summaryrefslogtreecommitdiffstats
path: root/kernel/mm/zswap.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/mm/zswap.c')
-rw-r--r--kernel/mm/zswap.c772
1 files changed, 544 insertions, 228 deletions
diff --git a/kernel/mm/zswap.c b/kernel/mm/zswap.c
index 4249e82ff..bf14508af 100644
--- a/kernel/mm/zswap.c
+++ b/kernel/mm/zswap.c
@@ -75,89 +75,53 @@ static u64 zswap_duplicate_entry;
/*********************************
* tunables
**********************************/
-/* Enable/disable zswap (disabled by default, fixed at boot for now) */
-static bool zswap_enabled __read_mostly;
-module_param_named(enabled, zswap_enabled, bool, 0444);
-/* Compressor to be used by zswap (fixed at boot for now) */
+/* Enable/disable zswap (disabled by default) */
+static bool zswap_enabled;
+module_param_named(enabled, zswap_enabled, bool, 0644);
+
+/* Crypto compressor to use */
#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
-module_param_named(compressor, zswap_compressor, charp, 0444);
-
-/* 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);
+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 to use */
+/* Compressed storage zpool to use */
#define ZSWAP_ZPOOL_DEFAULT "zbud"
static char *zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
-module_param_named(zpool, zswap_zpool_type, charp, 0444);
+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);
-/* zpool is shared by all of zswap backend */
-static struct zpool *zswap_pool;
+/* 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);
/*********************************
-* compression functions
+* data structures
**********************************/
-/* per-cpu compression transforms */
-static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms;
-enum comp_op {
- ZSWAP_COMPOP_COMPRESS,
- ZSWAP_COMPOP_DECOMPRESS
+struct zswap_pool {
+ struct zpool *zpool;
+ struct crypto_comp * __percpu *tfm;
+ struct kref kref;
+ struct list_head list;
+ struct rcu_head rcu_head;
+ struct notifier_block notifier;
+ char tfm_name[CRYPTO_MAX_ALG_NAME];
};
-static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen,
- u8 *dst, unsigned int *dlen)
-{
- struct crypto_comp *tfm;
- int ret;
-
- tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu());
- switch (op) {
- case ZSWAP_COMPOP_COMPRESS:
- ret = crypto_comp_compress(tfm, src, slen, dst, dlen);
- break;
- case ZSWAP_COMPOP_DECOMPRESS:
- ret = crypto_comp_decompress(tfm, src, slen, dst, dlen);
- break;
- default:
- ret = -EINVAL;
- }
-
- put_cpu();
- return ret;
-}
-
-static int __init zswap_comp_init(void)
-{
- if (!crypto_has_comp(zswap_compressor, 0, 0)) {
- pr_info("%s compressor not available\n", zswap_compressor);
- /* fall back to default compressor */
- zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
- if (!crypto_has_comp(zswap_compressor, 0, 0))
- /* can't even load the default compressor */
- return -ENODEV;
- }
- pr_info("using %s compressor\n", zswap_compressor);
-
- /* alloc percpu transforms */
- zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *);
- if (!zswap_comp_pcpu_tfms)
- return -ENOMEM;
- return 0;
-}
-
-static void __init zswap_comp_exit(void)
-{
- /* free percpu transforms */
- free_percpu(zswap_comp_pcpu_tfms);
-}
-
-/*********************************
-* data structures
-**********************************/
/*
* struct zswap_entry
*
@@ -165,22 +129,24 @@ static void __init zswap_comp_exit(void)
* 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.
- * offset - the swap offset for the entry. Index into the red-black tree.
