/* memcontrol.c - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov * * Memory thresholds * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Kernel Memory Controller * Copyright (C) 2012 Parallels Inc. and Google Inc. * Authors: Glauber Costa and Suleiman Souhlal * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" #include #include #include #include "slab.h" #include #include struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP int do_swap_account __read_mostly; #else #define do_swap_account 0 #endif static const char * const mem_cgroup_stat_names[] = { "cache", "rss", "rss_huge", "mapped_file", "writeback", "swap", }; static const char * const mem_cgroup_events_names[] = { "pgpgin", "pgpgout", "pgfault", "pgmajfault", }; static const char * const mem_cgroup_lru_names[] = { "inactive_anon", "active_anon", "inactive_file", "active_file", "unevictable", }; /* * 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 * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_TARGET_NUMAINFO, MEM_CGROUP_NTARGETS, }; #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 #define NUMAINFO_EVENTS_TARGET 1024 struct mem_cgroup_stat_cpu { long count[MEM_CGROUP_STAT_NSTATS]; unsigned long events[MEMCG_NR_EVENTS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; struct reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; /* * per-zone information in memory controller. */ struct mem_cgroup_per_zone { struct lruvec lruvec; unsigned long lru_size[NR_LRU_LISTS]; struct reclaim_iter iter[DEF_PRIORITY + 1]; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; /* * Cgroups above their limits are maintained in a RB-Tree, independent of * their hierarchy representation */ struct mem_cgroup_tree_per_zone { struct rb_root rb_root; spinlock_t lock; }; struct mem_cgroup_tree_per_node { struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; }; struct mem_cgroup_tree { struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; }; static struct mem_cgroup_tree soft_limit_tree __read_mostly; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[0]; }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; /* for OOM */ struct mem_cgroup_eventfd_list { struct list_head list; struct eventfd_ctx *eventfd; }; /* * cgroup_event represents events which userspace want to receive. */ struct mem_cgroup_event { /* * memcg which the event belongs to. */ struct mem_cgroup *memcg; /* * eventfd to signal userspace about the event. */ struct eventfd_ctx *eventfd; /* * Each of these stored in a list by the cgroup. */ struct list_head list; /* * register_event() callback will be used to add new userspace * waiter for changes related to this event. Use eventfd_signal() * on eventfd to send notification to userspace. */ int (*register_event)(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args); /* * unregister_event() callback will be called when userspace closes * the eventfd or on cgroup removing. This callback must be set, * if you want provide notification functionality. */ void (*unregister_event)(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd); /* * All fields below needed to unregister event when * userspace closes eventfd. */ poll_table pt; wait_queue_head_t *wqh; wait_queue_t wait; struct work_struct remove; }; static void mem_cgroup_threshold(struct mem_cgroup *memcg); static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* * 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, * to help the administrator determine what knobs to tune. * * TODO: Add a water mark for the memory controller. Reclaim will begin when * we hit the water mark. May be even add a low water mark, such that * no reclaim occurs from a cgroup at it's low water mark, this is * a feature that will be implemented much later in the future. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Accounted resources */ struct page_counter memory; struct page_counter memsw; struct page_counter kmem; /* Normal memory consumption range */ unsigned long low; unsigned long high; unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* css_online() has been completed */ int initialized; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; bool oom_lock; atomic_t under_oom; atomic_t oom_wakeups; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; /* taken only while moving_account > 0 */ spinlock_t move_lock; struct task_struct *move_lock_task; unsigned long move_lock_flags; /* * percpu counter. */ struct mem_cgroup_stat_cpu __percpu *stat; /* * used when a cpu is offlined or other synchronizations * See mem_cgroup_read_stat(). */ struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; bool kmem_acct_activated; bool kmem_acct_active; #endif int last_scanned_node; #if MAX_NUMNODES > 1 nodemask_t scan_nodes; atomic_t numainfo_events; atomic_t numainfo_updating; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; #ifdef CONFIG_MEMCG_KMEM bool memcg_kmem_is_active(struct mem_cgroup *memcg) { return memcg->kmem_acct_active; } #endif /* Stuffs for move charges at task migration. */ /* * Types of charges to be moved. */ #define MOVE_ANON 0x1U #define MOVE_FILE 0x2U #define MOVE_MASK (MOVE_ANON | MOVE_FILE) /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; unsigned long precharge; unsigned long moved_charge; unsigned long moved_swap; struct task_struct *moving_task; /* a task moving charges */ wait_queue_head_t waitq; /* a waitq for other context */ } mc = { .lock = __SPIN_LOCK_UNLOCKED(mc.lock), .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq), }; /* * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft * limit reclaim to prevent infinite loops, if they ever occur. */ #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 #define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, MEM_CGROUP_CHARGE_TYPE_ANON, MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, }; /* for encoding cft->private value on file */ enum res_type { _MEM, _MEMSWAP, _OOM_TYPE, _KMEM, }; #define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) #define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) /* Used for OOM nofiier */ #define OOM_CONTROL (0) /* * The memcg_create_mutex will be held whenever a new cgroup is created. * As a consequence, any change that needs to protect against new child cgroups * appearing has to hold it as well. */ static DEFINE_MUTEX(memcg_create_mutex); struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) { return s ? container_of(s, struct mem_cgroup, css) : NULL; } /* Some nice accessors for the vmpressure. */ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) { if (!memcg) memcg = root_mem_cgroup; return &memcg->vmpressure; } struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) { return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } /* * We restrict the id in the range of [1, 65535], so it can fit into * an unsigned short. */ #define MEM_CGROUP_ID_MAX USHRT_MAX static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return memcg->css.id; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; css = css_from_id(id, &memory_cgrp_subsys); return mem_cgroup_from_css(css); } /* Writing them here to avoid exposing memcg's inner layout */ #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk) { if (mem_cgroup_sockets_enabled) { struct mem_cgroup *memcg; struct cg_proto *cg_proto; BUG_ON(!sk->sk_prot->proto_cgroup); /* Socket cloning can throw us here with sk_cgrp already * filled. It won't however, necessarily happen from * process context. So the test for root memcg given * the current task's memcg won't help us in this case. * * Respecting the original socket's memcg is a better * decision in this case. */ if (sk->sk_cgrp) { BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); css_get(&sk->sk_cgrp->memcg->css); return; } rcu_read_lock(); memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); if (!mem_cgroup_is_root(memcg) && memcg_proto_active(cg_proto) && css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } rcu_read_unlock(); } } EXPORT_SYMBOL(sock_update_memcg); void sock_release_memcg(struct sock *sk) { if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { struct mem_cgroup *memcg; WARN_ON(!sk->sk_cgrp->memcg); memcg = sk->sk_cgrp->memcg; css_put(&sk->sk_cgrp->memcg->css); } } struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) { if (!memcg || mem_cgroup_is_root(memcg)) return NULL; return &memcg->tcp_mem; } EXPORT_SYMBOL(tcp_proto_cgroup); #endif #ifdef CONFIG_MEMCG_KMEM /* * This will be the memcg's index in each cache's ->memcg_params.memcg_caches. * The main reason for not using cgroup id for this: * this works better in sparse environments, where we have a lot of memcgs, * but only a few kmem-limited. Or also, if we have, for instance, 200 * memcgs, and none but the 200th is kmem-limited, we'd have to have a * 200 entry array for that. * * The current size of the caches array is stored in memcg_nr_cache_ids. It * will double each time we have to increase it. */ static DEFINE_IDA(memcg_cache_ida); int memcg_nr_cache_ids; /* Protects memcg_nr_cache_ids */ static DECLARE_RWSEM(memcg_cache_ids_sem); void memcg_get_cache_ids(void) { down_read(&memcg_cache_ids_sem); } void memcg_put_cache_ids(void) { up_read(&memcg_cache_ids_sem); } /* * MIN_SIZE is different than 1, because we would like to avoid going through * the alloc/free process all the time. In a small machine, 4 kmem-limited * cgroups is a reasonable guess. In the future, it could be a parameter or * tunable, but that is strictly not necessary. * * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get * this constant directly from cgroup, but it is understandable that this is * better kept as an internal representation in cgroup.c. In any case, the * cgrp_id space is not getting any smaller, and we don't have to necessarily * increase ours as well if it increases. */ #define MEMCG_CACHES_MIN_SIZE 4 #define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX /* * A lot of the calls to the cache allocation functions are expected to be * inlined by the compiler. Since the calls to memcg_kmem_get_cache are * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well */ struct static_key memcg_kmem_enabled_key; EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /* CONFIG_MEMCG_KMEM */ static struct mem_cgroup_per_zone * mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) { int nid = zone_to_nid(zone); int zid = zone_idx(zone); return &memcg->nodeinfo[nid]->zoneinfo[zid]; } struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) { return &memcg->css; } static struct mem_cgroup_per_zone * mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); return &memcg->nodeinfo[nid]->zoneinfo[zid]; } static struct mem_cgroup_tree_per_zone * soft_limit_tree_node_zone(int nid, int zid) { return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; } static struct mem_cgroup_tree_per_zone * soft_limit_tree_from_page(struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; } static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz, unsigned long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; struct mem_cgroup_per_zone *mz_node; if (mz->on_tree) return; mz->usage_in_excess = new_usage_in_excess; if (!mz->usage_in_excess) return; while (*p) { parent = *p; mz_node = rb_entry(parent, struct mem_cgroup_per_zone, tree_node); if (mz->usage_in_excess < mz_node->usage_in_excess) p = &(*p)->rb_left; /* * We can't avoid mem cgroups that are over their soft * limit by the same amount */ else if (mz->usage_in_excess >= mz_node->usage_in_excess) p = &(*p)->rb_right; } rb_link_node(&mz->tree_node, parent, p); rb_insert_color(&mz->tree_node, &mctz->rb_root); mz->on_tree = true; } static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { if (!mz->on_tree) return; rb_erase(&mz->tree_node, &mctz->rb_root); mz->on_tree = false; } static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { unsigned long flags; spin_lock_irqsave(&mctz->lock, flags); __mem_cgroup_remove_exceeded(mz, mctz); spin_unlock_irqrestore(&mctz->lock, flags); } static unsigned long soft_limit_excess(struct mem_cgroup *memcg) { unsigned long nr_pages = page_counter_read(&memcg->memory); unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit); unsigned long excess = 0; if (nr_pages > soft_limit) excess = nr_pages - soft_limit; return excess; } static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) { unsigned long excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; mctz = soft_limit_tree_from_page(page); /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { mz = mem_cgroup_page_zoneinfo(memcg, page); excess = soft_limit_excess(memcg); /* * We have to update the tree if mz is on RB-tree or * mem is over its softlimit. */ if (excess || mz->on_tree) { unsigned long flags; spin_lock_irqsave(&mctz->lock, flags); /* if on-tree, remove it */ if (mz->on_tree) __mem_cgroup_remove_exceeded(mz, mctz); /* * Insert again. mz->usage_in_excess will be updated. * If excess is 0, no tree ops. */ __mem_cgroup_insert_exceeded(mz, mctz, excess); spin_unlock_irqrestore(&mctz->lock, flags); } } } static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { struct mem_cgroup_tree_per_zone *mctz; struct mem_cgroup_per_zone *mz; int nid, zid; for_each_node(nid) { for (zid = 0; zid < MAX_NR_ZONES; zid++) { mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; mctz = soft_limit_tree_node_zone(nid, zid); mem_cgroup_remove_exceeded(mz, mctz); } } } static struct mem_cgroup_per_zone * __mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) { struct rb_node *rightmost = NULL; struct mem_cgroup_per_zone *mz; retry: mz = NULL; rightmost = rb_last(&mctz->rb_root); if (!rightmost) goto done; /* Nothing to reclaim from */ mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); /* * Remove the node now but someone else can add it back, * we will to add it back at the end of reclaim to its correct * position in the tree. */ __mem_cgroup_remove_exceeded(mz, mctz); if (!soft_limit_excess(mz->memcg) || !css_tryget_online(&mz->memcg->css)) goto retry; done: return mz; } static struct mem_cgroup_per_zone * mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) { struct mem_cgroup_per_zone *mz; spin_lock_irq(&mctz->lock); mz = __mem_cgroup_largest_soft_limit_node(mctz); spin_unlock_irq(&mctz->lock); return mz; } /* * Implementation Note: reading percpu statistics for memcg. * * Both of vmstat[] and percpu_counter has threshold and do periodic * synchronization to implement "quick" read. There are trade-off between * reading cost and precision of value. Then, we may have a chance to implement * a periodic synchronizion of counter in memcg's counter. * * But this _read() function is used for user interface now. The user accounts * memory usage by memory cgroup and he _always_ requires exact value because * he accounts memory. Even if we provide quick-and-fuzzy read, we always * have to visit all online cpus and make sum. So, for now, unnecessary * synchronization is not implemented. (just implemented for cpu hotplug) * * If there are kernel internal actions which can make use of some not-exact * value, and reading all cpu value can be performance bottleneck in some * common workload, threashold and synchonization as vmstat[] should be * implemented. */ static long mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { long val = 0; int cpu; get_online_cpus(); for_each_online_cpu(cpu) val += per_cpu(memcg->stat->count[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU spin_lock(&memcg->pcp_counter_lock); val += memcg->nocpu_base.count[idx]; spin_unlock(&memcg->pcp_counter_lock); #endif put_online_cpus(); return val; } static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx) { unsigned long val = 0; int cpu; get_online_cpus(); for_each_online_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU spin_lock(&memcg->pcp_counter_lock); val += memcg->nocpu_base.events[idx]; spin_unlock(&memcg->pcp_counter_lock); #endif put_online_cpus(); return val; } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is * counted as CACHE even if it's on ANON LRU. */ if (PageAnon(page)) __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); else __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); if (PageTransHuge(page)) __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_pages); /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]); else { __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]); nr_pages = -nr_pages; /* for event */ } __this_cpu_add(memcg->stat->nr_page_events, nr_pages); } unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_zone *mz; mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); return mz->lru_size[lru]; } static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) { unsigned long nr = 0; int zid; VM_BUG_ON((unsigned)nid >= nr_node_ids); for (zid = 0; zid < MAX_NR_ZONES; zid++) { struct mem_cgroup_per_zone *mz; enum lru_list lru; for_each_lru(lru) { if (!(BIT(lru) & lru_mask)) continue; mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; nr += mz->lru_size[lru]; } } return nr; } static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, unsigned int lru_mask) { unsigned long nr = 0; int nid; for_each_node_state(nid, N_MEMORY) nr += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); return nr; } static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, enum mem_cgroup_events_target target) { unsigned long val, next; val = __this_cpu_read(memcg->stat->nr_page_events); next = __this_cpu_read(memcg->stat->targets[target]); /* from time_after() in jiffies.h */ if ((long)next - (long)val < 0) { switch (target) { case MEM_CGROUP_TARGET_THRESH: next = val + THRESHOLDS_EVENTS_TARGET; break; case MEM_CGROUP_TARGET_SOFTLIMIT: next = val + SOFTLIMIT_EVENTS_TARGET; break; case MEM_CGROUP_TARGET_NUMAINFO: next = val + NUMAINFO_EVENTS_TARGET; break; default: break; } __this_cpu_write(memcg->stat->targets[target], next); return true; } return false; } /* * Check events in order. * */ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) { /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { bool do_softlimit; bool do_numainfo __maybe_unused; do_softlimit = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_SOFTLIMIT); #if MAX_NUMNODES > 1 do_numainfo = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_NUMAINFO); #endif mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) mem_cgroup_update_tree(memcg, page); #if MAX_NUMNODES > 1 if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); #endif } } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) { /* * mm_update_next_owner() may clear mm->owner to NULL * if it races with swapoff, page migration, etc. * So this can be called with p == NULL. */ if (unlikely(!p)) return NULL; return mem_cgroup_from_css(task_css(p, memory_cgrp_id)); } static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg = NULL; rcu_read_lock(); do { /* * Page cache insertions can happen withou an * actual mm context, e.g. during disk probing * on boot, loopback IO, acct() writes etc. */ if (unlikely(!mm)) memcg = root_mem_cgroup; else { memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (unlikely(!memcg)) memcg = root_mem_cgroup; } } while (!css_tryget_online(&memcg->css)); rcu_read_unlock(); return memcg; } /** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root * @prev: previously returned memcg, NULL on first invocation * @reclaim: cookie for shared reclaim walks, NULL for full walks * * Returns references to children of the hierarchy below @root, or * @root itself, or %NULL after a full round-trip. * * Caller must pass the return value in @prev on subsequent * invocations for reference counting, or