// SPDX-License-Identifier: GPL-2.0-or-later
|
/*
|
* zswap.c - zswap driver file
|
*
|
* zswap is a backend for frontswap that takes pages that are in the process
|
* of being swapped out and attempts to compress and store them in a
|
* RAM-based memory pool. This can result in a significant I/O reduction on
|
* the swap device and, in the case where decompressing from RAM is faster
|
* than reading from the swap device, can also improve workload performance.
|
*
|
* Copyright (C) 2012 Seth Jennings <sjenning@linux.vnet.ibm.com>
|
*/
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
#include <linux/module.h>
|
#include <linux/cpu.h>
|
#include <linux/highmem.h>
|
#include <linux/slab.h>
|
#include <linux/spinlock.h>
|
#include <linux/types.h>
|
#include <linux/atomic.h>
|
#include <linux/frontswap.h>
|
#include <linux/rbtree.h>
|
#include <linux/swap.h>
|
#include <linux/crypto.h>
|
#include <linux/mempool.h>
|
#include <linux/zpool.h>
|
|
#include <linux/mm_types.h>
|
#include <linux/page-flags.h>
|
#include <linux/swapops.h>
|
#include <linux/writeback.h>
|
#include <linux/pagemap.h>
|
#include <linux/workqueue.h>
|
|
/*********************************
|
* statistics
|
**********************************/
|
/* Total bytes used by the compressed storage */
|
static u64 zswap_pool_total_size;
|
/* The number of compressed pages currently stored in zswap */
|
static atomic_t zswap_stored_pages = ATOMIC_INIT(0);
|
/* The number of same-value filled pages currently stored in zswap */
|
static atomic_t zswap_same_filled_pages = ATOMIC_INIT(0);
|
|
/*
|
* The statistics below are not protected from concurrent access for
|
* performance reasons so they may not be a 100% accurate. However,
|
* they do provide useful information on roughly how many times a
|
* certain event is occurring.
|
*/
|
|
/* Pool limit was hit (see zswap_max_pool_percent) */
|
static u64 zswap_pool_limit_hit;
|
/* Pages written back when pool limit was reached */
|
static u64 zswap_written_back_pages;
|
/* Store failed due to a reclaim failure after pool limit was reached */
|
static u64 zswap_reject_reclaim_fail;
|
/* Compressed page was too big for the allocator to (optimally) store */
|
static u64 zswap_reject_compress_poor;
|
/* Store failed because underlying allocator could not get memory */
|
static u64 zswap_reject_alloc_fail;
|
/* Store failed because the entry metadata could not be allocated (rare) */
|
static u64 zswap_reject_kmemcache_fail;
|
/* Duplicate store was encountered (rare) */
|
static u64 zswap_duplicate_entry;
|
|
/* Shrinker work queue */
|
static struct workqueue_struct *shrink_wq;
|
/* Pool limit was hit, we need to calm down */
|
static bool zswap_pool_reached_full;
|
|
/*********************************
|
* tunables
|
**********************************/
|
|
#define ZSWAP_PARAM_UNSET ""
|
|
/* Enable/disable zswap */
|
static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON);
|
static int zswap_enabled_param_set(const char *,
|
const struct kernel_param *);
|
static struct kernel_param_ops zswap_enabled_param_ops = {
|
.set = zswap_enabled_param_set,
|
.get = param_get_bool,
|
};
|
module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
|
|
/* Crypto compressor to use */
|
static char *zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
|
static int zswap_compressor_param_set(const char *,
|
const struct kernel_param *);
|
static struct kernel_param_ops zswap_compressor_param_ops = {
|
.set = zswap_compressor_param_set,
|
.get = param_get_charp,
|
.free = param_free_charp,
|
};
|
module_param_cb(compressor, &zswap_compressor_param_ops,
|
&zswap_compressor, 0644);
|
|
/* Compressed storage zpool to use */
|
static char *zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT;
|
static int zswap_zpool_param_set(const char *, const struct kernel_param *);
|
static struct kernel_param_ops zswap_zpool_param_ops = {
|
.set = zswap_zpool_param_set,
|
.get = param_get_charp,
|
.free = param_free_charp,
|
};
|
module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_type, 0644);
|
|
/* The maximum percentage of memory that the compressed pool can occupy */
|
static unsigned int zswap_max_pool_percent = 20;
|
module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644);
|
|
/* The threshold for accepting new pages after the max_pool_percent was hit */
|
static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */
|
module_param_named(accept_threshold_percent, zswap_accept_thr_percent,
|
uint, 0644);
|
|
/* Enable/disable handling same-value filled pages (enabled by default) */
|
static bool zswap_same_filled_pages_enabled = true;
|
module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled,
|
bool, 0644);
|
|
/*********************************
|
* data structures
|
**********************************/
|
|
struct zswap_pool {
|
struct zpool *zpool;
|
struct crypto_comp * __percpu *tfm;
|
struct kref kref;
|
struct list_head list;
|
struct work_struct release_work;
|
struct work_struct shrink_work;
|
struct hlist_node node;
|
char tfm_name[CRYPTO_MAX_ALG_NAME];
|
};
|
|
/*
|
* struct zswap_entry
|
*
|
* This structure contains the metadata for tracking a single compressed
|
* page within zswap.
|
*
|
* rbnode - links the entry into red-black tree for the appropriate swap type
|
* offset - the swap offset for the entry. Index into the red-black tree.
