X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=c8569bc298ffc77c5a2627b5a4d2fd2a42b91742;hb=e17ab5cbed795d3823da830f5e8d3ffe25a38446;hp=8ffec674c5acc6904a53c45c55deefc816ac8233;hpb=ec64f51545fffbc4cb968f0cea56341a4b07e85a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8ffec67..c8569bc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6,6 +6,10 @@ * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov * + * Memory thresholds + * Copyright (C) 2009 Nokia Corporation + * Author: Kirill A. Shutemov + * * 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 @@ -21,37 +25,53 @@ #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 struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +struct mem_cgroup *root_mem_cgroup __read_mostly; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP -/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */ +/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; static int really_do_swap_account __initdata = 1; /* for remember boot option*/ #else #define do_swap_account (0) #endif -static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */ +/* + * Per memcg event counter is incremented at every pagein/pageout. This counter + * is used for trigger some periodic events. This is straightforward and better + * than using jiffies etc. to handle periodic memcg event. + * + * These values will be used as !((event) & ((1 <<(thresh)) - 1)) + */ +#define THRESHOLDS_EVENTS_THRESH (7) /* once in 128 */ +#define SOFTLIMIT_EVENTS_THRESH (10) /* once in 1024 */ /* * Statistics for memory cgroup. @@ -61,41 +81,21 @@ enum mem_cgroup_stat_index { * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. */ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */ + MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ + MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ + MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ + MEM_CGROUP_EVENTS, /* incremented at every pagein/pageout */ MEM_CGROUP_STAT_NSTATS, }; struct mem_cgroup_stat_cpu { s64 count[MEM_CGROUP_STAT_NSTATS]; -} ____cacheline_aligned_in_smp; - -struct mem_cgroup_stat { - struct mem_cgroup_stat_cpu cpustat[0]; }; /* - * For accounting under irq disable, no need for increment preempt count. - */ -static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat, - enum mem_cgroup_stat_index idx, int val) -{ - stat->count[idx] += val; -} - -static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat, - enum mem_cgroup_stat_index idx) -{ - int cpu; - s64 ret = 0; - for_each_possible_cpu(cpu) - ret += stat->cpustat[cpu].count[idx]; - return ret; -} - -/* * per-zone information in memory controller. */ struct mem_cgroup_per_zone { @@ -106,6 +106,12 @@ struct mem_cgroup_per_zone { unsigned long count[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; + struct rb_node tree_node; /* RB tree node */ + unsigned long long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *mem; /* Back pointer, we cannot */ + /* use container_of */ }; /* Macro for accessing counter */ #define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) @@ -119,6 +125,42 @@ struct mem_cgroup_lru_info { }; /* + * 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; + u64 threshold; +}; + +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below usage. */ + atomic_t current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +static void mem_cgroup_threshold(struct mem_cgroup *mem); + +/* * 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, @@ -153,31 +195,80 @@ struct mem_cgroup { int prev_priority; /* for recording reclaim priority */ /* - * While reclaiming in a hiearchy, we cache the last child we - * reclaimed from. Protected by hierarchy_mutex + * While reclaiming in a hierarchy, we cache the last child we + * reclaimed from. */ - struct mem_cgroup *last_scanned_child; + int last_scanned_child; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; - unsigned long last_oom_jiffies; + atomic_t oom_lock; atomic_t refcnt; unsigned int swappiness; + /* set when res.limit == memsw.limit */ + bool memsw_is_minimum; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_threshold_ary *thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_threshold_ary *memsw_thresholds; + /* - * statistics. This must be placed at the end of memcg. + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? */ - struct mem_cgroup_stat stat; + unsigned long move_charge_at_immigrate; + + /* + * percpu counter. + */ + struct mem_cgroup_stat_cpu *stat; +}; + +/* Stuffs for move charges at task migration. */ +/* + * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a + * left-shifted bitmap of these types. + */ +enum move_type { + MOVE_CHARGE_TYPE_ANON, /* private anonymous page and swap of it */ + NR_MOVE_TYPE, +}; + +/* "mc" and its members are protected by cgroup_mutex */ +static struct move_charge_struct { + struct mem_cgroup *from; + struct mem_cgroup *to; + 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 = { + .