diff options
Diffstat (limited to 'include/linux/list_lru.h')
| -rw-r--r-- | include/linux/list_lru.h | 163 |
1 files changed, 115 insertions, 48 deletions
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 9dcaa3e582c9..fe739d35a864 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> +#include <linux/xarray.h> struct mem_cgroup; @@ -23,85 +24,149 @@ enum lru_status { LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock internally, but has to return locked. */ + LRU_STOP, /* stop lru list walking. May drop the lock + internally, but has to return locked. */ }; struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; + /* protects all fields above */ + spinlock_t lock; }; struct list_lru_memcg { struct rcu_head rcu; - /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[]; + /* array of per cgroup per node lists, indexed by node id */ + struct list_lru_one node[]; }; struct list_lru_node { - /* protects all lists on the node, including per cgroup */ - spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; -#ifdef CONFIG_MEMCG_KMEM - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *memcg_lrus; -#endif - long nr_items; + atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { struct list_lru_node *node; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; 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_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp); +void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail - * @list_lru: the lru pointer + * @lru: the lru pointer * @item: the item to be added. + * @nid: the node id of the sublist to add the item to. + * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing - * nothing. Therefore the caller does not need to keep state about whether or - * not the element already belongs in the list and is allowed to lazy update - * it. Note however that this is valid for *a* list, not *this* list. If - * the caller organize itself in a way that elements can be in more than - * one type of list, it is up to the caller to fully remove the item from - * the previous list (with list_lru_del() for instance) before moving it - * to @list_lru - * - * Return value: true if the list was updated, false otherwise + * nothing. This means that it is not necessary to keep state about whether or + * not the element already belongs in the list. That said, this logic only + * works if the item is in *this* list. If the item might be in some other + * list, then you cannot rely on this check and you must remove it from the + * other list before trying to insert it. + * + * The lru list consists of many sublists internally; the @nid and @memcg + * parameters are used to determine which sublist to insert the item into. + * It's important to use the right value of @nid and @memcg when deleting the + * item, since it might otherwise get deleted from the wrong sublist. + * + * This also applies when attempting to insert the item multiple times - if + * the item is currently in one sublist and you call list_lru_add() again, you + * must pass the right @nid and @memcg parameters so that the same sublist is + * used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). + * + * Return: true if the list was updated, false otherwise + */ +bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg); + +/** + * list_lru_add_obj: add an element to the lru list's tail + * @lru: the lru pointer + * @item: the item to be added. + * + * This function is similar to list_lru_add(), but the NUMA node and the + * memcg of the sublist is determined by @item list_head. This assumption is + * valid for slab objects LRU such as dentries, inodes, etc. + * + * Return: true if the list was updated, false otherwise + */ +bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); + +/** + * list_lru_del: delete an element from the lru list + * @lru: the lru pointer + * @item: the item to be deleted. + * @nid: the node id of the sublist to delete the item from. + * @memcg: the cgroup of the sublist to delete the item from. + * + * This function works analogously as list_lru_add() in terms of list + * manipulation. + * + * The comments in list_lru_add() about an element already being in a list are + * also valid for list_lru_del(), that is, you can delete an item that has + * already been removed or never been added. However, if the item is in a + * list, it must be in *this* list, and you must pass the right value of @nid + * and @memcg so that the right sublist is used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries + * are automatically moved to the parent memcg. This is done in a race-free + * way, so during deletion of an memcg both the old and new memcg will resolve + * to the same sublist internally. + * + * Return: true if the list was updated, false otherwise */ -bool list_lru_add(struct list_lru *lru, struct list_head *item); +bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg); /** - * list_lru_del: delete an element to the lru list - * @list_lru: the lru pointer + * list_lru_del_obj: delete an element from the lru list + * @lru: the lru pointer * @item: the item to be deleted. * - * This function works analogously as list_lru_add in terms of list - * manipulation. The comments about an element already pertaining to - * a list are also valid for list_lru_del. + * This function is similar to list_lru_del(), but the NUMA node and the + * memcg of the sublist is determined by @item list_head. This assumption is + * valid for slab objects LRU such as dentries, inodes, etc. * - * Return value: true if the list was updated, false otherwise + * Return: true if the list was updated, false otherwise. */ -bool list_lru_del(struct list_lru *lru, struct list_head *item); +bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_count_one: return the number of objects currently held by @lru @@ -109,9 +174,11 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item); * @nid: the node id to count from. * @memcg: the cgroup to count from. * - * Always return a non-negative number, 0 for empty lists. There is no - * guarantee that the list is not updated while the count is being computed. - * Callers that want such a guarantee need to provide an outer lock. + * There is no guarantee that the list is not updated while the count is being + * computed. Callers that want such a guarantee need to provide an outer lock. + * + * Return: 0 for empty lists, otherwise the number of objects + * currently held by @lru. */ unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg); @@ -139,45 +206,45 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, - struct list_lru_one *list, spinlock_t *lock, void *cb_arg); + struct list_lru_one *list, void *cb_arg); /** - * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. - * @isolate: callback function that is resposible for deciding what to do with + * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * - * This function will scan all elements in a particular list_lru, calling the + * This function will scan all elements in a particular @lru, calling the * @isolate callback for each of those items, along with the current list * spinlock and a caller-provided opaque. The @isolate callback can choose to * drop the lock internally, but *must* return with the lock held. The callback - * will return an enum lru_status telling the list_lru infrastructure what to + * will return an enum lru_status telling the @lru infrastructure what to * do with the object being scanned. * - * Please note that nr_to_walk does not mean how many objects will be freed, + * Please note that @nr_to_walk does not mean how many objects will be freed, * just how many objects will be scanned. * - * Return value: the number of objects effectively removed from the LRU. + * Return: the number of objects effectively removed from the LRU. */ 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); /** - * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. - * @isolate: callback function that is resposible for deciding what to do with + * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * - * Same as @list_lru_walk_one except that the spinlock is acquired with + * Same as list_lru_walk_one() except that the spinlock is acquired with * spin_lock_irq(). */ unsigned long list_lru_walk_one_irq(struct list_lru *lru, |