|
* refcount - the number of outstanding reference to the entry. This is needed
|
* to protect against premature freeing of the entry by code
|
* concurrent calls to load, invalidate, and writeback. The lock
|
* for the zswap_tree structure that contains the entry must
|
* be held while changing the refcount. Since the lock must
|
* be held, there is no reason to also make refcount atomic.
|
* length - the length in bytes of the compressed page data. Needed during
|
* decompression. For a same value filled page length is 0.
|
* pool - the zswap_pool the entry's data is in
|
* handle - zpool allocation handle that stores the compressed page data
|
* value - value of the same-value filled pages which have same content
|
*/
|
struct zswap_entry {
|
struct rb_node rbnode;
|
pgoff_t offset;
|
int refcount;
|
unsigned int length;
|
struct zswap_pool *pool;
|
union {
|
unsigned long handle;
|
unsigned long value;
|
};
|
};
|
|
struct zswap_header {
|
swp_entry_t swpentry;
|
};
|
|
/*
|
* The tree lock in the zswap_tree struct protects a few things:
|
* - the rbtree
|
* - the refcount field of each entry in the tree
|
*/
|
struct zswap_tree {
|
struct rb_root rbroot;
|
spinlock_t lock;
|
};
|
|
static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
|
|
/* RCU-protected iteration */
|
static LIST_HEAD(zswap_pools);
|
/* protects zswap_pools list modification */
|
static DEFINE_SPINLOCK(zswap_pools_lock);
|
/* pool counter to provide unique names to zpool */
|
static atomic_t zswap_pools_count = ATOMIC_INIT(0);
|
|
/* used by param callback function */
|
static bool zswap_init_started;
|
|
/* fatal error during init */
|
static bool zswap_init_failed;
|
|
/* init completed, but couldn't create the initial pool */
|
static bool zswap_has_pool;
|
|
/*********************************
|
* helpers and fwd declarations
|
**********************************/
|
|
#define zswap_pool_debug(msg, p) \
|
pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name, \
|
zpool_get_type((p)->zpool))
|
|
static int zswap_writeback_entry(struct zpool *pool, unsigned long handle);
|
static int zswap_pool_get(struct zswap_pool *pool);
|
static void zswap_pool_put(struct zswap_pool *pool);
|
|
static const struct zpool_ops zswap_zpool_ops = {
|
.evict = zswap_writeback_entry
|
};
|
|
static bool zswap_is_full(void)
|
{
|
return totalram_pages() * zswap_max_pool_percent / 100 <
|
DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
|
}
|
|
static bool zswap_can_accept(void)
|
{
|
return totalram_pages() * zswap_accept_thr_percent / 100 *
|
zswap_max_pool_percent / 100 >
|
DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
|
}
|
|
static void zswap_update_total_size(void)
|
{
|
struct zswap_pool *pool;
|
u64 total = 0;
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(pool, &zswap_pools, list)
|
total += zpool_get_total_size(pool->zpool);
|
|
rcu_read_unlock();
|
|
zswap_pool_total_size = total;
|
}
|
|
/*********************************
|
* zswap entry functions
|
**********************************/
|
static struct kmem_cache *zswap_entry_cache;
|
|
static int __init zswap_entry_cache_create(void)
|
{
|
zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
|
return zswap_entry_cache == NULL;
|
}
|
|
static void __init zswap_entry_cache_destroy(void)
|
{
|
kmem_cache_destroy(zswap_entry_cache);
|
}
|
|
static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
|
{
|
struct zswap_entry *entry;
|
entry = kmem_cache_alloc(zswap_entry_cache, gfp);
|
if (!entry)
|
return NULL;
|
entry->refcount = 1;
|
RB_CLEAR_NODE(&entry->rbnode);
|
return entry;
|
}
|
|
static void zswap_entry_cache_free(struct zswap_entry *entry)
|
{
|
kmem_cache_free(zswap_entry_cache, entry);
|
}
|
|
/*********************************
|
* rbtree functions
|
**********************************/
|
static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
|
{
|
struct rb_node *node = root->rb_node;
|
struct zswap_entry *entry;
|
|
while (node) {
|
entry = rb_entry(node, struct zswap_entry, rbnode);
|
if (entry->offset > offset)
|
node = node->rb_left;
|
else if (entry->offset < offset)
|
node = node->rb_right;
|
else
|
return entry;
|
}
|
return NULL;
|
}
|
|
/*
|
* In the case that a entry with the same offset is found, a pointer to
|
* the existing entry is stored in dupentry and the function returns -EEXIST
|
*/
|
static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
|
struct zswap_entry **dupentry)
|
{
|
struct rb_node **link = &root->rb_node, *parent = NULL;
|
struct zswap_entry *myentry;
|
|
while (*link) {
|
parent = *link;
|
myentry = rb_entry(parent, struct zswap_entry, rbnode);
|
if (myentry->offset > entry->offset)
|
link = &(*link)->rb_left;
|
else if (myentry->offset < entry->offset)
|
link = &(*link)->rb_right;
|
else {
|
*dupentry = myentry;
|
return -EEXIST;
|
}
|
}
|
rb_link_node(&entry->rbnode, parent, link);
|
rb_insert_color(&entry->rbnode, root);
|
return 0;
|
}
|
|
static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
|
{
|
if (!RB_EMPTY_NODE(&entry->rbnode)) {
|
rb_erase(&entry->rbnode, root);
|
RB_CLEAR_NODE(&entry->rbnode);
|
}
|
}
|
|
/*
|
* Carries out the common pattern of freeing and entry's zpool allocation,
|
* freeing the entry itself, and decrementing the number of stored pages.