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_MAPPED, MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ + MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, }; @@ -185,13 +276,8 @@ enum charge_type { #define PCGF_CACHE (1UL << PCG_CACHE) #define PCGF_USED (1UL << PCG_USED) #define PCGF_LOCK (1UL << PCG_LOCK) -static const unsigned long -pcg_default_flags[NR_CHARGE_TYPE] = { - PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */ - PCGF_USED | PCGF_LOCK, /* Anon */ - PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */ - 0, /* FORCE */ -}; +/* Not used, but added here for completeness */ +#define PCGF_ACCT (1UL << PCG_ACCT) /* for encoding cft->private value on file */ #define _MEM (0) @@ -200,33 +286,20 @@ pcg_default_flags[NR_CHARGE_TYPE] = { #define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) +/* + * Reclaim flags for mem_cgroup_hierarchical_reclaim + */ +#define MEM_CGROUP_RECLAIM_NOSWAP_BIT 0x0 +#define MEM_CGROUP_RECLAIM_NOSWAP (1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT) +#define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 +#define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) +#define MEM_CGROUP_RECLAIM_SOFT_BIT 0x2 +#define MEM_CGROUP_RECLAIM_SOFT (1 << MEM_CGROUP_RECLAIM_SOFT_BIT) + static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); - -static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, - struct page_cgroup *pc, - bool charge) -{ - int val = (charge)? 1 : -1; - struct mem_cgroup_stat *stat = &mem->stat; - struct mem_cgroup_stat_cpu *cpustat; - int cpu = get_cpu(); - - cpustat = &stat->cpustat[cpu]; - if (PageCgroupCache(pc)) - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val); - else - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val); - - if (charge) - __mem_cgroup_stat_add_safe(cpustat, - MEM_CGROUP_STAT_PGPGIN_COUNT, 1); - else - __mem_cgroup_stat_add_safe(cpustat, - MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); - put_cpu(); -} +static void drain_all_stock_async(void); static struct mem_cgroup_per_zone * mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) @@ -234,6 +307,11 @@ mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) return &mem->info.nodeinfo[nid]->zoneinfo[zid]; } +struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem) +{ + return &mem->css; +} + static struct mem_cgroup_per_zone * page_cgroup_zoneinfo(struct page_cgroup *pc) { @@ -247,7 +325,219 @@ page_cgroup_zoneinfo(struct page_cgroup *pc) return mem_cgroup_zoneinfo(mem, nid, zid); } -static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem, +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 *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long 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 *mem, + 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 *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + __mem_cgroup_remove_exceeded(mem, mz, mctz); + spin_unlock(&mctz->lock); +} + + +static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) +{ + unsigned long long excess; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + int nid = page_to_nid(page); + int zid = page_zonenum(page); + mctz = soft_limit_tree_from_page(page); + + /* + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. + */ + for (; mem; mem = parent_mem_cgroup(mem)) { + mz = mem_cgroup_zoneinfo(mem, nid, zid); + excess = res_counter_soft_limit_excess(&mem->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(mem, mz, mctz); + /* + * Insert again. mz->usage_in_excess will be updated. + * If excess is 0, no tree ops. + */ + __mem_cgroup_insert_exceeded(mem, mz, mctz, excess); + spin_unlock(&mctz->lock); + } + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) +{ + int node, zone; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + for_each_node_state(node, N_POSSIBLE) { + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = mem_cgroup_zoneinfo(mem, node, zone); + mctz = soft_limit_tree_node_zone(node, zone); + mem_cgroup_remove_exceeded(mem, mz, mctz); + } + } +} + +static inline unsigned long mem_cgroup_get_excess(struct mem_cgroup *mem) +{ + return res_counter_soft_limit_excess(&mem->res) >> PAGE_SHIFT; +} + +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->mem, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->mem->res) || + !css_tryget(&mz->mem->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(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock(&mctz->lock); + return mz; +} + +static s64 mem_cgroup_read_stat(struct mem_cgroup *mem, + enum mem_cgroup_stat_index idx) +{ + int cpu; + s64 val = 0; + + for_each_possible_cpu(cpu) + val += per_cpu(mem->stat->count[idx], cpu); + return val; +} + +static s64 mem_cgroup_local_usage(struct mem_cgroup *mem) +{ + s64 ret; + + ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); + ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); + return ret; +} + +static void mem_cgroup_swap_statistics(struct mem_cgroup *mem, + bool charge) +{ + int val = (charge) ? 1 : -1; + this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); +} + +static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, + struct page_cgroup *pc, + bool charge) +{ + int val = (charge) ? 1 : -1; + + preempt_disable(); + + if (PageCgroupCache(pc)) + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], val); + else + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], val); + + if (charge) + __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]); + else + __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]); + __this_cpu_inc(mem->stat->count[MEM_CGROUP_EVENTS]); + + preempt_enable(); +} + +static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, enum lru_list idx) { int nid, zid; @@ -262,6 +552,29 @@ static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem, return total; } +static bool __memcg_event_check(struct mem_cgroup *mem, int event_mask_shift) +{ + s64 val; + + val = this_cpu_read(mem->stat->count[MEM_CGROUP_EVENTS]); + + return !