diff options
Diffstat (limited to 'include/linux/memcontrol.h')
| -rw-r--r-- | include/linux/memcontrol.h | 1284 |
1 files changed, 839 insertions, 445 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a7a0a1a5c8d5..e1644a24009c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -23,19 +23,20 @@ #include <linux/page-flags.h> struct mem_cgroup; +struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS, - MEMCG_RSS_HUGE, - MEMCG_SWAP, + MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, - /* XXX: why are these zone and not node counters? */ - MEMCG_KERNEL_STACK_KB, + MEMCG_PERCPU_B, + MEMCG_VMALLOC, + MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; @@ -45,17 +46,13 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, + MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; -enum mem_cgroup_protection { - MEMCG_PROT_NONE, - MEMCG_PROT_LOW, - MEMCG_PROT_MIN, -}; - struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; @@ -73,8 +70,8 @@ struct mem_cgroup_id { /* * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremated by the number of pages. This counter is used for - * for trigger some periodic events. This is straightforward and better + * it will be incremented by the number of pages. This counter is used + * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { @@ -83,12 +80,8 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -struct memcg_vmstats_percpu { - long stat[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; +struct memcg_vmstats_percpu; +struct memcg_vmstats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -96,17 +89,30 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; -struct lruvec_stat { - long count[NR_VM_NODE_STAT_ITEMS]; -}; - /* - * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, - * which have elements charged to this memcg. + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to this memcg. */ -struct memcg_shrinker_map { +struct shrinker_info { struct rcu_head rcu; - unsigned long map[0]; + atomic_long_t *nr_deferred; + unsigned long *map; +}; + +struct lruvec_stats_percpu { + /* Local (CPU and cgroup) state */ + long state[NR_VM_NODE_STAT_ITEMS]; + + /* Delta calculation for lockless upward propagation */ + long state_prev[NR_VM_NODE_STAT_ITEMS]; +}; + +struct lruvec_stats { + /* Aggregated (CPU and subtree) state */ + long state[NR_VM_NODE_STAT_ITEMS]; + + /* Pending child counts during tree propagation */ + long state_pending[NR_VM_NODE_STAT_ITEMS]; }; /* @@ -115,18 +121,14 @@ struct memcg_shrinker_map { struct mem_cgroup_per_node { struct lruvec lruvec; - /* Legacy local VM stats */ - struct lruvec_stat __percpu *lruvec_stat_local; - - /* Subtree VM stats (batched updates) */ - struct lruvec_stat __percpu *lruvec_stat_cpu; - atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; + struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; + struct lruvec_stats lruvec_stats; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; - struct memcg_shrinker_map __rcu *shrinker_map; + struct shrinker_info __rcu *shrinker_info; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ @@ -148,7 +150,7 @@ struct mem_cgroup_threshold_ary { /* Size of entries[] */ unsigned int size; /* Array of thresholds */ - struct mem_cgroup_threshold entries[0]; + struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { @@ -162,21 +164,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -enum memcg_kmem_state { - KMEM_NONE, - KMEM_ALLOCATED, - KMEM_ONLINE, -}; - -#if defined(CONFIG_SMP) -struct memcg_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name; -#else -#define MEMCG_PADDING(name) -#endif - /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss @@ -195,6 +182,22 @@ struct memcg_cgwb_frn { }; /* + * Bucket for arbitrarily byte-sized objects charged to a memory + * cgroup. The bucket can be reparented in one piece when the cgroup + * is destroyed, without having to round up the individual references + * of all live memory objects in the wild. + */ +struct obj_cgroup { + struct percpu_ref refcnt; + struct mem_cgroup *memcg; + atomic_t nr_charged_bytes; + union { + struct list_head list; /* protected by objcg_lock */ + struct rcu_head rcu; + }; +}; + +/* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, @@ -207,31 +210,30 @@ struct mem_cgroup { struct mem_cgroup_id id; /* Accounted resources */ - struct page_counter memory; - struct page_counter swap; + struct page_counter memory; /* Both v1 & v2 */ - /* Legacy consumer-oriented counters */ - struct page_counter memsw; - struct page_counter kmem; - struct page_counter tcpmem; + union { + struct page_counter swap; /* v2 only */ + struct page_counter memsw; /* v1 only */ + }; - /* Upper bound of normal memory consumption range */ - unsigned long high; + /* Legacy consumer-oriented counters */ + struct page_counter kmem; /* v1 only */ + struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + unsigned long zswap_max; +#endif + unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* - * Should the accounting and control be hierarchical, per subtree? - */ - bool use_hierarchy; - - /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; @@ -272,24 +274,10 @@ struct mem_cgroup { spinlock_t move_lock; unsigned long move_lock_flags; - MEMCG_PADDING(_pad1_); - - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; - - /* Legacy local VM stats and events */ - struct memcg_vmstats_percpu __percpu *vmstats_local; - - /* Subtree VM stats and events (batched updates) */ - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - - MEMCG_PADDING(_pad2_); + CACHELINE_PADDING(_pad1_); - atomic_long_t vmstats[MEMCG_NR_STAT]; - atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; + /* memory.stat */ + struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; @@ -302,12 +290,22 @@ struct mem_cgroup { int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM - /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; - enum memcg_kmem_state kmem_state; - struct list_head kmem_caches; + struct obj_cgroup __rcu *objcg; + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif + CACHELINE_PADDING(_pad2_); + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + struct memcg_vmstats_percpu __percpu *vmstats_percpu; + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; @@ -322,18 +320,238 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif - struct mem_cgroup_per_node *nodeinfo[0]; - /* WARNING: nodeinfo must be the last member here */ +#ifdef CONFIG_LRU_GEN + /* per-memcg mm_struct list */ + struct lru_gen_mm_list mm_list; +#endif + + struct mem_cgroup_per_node *nodeinfo[]; }; /* - * size of first charge trial. "32" comes from vmscan.c's magic value. - * TODO: maybe necessary to use big numbers in big irons. + * size of first charge trial. + * TODO: maybe necessary to use big numbers in big irons or dynamic based of the + * workload. */ -#define MEMCG_CHARGE_BATCH 32U +#define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; +enum page_memcg_data_flags { + /* page->memcg_data is a pointer to an objcgs vector */ + MEMCG_DATA_OBJCGS = (1UL << 0), + /* page has been accounted as a non-slab kernel page */ + MEMCG_DATA_KMEM = (1UL << 1), + /* the next bit after the last actual flag */ + __NR_MEMCG_DATA_FLAGS = (1UL << 2), +}; + +#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. + */ +static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) +{ + return READ_ONCE(objcg->memcg); +} + +/* + * __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: 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. + */ +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); +} + +/* + * folio_memcg - Get the memory cgroup associated with a 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. + * + * For a non-kmem folio any of the following ensures folio and memcg binding + * stability: + * + * - the folio lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + * - mem_cgroup_trylock_pages() + * + * For a kmem folio a caller should hold an rcu read lock to protect memcg + * associated with a kmem 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); +} + +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return folio_memcg(page_folio(page)); +} + +/** + * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. + * + * 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. + * + * Return: A pointer to the memory cgroup associated with the folio, + * or NULL. + */ +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) +{ + unsigned long memcg_data = READ_ONCE(folio->memcg_data); + + 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); + return obj_cgroup_memcg(objcg); + } + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * page_memcg_check - get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function unlike page_memcg() can take any page + * as an argument. It has to be used in cases when it's not known if a page + * 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 lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + * - mem_cgroup_trylock_pages() + * + * For a kmem page a caller should hold an rcu read lock to protect memcg + * associated with a kmem page from being released. + */ +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + /* + * Because page->memcg_data might be changed asynchronously + * for slab pages, READ_ONCE() should be used here. + */ + unsigned long memcg_data = READ_ONCE(page->memcg_data); + + 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); + } + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + +#ifdef CONFIG_MEMCG_KMEM +/* + * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. + * @folio: Pointer to the folio. + * + * Checks if the folio has MemcgKmem flag set. The caller must ensure + * that the folio has an associated memory cgroup. It's not safe to call + * this function against some types of folios, e.g. slab folios. + */ +static inline bool folio_memcg_kmem(struct folio *folio) +{ + VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + return folio->memcg_data & MEMCG_DATA_KMEM; +} + + +#else +static inline bool folio_memcg_kmem(struct folio *folio) +{ + return false; +} + +#endif + +static inline bool PageMemcgKmem(struct page *page) +{ + return folio_memcg_kmem(page_folio(page)); +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -344,49 +562,147 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { + *min = *low = 0; + if (mem_cgroup_disabled()) - return 0; + return; + + /* + * There is no reclaim protection applied to a targeted reclaim. + * We are special casing this specific case here because + * mem_cgroup_protected calculation is not robust enough to keep + * the protection invariant for calculated effective values for + * parallel reclaimers