|
*/
|
static void zswap_free_entry(struct zswap_entry *entry)
|
{
|
if (!entry->length)
|
atomic_dec(&zswap_same_filled_pages);
|
else {
|
zpool_free(entry->pool->zpool, entry->handle);
|
zswap_pool_put(entry->pool);
|
}
|
zswap_entry_cache_free(entry);
|
atomic_dec(&zswap_stored_pages);
|
zswap_update_total_size();
|
}
|
|
/* caller must hold the tree lock */
|
static void zswap_entry_get(struct zswap_entry *entry)
|
{
|
entry->refcount++;
|
}
|
|
/* caller must hold the tree lock
|
* remove from the tree and free it, if nobody reference the entry
|
*/
|
static void zswap_entry_put(struct zswap_tree *tree,
|
struct zswap_entry *entry)
|
{
|
int refcount = --entry->refcount;
|
|
BUG_ON(refcount < 0);
|
if (refcount == 0) {
|
zswap_rb_erase(&tree->rbroot, entry);
|
zswap_free_entry(entry);
|
}
|
}
|
|
/* caller must hold the tree lock */
|
static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
|
pgoff_t offset)
|
{
|
struct zswap_entry *entry;
|
|
entry = zswap_rb_search(root, offset);
|
if (entry)
|
zswap_entry_get(entry);
|
|
return entry;
|
}
|
|
/*********************************
|
* per-cpu code
|
**********************************/
|
static DEFINE_PER_CPU(u8 *, zswap_dstmem);
|
|
static int zswap_dstmem_prepare(unsigned int cpu)
|
{
|
u8 *dst;
|
|
dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
|
if (!dst)
|
return -ENOMEM;
|
|
per_cpu(zswap_dstmem, cpu) = dst;
|
return 0;
|
}
|
|
static int zswap_dstmem_dead(unsigned int cpu)
|
{
|
u8 *dst;
|
|
dst = per_cpu(zswap_dstmem, cpu);
|
kfree(dst);
|
per_cpu(zswap_dstmem, cpu) = NULL;
|
|
return 0;
|
}
|
|
static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
|
{
|
struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
|
struct crypto_comp *tfm;
|
|
if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
|
return 0;
|
|
tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
|
if (IS_ERR_OR_NULL(tfm)) {
|
pr_err("could not alloc crypto comp %s : %ld\n",
|
pool->tfm_name, PTR_ERR(tfm));
|
return -ENOMEM;
|
}
|
*per_cpu_ptr(pool->tfm, cpu) = tfm;
|
return 0;
|
}
|
|
static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
|
{
|
struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
|
struct crypto_comp *tfm;
|
|
tfm = *per_cpu_ptr(pool->tfm, cpu);
|
if (!IS_ERR_OR_NULL(tfm))
|
crypto_free_comp(tfm);
|
*per_cpu_ptr(pool->tfm, cpu) = NULL;
|
return 0;
|
}
|
|
/*********************************
|
* pool functions
|
**********************************/
|
|
static struct zswap_pool *__zswap_pool_current(void)
|
{
|
struct zswap_pool *pool;
|
|
pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list);
|
WARN_ONCE(!pool && zswap_has_pool,
|
"%s: no page storage pool!\n", __func__);
|
|
return pool;
|
}
|
|
static struct zswap_pool *zswap_pool_current(void)
|
{
|
assert_spin_locked(&zswap_pools_lock);
|
|
return __zswap_pool_current();
|
}
|
|
static struct zswap_pool *zswap_pool_current_get(void)
|
{
|
struct zswap_pool *pool;
|
|
rcu_read_lock();
|
|
pool = __zswap_pool_current();
|
if (!zswap_pool_get(pool))
|
pool = NULL;
|
|
rcu_read_unlock();
|
|
return pool;
|
}
|
|
static struct zswap_pool *zswap_pool_last_get(void)
|
{
|
struct zswap_pool *pool, *last = NULL;
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(pool, &zswap_pools, list)
|
last = pool;
|
WARN_ONCE(!last && zswap_has_pool,
|
"%s: no page storage pool!\n", __func__);
|
if (!zswap_pool_get(last))
|
last = NULL;
|
|
rcu_read_unlock();
|
|
return last;
|
}
|
|
/* type and compressor must be null-terminated */
|
static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
|
{
|
struct zswap_pool *pool;
|
|
assert_spin_locked(&zswap_pools_lock);
|
|
list_for_each_entry_rcu(pool, &zswap_pools, list) {
|
if (strcmp(pool->tfm_name, compressor))
|
continue;
|
if (strcmp(zpool_get_type(pool->zpool), type))
|
continue;
|
/* if we can't get it, it's about to be destroyed */
|
if (!zswap_pool_get(pool))
|
continue;
|
return pool;
|
}
|
|
return NULL;
|
}
|
|
static void shrink_worker(struct work_struct *w)
|
{
|
struct zswap_pool *pool = container_of(w, typeof(*pool),
|
shrink_work);
|
|
if (zpool_shrink(pool->zpool, 1, NULL))
|
zswap_reject_reclaim_fail++;
|
zswap_pool_put(pool);
|
}
|
|
static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
|
{
|
struct zswap_pool *pool;
|
char name[38]; /* 'zswap' + 32 char (max) num + \0 */
|
gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
|
int ret;
|
|
if (!zswap_has_pool) {
|
/* if either are unset, pool initialization failed, and we
|
* need both params to be set correctly before trying to
|
* create a pool.