- * handle - zpool allocation handle that stores the compressed page data
* length - the length in bytes of the compressed page data. Needed during
* decompression
+ * pool - the zswap_pool the entry's data is in
+ * handle - zpool allocation handle that stores the compressed page data
*/
struct zswap_entry {
struct rb_node rbnode;
pgoff_t offset;
int refcount;
unsigned int length;
+ struct zswap_pool *pool;
unsigned long handle;
};
@@ -200,6 +166,51 @@ struct zswap_tree {
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);
+
+/* used by param callback function */
+static bool zswap_init_started;
+
+/*********************************
+* 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 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
**********************************/
@@ -293,10 +304,11 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
*/
static void zswap_free_entry(struct zswap_entry *entry)
{
- zpool_free(zswap_pool, entry->handle);
+ zpool_free(entry->pool->zpool, entry->handle);
+ zswap_pool_put(entry->pool);
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
- zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+ zswap_update_total_size();
}
/* caller must hold the tree lock */
@@ -324,7 +336,7 @@ static void zswap_entry_put(struct zswap_tree *tree,
static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
pgoff_t offset)
{
- struct zswap_entry *entry = NULL;
+ struct zswap_entry *entry;
entry = zswap_rb_search(root, offset);
if (entry)
@@ -338,35 +350,21 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
**********************************/
static DEFINE_PER_CPU(u8 *, zswap_dstmem);
-static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
+static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
{
- struct crypto_comp *tfm;
u8 *dst;
switch (action) {
case CPU_UP_PREPARE:
- tfm = crypto_alloc_comp(zswap_compressor, 0, 0);
- if (IS_ERR(tfm)) {
- pr_err("can't allocate compressor transform\n");
- return NOTIFY_BAD;
- }
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm;
dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
if (!dst) {
pr_err("can't allocate compressor buffer\n");
- crypto_free_comp(tfm);
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
return NOTIFY_BAD;
}
per_cpu(zswap_dstmem, cpu) = dst;
break;
case CPU_DEAD:
case CPU_UP_CANCELED:
- tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu);
- if (tfm) {
- crypto_free_comp(tfm);
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
- }
dst = per_cpu(zswap_dstmem, cpu);
kfree(dst);
per_cpu(zswap_dstmem, cpu) = NULL;
@@ -377,43 +375,404 @@ static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
return NOTIFY_OK;
}
-static int zswap_cpu_notifier(struct notifier_block *nb,
- unsigned long action, void *pcpu)
+static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
+ unsigned long action, void *pcpu)
{
- unsigned long cpu = (unsigned long)pcpu;
- return __zswap_cpu_notifier(action, cpu);
+ return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
}
-static struct notifier_block zswap_cpu_notifier_block = {
- .notifier_call = zswap_cpu_notifier
+static struct notifier_block zswap_dstmem_notifier = {
+ .notifier_call = zswap_cpu_dstmem_notifier,
};
-static int __init zswap_cpu_init(void)
+static int __init zswap_cpu_dstmem_init(void)
{
unsigned long cpu;
cpu_notifier_register_begin();
for_each_online_cpu(cpu)
- if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
+ if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
+ NOTIFY_BAD)
goto cleanup;
- __register_cpu_notifier(&zswap_cpu_notifier_block);
+ __register_cpu_notifier(&zswap_dstmem_notifier);
cpu_notifier_register_done();
return 0;
cleanup:
for_each_online_cpu(cpu)
- __zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
+ __zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
cpu_notifier_register_done();
return -ENOMEM;
}
+static void zswap_cpu_dstmem_destroy(void)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ __zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
+ __unregister_cpu_notifier(&zswap_dstmem_notifier);
+ cpu_notifier_register_done();
+}
+
+static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
+ unsigned long action, unsigned long cpu)
+{
+ struct crypto_comp *tfm;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+ break;
+ 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 NOTIFY_BAD;
+ }
+ *per_cpu_ptr(pool->tfm, cpu) = tfm;
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ tfm = *per_cpu_ptr(pool->tfm, cpu);
+ if (!IS_ERR_OR_NULL(tfm))
+ crypto_free_comp(tfm);
+ *per_cpu_ptr(pool->tfm, cpu) = NULL;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static int zswap_cpu_comp_notifier(struct notifier_block *nb,
