diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 7675a48a07010..204039e54c607 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -54,18 +54,28 @@ struct list_lru { bool memcg_aware; struct xarray xa; #endif +#ifdef CONFIG_LOCKDEP + struct lock_class_key *key; +#endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker); + struct shrinker *shrinker); #define list_lru_init(lru) \ - __list_lru_init((lru), false, NULL, NULL) -#define list_lru_init_key(lru, key) \ - __list_lru_init((lru), false, (key), NULL) + __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ - __list_lru_init((lru), true, NULL, shrinker) + __list_lru_init((lru), true, shrinker) + +static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, + struct lock_class_key *key) +{ +#ifdef CONFIG_LOCKDEP + lru->key = key; +#endif + return list_lru_init_memcg(lru, shrinker); +} int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 351eafb55b672..4996cbfb186f6 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1268,6 +1268,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + return NULL; +} + static inline bool folio_memcg_kmem(struct folio *folio) { return false; diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 2a60ce39cfde1..e571e393669bb 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -15,6 +15,7 @@ bool zswap_load(struct folio *folio); void zswap_invalidate(int type, pgoff_t offset); void zswap_swapon(int type); void zswap_swapoff(int type); +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); #else @@ -31,6 +32,7 @@ static inline bool zswap_load(struct folio *folio) static inline void zswap_invalidate(int type, pgoff_t offset) {} static inline void zswap_swapon(int type) {} static inline void zswap_swapoff(int type) {} +static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} #endif diff --git a/mm/list_lru.c b/mm/list_lru.c index 80c0a43eae7fc..cfbbf6bff6cf9 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -59,6 +59,20 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) } return &lru->node[nid].lru; } + +static inline struct list_lru_one * +list_lru_from_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg) +{ + struct list_lru_one *l; +again: + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); + if (likely(l)) + return l; + + memcg = parent_mem_cgroup(memcg); + VM_WARN_ON(!css_is_dying(&memcg->css)); + goto again; +} #else static void list_lru_register(struct list_lru *lru) { @@ -83,6 +97,12 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } + +static inline struct list_lru_one * +list_lru_from_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg) +{ + return &lru->node[nid].lru; +} #endif /* CONFIG_MEMCG_KMEM */ /* The caller must ensure the memcg lifetime. */ @@ -94,7 +114,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, spin_lock(&nlru->lock); if (list_empty(item)) { - l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); + l = list_lru_from_memcg(lru, nid, memcg); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) @@ -106,7 +126,6 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, spin_unlock(&nlru->lock); return false; } -EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { @@ -134,7 +153,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, spin_lock(&nlru->lock); if (!list_empty(item)) { - l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); + l = list_lru_from_memcg(lru, nid, memcg); list_del_init(item); l->nr_items--; nlru->nr_items--; @@ -367,20 +386,6 @@ static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp) return mlru; } -static void memcg_list_lru_free(struct list_lru *lru, int src_idx) -{ - struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx); - - /* - * The __list_lru_walk_one() can walk the list of this node. - * We need kvfree_rcu() here. And the walking of the list - * is under lru->node[nid]->lock, which can serve as a RCU - * read-side critical section. - */ - if (mlru) - kvfree_rcu(mlru, rcu); -} - static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) @@ -405,22 +410,18 @@ static void memcg_destroy_list_lru(struct list_lru *lru) } static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, - int src_idx, struct mem_cgroup *dst_memcg) + struct list_lru_one *src, + struct mem_cgroup *dst_memcg) { struct list_lru_node *nlru = &lru->node[nid]; - int dst_idx = dst_memcg->kmemcg_id; - struct list_lru_one *src, *dst; + struct list_lru_one *dst; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); - - src = list_lru_from_memcg_idx(lru, nid, src_idx); - if (!src) - goto out; - dst = list_lru_from_memcg_idx(lru, nid, dst_idx); + dst = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(dst_memcg)); list_splice_init(&src->list, &dst->list); @@ -429,52 +430,44 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } -out: spin_unlock_irq(&nlru->lock); } -static void memcg_reparent_list_lru(struct list_lru *lru, - int src_idx, struct mem_cgroup *dst_memcg) +void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { + struct list_lru *lru; int i; - for_each_node(i) - memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg); - - memcg_list_lru_free(lru, src_idx); -} + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &memcg_list_lrus, list) { + struct list_lru_memcg *mlru; + XA_STATE(xas, &lru->xa, memcg->kmemcg_id); -void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) -{ - struct cgroup_subsys_state *css; - struct list_lru *lru; - int src_idx = memcg->kmemcg_id; + /* + * Lock the Xarray to ensure no on going list_lru_memcg + * allocation and further allocation will see css_is_dying(). + */ + xas_lock_irq(&xas); + mlru = xas_store(&xas, NULL); + xas_unlock_irq(&xas); + if (!mlru) + continue; - /* - * Change kmemcg_id of this cgroup and all its descendants to the - * parent's id, and then move all entries from this cgroup's list_lrus - * to ones of the parent. - * - * After we have finished, all list_lrus corresponding to this cgroup - * are guaranteed to remain empty. So we can safely free this cgroup's - * list lrus in memcg_list_lru_free(). - * - * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc() - * from allocating list lrus for this cgroup after memcg_list_lru_free() - * call. - */ - rcu_read_lock(); - css_for_each_descendant_pre(css, &memcg->css) { - struct mem_cgroup *child; + /* + * With Xarray value set to NULL, holding the lru lock below + * prevents list_lru_{add,del,isolate} from touching the lru, + * safe to reparent. + */ + for_each_node(i) + memcg_reparent_list_lru_node(lru, i, &mlru->node[i], parent); - child = mem_cgroup_from_css(css); - WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id); + /* + * Here all list_lrus corresponding to the cgroup are guaranteed + * to remain empty, we can safely free this lru, any further + * memcg_list_lru_alloc() call will simply bail out. + */ + kvfree_rcu(mlru, rcu); } - rcu_read_unlock(); - - mutex_lock(&list_lrus_mutex); - list_for_each_entry(lru, &memcg_list_lrus, list) - memcg_reparent_list_lru(lru, src_idx, parent); mutex_unlock(&list_lrus_mutex); } @@ -489,77 +482,48 @@ static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { - int i; unsigned long flags; - struct list_lru_memcg_table { - struct list_lru_memcg *mlru; - struct mem_cgroup *memcg; - } *table; + struct list_lru_memcg *mlru; + struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; - table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp); - if (!table) - return -ENOMEM; - /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ - for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) { - if (memcg_list_lru_allocated(memcg, lru)) - break; - - table[i].memcg = memcg; - table[i].mlru = memcg_init_list_lru_one(gfp); - if (!table[i].mlru) { - while (i--) - kfree(table[i].mlru); - kfree(table); - return -ENOMEM; + do { + /* + * Keep finding the farest parent that wasn't populated + * until found memcg itself. + */ + pos = memcg; + parent = parent_mem_cgroup(pos); + while (!memcg_list_lru_allocated(parent, lru)) { + pos = parent; + parent = parent_mem_cgroup(pos); } - } - xas_lock_irqsave(&xas, flags); - while (i--) { - int index = READ_ONCE(table[i].memcg->kmemcg_id); - struct list_lru_memcg *mlru = table[i].mlru; - - xas_set(&xas, index); -retry: - if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) { - kfree(mlru); - } else { - xas_store(&xas, mlru); - if (xas_error(&xas) == -ENOMEM) { - xas_unlock_irqrestore(&xas, flags); - if (xas_nomem(&xas, gfp)) - xas_set_err(&xas, 0); - xas_lock_irqsave(&xas, flags); - /* - * The xas lock has been released, this memcg - * can be reparented before us. So reload - * memcg id. More details see the comments - * in memcg_reparent_list_lrus(). - */ - index = READ_ONCE(table[i].memcg->kmemcg_id); - if (index < 0) - xas_set_err(&xas, 0); - else if (!xas_error(&xas) && index != xas.xa_index) - xas_set(&xas, index); - goto retry; + mlru = memcg_init_list_lru_one(gfp); + if (!mlru) + return -ENOMEM; + xas_set(&xas, pos->kmemcg_id); + do { + xas_lock_irqsave(&xas, flags); + if (!xas_load(&xas) && !css_is_dying(&pos->css)) { + xas_store(&xas, mlru); + if (!xas_error(&xas)) + mlru = NULL; } - } - } - /* xas_nomem() is used to free memory instead of memory allocation. */ - if (xas.xa_alloc) - xas_nomem(&xas, gfp); - xas_unlock_irqrestore(&xas, flags); - kfree(table); + xas_unlock_irqrestore(&xas, flags); + } while (xas_nomem(&xas, gfp)); + if (mlru) + kfree(mlru); + } while (pos != memcg && !css_is_dying(&pos->css)); return xas_error(&xas); } @@ -573,8 +537,7 @@ static void memcg_destroy_list_lru(struct list_lru *lru) } #endif /* CONFIG_MEMCG_KMEM */ -int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker) +int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; @@ -591,8 +554,10 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, for_each_node(i) { spin_lock_init(&lru->node[i].lock); - if (key) - lockdep_set_class(&lru->node[i].lock, key); +#ifdef CONFIG_LOCKDEP + if (lru->key) + lockdep_set_class(&lru->node[i].lock, lru->key); +#endif init_one_lru(&lru->node[i].lru); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b59a78a578a83..49ee72c17c228 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -64,6 +64,7 @@ #include #include #include +#include #include "internal.h" #include #include @@ -3944,13 +3945,6 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) parent = root_mem_cgroup; memcg_reparent_objcgs(memcg, parent); - - /* - * After we have finished memcg_reparent_objcgs(), all list_lrus - * corresponding to this cgroup are guaranteed to remain empty. - * The ordering is imposed by list_lru_node->lock taken by - * memcg_reparent_list_lrus(). - */ memcg_reparent_list_lrus(memcg, parent); } #else @@ -5658,6 +5652,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); + zswap_memcg_offline_cleanup(memcg); + memcg_offline_kmem(memcg); reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); diff --git a/mm/swap.h b/mm/swap.h index 3501fdf5f1a6e..3a9eb19e83d1b 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -52,7 +52,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct swap_iocb **plug); struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated); + bool *new_page_allocated, + bool skip_if_exists); struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct mempolicy *mpol, pgoff_t ilx); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, diff --git a/mm/swap_state.c b/mm/swap_state.c index eb1508a1c793a..59916faf938ef 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -423,7 +423,8 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping, struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated) + bool *new_page_allocated, + bool skip_if_exists) { struct swap_info_struct *si; struct folio *folio; @@ -481,6 +482,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, if (err != -EEXIST) goto fail_put_swap; + /* + * Protect against a recursive call to __read_swap_cache_async() + * on the same entry waiting forever here because SWAP_HAS_CACHE + * is set but the folio is not the swap cache yet. This can + * happen today if mem_cgroup_swapin_charge_folio() below + * triggers reclaim through zswap, which may call + * __read_swap_cache_async() in the writeback path. + */ + if (skip_if_exists) + goto fail_put_swap; + /* * We might race against __delete_from_swap_cache(), and * stumble across a swap_map entry whose SWAP_HAS_CACHE @@ -548,7 +560,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, mpol = get_vma_policy(vma, addr, 0, &ilx); page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); mpol_cond_put(mpol); if (page_allocated) @@ -665,7 +677,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( swp_entry(swp_type(entry), offset), - gfp_mask, mpol, ilx, &page_allocated); + gfp_mask, mpol, ilx, &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -683,7 +695,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); return page; @@ -838,7 +850,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, pte_unmap(pte); pte = NULL; page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -858,7 +870,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); return page; diff --git a/mm/workingset.c b/mm/workingset.c index e879a13fec317..d021a9fd1bcdb 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -787,13 +787,6 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, NULL); } -static struct shrinker workingset_shadow_shrinker = { - .count_objects = count_shadow_nodes, - .scan_objects = scan_shadow_nodes, - .seeks = 0, /* ->count reports only fully expendable nodes */ - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, -}; - /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. @@ -802,9 +795,10 @@ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { + struct shrinker *workingset_shadow_shrinker; unsigned int timestamp_bits; unsigned int max_order; - int ret; + int ret = -ENOMEM; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* @@ -821,17 +815,26 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); - if (ret) + workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE, + "mm-shadow"); + if (!workingset_shadow_shrinker) goto err; - ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, - &workingset_shadow_shrinker); + + ret = list_lru_init_memcg_key(&shadow_nodes, workingset_shadow_shrinker, + &shadow_nodes_key); if (ret) goto err_list_lru; - register_shrinker_prepared(&workingset_shadow_shrinker); + + workingset_shadow_shrinker->count_objects = count_shadow_nodes; + workingset_shadow_shrinker->scan_objects = scan_shadow_nodes; + /* ->count reports only fully expendable nodes */ + workingset_shadow_shrinker->seeks = 0; + + shrinker_register(workingset_shadow_shrinker); return 0; err_list_lru: - free_prealloced_shrinker(&workingset_shadow_shrinker); + shrinker_free(workingset_shadow_shrinker); err: