-			  struct policy_result *result)
-{
-	if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) <= 1) {
-		if (can_migrate)
-			insert_in_cache(mq, oblock, locker, result);
-		else
-			return -EWOULDBLOCK;
-	} else {
-		insert_in_pre_cache(mq, oblock);
-		result->op = POLICY_MISS;
-	}
-
-	return 0;
-}
-
-/*
- * Looks the oblock up in the hash table, then decides whether to put in
- * pre_cache, or cache etc.
- */
-static int map(struct mq_policy *mq, dm_oblock_t oblock,
-	       bool can_migrate, bool discarded_oblock,
-	       int data_dir, struct policy_locker *locker,
-	       struct policy_result *result)
-{
-	int r = 0;
-	struct entry *e = hash_lookup(mq, oblock);
-
-	if (e && in_cache(mq, e))
-		r = cache_entry_found(mq, e, result);
-
-	else if (mq->tracker.thresholds[PATTERN_SEQUENTIAL] &&
-		 iot_pattern(&mq->tracker) == PATTERN_SEQUENTIAL)
-		result->op = POLICY_MISS;
-
-	else if (e)
-		r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock,
-					  data_dir, locker, result);
-
-	else
-		r = no_entry_found(mq, oblock, can_migrate, discarded_oblock,
-				   data_dir, locker, result);
-
-	if (r == -EWOULDBLOCK)
-		result->op = POLICY_MISS;
-
-	return r;
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Public interface, via the policy struct.  See dm-cache-policy.h for a
- * description of these.
- */
-
-static struct mq_policy *to_mq_policy(struct dm_cache_policy *p)
-{
-	return container_of(p, struct mq_policy, policy);
-}
-
-static void mq_destroy(struct dm_cache_policy *p)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	vfree(mq->table);
-	epool_exit(&mq->cache_pool);
-	epool_exit(&mq->pre_cache_pool);
-	kfree(mq);
-}
-
-static void update_pre_cache_hits(struct list_head *h, void *context)
-{
-	struct entry *e = container_of(h, struct entry, list);
-	e->hit_count++;
-}
-
-static void update_cache_hits(struct list_head *h, void *context)
-{
-	struct mq_policy *mq = context;
-	struct entry *e = container_of(h, struct entry, list);
-	e->hit_count++;
-	mq->hit_count++;
-}
-
-static void copy_tick(struct mq_policy *mq)
-{
-	unsigned long flags, tick;
-
-	spin_lock_irqsave(&mq->tick_lock, flags);
-	tick = mq->tick_protected;
-	if (tick != mq->tick) {
-		queue_iterate_tick(&mq->pre_cache, update_pre_cache_hits, mq);
-		queue_iterate_tick(&mq->cache_dirty, update_cache_hits, mq);
-		queue_iterate_tick(&mq->cache_clean, update_cache_hits, mq);
-		mq->tick = tick;
-	}
-
-	queue_tick(&mq->pre_cache);
-	queue_tick(&mq->cache_dirty);
-	queue_tick(&mq->cache_clean);
-	queue_update_writeback_sentinels(&mq->cache_dirty);
-	spin_unlock_irqrestore(&mq->tick_lock, flags);
-}
-
-static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
-		  bool can_block, bool ca