diff options
Diffstat (limited to 'mm/zswap.c')
| -rw-r--r-- | mm/zswap.c | 2309 |
1 files changed, 1249 insertions, 1060 deletions
diff --git a/mm/zswap.c b/mm/zswap.c index 62195f72bf56..5d0f8b13a958 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -2,7 +2,7 @@ /* * zswap.c - zswap driver file * - * zswap is a backend for frontswap that takes pages that are in the process + * zswap is a cache 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 @@ -20,21 +20,21 @@ #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/scatterlist.h> +#include <linux/mempolicy.h> #include <linux/mempool.h> -#include <linux/zpool.h> #include <crypto/acompress.h> - +#include <linux/zswap.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> +#include <linux/list_lru.h> +#include <linux/zsmalloc.h> #include "swap.h" #include "internal.h" @@ -42,12 +42,10 @@ /********************************* * statistics **********************************/ -/* Total bytes used by the compressed storage */ -u64 zswap_pool_total_size; -/* The number of compressed pages currently stored in zswap */ -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 number of pages currently stored in zswap */ +atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0); +/* The number of incompressible pages currently stored in zswap */ +static atomic_long_t zswap_stored_incompressible_pages = ATOMIC_LONG_INIT(0); /* * The statistics below are not protected from concurrent access for @@ -62,14 +60,16 @@ static u64 zswap_pool_limit_hit; static u64 zswap_written_back_pages; /* Store failed due to a reclaim failure after pool limit was reached */ static u64 zswap_reject_reclaim_fail; +/* Store failed due to compression algorithm failure */ +static u64 zswap_reject_compress_fail; /* Compressed page was too big for the allocator to (optimally) store */ static u64 zswap_reject_compress_poor; +/* Load or writeback failed due to decompression failure */ +static u64 zswap_decompress_fail; /* 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; @@ -85,6 +85,7 @@ static bool zswap_pool_reached_full; static int zswap_setup(void); /* Enable/disable zswap */ +static DEFINE_STATIC_KEY_MAYBE(CONFIG_ZSWAP_DEFAULT_ON, zswap_ever_enabled); static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON); static int zswap_enabled_param_set(const char *, const struct kernel_param *); @@ -106,16 +107,6 @@ static const struct kernel_param_ops zswap_compressor_param_ops = { 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 const 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); @@ -125,22 +116,20 @@ 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). - * If disabled every page is considered non-same-value filled. - */ -static bool zswap_same_filled_pages_enabled = true; -module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled, - bool, 0644); +/* Enable/disable memory pressure-based shrinker. */ +static bool zswap_shrinker_enabled = IS_ENABLED( + CONFIG_ZSWAP_SHRINKER_DEFAULT_ON); +module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644); -/* Enable/disable handling non-same-value filled pages (enabled by default) */ -static bool zswap_non_same_filled_pages_enabled = true; -module_param_named(non_same_filled_pages_enabled, zswap_non_same_filled_pages_enabled, - bool, 0644); +bool zswap_is_enabled(void) +{ + return zswap_enabled; +} -static bool zswap_exclusive_loads_enabled = IS_ENABLED( - CONFIG_ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON); -module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644); +bool zswap_never_enabled(void) +{ + return !static_branch_maybe(CONFIG_ZSWAP_DEFAULT_ON, &zswap_ever_enabled); +} /********************************* * data structures @@ -150,8 +139,9 @@ struct crypto_acomp_ctx { struct crypto_acomp *acomp; struct acomp_req *req; struct crypto_wait wait; - u8 *dstmem; - struct mutex *mutex; + u8 *buffer; + struct mutex mutex; + bool is_sleepable; }; /* @@ -161,71 +151,60 @@ struct crypto_acomp_ctx { * needs to be verified that it's still valid in the tree. */ struct zswap_pool { - struct zpool *zpool; + struct zs_pool *zs_pool; struct crypto_acomp_ctx __percpu *acomp_ctx; - struct kref kref; + struct percpu_ref ref; 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 list_head lru; - spinlock_t lru_lock; }; +/* Global LRU lists shared by all zswap pools. */ +static struct list_lru zswap_list_lru; + +/* The lock protects zswap_next_shrink updates. */ +static DEFINE_SPINLOCK(zswap_shrink_lock); +static struct mem_cgroup *zswap_next_shrink; +static struct work_struct zswap_shrink_work; +static struct shrinker *zswap_shrinker; + /* * 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. + * swpentry - associated swap entry, the offset indexes into the xarray * length - the length in bytes of the compressed page data. Needed during - * decompression. For a same value filled page length is 0, and both - * pool and lru are invalid and must be ignored. + * decompression. + * referenced - true if the entry recently entered the zswap pool. Unset by the + * writeback logic. The entry is only reclaimed by the writeback + * logic if referenced is unset. See comments in the shrinker + * section for context. * 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 + * handle - zsmalloc allocation handle that stores the compressed page data + * objcg - the obj_cgroup that the compressed memory is charged to * lru - handle to the pool's lru used to evict pages. */ struct zswap_entry { - struct rb_node rbnode; swp_entry_t swpentry; - int refcount; unsigned int length; + bool referenced; struct zswap_pool *pool; - union { - unsigned long handle; - unsigned long value; - }; + unsigned long handle; struct obj_cgroup *objcg; struct list_head lru; }; -/* - * 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]; +static struct xarray *zswap_trees[MAX_SWAPFILES]; +static unsigned int nr_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 */ +/* pool counter to provide unique names to zsmalloc */ static atomic_t zswap_pools_count = ATOMIC_INIT(0); enum zswap_init_type { @@ -246,288 +225,165 @@ 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 zswap_entry *entry, - struct zswap_tree *tree); -static int zswap_pool_get(struct zswap_pool *pool); -static void zswap_pool_put(struct zswap_pool *pool); - -static bool zswap_is_full(void) +/* One swap address space for each 64M swap space */ +#define ZSWAP_ADDRESS_SPACE_SHIFT 14 +#define ZSWAP_ADDRESS_SPACE_PAGES (1 << ZSWAP_ADDRESS_SPACE_SHIFT) +static inline struct xarray *swap_zswap_tree(swp_entry_t swp) { - return totalram_pages() * zswap_max_pool_percent / 100 < - DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); + return &zswap_trees[swp_type(swp)][swp_offset(swp) + >> ZSWAP_ADDRESS_SPACE_SHIFT]; } -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); -} +#define zswap_pool_debug(msg, p) \ + pr_debug("%s pool %s\n", msg, (p)->tfm_name) + +/********************************* +* pool functions +**********************************/ +static void __zswap_pool_empty(struct percpu_ref *ref); -static void zswap_update_total_size(void) +static struct zswap_pool *zswap_pool_create(char *compressor) { struct zswap_pool *pool; - u64 total = 0; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ + int ret, cpu; - rcu_read_lock(); + if (!zswap_has_pool && !strcmp(compressor, ZSWAP_PARAM_UNSET)) + return NULL; - list_for_each_entry_rcu(pool, &zswap_pools, list) - total += zpool_get_total_size(pool->zpool); + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; - rcu_read_unlock(); + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + pool->zs_pool = zs_create_pool(name); + if (!pool->zs_pool) + goto error; - zswap_pool_total_size = total; -} + strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); -/********************************* -* zswap entry functions -**********************************/ -static struct kmem_cache *zswap_entry_cache; + pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx); + if (!pool->acomp_ctx) { + pr_err("percpu alloc failed\n"); + goto error; + } -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; -} + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); -static void zswap_entry_cache_free(struct zswap_entry *entry) -{ - kmem_cache_free(zswap_entry_cache, entry); -} + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, + &pool->node); + if (ret) + goto error; -/********************************* -* 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; - pgoff_t