+ unsigned long action, void *pcpu)
+{
+ unsigned long cpu = (unsigned long)pcpu;
+ struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
+
+ return __zswap_cpu_comp_notifier(pool, action, cpu);
+}
+
+static int zswap_cpu_comp_init(struct zswap_pool *pool)
+{
+ unsigned long cpu;
+
+ memset(&pool->notifier, 0, sizeof(pool->notifier));
+ pool->notifier.notifier_call = zswap_cpu_comp_notifier;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
+ NOTIFY_BAD)
+ goto cleanup;
+ __register_cpu_notifier(&pool->notifier);
+ cpu_notifier_register_done();
+ return 0;
+
+cleanup:
+ for_each_online_cpu(cpu)
+ __zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
+ cpu_notifier_register_done();
+ return -ENOMEM;
+}
+
+static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ __zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
+ __unregister_cpu_notifier(&pool->notifier);
+ cpu_notifier_register_done();
+}
+
/*********************************
-* helpers
+* pool functions
**********************************/
-static bool zswap_is_full(void)
+
+static struct zswap_pool *__zswap_pool_current(void)
{
- return totalram_pages * zswap_max_pool_percent / 100 <
- DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+ struct zswap_pool *pool;
+
+ pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list);
+ WARN_ON(!pool);
+
+ 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 (!pool || !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;
+ if (!WARN_ON(!last) && !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 struct zswap_pool *zswap_pool_create(char *type, char *compressor)
+{
+ struct zswap_pool *pool;
+ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool) {
+ pr_err("pool alloc failed\n");
+ return NULL;
+ }
+
+ pool->zpool = zpool_create_pool(type, "zswap", 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;
+ }
+
+ if (zswap_cpu_comp_init(pool))
+ 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);
+
+ 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)
+{
+ if (!crypto_has_comp(zswap_compressor, 0, 0)) {
+ if (!strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) {
+ pr_err("default compressor %s not available\n",
+ zswap_compressor);
+ return NULL;
+ }
+ pr_err("compressor %s not available, using default %s\n",
+ zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT);
+ param_free_charp(&zswap_compressor);
+ zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+ }
+ if (!zpool_has_pool(zswap_zpool_type)) {
+ if (!strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
+ pr_err("default zpool %s not available\n",
+ zswap_zpool_type);
+ return NULL;
+ }
+ pr_err("zpool %s not available, using default %s\n",
+ zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT);
+ param_free_charp(&zswap_zpool_type);
+ zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+ }
+
+ return zswap_pool_create(zswap_zpool_type, zswap_compressor);
+}
+
+static void zswap_pool_destroy(struct zswap_pool *pool)
+{
+ zswap_pool_debug("destroying", pool);
+
+ zswap_cpu_comp_destroy(pool);
+ free_percpu(pool->tfm);
+ zpool_destroy_pool(pool->zpool);
+ kfree(pool);
+}
+
+static int __must_check zswap_pool_get(struct zswap_pool *pool)
+{
+ return kref_get_unless_zero(&pool->kref);
+}
+
+static void __zswap_pool_release(struct rcu_head *head)
+{
+ struct zswap_pool *pool = container_of(head, typeof(*pool), rcu_head);
+
+ /* 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);
+ call_rcu(&pool->rcu_head, __zswap_pool_release);
+
+ 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;
+
+ /* no change required */
+ if (!strcmp(s, *(char **)kp->arg))
+ 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);
+ list_del_rcu(&pool->list);
+ } else {
+ spin_unlock(&zswap_pools_lock);
+ pool = zswap_pool_create(type, compressor);
+ spin_lock(&zswap_pools_lock);
+ }
+
+ if (pool)
+ ret = param_set_charp(s, kp);
+ else
+ ret = -EINVAL;
+
+ if (!ret) {
+ put_pool = zswap_pool_current();
+ list_add_rcu(&pool->list, &zswap_pools);
+ } 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);
+
+ /* 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);
}
/*********************************
@@ -445,75 +804,14 @@ enum zswap_get_swap_ret {
static int zswap_get_swap_cache_page(swp_entry_t entry,
struct page **retpage)
{
- struct page *found_page, *new_page = NULL;
- struct address_space *swapper_space = swap_address_space(entry);
- int err;
-
- *retpage = NULL;
- do {
- /*
- * First check the swap cache. Since this is normally
- * called after lookup_swap_cache() failed, re-calling
- * that would confuse statistics.