(val & ((1 << event_mask_shift) - 1)); +} + +/* + * Check events in order. + * + */ +static void memcg_check_events(struct mem_cgroup *mem, struct page *page) +{ + /* threshold event is triggered in finer grain than soft limit */ + if (unlikely(__memcg_event_check(mem, THRESHOLDS_EVENTS_THRESH))) { + mem_cgroup_threshold(mem); + if (unlikely(__memcg_event_check(mem, SOFTLIMIT_EVENTS_THRESH))) + mem_cgroup_update_tree(mem, page); + } +} + static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { return container_of(cgroup_subsys_state(cont, @@ -286,6 +599,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *mem = NULL; + + if (!mm) + return NULL; /* * Because we have no locks, mm->owner's may be being moved to other * cgroup. We use css_tryget() here even if this looks @@ -301,11 +617,44 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return mem; } -static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem) +/* + * Call callback function against all cgroup under hierarchy tree. + */ +static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data, + int (*func)(struct mem_cgroup *, void *)) { - if (!mem) - return true; - return css_is_removed(&mem->css); + int found, ret, nextid; + struct cgroup_subsys_state *css; + struct mem_cgroup *mem; + + if (!root->use_hierarchy) + return (*func)(root, data); + + nextid = 1; + do { + ret = 0; + mem = NULL; + + rcu_read_lock(); + css = css_get_next(&mem_cgroup_subsys, nextid, &root->css, + &found); + if (css && css_tryget(css)) + mem = container_of(css, struct mem_cgroup, css); + rcu_read_unlock(); + + if (mem) { + ret = (*func)(mem, data); + css_put(&mem->css); + } + nextid = found + 1; + } while (!ret && css); + + return ret; +} + +static inline bool mem_cgroup_is_root(struct mem_cgroup *mem) +{ + return (mem == root_mem_cgroup); } /* @@ -325,22 +674,24 @@ static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem) void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru) { struct page_cgroup *pc; - struct mem_cgroup *mem; struct mem_cgroup_per_zone *mz; if (mem_cgroup_disabled()) return; pc = lookup_page_cgroup(page); /* can happen while we handle swapcache. */ - if (list_empty(&pc->lru) || !pc->mem_cgroup) + if (!TestClearPageCgroupAcctLRU(pc)) return; + VM_BUG_ON(!pc->mem_cgroup); /* * We don't check PCG_USED bit. It's cleared when the "page" is finally * removed from global LRU. */ mz = page_cgroup_zoneinfo(pc); - mem = pc->mem_cgroup; MEM_CGROUP_ZSTAT(mz, lru) -= 1; + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; + VM_BUG_ON(list_empty(&pc->lru)); list_del_init(&pc->lru); return; } @@ -364,8 +715,8 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru) * For making pc->mem_cgroup visible, insert smp_rmb() here. */ smp_rmb(); - /* unused page is not rotated. */ - if (!PageCgroupUsed(pc)) + /* unused or root page is not rotated. */ + if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) return; mz = page_cgroup_zoneinfo(pc); list_move(&pc->lru, &mz->lists[lru]); @@ -379,6 +730,7 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) if (mem_cgroup_disabled()) return; pc = lookup_page_cgroup(page); + VM_BUG_ON(PageCgroupAcctLRU(pc)); /* * Used bit is set without atomic ops but after smp_wmb(). * For making pc->mem_cgroup visible, insert smp_rmb() here. @@ -389,6 +741,9 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) mz = page_cgroup_zoneinfo(pc); MEM_CGROUP_ZSTAT(mz, lru) += 1; + SetPageCgroupAcctLRU(pc); + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; list_add(&pc->lru, &mz->lists[lru]); } @@ -423,7 +778,7 @@ static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page) spin_lock_irqsave(&zone->lru_lock, flags); /* link when the page is linked to LRU but page_cgroup isn't */ - if (PageLRU(page) && list_empty(&pc->lru)) + if (PageLRU(page) && !PageCgroupAcctLRU(pc)) mem_cgroup_add_lru_list(page, page_lru(page)); spin_unlock_irqrestore(&zone->lru_lock, flags); } @@ -441,28 +796,27 @@ void mem_cgroup_move_lists(struct page *page, int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) { int ret; + struct mem_cgroup *curr = NULL; task_lock(task); - ret = task->mm && mm_match_cgroup(task->mm, mem); + rcu_read_lock(); + curr = try_get_mem_cgroup_from_mm(task->mm); + rcu_read_unlock(); task_unlock(task); - return ret; -} - -/* - * Calculate mapped_ratio under memory controller. This will be used in - * vmscan.c for deteremining we have to reclaim mapped pages. - */ -int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) -{ - long total, rss; - + if (!curr) + return 0; /* - * usage is recorded in bytes. But, here, we assume the number of - * physical pages can be represented by "long" on any arch. + * We should check use_hierarchy of "mem" not "curr". Because checking + * use_hierarchy of "curr" here make this function true if hierarchy is + * enabled in "curr" and "curr" is a child of "mem" in *cgroup* + * hierarchy(even if use_hierarchy is disabled in "mem"). */ - total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L; - rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); - return (int)((rss * 100L) / total); + if (mem->use_hierarchy) + ret = css_is_ancestor(&curr->css, &mem->css); + else + ret = (curr == mem); + css_put(&curr->css); + return ret; } /* @@ -501,8 +855,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_ unsigned long gb; unsigned long inactive_ratio; - inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON); - active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON); + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) @@ -536,6 +890,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) return 0; } +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) +{ + unsigned long active; + unsigned long inactive; + + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE); + + return (active > inactive); +} + unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, enum lru_list lru) @@ -598,7 +963,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, int nid = z->zone_pgdat->node_id; int zid = zone_idx(z); struct mem_cgroup_per_zone *mz; - int lru = LRU_FILE * !!file + !!active; + int lru = LRU_FILE * file + active; + int ret; BUG_ON(!mem_cont); mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); @@ -616,9 +982,19 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, continue; scan++; - if (__isolate_lru_page(page, mode, file) == 0) { + ret = __isolate_lru_page(page, mode, file); + switch (ret) { + case 0: list_move(&page->lru, dst); + mem_cgroup_del_lru(page); nr_taken++; + break; + case -EBUSY: + /* we don't affect global LRU but rotate in our LRU */ + mem_cgroup_rotate_lru_list(page, page_lru(page)); + break; + default: + break; } } @@ -629,207 +1005,525 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, #define mem_cgroup_from_res_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) -/* - * This routine finds the DFS walk successor. This routine should be - * called with hierarchy_mutex held - */ -static struct mem_cgroup * -__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem) +static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) { - struct cgroup *cgroup, *curr_cgroup, *root_cgroup; - - curr_cgroup = curr->css.cgroup; - root_cgroup = root_mem->css.cgroup; + if (do_swap_account) { + if (res_counter_check_under_limit(&mem->res) && + res_counter_check_under_limit(&mem->memsw)) + return true; + } else + if (res_counter_check_under_limit(&mem->res)) + return true; + return false; +} - if (!list_empty(&curr_cgroup->children)) { - /* - * Walk down to children - */ - cgroup = list_entry(curr_cgroup->children.next, - struct cgroup, sibling); - curr = mem_cgroup_from_cont(cgroup); - goto done; - } +static unsigned int get_swappiness(struct mem_cgroup *memcg) +{ + struct cgroup *cgrp = memcg->css.cgroup; + unsigned int swappiness; -visit_parent: - if (curr_cgroup == root_cgroup) { - /* caller handles NULL case */ - curr = NULL; - goto done; - } + /* root ? */ + if (cgrp->parent == NULL) + return vm_swappiness; - /* - * Goto next sibling - */ - if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) { - cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup, - sibling); - curr = mem_cgroup_from_cont(cgroup); - goto done; - } + spin_lock(&memcg->reclaim_param_lock); + swappiness = memcg->swappiness; + spin_unlock(&memcg->reclaim_param_lock); - /* - * Go up to next parent and next parent's sibling if need be - */ - curr_cgroup = curr_cgroup->parent; - goto visit_parent; + return swappiness; +} -done: - return curr; +static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) +{ + int *val = data; + (*val)++; + return 0; } -/* - * Visit the first child (need not be the first child as per the ordering - * of the cgroup list, since we track last_scanned_child) of @mem and use - * that to reclaim free pages from. +/** + * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode. + * @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 */ -static struct mem_cgroup * -mem_cgroup_get_next_node(struct mem_cgroup *root_mem) +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { - struct cgroup *cgroup; - struct mem_cgroup *orig, *next; - bool obsolete; - + struct cgroup *task_cgrp; + struct cgroup *mem_cgrp; /* - * Scan all children under the mem_cgroup mem + * Need a buffer in BSS, can't rely on allocations. The code relies + * on the assumption that OOM is serialized for memory controller. + * If this assumption is broken, revisit this code. */ - mutex_lock(&mem_cgroup_subsys.hierarchy_mutex); + static char memcg_name[PATH_MAX]; + int ret; + + if (!memcg || !p) + return; + - orig = root_mem->last_scanned_child; - obsolete = mem_cgroup_is_obsolete(orig); + rcu_read_lock(); + + mem_cgrp = memcg->css.cgroup; + task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); - if (list_empty(&root_mem->css.cgroup->children)) { + ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { /* - * root_mem might have children before and last_scanned_child - * may point to one of them. We put it later. + * Unfortunately, we are unable to convert to a useful name + * But we'll still print out the usage information */ - if (orig) - VM_BUG_ON(!obsolete); - next = NULL; + rcu_read_unlock(); goto done; } + rcu_read_unlock(); - if (!orig || obsolete) { - cgroup = list_first_entry(&root_mem->css.cgroup->children, - struct cgroup, sibling); - next = mem_cgroup_from_cont(cgroup); - } else - next = __mem_cgroup_get_next_node(orig, root_mem); + printk(KERN_INFO "Task in %s killed", memcg_name); + rcu_read_lock(); + ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + /* + * Continues from above, so we don't need an KERN_ level + */ + printk(KERN_CONT " as a result of limit of %s\n", memcg_name); done: - if (next) - mem_cgroup_get(next); - root_mem->last_scanned_child = next; - if (orig) - mem_cgroup_put(orig); - mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex); - return (next) ? next : root_mem; + + printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->res, RES_FAILCNT)); + printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " + "failcnt %llu\n", + res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); } -static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) +/* + * 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 *mem) { - if (do_swap_account) { - if (res_counter_check_under_limit(&mem->res) && - res_counter_check_under_limit(&mem->memsw)) - return true; - } else - if (res_counter_check_under_limit(&mem->res)) - return true; - return false; + int num = 0; + mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb); + return num; } -static unsigned int get_swappiness(struct mem_cgroup *memcg) +/* + * Visit the first child (need not be the first child as per the ordering + * of the cgroup list, since we track last_scanned_child) of @mem and use + * that