with different reclaim target. This is + * especially a problem for tail memcgs (as they have pages on LRU) + * which would want to have effective values 0 for targeted reclaim + * but a different value for external reclaim. + * + * Example + * Let's have global and A's reclaim in parallel: + * | + * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) + * |\ + * | C (low = 1G, usage = 2.5G) + * B (low = 1G, usage = 0.5G) + * + * For the global reclaim + * A.elow = A.low + * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow + * C.elow = min(C.usage, C.low) + * + * With the effective values resetting we have A reclaim + * A.elow = 0 + * B.elow = B.low + * C.elow = C.low + * + * If the global reclaim races with A's reclaim then + * B.elow = C.elow = 0 because children_low_usage > A.elow) + * is possible and reclaiming B would be violating the protection. + * + */ + if (root == memcg) + return; + + *min = READ_ONCE(memcg->memory.emin); + *low = READ_ONCE(memcg->memory.elow); +} + +void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg); + +static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg) +{ + /* + * The root memcg doesn't account charges, and doesn't support + * protection. + */ + return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg); + +} - if (in_low_reclaim) - return READ_ONCE(memcg->memory.emin); +static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) +{ + if (!mem_cgroup_supports_protection(memcg)) + return false; - return max(READ_ONCE(memcg->memory.emin), - READ_ONCE(memcg->memory.elow)); + return READ_ONCE(memcg->memory.elow) >= + page_counter_read(&memcg->memory); } -enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, - struct mem_cgroup *memcg); +static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) +{ + if (!mem_cgroup_supports_protection(memcg)) + return false; -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); -void mem_cgroup_uncharge(struct page *page); -void mem_cgroup_uncharge_list(struct list_head *page_list); + return READ_ONCE(memcg->memory.emin) >= + page_counter_read(&memcg->memory); +} -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); -static struct mem_cgroup_per_node * -mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) +/** + * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. + * @folio: Folio to charge. + * @mm: mm context of the allocating task. + * @gfp: Reclaim mode. + * + * Try to charge @folio to the memcg that @mm belongs to, reclaiming + * pages according to @gfp if necessary. If @mm is NULL, try to + * charge to the active memcg. + * + * Do not use this for folios allocated for swapin. + * + * Return: 0 on success. Otherwise, an error code is returned. + */ +static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, + gfp_t gfp) { - return memcg->nodeinfo[nid]; + if (mem_cgroup_disabled()) + return 0; + return __mem_cgroup_charge(folio, mm, 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); + +void __mem_cgroup_uncharge(struct folio *folio); + +/** + * mem_cgroup_uncharge - Uncharge a folio. + * @folio: Folio to uncharge. + * + * Uncharge a folio previously charged with mem_cgroup_charge(). + */ +static inline void mem_cgroup_uncharge(struct folio *folio) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge(folio); +} + +void __mem_cgroup_uncharge_list(struct list_head *page_list); +static inline void mem_cgroup_uncharge_list(struct list_head *page_list) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_list(page_list); +} + +void mem_cgroup_migrate(struct folio *old, struct folio *new); + /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec + * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & - * @node combination. This can be the node lruvec, if the memory + * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, @@ -403,7 +719,7 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, if (!memcg) memcg = root_mem_cgroup; - mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* @@ -416,19 +732,64 @@ out: return lruvec; } -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); +/** + * folio_lruvec - return lruvec for isolating/putting an LRU folio + * @folio: Pointer to the folio. + * + * This function relies on folio->mem_cgroup being stable. + */ +static inline struct lruvec *folio_lruvec(struct folio *folio) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); + return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); +} struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); +struct lruvec *folio_lruvec_lock(struct folio *folio); +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; } +static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) +{ + return percpu_ref_tryget(&objcg->refcnt); +} + +static inline void obj_cgroup_get(struct obj_cgroup *objcg) +{ + percpu_ref_get(&objcg->refcnt); +} + +static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, + unsigned long nr) +{ + percpu_ref_get_many(&objcg->refcnt, nr); +} + +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ + percpu_ref_put(&objcg->refcnt); +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) @@ -454,6 +815,15 @@ 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)); @@ -479,9 +849,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); + return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, @@ -489,8 +857,6 @@ static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, { if (root == memcg) return true; - if (!root->use_hierarchy) - return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } @@ -518,11 +884,6 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) return !!