diff options
Diffstat (limited to 'include/linux/memcontrol.h')
| -rw-r--r-- | include/linux/memcontrol.h | 239 |
1 files changed, 152 insertions, 87 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 04f2f33607e9..744cde2b2368 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -321,10 +321,10 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; +#endif struct obj_cgroup __rcu *objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; -#endif MEMCG_PADDING(_pad2_); @@ -353,6 +353,26 @@ struct mem_cgroup { struct mem_cgroup_per_node *nodeinfo[]; }; +struct memcg_reparent_ops { + /* + * Note that interrupt is disabled before calling those callbacks, + * so the interrupt should remain disabled when leaving those callbacks. + */ + void (*lock)(struct mem_cgroup *src, struct mem_cgroup *dst); + void (*relocate)(struct mem_cgroup *src, struct mem_cgroup *dst); + void (*unlock)(struct mem_cgroup *src, struct mem_cgroup *dst); +}; + +#define DEFINE_MEMCG_REPARENT_OPS(name) \ + const struct memcg_reparent_ops memcg_##name##_reparent_ops = { \ + .lock = name##_reparent_lock, \ + .relocate = name##_reparent_relocate, \ + .unlock = name##_reparent_unlock, \ + } + +#define DECLARE_MEMCG_REPARENT_OPS(name) \ + extern const struct memcg_reparent_ops memcg_##name##_reparent_ops + /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. @@ -372,14 +392,12 @@ enum page_memcg_data_flags { #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) -static inline bool folio_memcg_kmem(struct folio *folio); - /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released: - * e.g. acquire the rcu_read_lock or css_set_lock. + * e.g. acquire the rcu_read_lock or objcg_lock or cgroup_mutex. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { @@ -387,43 +405,19 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) } /* - * __folio_memcg - Get the memory cgroup associated with a non-kmem folio - * @folio: Pointer to the folio. - * - * Returns a pointer to the memory cgroup associated with the folio, - * or NULL. This function assumes that the folio is known to have a - * proper memory cgroup pointer. It's not safe to call this function - * against some type of folios, e.g. slab folios or ex-slab folios or - * kmem folios. - */ -static inline struct mem_cgroup *__folio_memcg(struct folio *folio) -{ - unsigned long memcg_data = folio->memcg_data; - - VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); - - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); -} - -/* - * __folio_objcg - get the object cgroup associated with a kmem folio. + * folio_objcg - get the object cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the object cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a - * proper object cgroup pointer. It's not safe to call this function - * against some type of folios, e.g. slab folios or ex-slab folios or - * LRU folios. + * proper object cgroup pointer. */ -static inline struct obj_cgroup *__folio_objcg(struct folio *folio) +static inline struct obj_cgroup *folio_objcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); - VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } @@ -437,30 +431,79 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * - * For a non-kmem folio any of the following ensures folio and memcg binding - * stability: + * For a folio any of the following ensures folio and objcg binding stability: * * - the folio lock * - LRU isolation * - lock_page_memcg() * - exclusive reference * - * For a kmem folio a caller should hold an rcu read lock to protect memcg - * associated with a kmem folio from being released. + * Based on the stable binding of folio and objcg, for a folio any of the + * following ensures folio and memcg binding stability: + * + * - objcg_lock + * - cgroup_mutex + * - the lruvec lock + * - the split queue lock (only THP page) + * + * If the caller only want to ensure that the page counters of memcg are + * updated correctly, ensure that the binding stability of folio and objcg + * is sufficient. + * + * Note: The caller should hold an rcu read lock to protect memcg associated + * with a folio from being released. */ static inline struct mem_cgroup *folio_memcg(struct folio *folio) { - if (folio_memcg_kmem(folio)) - return obj_cgroup_memcg(__folio_objcg(folio)); - return __folio_memcg(folio); + struct obj_cgroup *objcg = folio_objcg(folio); + + return objcg ? obj_cgroup_memcg(objcg) : NULL; } +/* + * page_memcg - Get the memory cgroup associated with a page. + * @page: Pointer to the page. + * + * See the cooments in folio_memcg(). + */ static inline struct mem_cgroup *page_memcg(struct page *page) { return folio_memcg(page_folio(page)); } -/** +/* + * get_mem_cgroup_from_folio - Obtain a reference on the memory cgroup + * associated with a folio. + * @folio: Pointer to the folio. + * + * Returns a pointer to the memory cgroup (and obtain a reference on it) + * associated with the folio, or NULL. This function assumes that the + * folio is known to have a proper memory cgroup pointer. It's not safe + * to call this function against some type of pages, e.g. slab pages or + * ex-slab pages. + * + * The page and objcg or memcg binding rules can refer to folio_memcg(). + */ +static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = folio_memcg(folio); + if (unlikely(memcg && !css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + +static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +{ + return get_mem_cgroup_from_folio(page_folio(page)); +} + +/* * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * @@ -470,22 +513,20 @@ static inline struct mem_cgroup *page_memcg(struct page *page) * * Return: A pointer to the memory cgroup associated with the