to reclaim free pages from. + */ +static struct mem_cgroup * +mem_cgroup_select_victim(struct mem_cgroup *root_mem) { - struct cgroup *cgrp = memcg->css.cgroup; - unsigned int swappiness; + struct mem_cgroup *ret = NULL; + struct cgroup_subsys_state *css; + int nextid, found; - /* root ? */ - if (cgrp->parent == NULL) - return vm_swappiness; + if (!root_mem->use_hierarchy) { + css_get(&root_mem->css); + ret = root_mem; + } - spin_lock(&memcg->reclaim_param_lock); - swappiness = memcg->swappiness; - spin_unlock(&memcg->reclaim_param_lock); + while (!ret) { + rcu_read_lock(); + nextid = root_mem->last_scanned_child + 1; + css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css, + &found); + if (css && css_tryget(css)) + ret = container_of(css, struct mem_cgroup, css); + + rcu_read_unlock(); + /* Updates scanning parameter */ + spin_lock(&root_mem->reclaim_param_lock); + if (!css) { + /* this means start scan from ID:1 */ + root_mem->last_scanned_child = 0; + } else + root_mem->last_scanned_child = found; + spin_unlock(&root_mem->reclaim_param_lock); + } - return swappiness; + return ret; } /* - * Dance down the hierarchy if needed to reclaim memory. We remember the - * last child we reclaimed from, so that we don't end up penalizing - * one child extensively based on its position in the children list. + * Scan the hierarchy if needed to reclaim memory. We remember the last child + * we reclaimed from, so that we don't end up penalizing one child extensively + * based on its position in the children list. * * root_mem is the original ancestor that we've been reclaim from. + * + * We give up and return to the caller when we visit root_mem twice. + * (other groups can be removed while we're walking....) + * + * If shrink==true, for avoiding to free too much, this returns immedieately. */ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, - gfp_t gfp_mask, bool noswap) + struct zone *zone, + gfp_t gfp_mask, + unsigned long reclaim_options) { - struct mem_cgroup *next_mem; - int ret = 0; + struct mem_cgroup *victim; + int ret, total = 0; + int loop = 0; + bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP; + bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK; + bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT; + unsigned long excess = mem_cgroup_get_excess(root_mem); + + /* If memsw_is_minimum==1, swap-out is of-no-use. */ + if (root_mem->memsw_is_minimum) + noswap = true; + + while (1) { + victim = mem_cgroup_select_victim(root_mem); + if (victim == root_mem) { + loop++; + if (loop >= 1) + drain_all_stock_async(); + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!check_soft || !total) { + css_put(&victim->css); + break; + } + /* + * We want to do more targetted 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)) { + css_put(&victim->css); + break; + } + } + } + if (!mem_cgroup_local_usage(victim)) { + /* this cgroup's local usage == 0 */ + css_put(&victim->css); + continue; + } + /* we use swappiness of local cgroup */ + if (check_soft) + ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, + noswap, get_swappiness(victim), zone, + zone->zone_pgdat->node_id); + else + ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, + noswap, get_swappiness(victim)); + css_put(&victim->css); + /* + * At shrinking usage, we can't check we should stop here or + * reclaim more. It's depends on callers. last_scanned_child + * will work enough for keeping fairness under tree. + */ + if (shrink) + return ret; + total += ret; + if (check_soft) { + if (res_counter_check_under_soft_limit(&root_mem->res)) + return total; + } else if (mem_cgroup_check_under_limit(root_mem)) + return 1 + total; + } + return total; +} +static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data) +{ + int *val = (int *)data; + int x; /* - * Reclaim unconditionally and don't check for return value. - * We need to reclaim in the current group and down the tree. - * One might think about checking for children before reclaiming, - * but there might be left over accounting, even after children - * have left. + * Logically, we can stop scanning immediately when we find + * a memcg is already locked. But condidering unlock ops and + * creation/removal of memcg, scan-all is simple operation. */ - ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap, - get_swappiness(root_mem)); - if (mem_cgroup_check_under_limit(root_mem)) - return 1; /* indicate reclaim has succeeded */ - if (!root_mem->use_hierarchy) - return ret; + x = atomic_inc_return(&mem->oom_lock); + *val = max(x, *val); + return 0; +} +/* + * Check OOM-Killer is already running under our hierarchy. + * If someone is running, return false. + */ +static bool mem_cgroup_oom_lock(struct mem_cgroup *mem) +{ + int lock_count = 0; - next_mem = mem_cgroup_get_next_node(root_mem); + mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb); - while (next_mem != root_mem) { - if (mem_cgroup_is_obsolete(next_mem)) { - next_mem = mem_cgroup_get_next_node(root_mem); - continue; - } - ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap, - get_swappiness(next_mem)); - if (mem_cgroup_check_under_limit(root_mem)) - return 1; /* indicate reclaim has succeeded */ - next_mem = mem_cgroup_get_next_node(root_mem); + if (lock_count == 1) + return true; + return false; +} + +static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data) +{ + /* + * 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. + */ + atomic_add_unless(&mem->oom_lock, -1, 0); + return 0; +} + +static void mem_cgroup_oom_unlock(struct mem_cgroup *mem) +{ + mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_unlock_cb); +} + +static DEFINE_MUTEX(memcg_oom_mutex); +static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); + +/* + * try to call OOM killer. returns false if we should exit memory-reclaim loop. + */ +bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) +{ + DEFINE_WAIT(wait); + bool locked; + + /* At first, try to OOM lock hierarchy under mem.