entry_offset; - - while (node) { - entry = rb_entry(node, struct zswap_entry, rbnode); - entry_offset = swp_offset(entry->swpentry); - if (entry_offset > offset) - node = node->rb_left; - else if (entry_offset < offset) - node = node->rb_right; - else - return entry; - } + /* being the current pool takes 1 ref; this func expects the + * caller to always add the new pool as the current pool + */ + ret = percpu_ref_init(&pool->ref, __zswap_pool_empty, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); + if (ret) + goto ref_fail; + INIT_LIST_HEAD(&pool->list); + + zswap_pool_debug("created", pool); + + return pool; + +ref_fail: + cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); +error: + if (pool->acomp_ctx) + free_percpu(pool->acomp_ctx); + if (pool->zs_pool) + zs_destroy_pool(pool->zs_pool); + kfree(pool); 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) +static struct zswap_pool *__zswap_pool_create_fallback(void) { - struct rb_node **link = &root->rb_node, *parent = NULL; - struct zswap_entry *myentry; - pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry); - - while (*link) { - parent = *link; - myentry = rb_entry(parent, struct zswap_entry, rbnode); - myentry_offset = swp_offset(myentry->swpentry); - if (myentry_offset > entry_offset) - link = &(*link)->rb_left; - else if (myentry_offset < entry_offset) - link = &(*link)->rb_right; - else { - *dupentry = myentry; - return -EEXIST; - } + if (!crypto_has_acomp(zswap_compressor, 0, 0) && + 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; } - rb_link_node(&entry->rbnode, parent, link); - rb_insert_color(&entry->rbnode, root); - return 0; -} -static bool 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); - return true; + /* Default compressor should be available. Kconfig bug? */ + if (WARN_ON_ONCE(!crypto_has_acomp(zswap_compressor, 0, 0))) { + zswap_compressor = ZSWAP_PARAM_UNSET; + return NULL; } - return false; -} -/* - * 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->objcg) { - obj_cgroup_uncharge_zswap(entry->objcg, entry->length); - obj_cgroup_put(entry->objcg); - } - if (!entry->length) - atomic_dec(&zswap_same_filled_pages); - else { - spin_lock(&entry->pool->lru_lock); - list_del(&entry->lru); - spin_unlock(&entry->pool->lru_lock); - 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(); + return zswap_pool_create(zswap_compressor); } -/* caller must hold the tree lock */ -static void zswap_entry_get(struct zswap_entry *entry) +static void zswap_pool_destroy(struct zswap_pool *pool) { - entry->refcount++; -} + zswap_pool_debug("destroying", pool); -/* 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; + cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); + free_percpu(pool->acomp_ctx); - BUG_ON(refcount < 0); - if (refcount == 0) { - zswap_rb_erase(&tree->rbroot, entry); - zswap_free_entry(entry); - } + zs_destroy_pool(pool->zs_pool); + kfree(pool); } -/* caller must hold the tree lock */ -static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, - pgoff_t offset) +static void __zswap_pool_release(struct work_struct *work) { - struct zswap_entry *entry; + struct zswap_pool *pool = container_of(work, typeof(*pool), + release_work); - entry = zswap_rb_search(root, offset); - if (entry) - zswap_entry_get(entry); + synchronize_rcu(); - return entry; + /* nobody should have been able to get a ref... */ + WARN_ON(!percpu_ref_is_zero(&pool->ref)); + percpu_ref_exit(&pool->ref); + + /* pool is now off zswap_pools list and has no references. */ + zswap_pool_destroy(pool); } -/********************************* -* per-cpu code -**********************************/ -static DEFINE_PER_CPU(u8 *, zswap_dstmem); -/* - * If users dynamically change the zpool type and compressor at runtime, i.e. - * zswap is running, zswap can have more than one zpool on one cpu, but they - * are sharing dtsmem. So we need this mutex to be per-cpu. - */ -static DEFINE_PER_CPU(struct mutex *, zswap_mutex); +static struct zswap_pool *zswap_pool_current(void); -static int zswap_dstmem_prepare(unsigned int cpu) +static void __zswap_pool_empty(struct percpu_ref *ref) { - struct mutex *mutex; - u8 *dst; + struct zswap_pool *pool; - dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!dst) - return -ENOMEM; + pool = container_of(ref, typeof(*pool), ref); - mutex = kmalloc_node(sizeof(*mutex), GFP_KERNEL, cpu_to_node(cpu)); - if (!mutex) { - kfree(dst); - return -ENOMEM; - } + spin_lock_bh(&zswap_pools_lock); - mutex_init(mutex); - per_cpu(zswap_dstmem, cpu) = dst; - per_cpu(zswap_mutex, cpu) = mutex; - return 0; -} - -static int zswap_dstmem_dead(unsigned int cpu) -{ - struct mutex *mutex; - u8 *dst; + WARN_ON(pool == zswap_pool_current()); - mutex = per_cpu(zswap_mutex, cpu); - kfree(mutex); - per_cpu(zswap_mutex, cpu) = NULL; + list_del_rcu(&pool->list); - dst = per_cpu(zswap_dstmem, cpu); - kfree(dst); - per_cpu(zswap_dstmem, cpu) = NULL; + INIT_WORK(&pool->release_work, __zswap_pool_release); + schedule_work(&pool->release_work); - return 0; + spin_unlock_bh(&zswap_pools_lock); } -static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) +static int __must_check zswap_pool_tryget(struct zswap_pool *pool) { - struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); - struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; - - acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); - if (IS_ERR(acomp)) { - pr_err("could not alloc crypto acomp %s : %ld\n", - pool->tfm_name, PTR_ERR(acomp)); - return PTR_ERR(acomp); - } - acomp_ctx->acomp = acomp; - - req = acomp_request_alloc(acomp_ctx->acomp); - if (!req) { - pr_err("could not alloc crypto acomp_request %s\n", - pool->tfm_name); - crypto_free_acomp(acomp_ctx->acomp); - return -ENOMEM; - } - acomp_ctx->req = req; - - crypto_init_wait(&acomp_ctx->wait); - /* - * if the backend of acomp is async zip, crypto_req_done() will wakeup - * crypto_wait_req(); if the backend of acomp is scomp, the callback - * won't be called, crypto_wait_req() will return without blocking. - */ - acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &acomp_ctx->wait); - - acomp_ctx->mutex = per_cpu(zswap_mutex, cpu); - acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu); + if (!pool) + return 0; - return 0; + return percpu_ref_tryget(&pool->ref); } -static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) +/* The caller must already have a reference. */ +static void zswap_pool_get(struct zswap_pool *pool) { - struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); - struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - - if (!IS_ERR_OR_NULL(acomp_ctx)) { - if (!IS_ERR_OR_NULL(acomp_ctx->req)) - acomp_request_free(acomp_ctx->req); - if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) - crypto_free_acomp(acomp_ctx->acomp); - } - - return 0; + percpu_ref_get(&pool->ref); } -/********************************* -* pool functions -**********************************/ +static void zswap_pool_put(struct zswap_pool *pool) +{ + percpu_ref_put(&pool->ref); +} static struct zswap_pool *__zswap_pool_current(void) { @@ -554,7 +410,7 @@ static struct zswap_pool *zswap_pool_current_get(void) rcu_read_lock(); pool = __zswap_pool_current(); - if (!zswap_pool_get(pool)) + if (!zswap_pool_tryget(pool)) pool = NULL; rcu_read_unlock(); @@ -562,26 +418,8 @@ static struct zswap_pool *zswap_pool_current_get(void) 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) +static struct zswap_pool *zswap_pool_find_get(char *compressor) { struct zswap_pool *pool; @@ -590,10 +428,8 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) 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)) + if (!zswap_pool_tryget(pool)) continue; return pool; } @@ -601,294 +437,64 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) return NULL; } -/* - * If the entry is still valid in the tree, drop the initial ref and remove it - * from the tree. This function must be called with an additional ref held, - * otherwise it may race with another invalidation freeing the entry. - */ -static void zswap_invalidate_entry(struct zswap_tree *tree, - struct zswap_entry *entry) +static unsigned long zswap_max_pages(void) { - if (zswap_rb_erase(&tree->rbroot, entry)) - zswap_entry_put(tree, entry); + return totalram_pages() * zswap_max_pool_percent / 100; } -static int zswap_reclaim_entry(struct zswap_pool *pool) +static unsigned long zswap_accept_thr_pages(void) { - struct zswap_entry *entry; - struct zswap_tree *tree; - pgoff_t swpoffset; - int ret; - - /* Get an entry off the LRU */ - spin_lock(&pool->lru_lock); - if (list_empty(&pool->lru)) { - spin_unlock(&pool->lru_lock); - return -EINVAL; - } - entry = list_last_entry(&pool->lru, struct zswap_entry, lru); - list_del_init(&entry->lru); - /* - * Once the lru lock is dropped, the entry might get freed. The - * swpoffset is copied to the stack, and entry isn't deref'd again - * until the entry is verified to still be alive in the tree. - */ - swpoffset = swp_offset(entry->swpentry); - tree = zswap_trees[swp_type(entry->swpentry)]; - spin_unlock(&pool->lru_lock); - - /* Check for invalidate() race */ - spin_lock(&tree->lock); - if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) { - ret = -EAGAIN; - goto unlock; - } - /* Hold a reference to prevent a free during writeback */ - zswap_entry_get(entry); - spin_unlock(&tree->lock); - - ret = zswap_writeback_entry(entry, tree); - - spin_lock(&tree->lock); - if (ret) { - /* Writeback failed, put entry back on LRU */ - spin_lock(&pool->lru_lock); - list_move(&entry->lru, &pool->lru); - spin_unlock(&pool->lru_lock); - goto put_unlock; - } - - /* - * Writeback started successfully, the page now belongs to the - * swapcache. Drop the entry from zswap - unless invalidate already - * took it out while we had the tree->lock released for IO. - */ - zswap_invalidate_entry(tree, entry); - -put_unlock: - /* Drop local reference */ - zswap_entry_put(tree, entry); -unlock: - spin_unlock(&tree->lock); - return ret ? -EAGAIN : 0; + return zswap_max_pages() * zswap_accept_thr_percent / 100; } -static void shrink_worker(struct work_struct *w) -{ - struct zswap_pool *pool = container_of(w, typeof(*pool), - shrink_work); - int ret, failures = 0; - - do { - ret = zswap_reclaim_entry(pool); - if (ret) { - zswap_reject_reclaim_fail++; - if (ret != -EAGAIN) - break; - if (++failures == MAX_RECLAIM_RETRIES) - break; - } - cond_resched(); - } while (!zswap_can_accept()); - zswap_pool_put(pool); -} - -static struct zswap_pool *zswap_pool_create(char *type, char *compressor) +unsigned long zswap_total_pages(void) { 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); - if (!pool->zpool) { - pr_err("%s zpool not available\n", type); - goto error; - } - pr_debug("using %s zpool\n", zpool_get_type(pool->zpool)); - - strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); + unsigned long total = 0; - pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx); - if (!pool->acomp_ctx) { - 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_LIST_HEAD(&pool->lru); - spin_lock_init(&pool->lru_lock); - INIT_WORK(&pool->shrink_work, shrink_worker); - - zswap_pool_debug("created", pool); - - return pool; + rcu_read_lock(); + list_for_each_entry_rcu(pool, &zswap_pools, list) + total += zs_get_total_pages(pool->zs_pool); + rcu_read_unlock(); -error: - if (pool->acomp_ctx) - free_percpu(pool->acomp_ctx); - if (pool->zpool) - zpool_destroy_pool(pool->zpool); - kfree(pool); - return NULL; + return total; } -static struct zswap_pool *__zswap_pool_create_fallback(void) +static bool zswap_check_limits(void) { - bool has_comp, has_zpool; - - has_comp = crypto_has_acomp(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_acomp(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; - } + unsigned long cur_pages = zswap_total_pages(); + unsigned long max_pages = zswap_max_pages(); - 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 (cur_pages >= max_pages) { + zswap_pool_limit_hit++; + zswap_pool_reached_full = true; + } else if (zswap_pool_reached_full && + cur_pages <= zswap_accept_thr_pages()) { + zswap_pool_reached_full = false; } - - 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->acomp_ctx); - 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); + return zswap_pool_reached_full; } /********************************* * param callbacks **********************************/ -static bool zswap_pool_changed(const char *s, const struct kernel_param *kp) -{ - /* no change required */ - if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) - return false; - return true; -} - -/* val must be a null-terminated string */ -static int __zswap_param_set(const char *val, const struct kernel_param *kp, - char *type, char *compressor) +static int zswap_compressor_param_set(const char *val, const struct kernel_param *kp) { struct zswap_pool *pool, *put_pool = NULL; char *s = strstrip((char *)val); + bool create_pool = false; int ret = 0; - bool new_pool = false; mutex_lock(&zswap_init_lock); switch (zswap_init_state) { case ZSWAP_UNINIT: - /* if this is load-time (pre-init) param setting, - * don't create a pool; that's done during init. - */ + /* Handled in zswap_setup() */ ret = param_set_charp(s, kp); break; case ZSWAP_INIT_SUCCEED: - new_pool = zswap_pool_changed(s, kp); + if (!zswap_has_pool || strcmp(s, *(char **)kp->arg)) + create_pool = true; break; case ZSWAP_INIT_FAILED: pr_err("can't set param, initialization failed\n"); @@ -896,54 +502,53 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, } mutex_unlock(&zswap_init_lock); - /* no need to create a new pool, return directly */ - if (!new_pool) + if (!create_pool) return ret; - 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_acomp(s, 0, 0)) { - pr_err("compressor %s not available\n", s); - return -ENOENT; - } - compressor = s; - } else { - WARN_ON(1); - return -EINVAL; + if (!crypto_has_acomp(s, 0, 0)) { + pr_err("compressor %s not available\n", s); + return -ENOENT; } - spin_lock(&zswap_pools_lock); + spin_lock_bh(&zswap_pools_lock); - pool = zswap_pool_find_get(type, compressor); + pool = zswap_pool_find_get(s); if (pool) { zswap_pool_debug("using existing", pool); WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); } - spin_unlock(&zswap_pools_lock); + spin_unlock_bh(&zswap_pools_lock); if (!pool) - pool = zswap_pool_create(type, compressor); + pool = zswap_pool_create(s); + else { + /* + * Restore the initial ref dropped by percpu_ref_kill() + * when the pool was decommissioned and switch it again + * to percpu mode. + */ + percpu_ref_resurrect(&pool->ref); + + /* Drop the ref from zswap_pool_find_get(). */ + zswap_pool_put(pool); + } if (pool) ret = param_set_charp(s, kp); else ret = -EINVAL; - spin_lock(&zswap_pools_lock); + spin_lock_bh(&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 + /* + * 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 */ @@ -951,40 +556,18 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, put_pool = pool; } - spin_unlock(&zswap_pools_lock); + spin_unlock_bh(&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_acomp() - * checks above. - */ - ret = param_set_charp(s, kp); - } - - /* drop the ref from either the old current pool, + /* + * 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); + percpu_ref_kill(&put_pool->ref); 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) { @@ -1015,533 +598,1115 @@ static int zswap_enabled_param_set(const char *val, } /********************************* -* writeback code +* lru functions **********************************/ -/* return enum for zswap_get_swap_cache_page */ -enum zswap_get_swap_ret { - ZSWAP_SWAPCACHE_NEW, - ZSWAP_SWAPCACHE_EXIST, - ZSWAP_SWAPCACHE_FAIL, -}; + +/* should be called under RCU */ +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL; +} +#else +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return NULL; +} +#endif + +static inline int entry_to_nid(struct zswap_entry *entry) +{ + return page_to_nid(virt_to_page(entry)); +} + +static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + + /* + * Note that it is safe to use rcu_read_lock() here, even in the face of + * concurrent memcg offlining: + * + * 1. list_lru_add() is called before list_lru_one is dead. The + * new entry will be reparented to memcg's parent's list_lru. + * 2. list_lru_add() is called after list_lru_one is dead. The + * new entry will be added directly to memcg's parent's list_lru. + * + * Similar reasoning holds for list_lru_del(). + */ + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_add(list_lru, &entry->lru, nid, memcg); + rcu_read_unlock(); +} + +static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_del(list_lru, &entry->lru, nid, memcg); + rcu_read_unlock(); +} + +void zswap_lruvec_state_init(struct lruvec *lruvec) +{ + atomic_long_set(&lruvec->zswap_lruvec_state.nr_disk_swapins, 0); +} + +void zswap_folio_swapin(struct folio *folio) +{ + struct lruvec *lruvec; + + if (folio) { + lruvec = folio_lruvec(folio); + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_disk_swapins); + } +} /* - * zswap_get_swap_cache_page - * - * This is an adaption of read_swap_cache_async() + * This function should be called when a memcg is being offlined. * - * 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. + * Since the global shrinker shrink_worker() may hold a reference + * of the memcg, we must check and release the reference in + * zswap_next_shrink. * - * 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 + * shrink_worker() must handle the case where this function releases + * the reference of memcg being shrunk. */ -static int zswap_get_swap_cache_page(swp_entry_t entry, - struct page **retpage) +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) +{ + /* lock out zswap shrinker walking memcg tree */ + spin_lock(&zswap_shrink_lock); + if (zswap_next_shrink == memcg) { + do { + zswap_next_shrink = mem_cgroup_iter(NULL, zswap_next_shrink, NULL); + } while (zswap_next_shrink && !mem_cgroup_online(zswap_next_shrink)); + } + spin_unlock(&zswap_shrink_lock); +} + +/********************************* +* zswap entry functions +**********************************/ +static struct kmem_cache *zswap_entry_cache; + +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) +{ + struct zswap_entry *entry; + entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); + if (!entry) + return NULL; + return entry; +} + +static void zswap_entry_cache_free(struct zswap_entry *entry) { - 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; + kmem_cache_free(zswap_entry_cache, entry); } /* - * 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. + * Carries out the common pattern of freeing an entry's zsmalloc allocation, + * freeing the entry itself, and decrementing the number of stored pages. */ -static int zswap_writeback_entry(struct zswap_entry *entry, - struct zswap_tree *tree) +static void zswap_entry_free(struct zswap_entry *entry) { - swp_entry_t swpentry = entry->swpentry; - struct page *page; - struct scatterlist input, output; - struct crypto_acomp_ctx *acomp_ctx; - struct zpool *pool = entry->pool->zpool; + zswap_lru_del(&zswap_list_lru, entry); + zs_free(entry->pool->zs_pool, entry->handle); + zswap_pool_put(entry->pool); + if (entry->objcg) { + obj_cgroup_uncharge_zswap(entry->objcg, entry->length); + obj_cgroup_put(entry->objcg); + } + if (entry->length == PAGE_SIZE) + atomic_long_dec(&zswap_stored_incompressible_pages); + zswap_entry_cache_free(entry); + atomic_long_dec(&zswap_stored_pages); +} - u8 *src, *tmp = NULL; - unsigned int dlen; +/********************************* +* compressed storage functions +**********************************/ +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_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - }; - - if (!zpool_can_sleep_mapped(pool)) { - tmp = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!tmp) - return -ENOMEM; - } - /* try to allocate swap cache page */ - switch (zswap_get_swap_cache_page(swpentry, &page)) { - case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ + buffer = kmalloc_node(PAGE_SIZE, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; goto fail; + } - case ZSWAP_SWAPCACHE_EXIST: - /* page is already in the swap cache, ignore for now */ - put_page(page); - ret = -EEXIST; + acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); + if (IS_ERR(acomp)) { + pr_err("could not alloc crypto acomp %s : %ld\n", + pool->tfm_name, PTR_ERR(acomp)); + ret = PTR_ERR(acomp); goto fail; + } + + req = acomp_request_alloc(acomp); + if (!req) { + pr_err("could not alloc crypto acomp_request %s\n", + pool->tfm_name); + ret = -ENOMEM; + goto fail; + } - case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); + crypto_init_wait(&acomp_ctx->wait); + + /* + * if the backend of acomp is async zip, crypto_req_done() will wakeup + * crypto_wait_req(); if the backend of acomp is scomp, the callback + * won't be called, crypto_wait_req() will return without blocking. + */ + acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &acomp_ctx->wait); + + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; + mutex_unlock(&acomp_ctx->mutex); + return 0; + +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); + return ret; +} + +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_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + struct acomp_req *req; + struct crypto_acomp *acomp; + u8 *buffer; + + if (IS_ERR_OR_NULL(acomp_ctx)) + return 0; + + mutex_lock(&acomp_ctx->mutex); + req = acomp_ctx->req; + acomp = acomp_ctx->acomp; + buffer = acomp_ctx->buffer; + acomp_ctx->req = NULL; + acomp_ctx->acomp = NULL; + acomp_ctx->buffer = NULL; + mutex_unlock(&acomp_ctx->mutex); + + /* + * Do the actual freeing after releasing the mutex to avoid subtle + * locking dependencies causing deadlocks. + */ + if (!IS_ERR_OR_NULL(req)) + acomp_request_free(req); + if (!IS_ERR_OR_NULL(acomp)) + crypto_free_acomp(acomp); + kfree(buffer); + + return 0; +} + +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; /* - * Having a local reference to the zswap entry doesn't exclude - * swapping from invalidating and recycling the swap slot. Once - * the swapcache is secured against concurrent swapping to and - * from the slot, recheck that the entry is still current before - * writing. + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. */ - spin_lock(&tree->lock); - if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) { - spin_unlock(&tree->lock); - delete_from_swap_cache(page_folio(page)); - ret = -ENOMEM; - goto fail; - } - spin_unlock(&tree->lock); + mutex_unlock(&acomp_ctx->mutex); + } +} - /* decompress */ - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - dlen = PAGE_SIZE; +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} - src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO); - if (!zpool_can_sleep_mapped(pool)) { - memcpy(tmp, src, entry->length); - src = tmp; - zpool_unmap_handle(pool, entry->handle); - } +static bool zswap_compress(struct page *page, struct zswap_entry *entry, + struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + struct scatterlist input, output; + int comp_ret = 0, alloc_ret = 0; + unsigned int dlen = PAGE_SIZE; + unsigned long handle; + gfp_t gfp; + u8 *dst; + bool mapped = false; - mutex_lock(acomp_ctx->mutex); - sg_init_one(&input, src, entry->length); - sg_init_table(&output, 1); - sg_set_page(&output, page, PAGE_SIZE, 0); - acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen); - ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); - dlen = acomp_ctx->req->dlen; - mutex_unlock(acomp_ctx->mutex); - - if (!zpool_can_sleep_mapped(pool)) - kfree(tmp); - else - zpool_unmap_handle(pool, entry->handle); + acomp_ctx = acomp_ctx_get_cpu_lock(pool); + dst = acomp_ctx->buffer; + sg_init_table(&input, 1); + sg_set_page(&input, page, PAGE_SIZE, 0); - BUG_ON(ret); - BUG_ON(dlen != PAGE_SIZE); + sg_init_one(&output, dst, PAGE_SIZE); + acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen); + + /* + * it maybe looks a little bit silly that we send an asynchronous request, + * then wait for its completion synchronously. This makes the process look + * synchronous in fact. + * Theoretically, acomp supports users send multiple acomp requests in one + * acomp instance, then get those requests done simultaneously. but in this + * case, zswap actually does store and load page by page, there is no + * existing method to send the second page before the first page is done + * in one thread doing zswap. + * but in different threads running on different cpu, we have different + * acomp instance, so multiple threads can do (de)compression in parallel. + */ + comp_ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); + dlen = acomp_ctx->req->dlen; - /* page is up to date */ - SetPageUptodate(page); + /* + * If a page cannot be compressed into a size smaller than PAGE_SIZE, + * save the content as is without a compression, to keep the LRU order + * of writebacks. If writeback is disabled, reject the page since it + * only adds metadata overhead. swap_writeout() will put the page back + * to the active LRU list in the case. + */ + if (comp_ret || !dlen || dlen >= PAGE_SIZE) { + if (!mem_cgroup_zswap_writeback_enabled( + folio_memcg(page_folio(page)))) { + comp_ret = comp_ret ? comp_ret : -EINVAL; + goto unlock; + } + comp_ret = 0; + dlen = PAGE_SIZE; + dst = kmap_local_page(page); + mapped = true; } - /* move it to the tail of the inactive list after end_writeback */ - SetPageReclaim(page); + gfp = GFP_NOWAIT | __GFP_NORETRY | __GFP_HIGHMEM | __GFP_MOVABLE; + handle = zs_malloc(pool->zs_pool, dlen, gfp, page_to_nid(page)); + if (IS_ERR_VALUE(handle)) { + alloc_ret = PTR_ERR((void *)handle); + goto unlock; + } - /* start writeback */ - __swap_writepage(page, &wbc); - put_page(page); - zswap_written_back_pages++; + zs_obj_write(pool->zs_pool, handle, dst, dlen); + entry->handle = handle; + entry->length = dlen; - return ret; -fail: - if (!zpool_can_sleep_mapped(pool)) - kfree(tmp); +unlock: + if (mapped) + kunmap_local(dst); + if (comp_ret == -ENOSPC || alloc_ret == -ENOSPC) + zswap_reject_compress_poor++; + else if (comp_ret) + zswap_reject_compress_fail++; + else if (alloc_ret) + zswap_reject_alloc_fail++; - /* - * if we get here due to ZSWAP_SWAPCACHE_EXIST - * a load may be happening concurrently. - * it is safe and okay to not free the entry. - * it is also okay to return !0 - */ - return ret; + acomp_ctx_put_unlock(acomp_ctx); + return comp_ret == 0 && alloc_ret == 0; } -static int zswap_is_page_same_filled(void *ptr, unsigned long *value) +static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio) { - unsigned long *page; - unsigned long val; - unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1; + struct zswap_pool *pool = entry->pool; + struct scatterlist input, output; + struct crypto_acomp_ctx *acomp_ctx; + int decomp_ret = 0, dlen = PAGE_SIZE; + u8 *src, *obj; - page = (unsigned long *)ptr; - val = page[0]; + acomp_ctx = acomp_ctx_get_cpu_lock(pool); + obj = zs_obj_read_begin(pool->zs_pool, entry->handle, acomp_ctx->buffer); - if (val != page[last_pos]) - return 0; + /* zswap entries of length PAGE_SIZE are not compressed. */ + if (entry->length == PAGE_SIZE) { + memcpy_to_folio(folio, 0, obj, entry->length); + goto read_done; + } - for (pos = 1; pos < last_pos; pos++) { - if (val != page[pos]) - return 0; + /* + * zs_obj_read_begin() might return a kmap address of highmem when + * acomp_ctx->buffer is not used. However, sg_init_one() does not + * handle highmem addresses, so copy the object to acomp_ctx->buffer. + */ + if (virt_addr_valid(obj)) { + src = obj; + } else { + WARN_ON_ONCE(obj == acomp_ctx->buffer); + memcpy(acomp_ctx->buffer, obj, entry->length); + src = acomp_ctx->buffer; } - *value = val; + sg_init_one(&input, src, entry->length); + sg_init_table(&output, 1); + sg_set_folio(&output, folio, PAGE_SIZE, 0); + acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); + decomp_ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); + dlen = acomp_ctx->req->dlen; - return 1; -} +read_done: + zs_obj_read_end(pool->zs_pool, entry->handle, obj); + acomp_ctx_put_unlock(acomp_ctx); -static void zswap_fill_page(void *ptr, unsigned long value) -{ - unsigned long *page; + if (!decomp_ret && dlen == PAGE_SIZE) + return true; - page = (unsigned long *)ptr; - memset_l(page, value, PAGE_SIZE / sizeof(unsigned long)); + zswap_decompress_fail++; + pr_alert_ratelimited("Decompression error from zswap (%d:%lu %s %u->%d)\n", + swp_type(entry->swpentry), + swp_offset(entry->swpentry), + entry->pool->tfm_name, entry->length, dlen); + return false; } /********************************* -* frontswap hooks +* writeback code **********************************/ -/* attempts to compress and store an single page */ -static int zswap_frontswap_store(unsigned type, pgoff_t offset, - struct page *page) +/* + * Attempts to free an entry by adding a folio to the swap cache, + * decompressing the entry data into the folio, and issuing a + * bio write to write the folio back to the swap device. + * + * This can be thought of as a "resumed writeback" of the folio + * to the swap device. We are basically resuming the same swap + * writeback path that was intercepted with the zswap_store() + * in the first place. After the folio has been decompressed into + * the swap cache, the compressed version stored by zswap can be + * freed. + */ +static int zswap_writeback_entry(struct zswap_entry *entry, + swp_entry_t swpentry) { - struct zswap_tree *tree = zswap_trees[type]; - struct zswap_entry *entry, *dupentry; - struct scatterlist input, output; - struct crypto_acomp_ctx *acomp_ctx; - struct obj_cgroup *objcg = NULL; - struct zswap_pool *pool; - int ret; - unsigned int dlen = PAGE_SIZE; - unsigned long handle, value; - char *buf; - u8 *src, *dst; - gfp_t gfp; + struct xarray *tree; + pgoff_t offset = swp_offset(swpentry); + struct folio *folio; + struct mempolicy *mpol; + bool folio_was_allocated; + struct swap_info_struct *si; + int ret = 0; - /* THP isn't supported */ - if (PageTransHuge(page)) { - ret = -EINVAL; - goto reject; - } + /* try to allocate swap cache folio */ + si = get_swap_device(swpentry); + if (!si) + return -EEXIST; - if (!zswap_enabled || !tree) { - ret = -ENODEV; - goto reject; + mpol = get_task_policy(current); + folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, + NO_INTERLEAVE_INDEX, &folio_was_allocated, true); + put_swap_device(si); + if (!folio) + return -ENOMEM; + + /* + * Found an existing folio, we raced with swapin or concurrent + * shrinker. We generally writeback cold folios from zswap, and + * swapin means the folio just became hot, so skip this folio. + * For unlikely concurrent shrinker case, it will be unlinked + * and freed when invalidated by the concurrent shrinker anyway. + */ + if (!folio_was_allocated) { + ret = -EEXIST; + goto out; } /* - * XXX: zswap reclaim does not work with cgroups yet. Without a - * cgroup-aware entry LRU, we will push out entries system-wide based on - * local cgroup limits. + * folio is locked, and the swapcache is now secured against + * concurrent swapping to and from the slot, and concurrent + * swapoff so we can safely dereference the zswap tree here. + * Verify that the swap entry hasn't been invalidated and recycled + * behind our backs, to avoid overwriting a new swap folio with + * old compressed data. Only when this is successful can the entry + * be dereferenced. */ - objcg = get_obj_cgroup_from_page(page); - if (objcg && !obj_cgroup_may_zswap(objcg)) { + tree = swap_zswap_tree(swpentry); + if (entry != xa_load(tree, offset)) { ret = -ENOMEM; - goto reject; + goto out; } - /* reclaim space if needed */ - if (zswap_is_full()) { - zswap_pool_limit_hit++; - zswap_pool_reached_full = true; - goto shrink; + if (!zswap_decompress(entry, folio)) { + ret = -EIO; + goto out; } - if (zswap_pool_reached_full) { - if (!zswap_can_accept()) { - ret = -ENOMEM; - goto shrink; - } else - zswap_pool_reached_full = false; + xa_erase(tree, offset); + + count_vm_event(ZSWPWB); + if (entry->objcg) + count_objcg_events(entry->objcg, ZSWPWB, 1); + + zswap_entry_free(entry); + + /* folio is up to date */ + folio_mark_uptodate(folio); + + /* move it to the tail of the inactive list after end_writeback */ + folio_set_reclaim(folio); + + /* start writeback */ + __swap_writepage(folio, NULL); + +out: + if (ret && ret != -EEXIST) { + swap_cache_del_folio(folio); + folio_unlock(folio); } + folio_put(folio); + return ret; +} - /* allocate entry */ - entry = zswap_entry_cache_alloc(GFP_KERNEL); - if (!entry) { - zswap_reject_kmemcache_fail++; - ret = -ENOMEM; - goto reject; +/********************************* +* shrinker functions +**********************************/ +/* + * The dynamic shrinker is modulated by the following factors: + * + * 1. Each zswap entry has a referenced bit, which the shrinker unsets (giving + * the entry a second chance) before rotating it in the LRU list. If the + * entry is considered again by the shrinker, with its referenced bit unset, + * it is written back. The writeback rate as a result is dynamically + * adjusted by the pool activities - if the pool is dominated by new entries + * (i.e lots of recent zswapouts), these entries will be protected and + * the writeback rate will slow down. On the other hand, if the pool has a + * lot of stagnant entries, these entries will be reclaimed immediately, + * effectively increasing the writeback rate. + * + * 2. Swapins counter: If we observe swapins, it is a sign that we are + * overshrinking and should slow down. We maintain a swapins counter, which + * is consumed and subtract from the number of eligible objects on the LRU + * in zswap_shrinker_count(). + * + * 3. Compression ratio. The better the workload compresses, the less gains we + * can expect from writeback. We scale down the number