|
*/
|
if (!strcmp(type, ZSWAP_PARAM_UNSET))
|
return NULL;
|
if (!strcmp(compressor, ZSWAP_PARAM_UNSET))
|
return NULL;
|
}
|
|
pool = kzalloc(sizeof(*pool), GFP_KERNEL);
|
if (!pool)
|
return NULL;
|
|
/* unique name for each pool specifically required by zsmalloc */
|
snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count));
|
|
pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops);
|
if (!pool->zpool) {
|
pr_err("%s zpool not available\n", type);
|
goto error;
|
}
|
pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
|
|
strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
|
pool->tfm = alloc_percpu(struct crypto_comp *);
|
if (!pool->tfm) {
|
pr_err("percpu alloc failed\n");
|
goto error;
|
}
|
|
ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
|
&pool->node);
|
if (ret)
|
goto error;
|
pr_debug("using %s compressor\n", pool->tfm_name);
|
|
/* being the current pool takes 1 ref; this func expects the
|
* caller to always add the new pool as the current pool
|
*/
|
kref_init(&pool->kref);
|
INIT_LIST_HEAD(&pool->list);
|
INIT_WORK(&pool->shrink_work, shrink_worker);
|
|
zswap_pool_debug("created", pool);
|
|
return pool;
|
|
error:
|
free_percpu(pool->tfm);
|
if (pool->zpool)
|
zpool_destroy_pool(pool->zpool);
|
kfree(pool);
|
return NULL;
|
}
|
|
static __init struct zswap_pool *__zswap_pool_create_fallback(void)
|
{
|
bool has_comp, has_zpool;
|
|
has_comp = crypto_has_comp(zswap_compressor, 0, 0);
|
if (!has_comp && strcmp(zswap_compressor,
|
CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) {
|
pr_err("compressor %s not available, using default %s\n",
|
zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT);
|
param_free_charp(&zswap_compressor);
|
zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
|
has_comp = crypto_has_comp(zswap_compressor, 0, 0);
|
}
|
if (!has_comp) {
|
pr_err("default compressor %s not available\n",
|
zswap_compressor);
|
param_free_charp(&zswap_compressor);
|
zswap_compressor = ZSWAP_PARAM_UNSET;
|
}
|
|
has_zpool = zpool_has_pool(zswap_zpool_type);
|
if (!has_zpool && strcmp(zswap_zpool_type,
|
CONFIG_ZSWAP_ZPOOL_DEFAULT)) {
|
pr_err("zpool %s not available, using default %s\n",
|
zswap_zpool_type, CONFIG_ZSWAP_ZPOOL_DEFAULT);
|
param_free_charp(&zswap_zpool_type);
|
zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT;
|
has_zpool = zpool_has_pool(zswap_zpool_type);
|
}
|
if (!has_zpool) {
|
pr_err("default zpool %s not available\n",
|
zswap_zpool_type);
|
param_free_charp(&zswap_zpool_type);
|
zswap_zpool_type = ZSWAP_PARAM_UNSET;
|
}
|
|
if (!has_comp || !has_zpool)
|
return NULL;
|
|
return zswap_pool_create(zswap_zpool_type, zswap_compressor);
|
}
|
|
static void zswap_pool_destroy(struct zswap_pool *pool)
|
{
|
zswap_pool_debug("destroying", pool);
|
|
cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
|
free_percpu(pool->tfm);
|
zpool_destroy_pool(pool->zpool);
|
kfree(pool);
|
}
|
|
static int __must_check zswap_pool_get(struct zswap_pool *pool)
|
{
|
if (!pool)
|
return 0;
|
|
return kref_get_unless_zero(&pool->kref);
|
}
|
|
static void __zswap_pool_release(struct work_struct *work)
|
{
|
struct zswap_pool *pool = container_of(work, typeof(*pool),
|
release_work);
|
|
synchronize_rcu();
|
|
/* nobody should have been able to get a kref... */
|
WARN_ON(kref_get_unless_zero(&pool->kref));
|
|
/* pool is now off zswap_pools list and has no references. */
|
zswap_pool_destroy(pool);
|
}
|
|
static void __zswap_pool_empty(struct kref *kref)
|
{
|
struct zswap_pool *pool;
|
|
pool = container_of(kref, typeof(*pool), kref);
|
|
spin_lock(&zswap_pools_lock);
|
|
WARN_ON(pool == zswap_pool_current());
|
|
list_del_rcu(&pool->list);
|
|
INIT_WORK(&pool->release_work, __zswap_pool_release);
|
schedule_work(&pool->release_work);
|
|
spin_unlock(&zswap_pools_lock);
|
}
|
|
static void zswap_pool_put(struct zswap_pool *pool)
|
{
|
kref_put(&pool->kref, __zswap_pool_empty);
|
}
|
|
/*********************************
|
* param callbacks
|
**********************************/
|
|
/* val must be a null-terminated string */
|
static int __zswap_param_set(const char *val, const struct kernel_param *kp,
|
char *type, char *compressor)
|
{
|
struct zswap_pool *pool, *put_pool = NULL;
|
char *s = strstrip((char *)val);
|
int ret;
|
|
if (zswap_init_failed) {
|
pr_err("can't set param, initialization failed\n");
|
return -ENODEV;
|
}
|
|
/* no change required */
|
if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool)
|
return 0;
|
|
/* if this is load-time (pre-init) param setting,
|
* don't create a pool; that's done during init.