use mem_cgroup_iter_break() * to cancel a hierarchy walk before the round-trip is complete. * * Reclaimers can specify a zone and a priority level in @reclaim to * divide up the memcgs in the hierarchy among all concurrent * reclaimers operating on the same zone and priority. */ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { struct reclaim_iter *uninitialized_var(iter); struct cgroup_subsys_state *css = NULL; struct mem_cgroup *memcg = NULL; struct mem_cgroup *pos = NULL; if (mem_cgroup_disabled()) return NULL; if (!root) root = root_mem_cgroup; if (prev && !reclaim) pos = prev; if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) goto out; return root; } rcu_read_lock(); if (reclaim) { struct mem_cgroup_per_zone *mz; mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); iter = &mz->iter[reclaim->priority]; if (prev && reclaim->generation != iter->generation) goto out_unlock; do { pos = ACCESS_ONCE(iter->position); /* * A racing update may change the position and * put the last reference, hence css_tryget(), * or retry to see the updated position. */ } while (pos && !css_tryget(&pos->css)); } if (pos) css = &pos->css; for (;;) { css = css_next_descendant_pre(css, &root->css); if (!css) { /* * Reclaimers share the hierarchy walk, and a * new one might jump in right at the end of * the hierarchy - make sure they see at least * one group and restart from the beginning. */ if (!prev) continue; break; } /* * Verify the css and acquire a reference. The root * is provided by the caller, so we know it's alive * and kicking, and don't take an extra reference. */ memcg = mem_cgroup_from_css(css); if (css == &root->css) break; if (css_tryget(css)) { /* * Make sure the memcg is initialized: * mem_cgroup_css_online() orders the the * initialization against setting the flag. */ if (smp_load_acquire(&memcg->initialized)) break; css_put(css); } memcg = NULL; } if (reclaim) { if (cmpxchg(&iter->position, pos, memcg) == pos) { if (memcg) css_get(&memcg->css); if (pos) css_put(&pos->css); } /* * pairs with css_tryget when dereferencing iter->position * above. */ if (pos) css_put(&pos->css); if (!memcg) iter->generation++; else if (!prev) reclaim->generation = iter->generation; } out_unlock: rcu_read_unlock(); out: if (prev && prev != root) css_put(&prev->css); return memcg; } /** * mem_cgroup_iter_break - abort a hierarchy walk prematurely * @root: hierarchy root * @prev: last visited hierarchy member as returned by mem_cgroup_iter() */ void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { if (!root) root = root_mem_cgroup; if (prev && prev != root) css_put(&prev->css); } /* * Iteration constructs for visiting all cgroups (under a tree). If * loops are exited prematurely (break), mem_cgroup_iter_break() must * be used for reference counting. */ #define for_each_mem_cgroup_tree(iter, root) \ for (iter = mem_cgroup_iter(root, NULL, NULL); \ iter != NULL; \ iter = mem_cgroup_iter(root, iter, NULL)) #define for_each_mem_cgroup(iter) \ for (iter = mem_cgroup_iter(NULL, NULL, NULL); \ iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (unlikely(!memcg)) goto out; switch (idx) { case PGFAULT: this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); break; case PGMAJFAULT: this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); break; default: BUG(); } out: rcu_read_unlock(); } EXPORT_SYMBOL(__mem_cgroup_count_vm_event); /** * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg * @zone: zone of the wanted lruvec * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for the given @zone and * @mem. This can be the global zone lruvec, if the memory controller * is disabled. */ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct mem_cgroup *memcg) { struct mem_cgroup_per_zone *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &zone->lruvec; goto out; } mz = mem_cgroup_zone_zoneinfo(memcg, zone); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->zone here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->zone != zone)) lruvec->zone = zone; return lruvec; } /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page * @zone: zone of the page * * This function is only safe when following the LRU page isolation * and putback protocol: the LRU lock must be held, and the page must * either be PageLRU() or the caller must have isolated/allocated it. */ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) { struct mem_cgroup_per_zone *mz; struct mem_cgroup *memcg; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &zone->lruvec; goto out; } memcg = page->mem_cgroup; /* * Swapcache readahead pages are added to the LRU - and * possibly migrated - before they are charged. */ if (!memcg) memcg = root_mem_cgroup; mz = mem_cgroup_page_zoneinfo(memcg, page); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->zone here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->zone != zone)) lruvec->zone = zone; return lruvec; } /** * mem_cgroup_update_lru_size - account for adding or removing an lru page * @lruvec: mem_cgroup per zone lru vector * @lru: index of lru list the page is sitting on * @nr_pages: positive when adding or negative when removing * * This function must be called when a page is added to or removed from an * lru list. */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int nr_pages) { struct mem_cgroup_per_zone *mz; unsigned long *lru_size; if (mem_cgroup_disabled()) return; mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); lru_size = mz->lru_size + lru; *lru_size += nr_pages; VM_BUG_ON((long)(*lru_size) < 0); } bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; if (!root->use_hierarchy) return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; struct task_struct *p; bool ret; p = find_lock_task_mm(task); if (p) { task_memcg = get_mem_cgroup_from_mm(p->mm); task_unlock(p); } else { /* * All threads may have already detached their mm's, but the oom * killer still needs to detect if they have already been oom * killed to prevent needlessly killing additional tasks. */ rcu_read_lock(); task_memcg = mem_cgroup_from_task(task); css_get(&task_memcg->css); rcu_read_unlock(); } ret = mem_cgroup_is_descendant(task_memcg, memcg); css_put(&task_memcg->css); return ret; } int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) { unsigned long inactive_ratio; unsigned long inactive; unsigned long active; unsigned long gb; inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } bool mem_cgroup_lruvec_online(struct lruvec *lruvec) { struct mem_cgroup_per_zone *mz; struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return true; mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); memcg = mz->memcg; return !!