diff options
Diffstat (limited to 'include/linux/memcontrol.h')
| -rw-r--r-- | include/linux/memcontrol.h | 304 |
1 files changed, 178 insertions, 126 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 70b685a85bf4..7d1c0ce189a8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,16 +29,17 @@ struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; +struct swap_cluster_info; /* Cgroup-specific page state, on top of universal node page state */ 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, }; @@ -115,6 +116,16 @@ struct mem_cgroup_per_node { 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; @@ -179,6 +190,7 @@ struct obj_cgroup { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; + bool is_root; }; /* @@ -227,8 +239,6 @@ struct mem_cgroup { */ bool oom_group; - int swappiness; - /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; @@ -257,26 +267,18 @@ struct mem_cgroup { 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; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; - struct wb_domain cgwb_domain; - struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - struct deferred_split deferred_split_queue; + /* Keep the hot per-CPU stats pointer away from memory event counters. */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu + ____cacheline_aligned_in_smp; + +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain cgwb_domain; + struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif #ifdef CONFIG_LRU_GEN_WALKS_MMU @@ -319,6 +321,8 @@ struct mem_cgroup { /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; + + int swappiness; #endif /* CONFIG_MEMCG_V1 */ struct mem_cgroup_per_node *nodeinfo[]; @@ -367,9 +371,6 @@ 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. @@ -383,43 +384,19 @@ 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); } @@ -433,21 +410,30 @@ 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; } /* @@ -471,15 +457,10 @@ 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) { @@ -488,18 +469,14 @@ 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); - objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } - - 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) @@ -548,6 +525,27 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return (memcg == root_mem_cgroup); } +/** + * mem_cgroup_shrink_is_root - is this a global or root-memcg shrink invocation? + * @sc: shrink_control describing the current shrinker call + * + * Returns true when @sc represents a global reclaim shrink (sc->memcg == NULL) + * or a root-memcg shrink, i.e. not a per-memcg iteration of + * shrink_slab_memcg(). Filesystems whose ->nr_cached_objects()/ + * ->free_cached_objects() implementations operate on filesystem-global state + * and do not honour sc->memcg can use this to early-return 0 in per-memcg + * contexts. + */ +static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) +{ + return !sc->memcg || mem_cgroup_is_root(sc->memcg); +} + +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); @@ -666,8 +664,8 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, 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); +int mem_cgroup_swapin_charge_folio(struct folio *folio, unsigned short id, + struct mm_struct *mm, gfp_t gfp); void __mem_cgroup_uncharge(struct folio *folio); @@ -735,7 +733,15 @@ 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) { @@ -758,15 +764,6 @@ 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; @@ -774,23 +771,26 @@ 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); } @@ -885,7 +885,7 @@ 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) @@ -896,7 +896,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) } 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, @@ -952,6 +952,8 @@ 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_monotonic(struct lruvec *lruvec, + enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); @@ -966,10 +968,15 @@ void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, 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, @@ -1087,6 +1094,16 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return true; } +static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) +{ + 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; @@ -1145,7 +1162,7 @@ static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, - struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) + unsigned short id, struct mm_struct *mm, gfp_t gfp) { return 0; } @@ -1179,11 +1196,6 @@ 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; @@ -1242,6 +1254,7 @@ 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; } @@ -1250,6 +1263,7 @@ 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; } @@ -1259,6 +1273,7 @@ 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; } @@ -1391,6 +1406,12 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } +static inline unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx) +{ + return node_page_state_monotonic(lruvec_pgdat(lruvec), idx); +} + static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { @@ -1453,19 +1474,6 @@ static inline void mem_cgroup_flush_workqueue(void) { } static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ -/* - * Extended information for slab objects stored as an array in page->memcg_data - * if MEMCG_DATA_OBJEXTS is set. - */ -struct slabobj_ext { -#ifdef CONFIG_MEMCG - struct obj_cgroup *objcg; -#endif -#ifdef CONFIG_MEM_ALLOC_PROFILING - union codetag_ref ref; -#endif -} __aligned(8); - static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; @@ -1479,20 +1487,53 @@ 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 struct lruvec *lruvec_live_lock_irq(struct lruvec *lruvec) +{ +#ifdef CONFIG_MEMCG + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + + rcu_read_lock(); + + /* + * The memcg can be NULL when the memory controller is disabled. + * Otherwise, the caller keeps the memcg owning @lruvec alive. + */ + while (unlikely(memcg && css_is_dying(&memcg->css))) { + memcg = parent_mem_cgroup(memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + } + + spin_lock_irq(&lruvec->lru_lock); +#else + lruvec_lock_irq(lruvec); +#endif + + return lruvec; +} + +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() */ @@ -1511,7 +1552,7 @@ 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); @@ -1525,7 +1566,7 @@ 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); @@ -1549,9 +1590,14 @@ 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); @@ -1896,9 +1942,6 @@ 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, @@ -1926,14 +1969,23 @@ static inline void mem_cgroup_exit_user_fault(void) { } -static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry) +#endif /* CONFIG_MEMCG_V1 */ + +#if defined(CONFIG_MEMCG_V1) && defined(CONFIG_SWAP) + +void __memcg1_swapout(struct folio *folio, struct swap_cluster_info *ci); +void memcg1_swapin(struct folio *folio); + +#else + +static inline void __memcg1_swapout(struct folio *folio, + struct swap_cluster_info *ci) { } -static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages) +static inline void memcg1_swapin(struct folio *folio) { } - -#endif /* CONFIG_MEMCG_V1 */ +#endif #endif /* _LINUX_MEMCONTROL_H */ |