|
*/
|
if (!zswap_init_started)
|
return param_set_charp(s, kp);
|
|
if (!type) {
|
if (!zpool_has_pool(s)) {
|
pr_err("zpool %s not available\n", s);
|
return -ENOENT;
|
}
|
type = s;
|
} else if (!compressor) {
|
if (!crypto_has_comp(s, 0, 0)) {
|
pr_err("compressor %s not available\n", s);
|
return -ENOENT;
|
}
|
compressor = s;
|
} else {
|
WARN_ON(1);
|
return -EINVAL;
|
}
|
|
spin_lock(&zswap_pools_lock);
|
|
pool = zswap_pool_find_get(type, compressor);
|
if (pool) {
|
zswap_pool_debug("using existing", pool);
|
WARN_ON(pool == zswap_pool_current());
|
list_del_rcu(&pool->list);
|
}
|
|
spin_unlock(&zswap_pools_lock);
|
|
if (!pool)
|
pool = zswap_pool_create(type, compressor);
|
|
if (pool)
|
ret = param_set_charp(s, kp);
|
else
|
ret = -EINVAL;
|
|
spin_lock(&zswap_pools_lock);
|
|
if (!ret) {
|
put_pool = zswap_pool_current();
|
list_add_rcu(&pool->list, &zswap_pools);
|
zswap_has_pool = true;
|
} else if (pool) {
|
/* add the possibly pre-existing pool to the end of the pools
|
* list; if it's new (and empty) then it'll be removed and
|
* destroyed by the put after we drop the lock
|
*/
|
list_add_tail_rcu(&pool->list, &zswap_pools);
|
put_pool = pool;
|
}
|
|
spin_unlock(&zswap_pools_lock);
|
|
if (!zswap_has_pool && !pool) {
|
/* if initial pool creation failed, and this pool creation also
|
* failed, maybe both compressor and zpool params were bad.
|
* Allow changing this param, so pool creation will succeed
|
* when the other param is changed. We already verified this
|
* param is ok in the zpool_has_pool() or crypto_has_comp()
|
* checks above.
|
*/
|
ret = param_set_charp(s, kp);
|
}
|
|
/* drop the ref from either the old current pool,
|
* or the new pool we failed to add
|
*/
|
if (put_pool)
|
zswap_pool_put(put_pool);
|
|
return ret;
|
}
|
|
static int zswap_compressor_param_set(const char *val,
|
const struct kernel_param *kp)
|
{
|
return __zswap_param_set(val, kp, zswap_zpool_type, NULL);
|
}
|
|
static int zswap_zpool_param_set(const char *val,
|
const struct kernel_param *kp)
|
{
|
return __zswap_param_set(val, kp, NULL, zswap_compressor);
|
}
|
|
static int zswap_enabled_param_set(const char *val,
|
const struct kernel_param *kp)
|
{
|
if (zswap_init_failed) {
|
pr_err("can't enable, initialization failed\n");
|
return -ENODEV;
|
}
|
if (!zswap_has_pool && zswap_init_started) {
|
pr_err("can't enable, no pool configured\n");
|
return -ENODEV;
|
}
|
|
return param_set_bool(val, kp);
|
}
|
|
/*********************************
|
* writeback code
|
**********************************/
|
/* return enum for zswap_get_swap_cache_page */
|
enum zswap_get_swap_ret {
|
ZSWAP_SWAPCACHE_NEW,
|
ZSWAP_SWAPCACHE_EXIST,
|
ZSWAP_SWAPCACHE_FAIL,
|
};
|
|
/*
|
* zswap_get_swap_cache_page
|
*
|
* This is an adaption of read_swap_cache_async()
|
*
|
* This function tries to find a page with the given swap entry
|
* in the swapper_space address space (the swap cache). If the page
|
* is found, it is returned in retpage. Otherwise, a page is allocated,
|
* added to the swap cache, and returned in retpage.
|
*
|
* If success, the swap cache page is returned in retpage
|
* Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
|
* Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
|
* the new page is added to swapcache and locked
|
* Returns ZSWAP_SWAPCACHE_FAIL on error
|
*/
|
static int zswap_get_swap_cache_page(swp_entry_t entry,
|
struct page **retpage)
|
{
|
bool page_was_allocated;
|
|
*retpage = __read_swap_cache_async(entry, GFP_KERNEL,
|
NULL, 0, &page_was_allocated);
|
if (page_was_allocated)
|
return ZSWAP_SWAPCACHE_NEW;
|
if (!*retpage)
|
return ZSWAP_SWAPCACHE_FAIL;
|
return ZSWAP_SWAPCACHE_EXIST;
|
}
|
|
/*
|
* Attempts to free an entry by adding a page to the swap cache,
|
* decompressing the entry data into the page, and issuing a
|
* bio write to write the page back to the swap device.
|
*
|
* This can be thought of as a "resumed writeback" of the page
|
* to the swap device. We are basically resuming the same swap
|
* writeback path that was intercepted with the frontswap_store()
|
* in the first place. After the page has been decompressed into
|
* the swap cache, the compressed version stored by zswap can be
|
* freed.