*/ + mutex_lock(&memcg_oom_mutex); + locked = mem_cgroup_oom_lock(mem); + /* + * Even if signal_pending(), we can't quit charge() loop without + * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL + * under OOM is always welcomed, use TASK_KILLABLE here. + */ + if (!locked) + prepare_to_wait(&memcg_oom_waitq, &wait, TASK_KILLABLE); + mutex_unlock(&memcg_oom_mutex); + + if (locked) + mem_cgroup_out_of_memory(mem, mask); + else { + schedule(); + finish_wait(&memcg_oom_waitq, &wait); } - return ret; + mutex_lock(&memcg_oom_mutex); + mem_cgroup_oom_unlock(mem); + /* + * Here, we use global waitq .....more fine grained waitq ? + * Assume following hierarchy. + * A/ + * 01 + * 02 + * assume OOM happens both in A and 01 at the same time. Tthey are + * mutually exclusive by lock. (kill in 01 helps A.) + * When we use per memcg waitq, we have to wake up waiters on A and 02 + * in addtion to waiters on 01. We use global waitq for avoiding mess. + * It will not be a big problem. + * (And a task may be moved to other groups while it's waiting for OOM.) + */ + wake_up_all(&memcg_oom_waitq); + mutex_unlock(&memcg_oom_mutex); + + if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) + return false; + /* Give chance to dying process */ + schedule_timeout(1); + return true; } -bool mem_cgroup_oom_called(struct task_struct *task) +/* + * Currently used to update mapped file statistics, but the routine can be + * generalized to update other statistics as well. + */ +void mem_cgroup_update_file_mapped(struct page *page, int val) { - bool ret = false; struct mem_cgroup *mem; - struct mm_struct *mm; + struct page_cgroup *pc; - rcu_read_lock(); - mm = task->mm; - if (!mm) - mm = &init_mm; - mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10)) - ret = true; - rcu_read_unlock(); + pc = lookup_page_cgroup(page); + if (unlikely(!pc)) + return; + + lock_page_cgroup(pc); + mem = pc->mem_cgroup; + if (!mem || !PageCgroupUsed(pc)) + goto done; + + /* + * Preemption is already disabled. We can use __this_cpu_xxx + */ + if (val > 0) { + __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + SetPageCgroupFileMapped(pc); + } else { + __this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + ClearPageCgroupFileMapped(pc); + } + +done: + unlock_page_cgroup(pc); +} + +/* + * 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_SIZE (32 * PAGE_SIZE) +struct memcg_stock_pcp { + struct mem_cgroup *cached; /* this never be root cgroup */ + int charge; + struct work_struct work; +}; +static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); +static atomic_t memcg_drain_count; + +/* + * Try to consume stocked charge on this cpu. If success, PAGE_SIZE is consumed + * from local stock and true is returned. If the stock is 0 or charges from a + * cgroup which is not current target, returns false. This stock will be + * refilled. + */ +static bool consume_stock(struct mem_cgroup *mem) +{ + struct memcg_stock_pcp *stock; + bool ret = true; + + stock = &get_cpu_var(memcg_stock); + if (mem == stock->cached && stock->charge) + stock->charge -= PAGE_SIZE; + else /* need to call res_counter_charge */ + ret = false; + put_cpu_var(memcg_stock); return ret; } + +/* + * Returns stocks cached in percpu to res_counter and reset cached information. + */ +static void drain_stock(struct memcg_stock_pcp *stock) +{ + struct mem_cgroup *old = stock->cached; + + if (stock->charge) { + res_counter_uncharge(&old->res, stock->charge); + if (do_swap_account) + res_counter_uncharge(&old->memsw, stock->charge); + } + stock->cached = NULL; + stock->charge = 0; +} + +/* + * 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 = &__get_cpu_var(memcg_stock); + drain_stock(stock); +} + +/* + * Cache charges(val) which is from res_counter, to local per_cpu area. + * This will be consumed by consume_stock() function, later. + */ +static void refill_stock(struct mem_cgroup *mem, int val) +{ + struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); + + if (stock->cached != mem) { /* reset if necessary */ + drain_stock(stock); + stock->cached = mem; + } + stock->charge += val; + put_cpu_var(memcg_stock); +} + +/* + * Tries to drain stocked charges in other cpus. This function is asynchronous + * and just put a work per cpu for draining localy on each cpu. Caller can + * expects some charges will be back to res_counter later but cannot wait for + * it. + */ +static void drain_all_stock_async(void) +{ + int cpu; + /* This function is for scheduling "drain" in asynchronous way. + * The result of "drain" is not directly handled by callers. Then, + * if someone is calling drain, we don't have to call drain more. + * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if + * there is a race. We just do loose check here. + */ + if (atomic_read(&memcg_drain_count)) + return; + /* Notify other cpus that system-wide "drain" is running */ + atomic_inc(&memcg_drain_count); + get_online_cpus(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + schedule_work_on(cpu, &stock->work); + } + put_online_cpus(); + atomic_dec(&memcg_drain_count); + /* We don't wait for flush_work */ +} + +/* This is a synchronous drain interface. */ +static void drain_all_stock_sync(void) +{ + /* called when force_empty is called */ + atomic_inc(&memcg_drain_count); + schedule_on_each_cpu(drain_local_stock); + atomic_dec(&memcg_drain_count); +} + +static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb, + unsigned