(memcg->css.flags & CSS_ONLINE); } -/* - * For memory reclaim. - */ -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); - void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); @@ -533,7 +894,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return mz->lru_zone_size[zone_idx][lru]; + return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); @@ -569,48 +930,29 @@ 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); -#ifdef CONFIG_MEMCG_SWAP -extern int do_swap_account; -#endif - -struct mem_cgroup *lock_page_memcg(struct page *page); -void __unlock_page_memcg(struct mem_cgroup *memcg); +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); +void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); -/* - * idx can be of type enum memcg_stat_item or node_stat_item. - * Keep in sync with memcg_exact_page_state(). - */ -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - long x = atomic_long_read(&memcg->vmstats[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} +void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); -/* - * idx can be of type enum memcg_stat_item or node_stat_item. - * Keep in sync with memcg_exact_page_state(). - */ -static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, - int idx) +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) { - long x = 0; - int cpu; + rcu_read_lock(); - for_each_possible_cpu(cpu) - x += per_cpu(memcg->vmstats_local->stat[idx], cpu); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; } -void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, @@ -623,37 +965,23 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } -/** - * mod_memcg_page_state - update page state statistics - * @page: the page - * @idx: page state item to account - * @val: number of pages (positive or negative) - * - * The @page must be locked or the caller must use lock_page_memcg() - * to prevent double accounting when the page is concurrently being - * moved to another memcg: - * - * lock_page(page) or lock_page_memcg(page) - * if (TestClearPageState(page)) - * mod_memcg_page_state(page, state, -1); - * unlock_page(page) or unlock_page_memcg(page) - * - * Kernel pages are an exception to this, since they'll never move. - */ -static inline void __mod_memcg_page_state(struct page *page, - int idx, int val) -{ - if (page->mem_cgroup) - __mod_memcg_state(page->mem_cgroup, idx, val); -} - static inline void mod_memcg_page_state(struct page *page, int idx, int val) { - if (page->mem_cgroup) - mod_memcg_state(page->mem_cgroup, idx, val); + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = page_memcg(page); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); } +unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); + static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { @@ -664,7 +992,7 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = atomic_long_read(&pn->lruvec_stat[idx]); + x = READ_ONCE(pn->lruvec_stats.state[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -684,7 +1012,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) - x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); + x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -692,50 +1020,33 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return x; } -void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val); -void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); +void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); + +void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val); +void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); -static inline void mod_lruvec_state(struct lruvec *lruvec, - 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_state(lruvec, idx, val); + __mod_lruvec_kmem_state(p, idx, val); local_irq_restore(flags); } -static inline void __mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - pg_data_t *pgdat = page_pgdat(page); - struct lruvec *lruvec; - - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!page->mem_cgroup) { - __mod_node_page_state(pgdat, idx, val); - return; - } - - lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); - __mod_lruvec_state(lruvec, idx, val); -} - -static inline void mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) +static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); - __mod_lruvec_page_state(page, idx, val); + __mod_memcg_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); - void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); @@ -753,8 +1064,19 @@ 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) { - if (page->mem_cgroup) - count_memcg_events(page->mem_cgroup, idx, 1); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + count_memcg_events(memcg, idx, 1); +} + +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); + + if (memcg) + count_memcg_events(memcg, idx, nr); } static inline void count_memcg_event_mm(struct mm_struct *mm, @@ -775,13 +1097,22 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, 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]); - cgroup_file_notify(&memcg->events_local_file); + if (!swap_event) + cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); - cgroup_file_notify(&memcg->events_file); + 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)) && @@ -803,16 +1134,47 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -void mem_cgroup_split_huge_fixup(struct page *head); -#endif +void split_page_memcg(struct page *head, unsigned int nr); + +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 -struct mem_cgroup; +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + return NULL; +} + +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return NULL; +} + +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + return NULL; +} + +static inline bool folio_memcg_kmem(struct folio *folio) +{ + return false; +} + +static inline bool PageMemcgKmem(struct page *page) +{ + return false; +} static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { @@ -834,50 +1196,46 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { - return 0; + *min = *low = 0; } -static inline enum mem_cgroup_protection mem_cgroup_protected( - struct mem_cgroup *root, struct mem_cgroup *memcg) +static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg) { - return MEMCG_PROT_NONE; } -static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) +static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { - *memcgp = NULL; - return 0; + return false; +} + +static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) +{ + return false; } -static inline int mem_cgroup_try_charge_delay(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) +static inline int mem_cgroup_charge(struct folio *folio, + struct mm_struct *mm, gfp_t gfp) { - *memcgp = NULL; return 0; } -static inline void mem_cgroup_commit_charge(struct page *page, - struct mem_cgroup *memcg, - bool lrucare, bool compound) +static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, + struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { + return 0; } -static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) +static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) { } -static inline void mem_cgroup_uncharge(struct page *page) +static inline void mem_cgroup_uncharge(struct folio *folio) { } @@ -885,7 +1243,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_migrate(struct page *old, struct page *new) +static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } @@ -895,12 +1253,17 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct pglist_data *pgdat) +static inline struct lruvec *folio_lruvec(struct folio *folio) { + struct pglist_data *pgdat = folio_pgdat(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; @@ -917,15 +1280,45 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } -static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } +static inline struct lruvec *folio_lruvec_lock(struct folio *folio) +{ + struct pglist_data *pgdat = folio_pgdat(folio); + + spin_lock(&pgdat->__lruvec.lru_lock); + return &pgdat->__lruvec; +} + +static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) +{ + struct pglist_data *pgdat = folio_pgdat(folio); + + spin_lock_irq(&pgdat->__lruvec.lru_lock); + return &pgdat->__lruvec; +} + +static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, + unsigned long *flagsp) +{ + struct pglist_data *pgdat = folio_pgdat(folio); + + spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); + return &pgdat->__lruvec; +} + static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -957,6 +1350,18 @@ 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; @@ -999,17 +1404,32 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline struct mem_cgroup *lock_page_memcg(struct page *page) +static inline void lock_page_memcg(struct page *page) { - return NULL; } -static inline void __unlock_page_memcg(struct mem_cgroup *memcg) +static inline void unlock_page_memcg(struct page *page) { } -static inline void unlock_page_memcg(struct page *page) +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) { + rcu_read_unlock(); } static inline void mem_cgroup_handle_over_high(void) @@ -1044,17 +1464,6 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - return 0; -} - -static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, - int idx) -{ - return 0; -} - static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) @@ -1067,16 +1476,14 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } -static inline void __mod_memcg_page_state(struct page *page, - int idx, - int nr) +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) { } -static inline void mod_memcg_page_state(struct page *page, - int idx, - int nr) +static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { + return 0; } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, @@ -1091,31 +1498,20 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } -static inline void __mod_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) +static inline void mem_cgroup_flush_stats(void) { - __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } -static inline void mod_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) +static inline void mem_cgroup_flush_stats_delayed(void) { - mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } -static inline void __mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) +static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { - __mod_node_page_state(page_pgdat(page), idx, val); } -static inline void mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - mod_node_page_state(page_pgdat(page), idx, val); -} - -static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, +static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); @@ -1123,16 +1519,12 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, __mod_node_page_state(page_pgdat(page), idx, val); } -static inline -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) +static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, + int val) { - return 0; -} + struct page *page = virt_to_head_page(p); -static inline void mem_cgroup_split_huge_fixup(struct page *head) -{ + mod_node_page_state(page_pgdat(page), idx, val); } static inline void count_memcg_events(struct mem_cgroup *memcg, @@ -1152,124 +1544,102 @@ static inline void count_memcg_page_event(struct page *page, { } -static inline -void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) -{ -} -#endif /* CONFIG_MEMCG */ - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __inc_memcg_state(struct mem_cgroup *memcg, - int idx) +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) { - __mod_memcg_state(memcg, idx, 1); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __dec_memcg_state(struct mem_cgroup *memcg, - int idx) +static inline +void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { - __mod_memcg_state(memcg, idx, -1); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __inc_memcg_page_state(struct page *page, - int idx) +static inline void split_page_memcg(struct page *head, unsigned int nr) { - __mod_memcg_page_state(page, idx, 1); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __dec_memcg_page_state(struct page *page, - int idx) +static inline +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { - __mod_memcg_page_state(page, idx, -1); + return 0; } +#endif /* CONFIG_MEMCG */ -static inline void __inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) +static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { - __mod_lruvec_state(lruvec, idx, 1); + __mod_lruvec_kmem_state(p, idx, 1); } -static inline void __dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) +static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) { - __mod_lruvec_state(lruvec, idx, -1); + __mod_lruvec_kmem_state(p, idx, -1); } -static inline void __inc_lruvec_page_state(struct page *page, - enum node_stat_item idx) +static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { - __mod_lruvec_page_state(page, idx, 1); -} + struct mem_cgroup *memcg; -static inline void __dec_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - __mod_lruvec_page_state(page, idx, -1); + memcg = lruvec_memcg(lruvec); + if (!memcg) + return NULL; + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } -static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) +static inline void unlock_page_lruvec(struct lruvec *lruvec) { - __mod_lruvec_slab_state(p, idx, 1); + spin_unlock(&lruvec->lru_lock); } -static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) +static inline void unlock_page_lruvec_irq(struct lruvec *lruvec) { - __mod_lruvec_slab_state(p, idx, -1); + spin_unlock_irq(&lruvec->lru_lock); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void inc_memcg_state(struct mem_cgroup *memcg, - int idx) +static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, + unsigned long flags) { - mod_memcg_state(memcg, idx, 1); + spin_unlock_irqrestore(&lruvec->lru_lock, flags); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void dec_memcg_state(struct mem_cgroup *memcg, - int idx) +/* Test requires a stable page->memcg binding, see page_memcg() */ +static inline bool folio_matches_lruvec(struct folio *folio, + struct lruvec *lruvec) { - mod_memcg_state(memcg, idx, -1); + return lruvec_pgdat(lruvec) == folio_pgdat(folio) && + lruvec_memcg(lruvec) == folio_memcg(folio); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void inc_memcg_page_state(struct page *page, - int idx) +/* Don't lock again iff page's lruvec locked */ +static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, + struct lruvec *locked_lruvec) { - mod_memcg_page_state(page, idx, 1); -} + if (locked_lruvec) { + if (folio_matches_lruvec(folio, locked_lruvec)) + return locked_lruvec; -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void dec_memcg_page_state(struct page *page, - int idx) -{ - mod_memcg_page_state(page, idx, -1); -} + unlock_page_lruvec_irq(locked_lruvec); + } -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); + return folio_lruvec_lock_irq(folio); } -static inline void dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) +/* Don't lock again iff page's lruvec locked */ +static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio, + struct lruvec *locked_lruvec, unsigned long *flags) { - mod_lruvec_state(lruvec, idx, -1); -} + if (locked_lruvec) { + if (folio_matches_lruvec(folio, locked_lruvec)) + return locked_lruvec; -static inline void inc_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - mod_lruvec_page_state(page, idx, 1); -} + unlock_page_lruvec_irqrestore(locked_lruvec, *flags); + } -static inline void dec_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - mod_lruvec_page_state(page, idx, -1); + return folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -1279,17 +1649,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; - if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) - mem_cgroup_track_foreign_dirty_slowpath(page, wb); + if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); @@ -1309,7 +1679,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, { } -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } @@ -1321,7 +1691,8 @@ 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); +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; @@ -1333,16 +1704,16 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } -extern int memcg_expand_shrinker_maps(int new_id); - -extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id); +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); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1352,122 +1723,145 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id) +static inline void set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id) { } #endif -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); -void memcg_kmem_put_cache(struct kmem_cache *cachep); - #ifdef CONFIG_MEMCG_KMEM -int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); -void __memcg_kmem_uncharge(struct page *page, int order); -int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg); -void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg, - unsigned int nr_pages); +bool mem_cgroup_kmem_disabled(void); +int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); +void __memcg_kmem_uncharge_page(struct page *page, int order); -extern struct static_key_false memcg_kmem_enabled_key; -extern struct workqueue_struct *memcg_kmem_cache_wq; +struct obj_cgroup *get_obj_cgroup_from_current(void); +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); -extern int memcg_nr_cache_ids; -void memcg_get_cache_ids(void); -void memcg_put_cache_ids(void); +int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); +void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); -/* - * Helper macro to loop through all memcg-specific caches. Callers must still - * check if the cache is valid (it is either valid or NULL). - * the slab_mutex must be held when looping through those caches - */ -#define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) +extern struct static_key_false memcg_kmem_enabled_key; static inline bool memcg_kmem_enabled(void) { - return static_branch_unlikely(&memcg_kmem_enabled_key); + return static_branch_likely(&memcg_kmem_enabled_key); } -static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, + int order) { if (memcg_kmem_enabled()) - return __memcg_kmem_charge(page, gfp, order); + return __memcg_kmem_charge_page(page, gfp, order); return 0; } -static inline void memcg_kmem_uncharge(struct page *page, int order) +static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_enabled()) - __memcg_kmem_uncharge(page, order); + __memcg_kmem_uncharge_page(page, order); } -static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, - int order, struct mem_cgroup *memcg) +/* + * A helper for accessing memcg's kmem_id, used for getting + * corresponding LRU lists. + */ +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { - if (memcg_kmem_enabled()) - return __memcg_kmem_charge_memcg(page, gfp, order, memcg); - return 0; + return memcg ? memcg->kmemcg_id : -1; } -static inline void memcg_kmem_uncharge_memcg(struct page *page, int order, - struct mem_cgroup *memcg) -{ - if (memcg_kmem_enabled()) - __memcg_kmem_uncharge_memcg(memcg, 1 << order); -} +struct mem_cgroup *mem_cgroup_from_obj(void *p); +struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -/* - * helper for accessing a memcg's index. It will be used as an index in the - * child cache array in kmem_cache, and also to derive its name. This function - * will return -1 when this is not a kmem-limited memcg. - */ -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) { - return memcg ? memcg->kmemcg_id : -1; + struct mem_cgroup *memcg; + + if (!memcg_kmem_enabled()) + return; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); } #else +static inline bool mem_cgroup_kmem_disabled(void) +{ + return true; +} -static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, + int order) { return 0; } -static inline void memcg_kmem_uncharge(struct page *page, int order) +static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } -static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, + int order) { return 0; } -static inline void __memcg_kmem_uncharge(struct page *page, int order) +static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -#define for_each_memcg_cache_index(_idx) \ - for (; NULL; ) +static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + return NULL; +} static inline bool memcg_kmem_enabled(void) { return false; } -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } -static inline void memcg_get_cache_ids(void) +static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { + return NULL; +} + +static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) +{ + return NULL; } -static inline void memcg_put_cache_ids(void) +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) { } #endif /* CONFIG_MEMCG_KMEM */ +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +#else +static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + return true; +} +static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +#endif + #endif /* _LINUX_MEMCONTROL_H */ |