diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/list_lru.c | 374 | ||||
-rw-r--r-- | mm/memcontrol.c | 20 |
2 files changed, 370 insertions, 24 deletions
diff --git a/mm/list_lru.c b/mm/list_lru.c index a9021cb3..79aee70 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -10,6 +10,7 @@ #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> +#include <linux/memcontrol.h> #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(list_lrus); @@ -38,16 +39,71 @@ static void list_lru_unregister(struct list_lru *lru) } #endif /* CONFIG_MEMCG_KMEM */ +#ifdef CONFIG_MEMCG_KMEM +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return !!lru->node[0].memcg_lrus; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + /* + * The lock protects the array of per cgroup lists from relocation + * (see memcg_update_list_lru_node). + */ + lockdep_assert_held(&nlru->lock); + if (nlru->memcg_lrus && idx >= 0) + return nlru->memcg_lrus->lru[idx]; + + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr) +{ + struct mem_cgroup *memcg; + + if (!nlru->memcg_lrus) + return &nlru->lru; + + memcg = mem_cgroup_from_kmem(ptr); + if (!memcg) + return &nlru->lru; + + return list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); +} +#else +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return false; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr) +{ + return &nlru->lru; +} +#endif /* CONFIG_MEMCG_KMEM */ + bool list_lru_add(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; spin_lock(&nlru->lock); - WARN_ON_ONCE(nlru->nr_items < 0); + l = list_lru_from_kmem(nlru, item); + WARN_ON_ONCE(l->nr_items < 0); if (list_empty(item)) { - list_add_tail(item, &nlru->list); - nlru->nr_items++; + list_add_tail(item, &l->list); + l->nr_items++; spin_unlock(&nlru->lock); return true; } @@ -60,12 +116,14 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; spin_lock(&nlru->lock); + l = list_lru_from_kmem(nlru, item); if (!list_empty(item)) { list_del_init(item); - nlru->nr_items--; - WARN_ON_ONCE(nlru->nr_items < 0); + l->nr_items--; + WARN_ON_ONCE(l->nr_items < 0); spin_unlock(&nlru->lock); return true; } @@ -74,33 +132,58 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) } EXPORT_SYMBOL_GPL(list_lru_del); -unsigned long -list_lru_count_node(struct list_lru *lru, int nid) +static unsigned long __list_lru_count_one(struct list_lru *lru, + int nid, int memcg_idx) { - unsigned long count = 0; struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; + unsigned long count; spin_lock(&nlru->lock); - WARN_ON_ONCE(nlru->nr_items < 0); - count += nlru->nr_items; + l = list_lru_from_memcg_idx(nlru, memcg_idx); + WARN_ON_ONCE(l->nr_items < 0); + count = l->nr_items; spin_unlock(&nlru->lock); return count; } + +unsigned long list_lru_count_one(struct list_lru *lru, + int nid, struct mem_cgroup *memcg) +{ + return __list_lru_count_one(lru, nid, memcg_cache_id(memcg)); +} +EXPORT_SYMBOL_GPL(list_lru_count_one); + +unsigned long list_lru_count_node(struct list_lru *lru, int nid) +{ + long count = 0; + int memcg_idx; + + count += __list_lru_count_one(lru, nid, -1); + if (list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) + count += __list_lru_count_one(lru, nid, memcg_idx); + } + return count; +} EXPORT_SYMBOL_GPL(list_lru_count_node); -unsigned long -list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, - void *cb_arg, unsigned long *nr_to_walk) +static unsigned long +__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) { - struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; spin_lock(&nlru->lock); + l = list_lru_from_memcg_idx(nlru, memcg_idx); restart: - list_for_each_safe(item, n, &nlru->list) { + list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* @@ -116,8 +199,8 @@ restart: case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); case LRU_REMOVED: - nlru->nr_items--; - WARN_ON_ONCE(nlru->nr_items < 0); + l->nr_items--; + WARN_ON_ONCE(l->nr_items < 0); isolated++; /* * If the lru lock has been dropped, our list @@ -128,7 +211,7 @@ restart: goto restart; break; case LRU_ROTATE: - list_move_tail(item, &nlru->list); + list_move_tail(item, &l->list); break; case LRU_SKIP: break; @@ -147,36 +230,279 @@ restart: spin_unlock(&nlru->lock); return isolated; } + +unsigned long +list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), + isolate, cb_arg, nr_to_walk); +} +EXPORT_SYMBOL_GPL(list_lru_walk_one); + +unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + long isolated = 0; + int memcg_idx; + + isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg, + nr_to_walk); + if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) { + isolated += __list_lru_walk_one(lru, nid, memcg_idx, + isolate, cb_arg, nr_to_walk); + if (*nr_to_walk <= 0) + break; + } + } + return isolated; +} EXPORT_SYMBOL_GPL(list_lru_walk_node); -int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) +static void init_one_lru(struct list_lru_one *l) +{ + INIT_LIST_HEAD(&l->list); + l->nr_items = 0; +} + +#ifdef CONFIG_MEMCG_KMEM +static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) + kfree(memcg_lrus->lru[i]); +} + +static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) { + struct