|
*/
|
static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
|
{
|
struct zswap_header *zhdr;
|
swp_entry_t swpentry;
|
struct zswap_tree *tree;
|
pgoff_t offset;
|
struct zswap_entry *entry;
|
struct page *page;
|
struct crypto_comp *tfm;
|
u8 *src, *dst;
|
unsigned int dlen;
|
int ret;
|
struct writeback_control wbc = {
|
.sync_mode = WB_SYNC_NONE,
|
};
|
|
/* extract swpentry from data */
|
zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
|
swpentry = zhdr->swpentry; /* here */
|
tree = zswap_trees[swp_type(swpentry)];
|
offset = swp_offset(swpentry);
|
|
/* find and ref zswap entry */
|
spin_lock(&tree->lock);
|
entry = zswap_entry_find_get(&tree->rbroot, offset);
|
if (!entry) {
|
/* entry was invalidated */
|
spin_unlock(&tree->lock);
|
zpool_unmap_handle(pool, handle);
|
return 0;
|
}
|
spin_unlock(&tree->lock);
|
BUG_ON(offset != entry->offset);
|
|
/* try to allocate swap cache page */
|
switch (zswap_get_swap_cache_page(swpentry, &page)) {
|
case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
|
ret = -ENOMEM;
|
goto fail;
|
|
case ZSWAP_SWAPCACHE_EXIST:
|
/* page is already in the swap cache, ignore for now */
|
put_page(page);
|
ret = -EEXIST;
|
goto fail;
|
|
case ZSWAP_SWAPCACHE_NEW: /* page is locked */
|
/* decompress */
|
dlen = PAGE_SIZE;
|
src = (u8 *)zhdr + sizeof(struct zswap_header);
|
dst = kmap_atomic(page);
|
tfm = *get_cpu_ptr(entry->pool->tfm);
|
ret = crypto_comp_decompress(tfm, src, entry->length,
|
dst, &dlen);
|
put_cpu_ptr(entry->pool->tfm);
|
kunmap_atomic(dst);
|
BUG_ON(ret);
|
BUG_ON(dlen != PAGE_SIZE);
|
|
/* page is up to date */
|
SetPageUptodate(page);
|
}
|
|
/* move it to the tail of the inactive list after end_writeback */
|
SetPageReclaim(page);
|
|
/* start writeback */
|
__swap_writepage(page, &wbc, end_swap_bio_write);
|
put_page(page);
|
zswap_written_back_pages++;
|
|
spin_lock(&tree->lock);
|
/* drop local reference */
|
zswap_entry_put(tree, entry);
|
|
/*
|
* There are two possible situations for entry here:
|
* (1) refcount is 1(normal case), entry is valid and on the tree
|
* (2) refcount is 0, entry is freed and not on the tree
|
* because invalidate happened during writeback
|
* search the tree and free the entry if find entry
|
*/
|
if (entry == zswap_rb_search(&tree->rbroot, offset))
|
zswap_entry_put(tree, entry);
|
spin_unlock(&tree->lock);
|
|
goto end;
|
|
/*
|
* if we get here due to ZSWAP_SWAPCACHE_EXIST
|
* a load may happening concurrently
|
* it is safe and okay to not free the entry
|
* if we free the entry in the following put
|
* it it either okay to return !0
|
*/
|
fail:
|
spin_lock(&tree->lock);
|
zswap_entry_put(tree, entry);
|
spin_unlock(&tree->lock);
|
|
end:
|
zpool_unmap_handle(pool, handle);
|
return ret;
|
}
|
|
static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
|
{
|
unsigned int pos;
|
unsigned long *page;
|
|
page = (unsigned long *)ptr;
|
for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
|
if (page[pos] != page[0])
|
return 0;
|
}
|
*value = page[0];
|
return 1;
|
}
|
|
static void zswap_fill_page(void *ptr, unsigned long value)
|
{
|
unsigned long *page;
|
|
page = (unsigned long *)ptr;
|
memset_l(page, value, PAGE_SIZE / sizeof(unsigned long));
|
}
|
|
/*********************************
|
* frontswap hooks
|
**********************************/
|
/* attempts to compress and store an single page */
|
static int zswap_frontswap_store(unsigned type, pgoff_t offset,
|
struct page *page)
|
{
|
struct zswap_tree *tree = zswap_trees[type];
|
struct zswap_entry *entry, *dupentry;
|
struct crypto_comp *tfm;
|
int ret;
|
unsigned int hlen, dlen = PAGE_SIZE;
|
unsigned long handle, value;
|
char *buf;
|
u8 *src, *dst;
|
struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) };
|
gfp_t gfp;
|
|
/* THP isn't supported */
|
if (PageTransHuge(page)) {
|
ret = -EINVAL;
|
goto reject;
|
}
|
|
if (!zswap_enabled || !tree) {
|
ret = -ENODEV;
|
goto reject;
|
}
|
|
/* reclaim space if needed */
|
if (zswap_is_full()) {
|
struct zswap_pool *pool;
|
|
zswap_pool_limit_hit++;
|
zswap_pool_reached_full = true;
|
pool = zswap_pool_last_get();
|
if (pool)
|
queue_work(shrink_wq, &pool->shrink_work);
|
ret = -ENOMEM;
|
goto reject;
|
}
|
|
if (zswap_pool_reached_full) {
|
if (!zswap_can_accept()) {