return ret; } diff --git a/mm/zswap.c b/mm/zswap.c index b75fa42bf468d..a3461f69e4b34 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -35,6 +35,7 @@ #include #include #include +#include #include "swap.h" #include "internal.h" @@ -172,8 +173,8 @@ struct zswap_pool { struct work_struct shrink_work; struct hlist_node node; char tfm_name[CRYPTO_MAX_ALG_NAME]; - struct list_head lru; - spinlock_t lru_lock; + struct list_lru list_lru; + struct mem_cgroup *next_shrink; }; /* @@ -289,15 +290,46 @@ static void zswap_update_total_size(void) zswap_pool_total_size = total; } +/* 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)); +} + +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + + /* lock out zswap pools list modification */ + spin_lock(&zswap_pools_lock); + list_for_each_entry(pool, &zswap_pools, list) { + if (pool->next_shrink == memcg) + pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL); + } + spin_unlock(&zswap_pools_lock); +} + /********************************* * zswap entry functions **********************************/ static struct kmem_cache *zswap_entry_cache; -static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) { struct zswap_entry *entry; - entry = kmem_cache_alloc(zswap_entry_cache, gfp); + entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; entry->refcount = 1; @@ -310,6 +342,60 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) kmem_cache_free(zswap_entry_cache, entry); } +/********************************* +* lru functions +**********************************/ +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_memcg is erased. The + * new entry will be reparented to memcg's parent's list_lru. + * 2. list_lru_add() is called after list_lru_memcg is erased. The + * new entry will be added directly to memcg's parent's list_lru. + * + * Similar reasoning holds for list_lru_del() and list_lru_putback(). + */ + 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(); +} + +static void zswap_lru_putback(struct list_lru *list_lru, + struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + spinlock_t *lock = &list_lru->node[nid].lock; + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + spin_lock(lock); + /* we cannot use list_lru_add here, because it increments node's lru count */ + list_lru_putback(list_lru, &entry->lru, nid, memcg); + spin_unlock(lock); + rcu_read_unlock(); +} + /********************************* * rbtree functions **********************************/ @@ -387,19 +473,17 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry) */ 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); + zswap_lru_del(&entry->pool->list_lru, entry); zpool_free(zswap_find_zpool(entry), entry->handle); zswap_pool_put(entry->pool); } + if (entry->objcg) { + obj_cgroup_uncharge_zswap(entry->objcg, entry->length); + obj_cgroup_put(entry->objcg); + } zswap_entry_cache_free(entry); atomic_dec(&zswap_stored_pages); zswap_update_total_size(); @@ -630,21 +714,15 @@ static void zswap_invalidate_entry(struct zswap_tree *tree, zswap_entry_put(tree, entry); } -static int zswap_reclaim_entry(struct zswap_pool *pool) +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + spinlock_t *lock, void *arg) { - struct zswap_entry *entry; + struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); struct zswap_tree *tree; pgoff_t swpoffset; - int ret; + enum lru_status ret = LRU_REMOVED_RETRY; + int writeback_result; - /* 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 @@ -652,28 +730,32 @@ static int zswap_reclaim_entry(struct zswap_pool *pool) */ swpoffset = swp_offset(entry->swpentry); tree = zswap_trees[swp_type(entry->swpentry)]; - spin_unlock(&pool->lru_lock); + list_lru_isolate(l, item); + /* + * It's safe to drop the lock here because we return either + * LRU_REMOVED_RETRY or LRU_RETRY. + */ + spin_unlock(lock); /* Check for invalidate() race */ spin_lock(&tree->lock); - if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) { - ret = -EAGAIN; + if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) 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); + writeback_result = 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); + if (writeback_result) { + zswap_reject_reclaim_fail++; + zswap_lru_putback(&entry->pool->list_lru, entry); + ret = LRU_RETRY; goto put_unlock; } + zswap_written_back_pages++; if (entry->objcg) count_objcg_event(entry->objcg, ZSWPWB); @@ -691,24 +773,91 @@ static int zswap_reclaim_entry(struct zswap_pool *pool) zswap_entry_put(tree, entry); unlock: spin_unlock(&tree->lock); - return ret ? -EAGAIN : 0; + spin_lock(lock); + return ret; +} + +static int shrink_memcg(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + int nid, shrunk = 0; + + /* + * 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; + + pool = zswap_pool_current_get(); + if (!pool) + return -EINVAL; + + for_each_node_state(nid, N_NORMAL_MEMORY) { + unsigned long nr_to_walk = 1; + + shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg, + &shrink_memcg_cb, NULL, &nr_to_walk); + } + zswap_pool_put(pool); + return shrunk ? 