- */
- found_page = find_get_page(swapper_space, entry.val);
- if (found_page)
- break;
-
- /*
- * Get a new page to read into from swap.
- */
- if (!new_page) {
- new_page = alloc_page(GFP_KERNEL);
- if (!new_page)
- break; /* Out of memory */
- }
-
- /*
- * call radix_tree_preload() while we can wait.
- */
- err = radix_tree_preload(GFP_KERNEL);
- if (err)
- break;
-
- /*
- * Swap entry may have been freed since our caller observed it.
- */
- err = swapcache_prepare(entry);
- if (err == -EEXIST) { /* seems racy */
- radix_tree_preload_end();
- continue;
- }
- if (err) { /* swp entry is obsolete ? */
- radix_tree_preload_end();
- break;
- }
-
- /* May fail (-ENOMEM) if radix-tree node allocation failed. */
- __set_page_locked(new_page);
- SetPageSwapBacked(new_page);
- err = __add_to_swap_cache(new_page, entry);
- if (likely(!err)) {
- radix_tree_preload_end();
- lru_cache_add_anon(new_page);
- *retpage = new_page;
- return ZSWAP_SWAPCACHE_NEW;
- }
- radix_tree_preload_end();
- ClearPageSwapBacked(new_page);
- __clear_page_locked(new_page);
- /*
- * add_to_swap_cache() doesn't return -EEXIST, so we can safely
- * clear SWAP_HAS_CACHE flag.
- */
- swapcache_free(entry);
- } while (err != -ENOMEM);
+ bool page_was_allocated;
- if (new_page)
- page_cache_release(new_page);
- if (!found_page)
+ *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;
- *retpage = found_page;
return ZSWAP_SWAPCACHE_EXIST;
}
@@ -537,6 +835,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
pgoff_t offset;
struct zswap_entry *entry;
struct page *page;
+ struct crypto_comp *tfm;
u8 *src, *dst;
unsigned int dlen;
int ret;
@@ -577,13 +876,15 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
case ZSWAP_SWAPCACHE_NEW: /* page is locked */
/* decompress */
dlen = PAGE_SIZE;
- src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ src = (u8 *)zpool_map_handle(entry->pool->zpool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
- ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
- entry->length, dst, &dlen);
+ 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(zswap_pool, entry->handle);
+ zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
BUG_ON(dlen != PAGE_SIZE);
@@ -632,6 +933,22 @@ end:
return ret;
}
+static int zswap_shrink(void)
+{
+ struct zswap_pool *pool;
+ int ret;
+
+ pool = zswap_pool_last_get();
+ if (!pool)
+ return -ENOENT;
+
+ ret = zpool_shrink(pool->zpool, 1, NULL);
+
+ zswap_pool_put(pool);
+
+ return ret;
+}
+
/*********************************
* frontswap hooks
**********************************/
@@ -641,6 +958,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry, *dupentry;
+ struct crypto_comp *tfm;
int ret;
unsigned int dlen = PAGE_SIZE, len;
unsigned long handle;
@@ -648,7 +966,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
u8 *src, *dst;
struct zswap_header *zhdr;
- if (!tree) {
+ if (!zswap_enabled || !tree) {
ret = -ENODEV;
goto reject;
}
@@ -656,7 +974,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
- if (zpool_shrink(zswap_pool, 1, NULL)) {
+ if (zswap_shrink()) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
@@ -671,33 +989,43 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
goto reject;
}
+ /* 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 = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
+ ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
kunmap_atomic(src);
+ put_cpu_ptr(entry->pool->tfm);
if (ret) {
ret = -EINVAL;
- goto freepage;
+ goto put_dstmem;
}
/* store */
len = dlen + sizeof(struct zswap_header);
- ret = zpool_malloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
- &handle);
+ ret = zpool_malloc(entry->pool->zpool, len,