list_lru_one *l; + + l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL); + if (!l) + goto fail; + + init_one_lru(l); + memcg_lrus->lru[i] = l; + } + return 0; +fail: + __memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1); + return -ENOMEM; +} + +static int memcg_init_list_lru_node(struct list_lru_node *nlru) +{ + int size = memcg_nr_cache_ids; + + nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL); + if (!nlru->memcg_lrus) + return -ENOMEM; + + if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) { + kfree(nlru->memcg_lrus); + return -ENOMEM; + } + + return 0; +} + +static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) +{ + __memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids); + kfree(nlru->memcg_lrus); +} + +static int memcg_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + struct list_lru_memcg *old, *new; + + BUG_ON(old_size > new_size); + + old = nlru->memcg_lrus; + new = kmalloc(new_size * sizeof(void *), GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (__memcg_init_list_lru_node(new, old_size, new_size)) { + kfree(new); + return -ENOMEM; + } + + memcpy(new, old, old_size * sizeof(void *)); + + /* + * The lock guarantees that we won't race with a reader + * (see list_lru_from_memcg_idx). + * + * 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); + nlru->memcg_lrus = new; + spin_unlock_irq(&nlru->lock); + + kfree(old); + return 0; +} + +static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + /* do not bother shrinking the array back to the old size, because we + * cannot handle allocation failures here */ + __memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size); +} + +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + int i; + + for (i = 0; i < nr_node_ids; i++) { + if (!memcg_aware) + lru->node[i].memcg_lrus = NULL; + else if (memcg_init_list_lru_node(&lru->node[i])) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) + memcg_destroy_list_lru_node(&lru->node[i]); + return -ENOMEM; +} + +static void memcg_destroy_list_lru(struct list_lru *lru) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for (i = 0; i < nr_node_ids; i++) + memcg_destroy_list_lru_node(&lru->node[i]); +} + +static int memcg_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return 0; + + for (i = 0; i < nr_node_ids; i++) { + if (memcg_update_list_lru_node(&lru->node[i], + old_size, new_size)) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); + return -ENOMEM; +} + +static void memcg_cancel_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for (i = 0; i < nr_node_ids; i++) + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); +} + +int memcg_update_all_list_lrus(int new_size) +{ + int ret = 0; + struct list_lru *lru; + int old_size = memcg_nr_cache_ids; + + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &list_lrus, list) { + ret = memcg_update_list_lru(lru, old_size, new_size); + if (ret) + goto fail; + } +out: + mutex_unlock(&list_lrus_mutex); + return ret; +fail: + list_for_each_entry_continue_reverse(lru, &list_lrus, list) + memcg_cancel_update_list_lru(lru, old_size, new_size); + goto out; +} +#else +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + return 0; +} + +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) { int i; size_t size = sizeof(*lru->node) * nr_node_ids; + int err = -ENOMEM; + + memcg_get_cache_ids(); lru->node = kzalloc(size, GFP_KERNEL); if (!lru->node) - return -ENOMEM; + goto out; for (i = 0; i < nr_node_ids; i++) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); - INIT_LIST_HEAD(&lru->node[i].list); - lru->node[i].nr_items = 0; + init_one_lru(&lru->node[i].lru); + } + + err = memcg_init_list_lru(lru, memcg_aware); + if (err) { + kfree(lru->node); + goto out; } + list_lru_register(lru); - return 0; +out: + memcg_put_cache_ids(); + return err; } -EXPORT_SYMBOL_GPL(list_lru_init_key); +EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; + + memcg_get_cache_ids(); + list_lru_unregister(lru); + + memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; + + memcg_put_cache_ids(); } EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6706e5f..afa55bb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2572,6 +2572,8 @@ static int memcg_alloc_cache_id(void) err = memcg_update_all_caches(size); if (!err) + err = memcg_update_all_list_lrus(size); + if (!err) memcg_nr_cache_ids = size; up_write(&memcg_cache_ids_sem); @@ -2765,6 +2767,24 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, 1 << order); page->mem_cgroup = NULL; } + +struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr) +{ + struct mem_cgroup *memcg = NULL; + struct kmem_cache *cachep; + struct page *page; + + page = virt_to_head_page(ptr); + if (PageSlab(page)) { + cachep = page->slab_cache; + if (!is_root_cache(cachep)) + memcg = cachep->memcg_params->memcg; + } else + /* page allocated by alloc_kmem_pages */ + memcg = page->mem_cgroup; + + return memcg; +} #endif /* CONFIG_MEMCG_KMEM */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE |