diff options
Diffstat (limited to 'include/linux/memcontrol.h')
| -rw-r--r-- | include/linux/memcontrol.h | 544 |
1 files changed, 303 insertions, 241 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6e74b8254d9b..dc3fa687759b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,10 +35,10 @@ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, - MEMCG_VMALLOC, MEMCG_KMEM, MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, + MEMCG_ZSWAP_INCOMP, MEMCG_NR_STAT, }; @@ -52,6 +52,7 @@ enum memcg_memory_event { MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, + MEMCG_SOCK_THROTTLED, MEMCG_NR_MEMORY_EVENTS, }; @@ -64,7 +65,7 @@ struct mem_cgroup_reclaim_cookie { #define MEM_CGROUP_ID_SHIFT 16 -struct mem_cgroup_id { +struct mem_cgroup_private_id { int id; refcount_t ref; }; @@ -113,6 +114,22 @@ struct mem_cgroup_per_node { CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; + + /* + * objcg is wiped out as a part of the objcg repaprenting process. + * orig_objcg preserves a pointer (and a reference) to the original + * objcg until the end of live of memcg. + */ + struct obj_cgroup __rcu *objcg; + struct obj_cgroup *orig_objcg; + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; + +#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC + /* slab stats for nmi context */ + atomic_t slab_reclaimable; + atomic_t slab_unreclaimable; +#endif }; struct mem_cgroup_threshold { @@ -172,6 +189,7 @@ struct obj_cgroup { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; + bool is_root; }; /* @@ -184,7 +202,7 @@ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ - struct mem_cgroup_id id; + struct mem_cgroup_private_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ @@ -236,23 +254,20 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; +#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC + /* MEMCG_KMEM for nmi context */ + atomic_t kmem_stat; +#endif /* * Hint of reclaim pressure for socket memroy management. Note * that this indicator should NOT be used in legacy cgroup mode * where socket memory is accounted/charged separately. */ - unsigned long socket_pressure; - + u64 socket_pressure; +#if BITS_PER_LONG < 64 + seqlock_t socket_pressure_seqlock; +#endif int kmemcg_id; - /* - * memcg->objcg is wiped out as a part of the objcg repaprenting - * process. memcg->orig_objcg preserves a pointer (and a reference) - * to the original objcg until the end of live of memcg. - */ - struct obj_cgroup __rcu *objcg; - struct obj_cgroup *orig_objcg; - /* list of inherited objcgs, protected by objcg_lock */ - struct list_head objcg_list; struct memcg_vmstats_percpu __percpu *vmstats_percpu; @@ -329,17 +344,24 @@ enum page_memcg_data_flags { __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; +#define __OBJEXTS_ALLOC_FAIL MEMCG_DATA_OBJEXTS #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ +#define __OBJEXTS_ALLOC_FAIL (1UL << 0) #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { - /* slabobj_ext vector failed to allocate */ - OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, + /* + * Use bit 0 with zero other bits to signal that slabobj_ext vector + * failed to allocate. The same bit 0 with valid upper bits means + * MEMCG_DATA_OBJEXTS. + */ + OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, + __OBJEXTS_FLAG_UNUSED = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; @@ -347,9 +369,6 @@ enum objext_flags { #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) #ifdef CONFIG_MEMCG - -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. @@ -363,43 +382,19 @@ 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_OBJEXTS, folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); - - return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_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_OBJEXTS, folio); - VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } @@ -413,21 +408,30 @@ 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 * - 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: + * + * - cgroup_mutex + * - the lruvec lock + * + * 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 or cgroup_mutex 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; } /* @@ -438,9 +442,7 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) */ static inline bool folio_memcg_charged(struct folio *folio) { - if (folio_memcg_kmem(folio)) - return __folio_objcg(folio) != NULL; - return __folio_memcg(folio) != NULL; + return folio->memcg_data != 0; } /* @@ -453,15 +455,10 @@ static inline bool folio_memcg_charged(struct folio *folio) * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * - * For a non-kmem folio any of the following ensures folio and memcg binding - * stability: - * - * - the folio lock - * - LRU isolation - * - exclusive reference + * The page and objcg or memcg binding rules can refer to folio_memcg(). * - * For a kmem folio a caller should hold an rcu read lock to protect memcg - * associated with a kmem folio 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 *folio_memcg_check(struct folio *folio) { @@ -470,18 +467,14 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) * for slabs, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); + struct obj_cgroup *objcg; if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; - - objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); - return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); + return objcg ? obj_cgroup_memcg(objcg) : NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) @@ -530,6 +523,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return (memcg == root_mem_cgroup); } +static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) +{ + return objcg->is_root; +} + static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); @@ -538,13 +536,15 @@ static inline bool mem_cgroup_disabled(void) static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, - unsigned long *low) + unsigned long *low, + unsigned long *usage) { - *min = *low = 0; + *min = *low = *usage = 0; if (mem_cgroup_disabled()) return; + *usage = page_counter_read(&memcg->memory); /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because @@ -649,8 +649,6 @@ int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); -void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); - void __mem_cgroup_uncharge(struct folio *folio); /** @@ -717,7 +715,15 @@ 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. + * Call with rcu_read_lock() held to ensure the lifetime of the returned lruvec. + * Note that this alone will NOT guarantee the stability of the folio->lruvec + * association; the folio can be reparented to an ancestor if this races with + * cgroup deletion. + * + * Use folio_lruvec_lock() to ensure both lifetime and stability of the binding. + * Once a lruvec is locked, folio_lruvec() can be called on other folios, and + * their binding is stable if the returned lruvec matches the one the caller has + * locked. Useful for lock batching. */ static inline struct lruvec *folio_lruvec(struct folio *folio) { @@ -740,15 +746,6 @@ 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; @@ -756,23 +753,26 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { + if (obj_cgroup_is_root(objcg)) + return true; return percpu_ref_tryget(&objcg->refcnt); } -static inline void obj_cgroup_get(struct obj_cgroup *objcg) +static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, + unsigned long nr) { - percpu_ref_get(&objcg->refcnt); + if (!obj_cgroup_is_root(objcg)) + percpu_ref_get_many(&objcg->refcnt, nr); } -static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, - unsigned long nr) +static inline void obj_cgroup_get(struct obj_cgroup *objcg) { - percpu_ref_get_many(&objcg->refcnt, nr); + obj_cgroup_get_many(objcg, 1); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { - if (objcg) + if (objcg && !obj_cgroup_is_root(objcg)) percpu_ref_put(&objcg->refcnt); } @@ -802,23 +802,21 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*)(struct task_struct *, void *), void *arg); -static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) +static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } -struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id); -#ifdef CONFIG_SHRINKER_DEBUG -static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { - return memcg ? cgroup_ino(memcg->css.cgroup) : 0; + return memcg ? cgroup_id(memcg->css.cgroup) : 0; } -struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); -#endif +struct mem_cgroup *mem_cgroup_get_from_id(u64 id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { @@ -869,18 +867,18 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio); +struct cgroup_subsys_state *get_mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; - return !!(memcg->css.flags & CSS_ONLINE); + return css_is_online(&memcg->css); } void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int zid, int nr_pages); + int zid, long nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, @@ -892,11 +890,15 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(gfp_t gfp_mask); +void __mem_cgroup_handle_over_high(gfp_t gfp_mask); -unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) +{ + if (unlikely(current->memcg_nr_pages_over_high)) + __mem_cgroup_handle_over_high(gfp_mask); +} -unsigned long mem_cgroup_size(struct mem_cgroup *memcg); +unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); @@ -907,19 +909,9 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, - int val); - /* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_memcg_state(memcg, idx, val); - local_irq_restore(flags); -} +void mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, int val); static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) @@ -936,7 +928,11 @@ static inline void mod_memcg_page_state(struct page *page, rcu_read_unlock(); } +unsigned long memcg_events(struct mem_cgroup *memcg, int event); unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); +unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); +bool memcg_stat_item_valid(int idx); +bool memcg_vm_event_item_valid(enum vm_event_item idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); @@ -944,39 +940,23 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec, void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); -void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); - -static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, - int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_lruvec_kmem_state(p, idx, val); - local_irq_restore(flags); -} - -void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, - unsigned long count); - -static inline void count_memcg_events(struct mem_cgroup *memcg, - enum vm_event_item idx, - unsigned long count) -{ - unsigned long flags; +void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); - local_irq_save(flags); - __count_memcg_events(memcg, idx, count); - local_irq_restore(flags); -} +void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, + unsigned long count); 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; - if (memcg) - count_memcg_events(memcg, idx, nr); + if (!folio_memcg_charged(folio)) + return; + + rcu_read_lock(); + memcg = folio_memcg(folio); + count_memcg_events(memcg, idx, nr); + rcu_read_unlock(); } static inline void count_memcg_events_mm(struct mm_struct *mm, @@ -1000,29 +980,13 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, count_memcg_events_mm(mm, idx, 1); } +void __memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event, bool allow_spinning); + static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { - bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || - event == MEMCG_SWAP_FAIL; - - atomic_long_inc(&memcg->memory_events_local[event]); - if (!swap_event) - cgroup_file_notify(&memcg->events_local_file); - - do { - atomic_long_inc(&memcg->memory_events[event]); - if (swap_event) - cgroup_file_notify(&memcg->swap_events_file); - else - cgroup_file_notify(&memcg->events_file); - - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - break; - if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) - break; - } while ((memcg = parent_mem_cgroup(memcg)) && - !mem_cgroup_is_root(memcg)); + __memcg_memory_event(memcg, event, true); } static inline void memcg_memory_event_mm(struct mm_struct *mm, @@ -1040,7 +1004,9 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -void split_page_memcg(struct page *head, int old_order, int new_order); +void split_page_memcg(struct page *first, unsigned order); +void folio_split_memcg_refs(struct folio *folio, unsigned old_order, + unsigned new_order); static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { @@ -1059,10 +1025,15 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm) return id; } +void mem_cgroup_flush_workqueue(void); + +extern int mem_cgroup_init(void); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 +#define root_mem_cgroup (NULL) + static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; @@ -1103,6 +1074,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return true; } +static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) +{ + return true; +} + static inline bool mem_cgroup_disabled(void) { return true; @@ -1121,9 +1097,10 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, - unsigned long *low) + unsigned long *low, + unsigned long *usage) { - *min = *low = 0; + *min = *low = *usage = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, @@ -1165,10 +1142,6 @@ static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, return 0; } -static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr) -{ -} - static inline void mem_cgroup_uncharge(struct folio *folio) { } @@ -1198,11 +1171,6 @@ 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; @@ -1261,6 +1229,7 @@ static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); + rcu_read_lock(); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } @@ -1269,6 +1238,7 @@ static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); + rcu_read_lock(); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } @@ -1278,6 +1248,7 @@ static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, { struct pglist_data *pgdat = folio_pgdat(folio); + rcu_read_lock(); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; } @@ -1300,29 +1271,27 @@ static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { } -static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) +static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { return 0; } -static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +static inline struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } -#ifdef CONFIG_SHRINKER_DEBUG -static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } -static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) +static inline struct mem_cgroup *mem_cgroup_get_from_id(u64 id) { return NULL; } -#endif static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { @@ -1351,11 +1320,6 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return 0; } -static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) -{ - return 0; -} - static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { @@ -1380,12 +1344,6 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } -static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, - int nr) -{ -} - static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) @@ -1402,6 +1360,21 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) return 0; } +static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item) +{ + return 0; +} + +static inline bool memcg_stat_item_valid(int idx) +{ + return false; +} + +static inline bool memcg_vm_event_item_valid(enum vm_event_item idx) +{ + return false; +} + static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { @@ -1422,14 +1395,6 @@ static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } -static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, - int val) -{ - struct page *page = virt_to_head_page(p); - - __mod_node_page_state(page_pgdat(page), idx, val); -} - static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { @@ -1439,12 +1404,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, } static inline void count_memcg_events(struct mem_cgroup *memcg, - enum vm_event_item idx, - unsigned long count) -{ -} - -static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { @@ -1465,7 +1424,12 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void split_page_memcg(struct page *head, int old_order, int new_order) +static inline void split_page_memcg(struct page *first, unsigned order) +{ +} + +static inline void folio_split_memcg_refs(struct folio *folio, + unsigned old_order, unsigned new_order) { } @@ -1473,6 +1437,10 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } + +static inline void mem_cgroup_flush_workqueue(void) { } + +static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ /* @@ -1488,16 +1456,6 @@ struct slabobj_ext { #endif } __aligned(8); -static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) -{ - __mod_lruvec_kmem_state(p, idx, 1); -} - -static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) -{ - __mod_lruvec_kmem_state(p, idx, -1); -} - static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; @@ -1511,20 +1469,28 @@ 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_lock_irq(struct lruvec *lruvec) +{ + rcu_read_lock(); + spin_lock_irq(&lruvec->lru_lock); +} + +static inline void lruvec_unlock(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); + rcu_read_unlock(); } -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); + rcu_read_unlock(); } -static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, - unsigned long flags) +static inline void lruvec_unlock_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); + rcu_read_unlock(); } /* Test requires a stable folio->memcg binding, see folio_memcg() */ @@ -1543,7 +1509,7 @@ 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); @@ -1557,7 +1523,7 @@ static inline void folio_lruvec_relock_irqsave(struct folio *folio, if (folio_matches_lruvec(folio, *lruvecp)) return; - unlock_page_lruvec_irqrestore(*lruvecp, *flags); + lruvec_unlock_irqrestore(*lruvecp, *flags); } *lruvecp = folio_lruvec_lock_irqsave(folio, flags); @@ -1581,9 +1547,14 @@ static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, if (mem_cgroup_disabled()) return; + if (!folio_memcg_charged(folio)) + return; + + rcu_read_lock(); memcg = folio_memcg(folio); - if (unlikely(memcg && &memcg->css != wb->memcg_css)) + if (unlikely(&memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); + rcu_read_unlock(); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); @@ -1615,44 +1586,97 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, - gfp_t gfp_mask); -void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) + void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); -static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) +void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk); +bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, + gfp_t gfp_mask); +void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages); + +#if BITS_PER_LONG < 64 +static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { -#ifdef CONFIG_MEMCG_V1 - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return !!memcg->tcpmem_pressure; -#endif /* CONFIG_MEMCG_V1 */ + u64 val = get_jiffies_64() + HZ; + unsigned long flags; + + write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags); + memcg->socket_pressure = val; + write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags); +} + +static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) +{ + unsigned int seq; + u64 val; + do { - if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) - return true; - } while ((memcg = parent_mem_cgroup(memcg))); - return false; + seq = read_seqbegin(&memcg->socket_pressure_seqlock); + val = memcg->socket_pressure; + } while (read_seqretry(&memcg->socket_pressure_seqlock, seq)); + + return val; +} +#else +static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) +{ + WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } +static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) +{ + return READ_ONCE(memcg->socket_pressure); +} +#endif + 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) { }; -static inline void mem_cgroup_sk_free(struct sock *sk) { }; -static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) + +static inline void mem_cgroup_sk_alloc(struct sock *sk) +{ +} + +static inline void mem_cgroup_sk_free(struct sock *sk) +{ +} + +static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) +{ +} + +static inline bool mem_cgroup_sk_charge(const struct sock *sk, + unsigned int nr_pages, + gfp_t gfp_mask) { return false; } +static inline void mem_cgroup_sk_uncharge(const struct sock *sk, + unsigned int nr_pages) +{ +} + 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 @@ -1720,7 +1744,7 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); +struct mem_cgroup *mem_cgroup_from_virt(void *p); static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, @@ -1737,6 +1761,15 @@ static inline void count_objcg_events(struct obj_cgroup *objcg, rcu_read_unlock(); } +void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask); + +void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg); + +static inline bool memcg_is_dying(struct mem_cgroup *memcg) +{ + return memcg ? css_is_dying(&memcg->css) : false; +} + #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1783,7 +1816,7 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return -1; } -static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) +static inline struct mem_cgroup *mem_cgroup_from_virt(void *p) { return NULL; } @@ -1794,6 +1827,24 @@ static inline void count_objcg_events(struct obj_cgroup *objcg, { } +static inline ino_t page_cgroup_ino(struct page *page) +{ + return 0; +} + +static inline void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, + nodemask_t *mask) +{ +} + +static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) +{ +} + +static inline bool memcg_is_dying(struct mem_cgroup *memcg) +{ + return false; +} #endif /* CONFIG_MEMCG */ #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) @@ -1848,6 +1899,9 @@ static inline void mem_cgroup_exit_user_fault(void) current->in_user_fault = 0; } +void memcg1_swapout(struct folio *folio, swp_entry_t entry); +void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages); + #else /* CONFIG_MEMCG_V1 */ static inline unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, @@ -1875,6 +1929,14 @@ static inline void mem_cgroup_exit_user_fault(void) { } +static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry) +{ +} + +static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages) +{ +} + #endif /* CONFIG_MEMCG_V1 */ #endif /* _LINUX_MEMCONTROL_H */ |