of objects available + * for reclaim by this ratio. + */ +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + void *arg) +{ + struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); + bool *encountered_page_in_swapcache = (bool *)arg; + swp_entry_t swpentry; + enum lru_status ret = LRU_REMOVED_RETRY; + int writeback_result; + + /* + * Second chance algorithm: if the entry has its referenced bit set, give it + * a second chance. Only clear the referenced bit and rotate it in the + * zswap's LRU list. + */ + if (entry->referenced) { + entry->referenced = false; + return LRU_ROTATE; } - if (zswap_same_filled_pages_enabled) { - src = kmap_atomic(page); - if (zswap_is_page_same_filled(src, &value)) { - kunmap_atomic(src); - entry->swpentry = swp_entry(type, offset); - entry->length = 0; - entry->value = value; - atomic_inc(&zswap_same_filled_pages); - goto insert_entry; + /* + * As soon as we drop the LRU lock, the entry can be freed by + * a concurrent invalidation. This means the following: + * + * 1. We extract the swp_entry_t to the stack, allowing + * zswap_writeback_entry() to pin the swap entry and + * then validate the zswap entry against that swap entry's + * tree using pointer value comparison. Only when that + * is successful can the entry be dereferenced. + * + * 2. Usually, objects are taken off the LRU for reclaim. In + * this case this isn't possible, because if reclaim fails + * for whatever reason, we have no means of knowing if the + * entry is alive to put it back on the LRU. + * + * So rotate it before dropping the lock. If the entry is + * written back or invalidated, the free path will unlink + * it. For failures, rotation is the right thing as well. + * + * Temporary failures, where the same entry should be tried + * again immediately, almost never happen for this shrinker. + * We don't do any trylocking; -ENOMEM comes closest, + * but that's extremely rare and doesn't happen spuriously + * either. Don't bother distinguishing this case. + */ + list_move_tail(item, &l->list); + + /* + * Once the lru lock is dropped, the entry might get freed. The + * swpentry is copied to the stack, and entry isn't deref'd again + * until the entry is verified to still be alive in the tree. + */ + swpentry = entry->swpentry; + + /* + * It's safe to drop the lock here because we return either + * LRU_REMOVED_RETRY, LRU_RETRY or LRU_STOP. + */ + spin_unlock(&l->lock); + + writeback_result = zswap_writeback_entry(entry, swpentry); + + if (writeback_result) { + zswap_reject_reclaim_fail++; + ret = LRU_RETRY; + + /* + * Encountering a page already in swap cache is a sign that we are shrinking + * into the warmer region. We should terminate shrinking (if we're in the dynamic + * shrinker context). + */ + if (writeback_result == -EEXIST && encountered_page_in_swapcache) { + ret = LRU_STOP; + *encountered_page_in_swapcache = true; } - kunmap_atomic(src); + } else { + zswap_written_back_pages++; } - if (!zswap_non_same_filled_pages_enabled) { - ret = -EINVAL; - goto freepage; + return ret; +} + +static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long shrink_ret; + bool encountered_page_in_swapcache = false; + + if (!zswap_shrinker_enabled || + !mem_cgroup_zswap_writeback_enabled(sc->memcg)) { + sc->nr_scanned = 0; + return SHRINK_STOP; } - /* if entry is successfully added, it keeps the reference */ - entry->pool = zswap_pool_current_get(); - if (!entry->pool) { - ret = -EINVAL; - goto freepage; + shrink_ret = list_lru_shrink_walk(&zswap_list_lru, sc, &shrink_memcg_cb, + &encountered_page_in_swapcache); + + if (encountered_page_in_swapcache) + return SHRINK_STOP; + + return shrink_ret ? shrink_ret : SHRINK_STOP; +} + +static unsigned long zswap_shrinker_count(struct shrinker *shrinker, + struct shrink_control *sc) +{ + struct mem_cgroup *memcg = sc->memcg; + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); + atomic_long_t *nr_disk_swapins = + &lruvec->zswap_lruvec_state.nr_disk_swapins; + unsigned long nr_backing, nr_stored, nr_freeable, nr_disk_swapins_cur, + nr_remain; + + if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) + return 0; + + /* + * The shrinker resumes swap writeback, which will enter block + * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS + * rules (may_enter_fs()), which apply on a per-folio basis. + */ + if (!gfp_has_io_fs(sc->gfp_mask)) + return 0; + + /* + * For memcg, use the cgroup-wide ZSWAP stats since we don't + * have them per-node and thus per-lruvec. Careful if memcg is + * runtime-disabled: we can get sc->memcg == NULL, which is ok + * for the lruvec, but not for memcg_page_state(). + * + * Without memcg, use the zswap pool-wide metrics. + */ + if (!mem_cgroup_disabled()) { + mem_cgroup_flush_stats(memcg); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); + } else { + nr_backing = zswap_total_pages(); + nr_stored = atomic_long_read(&zswap_stored_pages); } - /* compress */ - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); + if (!nr_stored) + return 0; - mutex_lock(acomp_ctx->mutex); + nr_freeable = list_lru_shrink_count(&zswap_list_lru, sc); + if (!nr_freeable) + return 0; - dst = acomp_ctx->dstmem; - sg_init_table(&input, 1); - sg_set_page(&input, page, PAGE_SIZE, 0); + /* + * Subtract from the lru size the number of pages that are recently swapped + * in from disk. The idea is that had we protect the zswap's LRU by this + * amount of pages, these disk swapins would not have happened. + */ + nr_disk_swapins_cur = atomic_long_read(nr_disk_swapins); + do { + if (nr_freeable >= nr_disk_swapins_cur) + nr_remain = 0; + else + nr_remain = nr_disk_swapins_cur - nr_freeable; + } while (!atomic_long_try_cmpxchg( + nr_disk_swapins, &nr_disk_swapins_cur, nr_remain)); + + nr_freeable -= nr_disk_swapins_cur - nr_remain; + if (!nr_freeable) + return 0; - /* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */ - sg_init_one(&output, dst, PAGE_SIZE * 2); - acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen); /* - * it maybe looks a little bit silly that we send an asynchronous request, - * then wait for its completion synchronously. This makes the process look - * synchronous in fact. - * Theoretically, acomp supports users send multiple acomp requests in one - * acomp instance, then get those requests done simultaneously. but in this - * case, frontswap actually does store and load page by page, there is no - * existing method to send the second page before the first page is done - * in one thread doing frontswap. - * but in different threads running on different cpu, we have different - * acomp instance, so multiple threads can do (de)compression in parallel. + * Scale the number of freeable pages by the memory saving factor. + * This ensures that the better zswap compresses memory, the fewer + * pages we will evict to swap (as it will otherwise incur IO for + * relatively small memory saving). */ - ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); - dlen = acomp_ctx->req->dlen; + return mult_frac(nr_freeable, nr_backing, nr_stored); +} - if (ret) { - ret = -EINVAL; - goto put_dstmem; +static struct shrinker *zswap_alloc_shrinker(void) +{ + struct shrinker *shrinker; + + shrinker = + shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap"); + if (!shrinker) + return NULL; + + shrinker->scan_objects = zswap_shrinker_scan; + shrinker->count_objects = zswap_shrinker_count; + shrinker->batch = 0; + shrinker->seeks = DEFAULT_SEEKS; + return shrinker; +} + +static int shrink_memcg(struct mem_cgroup *memcg) +{ + int nid, shrunk = 0, scanned = 0; + + if (!mem_cgroup_zswap_writeback_enabled(memcg)) + return -ENOENT; + + /* + * Skip zombies because their LRUs are reparented and we would be + * reclaiming from the parent instead of the dead memcg. + */ + if (memcg && !mem_cgroup_online(memcg)) + return -ENOENT; + + for_each_node_state(nid, N_NORMAL_MEMORY) { + unsigned long nr_to_walk = 1; + + shrunk += list_lru_walk_one(&zswap_list_lru, nid, memcg, + &shrink_memcg_cb, NULL, &nr_to_walk); + scanned += 1 - nr_to_walk; } - /* store */ - 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, dlen, gfp, &handle); - if (ret == -ENOSPC) { - zswap_reject_compress_poor++; - goto put_dstmem; + if (!scanned) + return -ENOENT; + + return shrunk ? 