(memcg->css.flags & CSS_ONLINE); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup * * Returns the maximum amount of memory @mem can be charged with, in * pages. */ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) { unsigned long margin = 0; unsigned long count; unsigned long limit; count = page_counter_read(&memcg->memory); limit = ACCESS_ONCE(memcg->memory.limit); if (count < limit) margin = limit - count; if (do_swap_account) { count = page_counter_read(&memcg->memsw); limit = ACCESS_ONCE(memcg->memsw.limit); if (count <= limit) margin = min(margin, limit - count); } return margin; } int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; return memcg->swappiness; } /* * A routine for checking "mem" is under move_account() or not. * * Checking a cgroup is mc.from or mc.to or under hierarchy of * moving cgroups. This is for waiting at high-memory pressure * caused by "move". */ static bool mem_cgroup_under_move(struct mem_cgroup *memcg) { struct mem_cgroup *from; struct mem_cgroup *to; bool ret = false; /* * Unlike task_move routines, we access mc.to, mc.from not under * mutual exclusion by cgroup_mutex. Here, we take spinlock instead. */ spin_lock(&mc.lock); from = mc.from; to = mc.to; if (!from) goto unlock; ret = mem_cgroup_is_descendant(from, memcg) || mem_cgroup_is_descendant(to, memcg); unlock: spin_unlock(&mc.lock); return ret; } static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) { if (mc.moving_task && current != mc.moving_task) { if (mem_cgroup_under_move(memcg)) { DEFINE_WAIT(wait); prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); /* moving charge context might have finished. */ if (mc.moving_task) schedule(); finish_wait(&mc.waitq, &wait); return true; } } return false; } #define K(x) ((x) << (PAGE_SHIFT-10)) /** * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller. * @memcg: The memory cgroup that went over limit * @p: Task that is going to be killed * * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is * enabled */ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { /* oom_info_lock ensures that parallel ooms do not interleave */ static DEFINE_MUTEX(oom_info_lock); struct mem_cgroup *iter; unsigned int i; if (!p) return; mutex_lock(&oom_info_lock); rcu_read_lock(); pr_info("Task in "); pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); pr_cont(" killed as a result of limit of "); pr_cont_cgroup_path(memcg->css.cgroup); pr_cont("\n"); rcu_read_unlock(); pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), K((u64)memcg->memory.limit), memcg->memory.failcnt); pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memsw)), K((u64)memcg->memsw.limit), memcg->memsw.failcnt); pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->kmem)), K((u64)memcg->kmem.limit), memcg->kmem.failcnt); for_each_mem_cgroup_tree(iter, memcg) { pr_info("Memory cgroup stats for "); pr_cont_cgroup_path(iter->css.cgroup); pr_cont(":"); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i], K(mem_cgroup_read_stat(iter, i))); } for (i = 0; i < NR_LRU_LISTS; i++) pr_cont(" %s:%luKB", mem_cgroup_lru_names[i], K(mem_cgroup_nr_lru_pages(iter, BIT(i)))); pr_cont("\n"); } mutex_unlock(&oom_info_lock); } /* * This function returns the number of memcg under hierarchy tree. Returns * 1(self count) if no children. */ static int mem_cgroup_count_children(struct mem_cgroup *memcg) { int num = 0; struct mem_cgroup *iter; for_each_mem_cgroup_tree(iter, memcg) num++; return num; } /* * Return the memory (and swap, if configured) limit for a memcg. */ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) { unsigned long limit; limit = memcg->memory.limit; if (mem_cgroup_swappiness(memcg)) { unsigned long memsw_limit; memsw_limit = memcg->memsw.limit; limit = min(limit + total_swap_pages, memsw_limit); } return limit; } static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { struct mem_cgroup *iter; unsigned long chosen_points = 0; unsigned long totalpages; unsigned int points = 0; struct task_struct *chosen = NULL; /* * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ if (fatal_signal_pending(current) || task_will_free_mem(current)) { mark_tsk_oom_victim(current); return; } check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); totalpages = mem_cgroup_get_limit(memcg) ? : 1; for_each_mem_cgroup_tree(iter, memcg) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&iter->css, &it); while ((task = css_task_iter_next(&it))) { switch (oom_scan_process_thread(task, totalpages, NULL, false)) { case OOM_SCAN_SELECT: if (chosen) put_task_struct(chosen); chosen = task; chosen_points = ULONG_MAX; get_task_struct(chosen); /* fall through */ case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: css_task_iter_end(&it); mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); return; case OOM_SCAN_OK: break; }; points = oom_badness(task, memcg, NULL, totalpages); if (!points || points < chosen_points) continue; /* Prefer thread group leaders for display purposes */ if (points == chosen_points && thread_group_leader(chosen)) continue; if (chosen) put_task_struct(chosen); chosen = task; chosen_points = points; get_task_struct(chosen); } css_task_iter_end(&it); } if (!chosen) return; points = chosen_points * 1000 / totalpages; oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, NULL, "Memory cgroup out of memory"); } #if MAX_NUMNODES > 1 /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg * @nid: the node ID to be checked. * @noswap : specify true here if the user wants flle only information. * * This function returns whether the specified memcg contains any * reclaimable pages on a node. Returns true if there are any reclaimable * pages in the node. */ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, int nid, bool noswap) { if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE)) return true; if (noswap || !total_swap_pages) return false; if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON)) return true; return false; } /* * Always updating the nodemask is not very good - even if we have an empty * list or the wrong list here, we can start from some node and traverse all * nodes based on the zonelist. So update the list loosely once per 10 secs. * */ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg) { int nid; /* * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET * pagein/pageout changes since the last update. */ if (!atomic_read(&memcg->numainfo_events)) return; if (atomic_inc_return(&memcg->numainfo_updating) > 1) return; /* make a nodemask where this memcg uses memory from */ memcg->scan_nodes = node_states[N_MEMORY]; for_each_node_mask(nid, node_states[N_MEMORY]) { if (!test_mem_cgroup_node_reclaimable(memcg, nid, false)) node_clear(nid, memcg->scan_nodes); } atomic_set(&memcg->numainfo_events, 0); atomic_set(&memcg->numainfo_updating, 0); } /* * Selecting a node where we start reclaim from. Because what we need is just * reducing usage counter, start from anywhere is O,K. Considering * memory reclaim from current node, there are pros. and cons. * * Freeing memory from current node means freeing memory from a node which * we'll use or we've used. So, it may make LRU bad. And if several threads * hit limits, it will see a contention on a node. But freeing from remote * node means more costs for memory reclaim because of memory latency. * * Now, we use round-robin. Better algorithm is welcomed. */ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { int node; mem_cgroup_may_update_nodemask(memcg); node = memcg->last_scanned_node; node = next_node(node, memcg->scan_nodes); if (node == MAX_NUMNODES) node = first_node(memcg->scan_nodes); /* * We call this when we hit limit, not when pages are added to LRU. * No LRU may hold pages because all pages are UNEVICTABLE or * memcg is too small and all pages are not on LRU. In that case, * we use curret node. */ if (unlikely(node == MAX_NUMNODES)) node = numa_node_id(); memcg->last_scanned_node = node; return node; } #else int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } #endif static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, struct zone *zone, gfp_t gfp_mask, unsigned long *total_scanned) { struct mem_cgroup *victim = NULL; int total = 0; int loop = 0; unsigned long excess; unsigned long nr_scanned; struct mem_cgroup_reclaim_cookie reclaim = { .zone = zone, .priority = 0, }; excess = soft_limit_excess(root_memcg); while (1) { victim = mem_cgroup_iter(root_memcg, victim, &reclaim); if (!victim) { loop++; if (loop >= 2) { /* * If we have not been able to reclaim * anything, it might because there are * no reclaimable pages under this hierarchy */ if (!total) break; /* * We want to do more targeted reclaim. * excess >> 2 is not to excessive so as to * reclaim too much, nor too less that we keep * coming back to reclaim from this cgroup */ if (total >= (excess >> 2) || (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) break; } continue; } total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, zone, &nr_scanned); *total_scanned += nr_scanned; if (!soft_limit_excess(root_memcg)) break; } mem_cgroup_iter_break(root_memcg, victim); return total; } #ifdef CONFIG_LOCKDEP static struct lockdep_map memcg_oom_lock_dep_map = { .name = "memcg_oom_lock", }; #endif static DEFINE_SPINLOCK(memcg_oom_lock); /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. */ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) { struct mem_cgroup *iter, *failed = NULL; spin_lock(&memcg_oom_lock); for_each_mem_cgroup_tree(iter, memcg) { if (iter->oom_lock) { /* * this subtree of our hierarchy is already locked * so we cannot give a lock. */ failed = iter; mem_cgroup_iter_break(memcg, iter); break; } else iter->oom_lock = true; } if (failed) { /* * OK, we failed to lock the whole subtree so we have * to clean up what we set up to the failing subtree */ for_each_mem_cgroup_tree(iter, memcg) { if (iter == failed) { mem_cgroup_iter_break(memcg, iter); break; } iter->oom_lock = false; } } else mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); spin_unlock(&memcg_oom_lock); return !failed; } static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) { struct mem_cgroup *iter; spin_lock(&memcg_oom_lock); mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; spin_unlock(&memcg_oom_lock); } static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) { struct mem_cgroup *iter; for_each_mem_cgroup_tree(iter, memcg) atomic_inc(&iter->under_oom); } static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) { struct mem_cgroup *iter; /* * When a new child is created while the hierarchy is under oom, * mem_cgroup_oom_lock() may not be called. We have to use * atomic_add_unless() here. */ for_each_mem_cgroup_tree(iter, memcg) atomic_add_unless(&iter->under_oom, -1, 0); } static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { struct mem_cgroup *memcg; wait_queue_t wait; }; static int memcg_oom_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) { struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; struct mem_cgroup *oom_wait_memcg; struct oom_wait_info *oom_wait_info; oom_wait_info = container_of(wait, struct oom_wait_info, wait); oom_wait_memcg = oom_wait_info->memcg; if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) && !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg)) return 0; return autoremove_wake_function(wait, mode, sync, arg); } static void memcg_wakeup_oom(struct mem_cgroup *memcg) { atomic_inc(&memcg->oom_wakeups); /* for filtering, pass "memcg" as argument. */ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } static void memcg_oom_recover(struct mem_cgroup *memcg) { if (memcg && atomic_read(&memcg->under_oom)) memcg_wakeup_oom(memcg); } static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { if (!current->memcg_oom.may_oom) return; /* * We are in the middle of the charge context here, so we * don't want to block when potentially sitting on a callstack * that holds all kinds of filesystem and mm locks. * * Also, the caller may handle a failed allocation gracefully * (like optional page cache readahead) and so an OOM killer * invocation might not even be necessary. * * That's why we don't do anything here except remember the * OOM context and then deal with it at the end of the page * fault when the stack is unwound, the locks are released, * and when we know whether the fault was overall successful. */ css_get(&memcg->css); current->memcg_oom.memcg = memcg; current->memcg_oom.gfp_mask = mask; current->memcg_oom.order = order; } /** * mem_cgroup_oom_synchronize - complete memcg OOM handling * @handle: actually kill/wait or just clean up the OOM state * * This has to be called at the end of a page fault if the memcg OOM * handler was enabled. * * Memcg supports userspace OOM handling where failed allocations must * sleep on a waitqueue until the userspace task resolves the * situation. Sleeping directly in the charge context with all kinds * of locks held is not a good idea, instead we remember an OOM state * in the task