0 : -EAGAIN; } static void shrink_worker(struct work_struct *w) { struct zswap_pool *pool = container_of(w, typeof(*pool), shrink_work); + struct mem_cgroup *memcg; int ret, failures = 0; + /* global reclaim will select cgroup in a round-robin fashion. */ do { - ret = zswap_reclaim_entry(pool); - if (ret) { - zswap_reject_reclaim_fail++; - if (ret != -EAGAIN) + spin_lock(&zswap_pools_lock); + pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL); + memcg = pool->next_shrink; + + /* + * We need to retry if we have gone through a full round trip, or if we + * got an offline memcg (or else we risk undoing the effect of the + * zswap memcg offlining cleanup callback). This is not catastrophic + * per se, but it will keep the now offlined memcg hostage for a while. + * + * Note that if we got an online memcg, we will keep the extra + * reference in case the original reference obtained by mem_cgroup_iter + * is dropped by the zswap memcg offlining callback, ensuring that the + * memcg is not killed when we are reclaiming. + */ + if (!memcg) { + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; + } + + if (!mem_cgroup_tryget_online(memcg)) { + /* drop the reference from mem_cgroup_iter() */ + mem_cgroup_iter_break(NULL, memcg); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; } + spin_unlock(&zswap_pools_lock); + + ret = shrink_memcg(memcg); + /* drop the extra reference */ + mem_cgroup_put(memcg); + + if (ret == -EINVAL) + break; + if (ret && ++failures == MAX_RECLAIM_RETRIES) + break; + +resched: cond_resched(); } while (!zswap_can_accept()); zswap_pool_put(pool); @@ -769,8 +918,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) */ kref_init(&pool->kref); INIT_LIST_HEAD(&pool->list); - INIT_LIST_HEAD(&pool->lru); - spin_lock_init(&pool->lru_lock); + list_lru_init_memcg(&pool->list_lru, NULL); INIT_WORK(&pool->shrink_work, shrink_worker); zswap_pool_debug("created", pool); @@ -836,6 +984,13 @@ static void zswap_pool_destroy(struct zswap_pool *pool) cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); free_percpu(pool->acomp_ctx); + list_lru_destroy(&pool->list_lru); + + spin_lock(&zswap_pools_lock); + mem_cgroup_iter_break(NULL, pool->next_shrink); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) zpool_destroy_pool(pool->zpools[i]); kfree(pool); @@ -1083,7 +1238,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* try to allocate swap cache page */ mpol = get_task_policy(current); page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, - NO_INTERLEAVE_INDEX, &page_was_allocated); + NO_INTERLEAVE_INDEX, &page_was_allocated, true); if (!page) { ret = -ENOMEM; goto fail; @@ -1151,7 +1306,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* start writeback */ __swap_writepage(page, &wbc); put_page(page); - zswap_written_back_pages++; return ret; @@ -1208,6 +1362,7 @@ bool zswap_store(struct folio *folio) struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; struct zpool *zpool; unsigned int dlen = PAGE_SIZE; @@ -1243,14 +1398,15 @@ bool zswap_store(struct folio *folio) if (!zswap_enabled) return false; - /* - * 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. - */ objcg = get_obj_cgroup_from_folio(folio); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto reject; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (shrink_memcg(memcg)) { + mem_cgroup_put(memcg); + goto reject; + } + mem_cgroup_put(memcg); + } /* reclaim space if needed */ if (zswap_is_full()) { @@ -1267,7 +1423,7 @@ bool zswap_store(struct folio *folio) } /* allocate entry */ - entry = zswap_entry_cache_alloc(GFP_KERNEL); + entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; goto reject; @@ -1294,6 +1450,15 @@ bool zswap_store(struct folio *folio) if (!entry->pool) goto freepage; + if (objcg) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) { + mem_cgroup_put(memcg); + goto put_pool; + } + mem_cgroup_put(memcg); + } + /* compress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); @@ -1370,9 +1535,8 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } 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(&entry->pool->list_lru, entry); } spin_unlock(&tree->lock); @@ -1385,6 +1549,7 @@ bool zswap_store(struct folio *folio) put_dstmem: mutex_unlock(acomp_ctx->mutex); +put_pool: zswap_pool_put(entry->pool); freepage: zswap_entry_cache_free(entry); @@ -1479,9 +1644,8 @@ bool zswap_load(struct folio *folio) zswap_invalidate_entry(tree, entry); folio_mark_dirty(folio); } else if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_move(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + zswap_lru_del(&entry->pool->list_lru, entry); + zswap_lru_add(&entry->pool->list_lru, entry); } zswap_entry_put(tree, entry); spin_unlock(&tree->lock);