0 : -EAGAIN; +} + +static void shrink_worker(struct work_struct *w) +{ + struct mem_cgroup *memcg; + int ret, failures = 0, attempts = 0; + unsigned long thr; + + /* Reclaim down to the accept threshold */ + thr = zswap_accept_thr_pages(); + + /* + * Global reclaim will select cgroup in a round-robin fashion from all + * online memcgs, but memcgs that have no pages in zswap and + * writeback-disabled memcgs (memory.zswap.writeback=0) are not + * candidates for shrinking. + * + * Shrinking will be aborted if we encounter the following + * MAX_RECLAIM_RETRIES times: + * - No writeback-candidate memcgs found in a memcg tree walk. + * - Shrinking a writeback-candidate memcg failed. + * + * We save iteration cursor memcg into zswap_next_shrink, + * which can be modified by the offline memcg cleaner + * zswap_memcg_offline_cleanup(). + * + * Since the offline cleaner is called only once, we cannot leave an + * offline memcg reference in zswap_next_shrink. + * We can rely on the cleaner only if we get online memcg under lock. + * + * If we get an offline memcg, we cannot determine if the cleaner has + * already been called or will be called later. We must put back the + * reference before returning from this function. Otherwise, the + * offline memcg left in zswap_next_shrink will hold the reference + * until the next run of shrink_worker(). + */ + do { + /* + * Start shrinking from the next memcg after zswap_next_shrink. + * When the offline cleaner has already advanced the cursor, + * advancing the cursor here overlooks one memcg, but this + * should be negligibly rare. + * + * If we get an online memcg, keep the extra reference in case + * the original one obtained by mem_cgroup_iter() is dropped by + * zswap_memcg_offline_cleanup() while we are shrinking the + * memcg. + */ + spin_lock(&zswap_shrink_lock); + do { + memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL); + zswap_next_shrink = memcg; + } while (memcg && !mem_cgroup_tryget_online(memcg)); + spin_unlock(&zswap_shrink_lock); + + if (!memcg) { + /* + * Continue shrinking without incrementing failures if + * we found candidate memcgs in the last tree walk. + */ + if (!attempts && ++failures == MAX_RECLAIM_RETRIES) + break; + + attempts = 0; + goto resched; + } + + ret = shrink_memcg(memcg); + /* drop the extra reference */ + mem_cgroup_put(memcg); + + /* + * There are no writeback-candidate pages in the memcg. + * This is not an issue as long as we can find another memcg + * with pages in zswap. Skip this without incrementing attempts + * and failures. + */ + if (ret == -ENOENT) + continue; + ++attempts; + + if (ret && ++failures == MAX_RECLAIM_RETRIES) + break; +resched: + cond_resched(); + } while (zswap_total_pages() > thr); +} + +/********************************* +* main API +**********************************/ + +static bool zswap_store_page(struct page *page, + struct obj_cgroup *objcg, + struct zswap_pool *pool) +{ + swp_entry_t page_swpentry = page_swap_entry(page); + struct zswap_entry *entry, *old; + + /* allocate entry */ + entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); + if (!entry) { + zswap_reject_kmemcache_fail++; + return false; } - if (ret) { + + if (!zswap_compress(page, entry, pool)) + goto compress_failed; + + old = xa_store(swap_zswap_tree(page_swpentry), + swp_offset(page_swpentry), + entry, GFP_KERNEL); + if (xa_is_err(old)) { + int err = xa_err(old); + + WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n", err); zswap_reject_alloc_fail++; - goto put_dstmem; + goto store_failed; } - buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_WO); - memcpy(buf, dst, dlen); - zpool_unmap_handle(entry->pool->zpool, handle); - mutex_unlock(acomp_ctx->mutex); - /* populate entry */ - entry->swpentry = swp_entry(type, offset); - entry->handle = handle; - entry->length = dlen; + /* + * We may have had an existing entry that became stale when + * the folio was redirtied and now the new version is being + * swapped out. Get rid of the old. + */ + if (old) + zswap_entry_free(old); -insert_entry: - entry->objcg = objcg; + /* + * The entry is successfully compressed and stored in the tree, there is + * no further possibility of failure. Grab refs to the pool and objcg, + * charge zswap memory, and increment zswap_stored_pages. + * The opposite actions will be performed by zswap_entry_free() + * when the entry is removed from the tree. + */ + zswap_pool_get(pool); if (objcg) { + obj_cgroup_get(objcg); obj_cgroup_charge_zswap(objcg, entry->length); - /* Account before objcg ref is moved to tree */ - count_objcg_event(objcg, ZSWPOUT); } + atomic_long_inc(&zswap_stored_pages); + if (entry->length == PAGE_SIZE) + atomic_long_inc(&zswap_stored_incompressible_pages); - /* 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); + /* + * We finish initializing the entry while it's already in xarray. + * This is safe because: + * + * 1. Concurrent stores and invalidations are excluded by folio lock. + * + * 2. Writeback is excluded by the entry not being on the LRU yet. + * The publishing order matters to prevent writeback from seeing + * an incoherent entry. + */ + entry->pool = pool; + entry->swpentry = page_swpentry; + entry->objcg = objcg; + entry->referenced = true; if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_add(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + INIT_LIST_HEAD(&entry->lru); + zswap_lru_add(&zswap_list_lru, entry); } - spin_unlock(&tree->lock); - - /* update stats */ - atomic_inc(&zswap_stored_pages); - zswap_update_total_size(); - count_vm_event(ZSWPOUT); - return 0; + return true; -put_dstmem: - mutex_unlock(acomp_ctx->mutex); - zswap_pool_put(entry->pool); -freepage: +store_failed: + zs_free(pool->zs_pool, entry->handle); +compress_failed: zswap_entry_cache_free(entry); -reject: - if (objcg) - obj_cgroup_put(objcg); - return ret; - -shrink: - pool = zswap_pool_last_get(); - if (pool) - queue_work(shrink_wq, &pool->shrink_work); - ret = -ENOMEM; - goto reject; + return false; } -/* - * 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, bool *exclusive) +bool zswap_store(struct folio *folio) { - struct zswap_tree *tree = zswap_trees[type]; - struct zswap_entry *entry; - struct scatterlist input, output; - struct crypto_acomp_ctx *acomp_ctx; - u8 *src, *dst, *tmp; - unsigned int dlen; - int ret; + long nr_pages = folio_nr_pages(folio); + swp_entry_t swp = folio->swap; + struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg = NULL; + struct zswap_pool *pool; + bool ret = false; + long index; - /* 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); - ret = 0; - goto stats; + VM_WARN_ON_ONCE(!folio_test_locked(folio)); + VM_WARN_ON_ONCE(!folio_test_swapcache(folio)); + + if (!zswap_enabled) + goto check_old; + + objcg = get_obj_cgroup_from_folio(folio); + if (objcg && !obj_cgroup_may_zswap(objcg)) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (shrink_memcg(memcg)) { + mem_cgroup_put(memcg); + goto put_objcg; + } + mem_cgroup_put(memcg); } - if (!zpool_can_sleep_mapped(entry->pool->zpool)) { - tmp = kmalloc(entry->length, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto freeentry; + if (zswap_check_limits()) + goto put_objcg; + + pool = zswap_pool_current_get(); + if (!pool) + goto put_objcg; + + if (objcg) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) { + mem_cgroup_put(memcg); + goto put_pool; } + mem_cgroup_put(memcg); } - /* decompress */ - dlen = PAGE_SIZE; - src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO); + for (index = 0; index < nr_pages; ++index) { + struct page *page = folio_page(folio, index); - if (!zpool_can_sleep_mapped(entry->pool->zpool)) { - memcpy(tmp, src, entry->length); - src = tmp; - zpool_unmap_handle(entry->pool->zpool, entry->handle); + if (!zswap_store_page(page, objcg, pool)) + goto put_pool; } - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(acomp_ctx->mutex); - sg_init_one(&input, src, entry->length); - sg_init_table(&output, 1); - sg_set_page(&output, page, PAGE_SIZE, 0); - acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen); - ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); - mutex_unlock(acomp_ctx->mutex); + if (objcg) + count_objcg_events(objcg, ZSWPOUT, nr_pages); - if (zpool_can_sleep_mapped(entry->pool->zpool)) - zpool_unmap_handle(entry->pool->zpool, entry->handle); - else - kfree(tmp); + count_vm_events(ZSWPOUT, nr_pages); - BUG_ON(ret); -stats: - count_vm_event(ZSWPIN); - if (entry->objcg) - count_objcg_event(entry->objcg, ZSWPIN); -freeentry: - spin_lock(&tree->lock); - if (!ret && zswap_exclusive_loads_enabled) { - zswap_invalidate_entry(tree, entry); - *exclusive = true; - } else