and mem_cgroup_oom_synchronize() has to be called at * the end of the page fault to complete the OOM handling. * * Returns %true if an ongoing memcg OOM situation was detected and * completed, %false otherwise. */ bool mem_cgroup_oom_synchronize(bool handle) { struct mem_cgroup *memcg = current->memcg_oom.memcg; struct oom_wait_info owait; bool locked; /* OOM is global, do not handle */ if (!memcg) return false; if (!handle || oom_killer_disabled) goto cleanup; owait.memcg = memcg; owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; INIT_LIST_HEAD(&owait.wait.task_list); prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); mem_cgroup_mark_under_oom(memcg); locked = mem_cgroup_oom_trylock(memcg); if (locked) mem_cgroup_oom_notify(memcg); if (locked && !memcg->oom_kill_disable) { mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask, current->memcg_oom.order); } else { schedule(); mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); } if (locked) { mem_cgroup_oom_unlock(memcg); /* * There is no guarantee that an OOM-lock contender * sees the wakeups triggered by the OOM kill * uncharges. Wake any sleepers explicitely. */ memcg_oom_recover(memcg); } cleanup: current->memcg_oom.memcg = NULL; css_put(&memcg->css); return true; } /** * mem_cgroup_begin_page_stat - begin a page state statistics transaction * @page: page that is going to change accounted state * * This function must mark the beginning of an accounted page state * change to prevent double accounting when the page is concurrently * being moved to another memcg: * * memcg = mem_cgroup_begin_page_stat(page); * if (TestClearPageState(page)) * mem_cgroup_update_page_stat(memcg, state, -1); * mem_cgroup_end_page_stat(memcg); */ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { struct mem_cgroup *memcg; unsigned long flags; /* * The RCU lock is held throughout the transaction. The fast * path can get away without acquiring the memcg->move_lock * because page moving starts with an RCU grace period. * * The RCU lock also protects the memcg from being freed when * the page state that is going to change is the only thing * preventing the page from being uncharged. * E.g. end-writeback clearing PageWriteback(), which allows * migration to go ahead and uncharge the page before the * account transaction might be complete. */ rcu_read_lock(); if (mem_cgroup_disabled()) return NULL; again: memcg = page->mem_cgroup; if (unlikely(!memcg)) return NULL; if (atomic_read(&memcg->moving_account) <= 0) return memcg; spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page->mem_cgroup) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } /* * When charge migration first begins, we can have locked and * unlocked page stat updates happening concurrently. Track * the task who has the lock for mem_cgroup_end_page_stat(). */ memcg->move_lock_task = current; memcg->move_lock_flags = flags; return memcg; } /** * mem_cgroup_end_page_stat - finish a page state statistics transaction * @memcg: the memcg that was accounted against */ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; memcg->move_lock_task = NULL; memcg->move_lock_flags = 0; spin_unlock_irqrestore(&memcg->move_lock, flags); } rcu_read_unlock(); } /** * mem_cgroup_update_page_stat - update page state statistics * @memcg: memcg to account against * @idx: page state item to account * @val: number of pages (positive or negative) * * See mem_cgroup_begin_page_stat() for locking requirements. */ void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val) { VM_BUG_ON(!rcu_read_lock_held()); if (memcg) this_cpu_add(memcg->stat->count[idx], val); } /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define CHARGE_BATCH 32U struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; struct work_struct work; unsigned long flags; #define FLUSHING_CACHED_CHARGE 0 }; static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); static DEFINE_MUTEX(percpu_charge_mutex); /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. * @nr_pages: how many pages to charge. * * The charges will only happen if @memcg matches the current cpu's memcg * stock, and at least @nr_pages are available in that stock. Failure to * service an allocation will refill the stock. * * returns true if successful, false otherwise. */ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { struct memcg_stock_pcp *stock; bool ret = false; if (nr_pages > CHARGE_BATCH) return ret; stock = &get_cpu_var(memcg_stock); if (memcg == stock->cached && stock->nr_pages >= nr_pages) { stock->nr_pages -= nr_pages; ret = true; } put_cpu_var(memcg_stock); return ret; } /* * Returns stocks cached in percpu and reset cached information. */ static void drain_stock(struct memcg_stock_pcp *stock) { struct mem_cgroup *old = stock->cached; if (stock->nr_pages) { page_counter_uncharge(&old->memory, stock->nr_pages); if (do_swap_account) page_counter_uncharge(&old->memsw, stock->nr_pages); css_put_many(&old->css, stock->nr_pages); stock->nr_pages = 0; } stock->cached = NULL; } /* * This must be called under preempt disabled or must be called by * a thread which is pinned to local cpu. */ static void drain_local_stock(struct work_struct *dummy) { struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } /* * Cache charges(val) to local per_cpu area. * This will be consumed by consume_stock() function, later. */ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); if (stock->cached != memcg) { /* reset if necessary */ drain_stock(stock); stock->cached = memcg; } stock->nr_pages += nr_pages; put_cpu_var(memcg_stock); } /* * Drains all per-CPU charge caches for given root_memcg resp. subtree * of the hierarchy under it. */ static void drain_all_stock(struct mem_cgroup *root_memcg) { int cpu, curcpu; /* If someone's already draining, avoid adding running more workers. */ if (!mutex_trylock(&percpu_charge_mutex)) return; /* Notify other cpus that system-wide "drain" is running */ get_online_cpus(); curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; memcg = stock->cached; if (!memcg || !stock->nr_pages) continue; if (!mem_cgroup_is_descendant(memcg, root_memcg)) continue; if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); else schedule_work_on(cpu, &stock->work); } } put_cpu(); put_online_cpus(); mutex_unlock(&percpu_charge_mutex); } /* * This function drains percpu counter value from DEAD cpu and * move it to local cpu. Note that this function can be preempted. */ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) { int i; spin_lock(&memcg->pcp_counter_lock); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { long x = per_cpu(memcg->stat->count[i], cpu); per_cpu(memcg->stat->count[i], cpu) = 0; memcg->nocpu_base.count[i] += x; } for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) { unsigned long x = per_cpu(memcg->stat->events[i], cpu); per_cpu(memcg->stat->events[i], cpu) = 0; memcg->nocpu_base.events[i] += x; } spin_unlock(&memcg->pcp_counter_lock); } static int memcg_cpu_hotplug_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { int cpu = (unsigned long)hcpu; struct memcg_stock_pcp *stock; struct mem_cgroup *iter; if (action == CPU_ONLINE) return NOTIFY_OK; if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; for_each_mem_cgroup(iter) mem_cgroup_drain_pcp_counter(iter, cpu); stock = &per_cpu(memcg_stock, cpu); drain_stock(stock); return NOTIFY_OK; } static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int nr_pages) { unsigned int batch = max(CHARGE_BATCH, nr_pages); int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup *mem_over_limit; struct page_counter *counter; unsigned long nr_reclaimed; bool may_swap = true; bool drained = false; int ret = 0; if (mem_cgroup_is_root(memcg)) goto done; retry: if (consume_stock(memcg, nr_pages)) goto done; if (!do_swap_account || !page_counter_try_charge(&memcg->memsw, batch, &counter)) { if (!page_counter_try_charge(&memcg->memory, batch, &counter)) goto done_restock; if (do_swap_account) page_counter_uncharge(&memcg->memsw, batch); mem_over_limit = mem_cgroup_from_counter(counter, memory); } else { mem_over_limit = mem_cgroup_from_counter(counter, memsw); may_swap = false; } if (batch > nr_pages) { batch = nr_pages; goto retry; } /* * Unlike in global OOM situations, memcg is not in a physical * memory shortage. Allow dying and OOM-killed tasks to * bypass the last charges so that they can exit quickly and * free their memory. */ if (unlikely(test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current) || current->flags & PF_EXITING)) goto bypass; if (unlikely(task_in_memcg_oom(current))) goto nomem; if (!(gfp_mask & __GFP_WAIT)) goto nomem; mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) goto retry; if (!drained) { drain_all_stock(mem_over_limit); drained = true; goto retry; } if (gfp_mask & __GFP_NORETRY) goto nomem; /* * Even though the limit is exceeded at this point, reclaim * may have been able to free some pages. Retry the charge * before killing the task. * * Only for regular pages, though: huge pages are rather * unlikely to succeed so close to the limit, and we fall back * to regular pages anyway in case of failure. */ if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) goto retry; /* * At task move, charge accounts can be doubly counted. So, it's * better to wait until the end of task_move if something is going on. */ if (mem_cgroup_wait_acct_move(mem_over_limit)) goto retry; if (nr_retries--) goto retry; if (gfp_mask & __GFP_NOFAIL) goto bypass; if (fatal_signal_pending(current)) goto bypass; mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages)); nomem: if (!(gfp_mask & __GFP_NOFAIL)) return -ENOMEM; bypass: return -EINTR; done_restock: css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); /* * If the hierarchy is above the normal consumption range, * make the charging task trim their excess contribution. */ do { if (page_counter_read(&memcg->memory) <= memcg->high) continue; mem_cgroup_events(memcg, MEMCG_HIGH, 1); try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); } while ((memcg = parent_mem_cgroup(memcg))); done: return ret; } static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) return; page_counter_uncharge(&memcg->memory, nr_pages); if (do_swap_account) page_counter_uncharge(&memcg->memsw, nr_pages); css_put_many(&memcg->css, nr_pages); } /* * A helper function to get mem_cgroup from ID. must be called under * rcu_read_lock(). The caller is responsible for calling * css_tryget_online() if the mem_cgroup is used for charging. (dropping * refcnt from swap can be called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { /* ID 0 is unused ID */ if (!id) return NULL; return mem_cgroup_from_id(id); } /* * try_get_mem_cgroup_from_page - look up page's memcg association * @page: the page * * Look up, get a css reference, and return the memcg that owns @page. * * The page must be locked to prevent racing with swap-in and page * cache charges. If coming from an unlocked page table, the caller * must ensure the page is on the LRU or this can race with charging. */ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) { struct mem_cgroup *memcg; unsigned short id; swp_entry_t ent; VM_BUG_ON_PAGE(!PageLocked(page), page); memcg = page->mem_cgroup; if (memcg) { if (!css_tryget_online(&memcg->css)) memcg = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_lookup(id); if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); } return memcg; } static void lock_page_lru(struct page *page, int *isolated) { struct zone *zone = page_zone(page); spin_lock_irq(&zone->lru_lock); if (PageLRU(page)) { struct lruvec *lruvec; lruvec = mem_cgroup_page_lruvec(page, zone); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_lru(page)); *isolated = 1; } else *isolated = 0; } static void unlock_page_lru(struct page *page, int isolated) { struct zone *zone = page_zone(page); if (isolated) { struct lruvec *lruvec; lruvec = mem_cgroup_page_lruvec(page, zone); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } spin_unlock_irq(&zone->lru_lock); } static void commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare) { int isolated; VM_BUG_ON_PAGE(page->mem_cgroup, page); /* * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page * may already be on some other mem_cgroup's LRU. Take care of it. */ if (lrucare) lock_page_lru(page, &isolated); /* * Nobody should be changing or seriously looking at * page->mem_cgroup at this point: * * - the page is uncharged * * - the page is off-LRU * * - an anonymous fault has exclusive page access, except for * a locked page table * * - a page cache insertion, a swapin fault, or a migration * have the page locked */ page->mem_cgroup = memcg; if (lrucare) unlock_page_lru(page, isolated); } #ifdef CONFIG_MEMCG_KMEM int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, unsigned long nr_pages) { struct page_counter *counter; int ret = 0; ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter); if (ret < 0) return ret; ret = try_charge(memcg, gfp, nr_pages); if (ret == -EINTR) { /* * try_charge() chose to bypass to root due to OOM kill or * fatal signal. Since our on