|
ret = -ENOMEM;
|
goto reject;
|
} else
|
zswap_pool_reached_full = false;
|
}
|
|
/* allocate entry */
|
entry = zswap_entry_cache_alloc(GFP_KERNEL);
|
if (!entry) {
|
zswap_reject_kmemcache_fail++;
|
ret = -ENOMEM;
|
goto reject;
|
}
|
|
if (zswap_same_filled_pages_enabled) {
|
src = kmap_atomic(page);
|
if (zswap_is_page_same_filled(src, &value)) {
|
kunmap_atomic(src);
|
entry->offset = offset;
|
entry->length = 0;
|
entry->value = value;
|
atomic_inc(&zswap_same_filled_pages);
|
goto insert_entry;
|
}
|
kunmap_atomic(src);
|
}
|
|
/* if entry is successfully added, it keeps the reference */
|
entry->pool = zswap_pool_current_get();
|
if (!entry->pool) {
|
ret = -EINVAL;
|
goto freepage;
|
}
|
|
/* compress */
|
dst = get_cpu_var(zswap_dstmem);
|
tfm = *get_cpu_ptr(entry->pool->tfm);
|
src = kmap_atomic(page);
|
ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
|
kunmap_atomic(src);
|
put_cpu_ptr(entry->pool->tfm);
|
if (ret) {
|
ret = -EINVAL;
|
goto put_dstmem;
|
}
|
|
/* store */
|
hlen = zpool_evictable(entry->pool->zpool) ? sizeof(zhdr) : 0;
|
gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
|
if (zpool_malloc_support_movable(entry->pool->zpool))
|
gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
|
ret = zpool_malloc(entry->pool->zpool, hlen + dlen, gfp, &handle);
|
if (ret == -ENOSPC) {
|
zswap_reject_compress_poor++;
|
goto put_dstmem;
|
}
|
if (ret) {
|
zswap_reject_alloc_fail++;
|
goto put_dstmem;
|
}
|
buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW);
|
memcpy(buf, &zhdr, hlen);
|
memcpy(buf + hlen, dst, dlen);
|
zpool_unmap_handle(entry->pool->zpool, handle);
|
put_cpu_var(zswap_dstmem);
|
|
/* populate entry */
|
entry->offset = offset;
|
entry->handle = handle;
|
entry->length = dlen;
|
|
insert_entry:
|
/* map */
|
spin_lock(&tree->lock);
|
do {
|
ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
|
if (ret == -EEXIST) {
|
zswap_duplicate_entry++;
|
/* remove from rbtree */
|
zswap_rb_erase(&tree->rbroot, dupentry);
|
zswap_entry_put(tree, dupentry);
|
}
|
} while (ret == -EEXIST);
|
spin_unlock(&tree->lock);
|
|
/* update stats */
|
atomic_inc(&zswap_stored_pages);
|
zswap_update_total_size();
|
|
return 0;
|
|
put_dstmem:
|
put_cpu_var(zswap_dstmem);
|
zswap_pool_put(entry->pool);
|
freepage:
|
zswap_entry_cache_free(entry);
|
reject:
|
return ret;
|
}
|
|
/*
|
* returns 0 if the page was successfully decompressed
|
* return -1 on entry not found or error
|
*/
|
static int zswap_frontswap_load(unsigned type, pgoff_t offset,
|
struct page *page)
|
{
|
struct zswap_tree *tree = zswap_trees[type];
|
struct zswap_entry *entry;
|
struct crypto_comp *tfm;
|
u8 *src, *dst;
|
unsigned int dlen;
|
int ret;
|
|
/* find */
|
spin_lock(&tree->lock);
|
entry = zswap_entry_find_get(&tree->rbroot, offset);
|
if (!entry) {
|
/* entry was written back */
|
spin_unlock(&tree->lock);
|
return -1;
|
}
|
spin_unlock(&tree->lock);
|
|
if (!entry->length) {
|
dst = kmap_atomic(page);
|
zswap_fill_page(dst, entry->value);
|
kunmap_atomic(dst);
|
goto freeentry;
|
}
|
|
/* decompress */
|
dlen = PAGE_SIZE;
|
src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
|
if (zpool_evictable(entry->pool->zpool))
|
src += sizeof(struct zswap_header);
|
dst = kmap_atomic(page);
|
tfm = *get_cpu_ptr(entry->pool->tfm);
|
ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
|
put_cpu_ptr(entry->pool->tfm);
|
kunmap_atomic(dst);
|
zpool_unmap_handle(entry->pool->zpool, entry->handle);
|
BUG_ON(ret);
|
|
freeentry:
|
spin_lock(&tree->lock);
|
zswap_entry_put(tree, entry);
|
spin_unlock(&tree->lock);
|
|
return 0;
|
}
|
|
/* frees an entry in zswap */
|
static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
|
{
|
struct zswap_tree *tree = zswap_trees[type];
|
struct zswap_entry *entry;
|
|
/* find */
|
spin_lock(&tree->lock);
|
entry = zswap_rb_search(&tree->rbroot, offset);
|
if (!entry) {
|
/* entry was written back */
|
spin_unlock(&tree->lock);
|
return;
|
}
|
|
/* remove from rbtree */
|
zswap_rb_erase(&tree->rbroot, entry);
|
|
/* drop the initial reference from entry creation */
|
zswap_entry_put(tree, entry);
|
|
spin_unlock(&tree->lock);
|
}
|
|
/* frees all zswap entries for the given swap type */
|
static void zswap_frontswap_invalidate_area(unsigned type)