if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_move(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + ret = true; + +put_pool: + zswap_pool_put(pool); +put_objcg: + obj_cgroup_put(objcg); + if (!ret && zswap_pool_reached_full) + queue_work(shrink_wq, &zswap_shrink_work); +check_old: + /* + * If the zswap store fails or zswap is disabled, we must invalidate + * the possibly stale entries which were previously stored at the + * offsets corresponding to each page of the folio. Otherwise, + * writeback could overwrite the new data in the swapfile. + */ + if (!ret) { + unsigned type = swp_type(swp); + pgoff_t offset = swp_offset(swp); + struct zswap_entry *entry; + struct xarray *tree; + + for (index = 0; index < nr_pages; ++index) { + tree = swap_zswap_tree(swp_entry(type, offset + index)); + entry = xa_erase(tree, offset + index); + if (entry) + zswap_entry_free(entry); + } } - zswap_entry_put(tree, entry); - spin_unlock(&tree->lock); return ret; } -/* frees an entry in zswap */ -static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) +/** + * zswap_load() - load a folio from zswap + * @folio: folio to load + * + * Return: 0 on success, with the folio unlocked and marked up-to-date, or one + * of the following error codes: + * + * -EIO: if the swapped out content was in zswap, but could not be loaded + * into the page due to a decompression failure. The folio is unlocked, but + * NOT marked up-to-date, so that an IO error is emitted (e.g. do_swap_page() + * will SIGBUS). + * + * -EINVAL: if the swapped out content was in zswap, but the page belongs + * to a large folio, which is not supported by zswap. The folio is unlocked, + * but NOT marked up-to-date, so that an IO error is emitted (e.g. + * do_swap_page() will SIGBUS). + * + * -ENOENT: if the swapped out content was not in zswap. The folio remains + * locked on return. + */ +int zswap_load(struct folio *folio) { - struct zswap_tree *tree = zswap_trees[type]; + swp_entry_t swp = folio->swap; + pgoff_t offset = swp_offset(swp); + bool swapcache = folio_test_swapcache(folio); + struct xarray *tree = swap_zswap_tree(swp); 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; + VM_WARN_ON_ONCE(!folio_test_locked(folio)); + + if (zswap_never_enabled()) + return -ENOENT; + + /* + * Large folios should not be swapped in while zswap is being used, as + * they are not properly handled. Zswap does not properly load large + * folios, and a large folio may only be partially in zswap. + */ + if (WARN_ON_ONCE(folio_test_large(folio))) { + folio_unlock(folio); + return -EINVAL; + } + + entry = xa_load(tree, offset); + if (!entry) + return -ENOENT; + + if (!zswap_decompress(entry, folio)) { + folio_unlock(folio); + return -EIO; + } + + folio_mark_uptodate(folio); + + count_vm_event(ZSWPIN); + if (entry->objcg) + count_objcg_events(entry->objcg, ZSWPIN, 1); + + /* + * When reading into the swapcache, invalidate our entry. The + * swapcache can be the authoritative owner of the page and + * its mappings, and the pressure that results from having two + * in-memory copies outweighs any benefits of caching the + * compression work. + * + * (Most swapins go through the swapcache. The notable + * exception is the singleton fault on SWP_SYNCHRONOUS_IO + * files, which reads into a private page and may free it if + * the fault fails. We remain the primary owner of the entry.) + */ + if (swapcache) { + folio_mark_dirty(folio); + xa_erase(tree, offset); + zswap_entry_free(entry); } - zswap_invalidate_entry(tree, entry); - spin_unlock(&tree->lock); + + folio_unlock(folio); + return 0; } -/* frees all zswap entries for the given swap type */ -static void zswap_frontswap_invalidate_area(unsigned type) +void zswap_invalidate(swp_entry_t swp) { - struct zswap_tree *tree = zswap_trees[type]; - struct zswap_entry *entry, *n; + pgoff_t offset = swp_offset(swp); + struct xarray *tree = swap_zswap_tree(swp); + struct zswap_entry *entry; - if (!tree) + if (xa_empty(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; + entry = xa_erase(tree, offset); + if (entry) + zswap_entry_free(entry); } -static void zswap_frontswap_init(unsigned type) +int zswap_swapon(int type, unsigned long nr_pages) { - struct zswap_tree *tree; + struct xarray *trees, *tree; + unsigned int nr, i; - tree = kzalloc(sizeof(*tree), GFP_KERNEL); - if (!tree) { + nr = DIV_ROUND_UP(nr_pages, ZSWAP_ADDRESS_SPACE_PAGES); + trees = kvcalloc(nr, sizeof(*tree), GFP_KERNEL); + if (!trees) { pr_err("alloc failed, zswap disabled for swap type %d\n", type); - return; + return -ENOMEM; } - tree->rbroot = RB_ROOT; - spin_lock_init(&tree->lock); - zswap_trees[type] = tree; + for (i = 0; i < nr; i++) + xa_init(trees + i); + + nr_zswap_trees[type] = nr; + zswap_trees[type] = trees; + return 0; } -static const 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 -}; +void zswap_swapoff(int type) +{ + struct xarray *trees = zswap_trees[type]; + unsigned int i; + + if (!trees) + return; + + /* try_to_unuse() invalidated all the entries already */ + for (i = 0; i < nr_zswap_trees[type]; i++) + WARN_ON_ONCE(!xa_empty(trees + i)); + + kvfree(trees); + nr_zswap_trees[type] = 0; + zswap_trees[type] = NULL; +} /********************************* * debugfs functions @@ -1551,6 +1716,28 @@ static const struct frontswap_ops zswap_frontswap_ops = { static struct dentry *zswap_debugfs_root; +static int debugfs_get_total_size(void *data, u64 *val) +{ + *val = zswap_total_pages() * PAGE_SIZE; + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); + +static int debugfs_get_stored_pages(void *data, u64 *val) +{ + *val = atomic_long_read(&zswap_stored_pages); + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(stored_pages_fops, debugfs_get_stored_pages, NULL, "%llu\n"); + +static int debugfs_get_stored_incompressible_pages(void *data, u64 *val) +{ + *val = atomic_long_read(&zswap_stored_incompressible_pages); + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(stored_incompressible_pages_fops, + debugfs_get_stored_incompressible_pages, NULL, "%llu\n"); + static int zswap_debugfs_init(void) { if (!debugfs_initialized()) @@ -1566,18 +1753,21 @@ static int zswap_debugfs_init(void) 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_fail", 0444, + zswap_debugfs_root, &zswap_reject_compress_fail); debugfs_create_u64("reject_compress_poor", 0444, zswap_debugfs_root, &zswap_reject_compress_poor); + debugfs_create_u64("decompress_fail", 0444, + zswap_debugfs_root, &zswap_decompress_fail); 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); + debugfs_create_file("pool_total_size", 0444, + zswap_debugfs_root, NULL, &total_size_fops); + debugfs_create_file("stored_pages", 0444, + zswap_debugfs_root, NULL, &stored_pages_fops); + debugfs_create_file("stored_incompressible_pages", 0444, + zswap_debugfs_root, NULL, + &stored_incompressible_pages_fops); return 0; } @@ -1602,13 +1792,6 @@ static int zswap_setup(void) 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, @@ -1616,37 +1799,43 @@ static int zswap_setup(void) if (ret) goto hp_fail; + shrink_wq = alloc_workqueue("zswap-shrink", + WQ_UNBOUND|WQ_MEM_RECLAIM, 1); + if (!shrink_wq) + goto shrink_wq_fail; + + zswap_shrinker = zswap_alloc_shrinker(); + if (!zswap_shrinker) + goto shrinker_fail; + if (list_lru_init_memcg(&zswap_list_lru, zswap_shrinker)) + goto lru_fail; + shrinker_register(zswap_shrinker); + + INIT_WORK(&zswap_shrink_work, shrink_worker); + pool = __zswap_pool_create_fallback(); if (pool) { - pr_info("loaded using pool %s/%s\n", pool->tfm_name, - zpool_get_type(pool->zpool)); + pr_info("loaded using pool %s\n", pool->tfm_name); list_add(&pool->list, &zswap_pools); zswap_has_pool = true; + static_branch_enable(&zswap_ever_enabled); } else { pr_err("pool creation failed\n"); zswap_enabled = false; } - shrink_wq = create_workqueue("zswap-shrink"); - if (!shrink_wq) - goto fallback_fail; - - ret = frontswap_register_ops(&zswap_frontswap_ops); - if (ret) - goto destroy_wq; if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); zswap_init_state = ZSWAP_INIT_SUCCEED; return 0; -destroy_wq: +lru_fail: + shrinker_free(zswap_shrinker); +shrinker_fail: destroy_workqueue(shrink_wq); -fallback_fail: - if (pool) - zswap_pool_destroy(pool); +shrink_wq_fail: + cpuhp_remove_multi_state(CPUHP_MM_ZSWP_POOL_PREPARE); hp_fail: - cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE); -dstmem_fail: kmem_cache_destroy(zswap_entry_cache); cache_fail: /* if built-in, we aren't unloaded on failure; don't allow use */ |