+ __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM,
+ &handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
- goto freepage;
+ goto put_dstmem;
}
if (ret) {
zswap_reject_alloc_fail++;
- goto freepage;
+ goto put_dstmem;
}
- zhdr = zpool_map_handle(zswap_pool, handle, ZPOOL_MM_RW);
+ zhdr = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW);
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
- zpool_unmap_handle(zswap_pool, handle);
+ zpool_unmap_handle(entry->pool->zpool, handle);
put_cpu_var(zswap_dstmem);
/* populate entry */
@@ -720,12 +1048,14 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* update stats */
atomic_inc(&zswap_stored_pages);
- zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+ zswap_update_total_size();
return 0;
-freepage:
+put_dstmem:
put_cpu_var(zswap_dstmem);
+ zswap_pool_put(entry->pool);
+freepage:
zswap_entry_cache_free(entry);
reject:
return ret;
@@ -740,6 +1070,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry;
+ struct crypto_comp *tfm;
u8 *src, *dst;
unsigned int dlen;
int ret;
@@ -756,13 +1087,14 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
/* decompress */
dlen = PAGE_SIZE;
- src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ src = (u8 *)zpool_map_handle(entry->pool->zpool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
- ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
- dst, &dlen);
+ 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(zswap_pool, entry->handle);
+ zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
spin_lock(&tree->lock);
@@ -815,10 +1147,6 @@ static void zswap_frontswap_invalidate_area(unsigned type)
zswap_trees[type] = NULL;
}
-static struct zpool_ops zswap_zpool_ops = {
- .evict = zswap_writeback_entry
-};
-
static void zswap_frontswap_init(unsigned type)
{
struct zswap_tree *tree;
@@ -899,52 +1227,40 @@ static void __exit zswap_debugfs_exit(void) { }
**********************************/
static int __init init_zswap(void)
{
- gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+ struct zswap_pool *pool;
- if (!zswap_enabled)
- return 0;
-
- pr_info("loading zswap\n");
-
- zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
- &zswap_zpool_ops);
- if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
- pr_info("%s zpool not available\n", zswap_zpool_type);
- zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
- zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
- &zswap_zpool_ops);
- }
- if (!zswap_pool) {
- pr_err("%s zpool not available\n", zswap_zpool_type);
- pr_err("zpool creation failed\n");
- goto error;
- }
- pr_info("using %s pool\n", zswap_zpool_type);
+ zswap_init_started = true;
if (zswap_entry_cache_create()) {
pr_err("entry cache creation failed\n");
- goto cachefail;
+ goto cache_fail;
}
- if (zswap_comp_init()) {
- pr_err("compressor initialization failed\n");
- goto compfail;
+
+ if (zswap_cpu_dstmem_init()) {
+ pr_err("dstmem alloc failed\n");
+ goto dstmem_fail;
}
- if (zswap_cpu_init()) {
- pr_err("per-cpu initialization failed\n");
- goto pcpufail;
+
+ pool = __zswap_pool_create_fallback();
+ if (!pool) {
+ pr_err("pool creation failed\n");
+ goto pool_fail;
}
+ pr_info("loaded using pool %s/%s\n", pool->tfm_name,
+ zpool_get_type(pool->zpool));
+
+ list_add(&pool->list, &zswap_pools);
frontswap_register_ops(&zswap_frontswap_ops);
if (zswap_debugfs_init())
pr_warn("debugfs initialization failed\n");
return 0;
-pcpufail:
- zswap_comp_exit();
-compfail:
+
+pool_fail:
+ zswap_cpu_dstmem_destroy();
+dstmem_fail:
zswap_entry_cache_destroy();
-cachefail:
- zpool_destroy_pool(zswap_pool);
-error:
+cache_fail:
return -ENOMEM;
}
/* must be late so crypto has time to come up */