|
{
|
struct zswap_tree *tree = zswap_trees[type];
|
struct zswap_entry *entry, *n;
|
|
if (!tree)
|
return;
|
|
/* walk the tree and free everything */
|
spin_lock(&tree->lock);
|
rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
|
zswap_free_entry(entry);
|
tree->rbroot = RB_ROOT;
|
spin_unlock(&tree->lock);
|
kfree(tree);
|
zswap_trees[type] = NULL;
|
}
|
|
static void zswap_frontswap_init(unsigned type)
|
{
|
struct zswap_tree *tree;
|
|
tree = kzalloc(sizeof(*tree), GFP_KERNEL);
|
if (!tree) {
|
pr_err("alloc failed, zswap disabled for swap type %d\n", type);
|
return;
|
}
|
|
tree->rbroot = RB_ROOT;
|
spin_lock_init(&tree->lock);
|
zswap_trees[type] = tree;
|
}
|
|
static struct frontswap_ops zswap_frontswap_ops = {
|
.store = zswap_frontswap_store,
|
.load = zswap_frontswap_load,
|
.invalidate_page = zswap_frontswap_invalidate_page,
|
.invalidate_area = zswap_frontswap_invalidate_area,
|
.init = zswap_frontswap_init
|
};
|
|
/*********************************
|
* debugfs functions
|
**********************************/
|
#ifdef CONFIG_DEBUG_FS
|
#include <linux/debugfs.h>
|
|
static struct dentry *zswap_debugfs_root;
|
|
static int __init zswap_debugfs_init(void)
|
{
|
if (!debugfs_initialized())
|
return -ENODEV;
|
|
zswap_debugfs_root = debugfs_create_dir("zswap", NULL);
|
|
debugfs_create_u64("pool_limit_hit", 0444,
|
zswap_debugfs_root, &zswap_pool_limit_hit);
|
debugfs_create_u64("reject_reclaim_fail", 0444,
|
zswap_debugfs_root, &zswap_reject_reclaim_fail);
|
debugfs_create_u64("reject_alloc_fail", 0444,
|
zswap_debugfs_root, &zswap_reject_alloc_fail);
|
debugfs_create_u64("reject_kmemcache_fail", 0444,
|
zswap_debugfs_root, &zswap_reject_kmemcache_fail);
|
debugfs_create_u64("reject_compress_poor", 0444,
|
zswap_debugfs_root, &zswap_reject_compress_poor);
|
debugfs_create_u64("written_back_pages", 0444,
|
zswap_debugfs_root, &zswap_written_back_pages);
|
debugfs_create_u64("duplicate_entry", 0444,
|
zswap_debugfs_root, &zswap_duplicate_entry);
|
debugfs_create_u64("pool_total_size", 0444,
|
zswap_debugfs_root, &zswap_pool_total_size);
|
debugfs_create_atomic_t("stored_pages", 0444,
|
zswap_debugfs_root, &zswap_stored_pages);
|
debugfs_create_atomic_t("same_filled_pages", 0444,
|
zswap_debugfs_root, &zswap_same_filled_pages);
|
|
return 0;
|
}
|
|
static void __exit zswap_debugfs_exit(void)
|
{
|
debugfs_remove_recursive(zswap_debugfs_root);
|
}
|
#else
|
static int __init zswap_debugfs_init(void)
|
{
|
return 0;
|
}
|
|
static void __exit zswap_debugfs_exit(void) { }
|
#endif
|
|
/*********************************
|
* module init and exit
|
**********************************/
|
static int __init init_zswap(void)
|
{
|
struct zswap_pool *pool;
|
int ret;
|
|
zswap_init_started = true;
|
|
if (zswap_entry_cache_create()) {
|
pr_err("entry cache creation failed\n");
|
goto cache_fail;
|
}
|
|
ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
|
zswap_dstmem_prepare, zswap_dstmem_dead);
|
if (ret) {
|
pr_err("dstmem alloc failed\n");
|
goto dstmem_fail;
|
}
|
|
ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
|
"mm/zswap_pool:prepare",
|
zswap_cpu_comp_prepare,
|
zswap_cpu_comp_dead);
|
if (ret)
|
goto hp_fail;
|
|
pool = __zswap_pool_create_fallback();
|
if (pool) {
|
pr_info("loaded using pool %s/%s\n", pool->tfm_name,
|
zpool_get_type(pool->zpool));
|
list_add(&pool->list, &zswap_pools);
|
zswap_has_pool = true;
|
} else {
|
pr_err("pool creation failed\n");
|
zswap_enabled = false;
|
}
|
|
shrink_wq = create_workqueue("zswap-shrink");
|
if (!shrink_wq)
|
goto fallback_fail;
|
|
frontswap_register_ops(&zswap_frontswap_ops);
|
if (zswap_debugfs_init())
|
pr_warn("debugfs initialization failed\n");
|
return 0;
|
|
fallback_fail:
|
if (pool)
|
zswap_pool_destroy(pool);
|
hp_fail:
|
cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
|
dstmem_fail:
|
zswap_entry_cache_destroy();
|
cache_fail:
|
/* if built-in, we aren't unloaded on failure; don't allow use */
|
zswap_init_failed = true;
|
zswap_enabled = false;
|
return -ENOMEM;
|
}
|
/* must be late so crypto has time to come up */
|
late_initcall(init_zswap);
|
|
MODULE_LICENSE("GPL");
|
MODULE_AUTHOR("Seth Jennings <sjennings@variantweb.net>");
|
MODULE_DESCRIPTION("Compressed cache for swap pages");
|