folio, * or NULL. + * + * The folio and objcg or memcg binding rules can refer to folio_memcg(). */ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { unsigned long memcg_data = READ_ONCE(folio->memcg_data); + struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); WARN_ON_ONCE(!rcu_read_lock_held()); - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; + objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } - - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return objcg ? obj_cgroup_memcg(objcg) : NULL; } /* @@ -498,16 +539,10 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * - * For a non-kmem page any of the following ensures page and memcg binding - * stability: + * The page and objcg or memcg binding rules can refer to page_memcg(). * - * - the page lock - * - LRU isolation - * - lock_page_memcg() - * - exclusive reference - * - * For a kmem page a caller should hold an rcu read lock to protect memcg - * associated with a kmem page from being released. + * A caller should hold an rcu read lock to protect memcg associated with a + * page from being released. */ static inline struct mem_cgroup *page_memcg_check(struct page *page) { @@ -516,18 +551,14 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) * for slab pages, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(page->memcg_data); + struct obj_cgroup *objcg; if (memcg_data & MEMCG_DATA_OBJCGS) return NULL; - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; - - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } + objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return objcg ? obj_cgroup_memcg(objcg) : NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) @@ -758,7 +789,9 @@ out: * folio_lruvec - return lruvec for isolating/putting an LRU folio * @folio: Pointer to the folio. * - * This function relies on folio->mem_cgroup being stable. + * The lruvec can be changed to its parent lruvec when the page reparented. + * The caller need to recheck if it cares about this changes (just like + * folio_lruvec_lock() does). */ static inline struct lruvec *folio_lruvec(struct folio *folio) { @@ -777,15 +810,6 @@ struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); -#ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); -#else -static inline -void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) -{ -} -#endif - static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; @@ -837,6 +861,15 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return memcg ? cgroup_ino(memcg->css.cgroup) : 0; +} + +struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); @@ -857,8 +890,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * - * Returns the parent memcg, or NULL if this is the root or the memory - * controller is in legacy no-hierarchy mode. + * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { @@ -887,7 +919,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); +struct cgroup_subsys_state *get_mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) @@ -1057,19 +1089,25 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg; + rcu_read_lock(); + memcg = page_memcg(page); if (memcg) count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { - struct mem_cgroup *memcg = folio_memcg(folio); + struct mem_cgroup *memcg; + rcu_read_lock(); + memcg = folio_memcg(folio); if (memcg) count_memcg_events(memcg, idx, nr); + rcu_read_unlock(); } static inline void count_memcg_event_mm(struct mm_struct *mm, @@ -1148,6 +1186,16 @@ static inline struct mem_cgroup *page_memcg(struct page *page) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) +{ + return NULL; +} + +static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +{ + return NULL; +} + static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); @@ -1252,11 +1300,6 @@ static inline struct lruvec *folio_lruvec(struct folio *folio) return &pgdat->__lruvec; } -static inline -void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) -{ -} - static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; @@ -1343,6 +1386,18 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return 0; +} + +static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) +{ + return NULL; +} +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; @@ -1559,17 +1614,17 @@ static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } -static inline void unlock_page_lruvec(struct lruvec *lruvec) +static inline void lruvec_unlock(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); } -static inline void unlock_page_lruvec_irq(struct lruvec *lruvec) +static inline void lruvec_unlock_irq(struct lruvec *lruvec) { spin_unlock_irq(&lruvec->lru_lock); } -static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, +static inline void lruvec_unlock_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); @@ -1591,7 +1646,7 @@ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; - unlock_page_lruvec_irq(locked_lruvec); + lruvec_unlock_irq(locked_lruvec); } return folio_lruvec_lock_irq(folio); @@ -1605,7 +1660,7 @@ static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio, if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; - unlock_page_lruvec_irqrestore(locked_lruvec, *flags); + lruvec_unlock_irqrestore(locked_lruvec, *flags); } return folio_lruvec_lock_irqsave(folio, flags); @@ -1683,6 +1738,11 @@ int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); + +static inline int shrinker_id(struct shrinker *shrinker) +{ + return shrinker->id; +} #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1696,6 +1756,11 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } + +static inline int shrinker_id(struct shrinker *shrinker) +{ + return -1; +} #endif #ifdef CONFIG_MEMCG_KMEM |