long action, + void *hcpu) +{ + int cpu = (unsigned long)hcpu; + struct memcg_stock_pcp *stock; + + if (action != CPU_DEAD) + return NOTIFY_OK; + stock = &per_cpu(memcg_stock, cpu); + drain_stock(stock); + return NOTIFY_OK; +} + /* * Unlike exported interface, "oom" parameter is added. if oom==true, * oom-killer can be invoked. */ static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcg, - bool oom) + gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) { struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct res_counter *fail_res; + int csize = CHARGE_SIZE; - if (unlikely(test_thread_flag(TIF_MEMDIE))) { - /* Don't account this! */ - *memcg = NULL; - return 0; - } + /* + * Unlike gloval-vm's OOM-kill, we're not in memory shortage + * in system level. So, allow to go ahead dying process in addition to + * MEMDIE process. + */ + if (unlikely(test_thread_flag(TIF_MEMDIE) + || fatal_signal_pending(current))) + goto bypass; /* * We always charge the cgroup the mm_struct belongs to. @@ -847,23 +1541,27 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (unlikely(!mem)) return 0; - VM_BUG_ON(mem_cgroup_is_obsolete(mem)); + VM_BUG_ON(css_is_removed(&mem->css)); + if (mem_cgroup_is_root(mem)) + goto done; while (1) { - int ret; - bool noswap = false; + int ret = 0; + unsigned long flags = 0; - ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); + if (consume_stock(mem)) + goto done; + + ret = res_counter_charge(&mem->res, csize, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; - ret = res_counter_charge(&mem->memsw, PAGE_SIZE, - &fail_res); + ret = res_counter_charge(&mem->memsw, csize, &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ - res_counter_uncharge(&mem->res, PAGE_SIZE); - noswap = true; + res_counter_uncharge(&mem->res, csize); + flags |= MEM_CGROUP_RECLAIM_NOSWAP; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); } else @@ -871,11 +1569,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); + /* reduce request size and retry */ + if (csize > PAGE_SIZE) { + csize = PAGE_SIZE; + continue; + } if (!(gfp_mask & __GFP_WAIT)) goto nomem; - ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask, - noswap); + ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, + gfp_mask, flags); if (ret) continue; @@ -890,36 +1593,138 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (mem_cgroup_check_under_limit(mem_over_limit)) continue; + /* try to avoid oom while someone is moving charge */ + if (mc.moving_task && current != mc.moving_task) { + struct mem_cgroup *from, *to; + bool do_continue = false; + /* + * There is a small race that "from" or "to" can be + * freed by rmdir, so we use css_tryget(). + */ + from = mc.from; + to = mc.to; + if (from && css_tryget(&from->css)) { + if (mem_over_limit->use_hierarchy) + do_continue = css_is_ancestor( + &from->css, + &mem_over_limit->css); + else + do_continue = (from == mem_over_limit); + css_put(&from->css); + } + if (!do_continue && to && css_tryget(&to->css)) { + if (mem_over_limit->use_hierarchy) + do_continue = css_is_ancestor( + &to->css, + &mem_over_limit->css); + else + do_continue = (to == mem_over_limit); + css_put(&to->css); + } + if (do_continue) { + 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); + continue; + } + } + if (!nr_retries--) { - if (oom) { - mutex_lock(&memcg_tasklist); - mem_cgroup_out_of_memory(mem_over_limit, gfp_mask); - mutex_unlock(&memcg_tasklist); - mem_over_limit->last_oom_jiffies = jiffies; + if (!oom) + goto nomem; + if (mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) { + nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + continue; } - goto nomem; + /* When we reach here, current task is dying .*/ + css_put(&mem->css); + goto bypass; } } + if (csize > PAGE_SIZE) + refill_stock(mem, csize - PAGE_SIZE); +done: return 0; nomem: css_put(&mem->css); return -ENOMEM; +bypass: + *memcg = NULL; + return 0; } -static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page) +/* + * Somemtimes we have to undo a charge we got by try_charge(). + * This function is for that and do uncharge, put css's refcnt. + * gotten by try_charge(). + */ +static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem, + unsigned long count) { - struct mem_cgroup *mem; - swp_entry_t ent; + if (!mem_cgroup_is_root(mem)) { + res_counter_uncharge(&mem->res, PAGE_SIZE * count); + if (do_swap_account) + res_counter_uncharge(&mem->memsw, PAGE_SIZE * count); + VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags)); + WARN_ON_ONCE(count > INT_MAX); + __css_put(&mem->css, (int)count); + } + /* we don't need css_put for root */ +} - if (!PageSwapCache(page)) - return NULL; +static void mem_cgroup_cancel_charge(struct mem_cgroup *mem) +{ + __mem_cgroup_cancel_charge(mem, 1); +} - ent.val = page_private(page); - mem = lookup_swap_cgroup(ent); - if (!mem) +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller must check css_is_removed() or some if + * it's concern. (dropping refcnt from swap can be called against removed + * memcg.) + */ +static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) +{ + struct cgroup_subsys_state *css; + + /* ID 0 is unused ID */ + if (!id) return NULL; - if (!css_tryget(&mem->css)) + css = css_lookup(&mem_cgroup_subsys, id); + if (!css) return NULL; + return container_of(css, struct mem_cgroup, css); +} + +struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) +{ + struct mem_cgroup *mem = NULL; + struct page_cgroup *pc; + unsigned short id; + swp_entry_t ent; + + VM_BUG_ON(!PageLocked(page)); + + pc = lookup_page_cgroup(page); + lock_page_cgroup(pc); + if (PageCgroupUsed(pc)) { + mem = pc->mem_cgroup; + if (mem && !css_tryget(&mem->css)) + mem = NULL; + } else if (PageSwapCache(page)) { + ent.val = page_private(page); + id = lookup_swap_cgroup(ent); + rcu_read_lock(); + mem = mem_cgroup_lookup(id); + if (mem && !css_tryget(&mem->css)) + mem = NULL; + rcu_read_unlock(); + } + unlock_page_cgroup(pc); return mem; } @@ -939,73 +1744,113 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); - res_counter_uncharge(&mem->res, PAGE_SIZE); - if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); - css_put(&mem->css); + mem_cgroup_cancel_charge(mem); return; } + pc->mem_cgroup = mem; + /* + * We access a page_cgroup asynchronously without lock_page_cgroup(). + * Especially when a page_cgroup is taken from a page, pc->mem_cgroup + * is accessed after testing USED bit. To make pc->mem_cgroup visible + * before USED bit, we need memory barrier here. + * See mem_cgroup_add_lru_list(), etc. + */ smp_wmb(); - pc->flags = pcg_default_flags[ctype]; + switch (ctype) { + case MEM_CGROUP_CHARGE_TYPE_CACHE: + case MEM_CGROUP_CHARGE_TYPE_SHMEM: + SetPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + case MEM_CGROUP_CHARGE_TYPE_MAPPED: + ClearPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + default: + break; + } mem_cgroup_charge_statistics(mem, pc, true); unlock_page_cgroup(pc); + /* + * "charge_statistics" updated event counter. Then, check it. + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. + */ + memcg_check_events(mem, pc->page); } /** - * mem_cgroup_move_account - move account of the page + * __mem_cgroup_move_account - move account of the page * @pc: page_cgroup of the page. * @from: mem_cgroup which the page is moved from. * @to: mem_cgroup which the page is moved to. @from != @to. + * @uncharge: whether we should call uncharge and css_put against @from. * * The caller must confirm following. * - page is not on LRU (isolate_page() is useful.) + * - the pc is locked, used, and ->mem_cgroup points to @from. * - * returns 0 at success, - * returns -EBUSY when lock is busy or "pc" is unstable. - * - * This function does "uncharge" from old cgroup but doesn't do "charge" to - * new cgroup. It should be done by a caller. + * This function doesn't do "charge" nor css_get to new cgroup. It should be + * done by a caller(__mem_cgroup_try_charge would be usefull). If @uncharge is + * true, this function does "uncharge" from old cgroup, but it doesn't if + * @uncharge is false, so a caller should do "uncharge". */ -static int mem_cgroup_move_account(struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to) +static void __mem_cgroup_move_account(struct page_cgroup *pc, + struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) { - struct mem_cgroup_per_zone *from_mz, *to_mz; - int nid, zid; - int ret = -EBUSY; - VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); - - nid = page_cgroup_nid(pc); - zid = page_cgroup_zid(pc); - from_mz = mem_cgroup_zoneinfo(from, nid, zid); - to_mz = mem_cgroup_zoneinfo(to, nid, zid); - - if (!trylock_page_cgroup(pc)) - return ret; - - if (!PageCgroupUsed(pc)) - goto out; - - if (pc->mem_cgroup != from) - goto out; - - res_counter_uncharge(&from->res, PAGE_SIZE); + VM_BUG_ON(!PageCgroupLocked(pc)); + VM_BUG_ON(!PageCgroupUsed(pc)); + VM_BUG_ON(pc->mem_cgroup != from); + + if (PageCgroupFileMapped(pc)) { + /* Update mapped_file data for mem_cgroup */ + preempt_disable(); + __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + preempt_enable(); + } mem_cgroup_charge_statistics(from, pc, false); - if (do_swap_account) - res_counter_uncharge(&from->memsw, PAGE_SIZE); - css_put(&from->css); + if (uncharge) + /* This is not "cancel", but cancel_charge does all we need. */ + mem_cgroup_cancel_charge(from); - css_get(&to->css); + /* caller should have done css_get */ pc->mem_cgroup = to; mem_cgroup_charge_statistics(to, pc, true); - ret = 0; -out: + /* + * We charges against "to" which may not have any tasks. Then, "to" + * can be under rmdir(). But in current implementation, caller of + * this function is just force_empty() and move charge, so it's + * garanteed that "to" is never removed. So, we don't check rmdir + * status here. + */ +} + +/* + * check whether the @pc is valid for moving account and call + * __mem_cgroup_move_account() + */ +static int mem_cgroup_move_account(struct page_cgroup *pc, + struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) +{ + int ret = -EINVAL; + lock_page_cgroup(pc); + if (PageCgroupUsed(pc) && pc->mem_cgroup == from) { + __mem_cgroup_move_account(pc, from, to, uncharge); + ret = 0; + } unlock_page_cgroup(pc); + /* + * check events + */ + memcg_check_events(to, pc->page); + memcg_check_events(from, pc->page); return ret; } @@ -1027,43 +1872,25 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, if (!pcg) return -EINVAL; + ret = -EBUSY; + if (!get_page_unless_zero(page)) + goto out; + if (isolate_lru_page(page)) + goto put; parent = mem_cgroup_from_cont(pcg); - - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); if (ret || !parent) - return ret; - - if (!get_page_unless_zero(page)) { - ret = -EBUSY; - goto uncharge; - } - - ret = isolate_lru_page(page); + goto put_back; + ret = mem_cgroup_move_account(pc, child, parent, true); if (ret) - goto cancel; - - ret = mem_cgroup_move_account(pc, child, parent); - + mem_cgroup_cancel_charge(parent); +put_back: putback_lru_page(page); - if (!ret) { - put_page(page); - /* drop extra refcnt by try_charge() */ - css_put(&parent->css); - return 0; - } - -cancel: +put: put_page(page); -uncharge: - /* drop extra refcnt by try_charge() */ - css_put(&parent->css); - /* uncharge if move fails */ - res_counter_uncharge(&parent->res, PAGE_SIZE); - if (do_swap_account) - res_counter_uncharge(&parent->memsw, PAGE_SIZE); +out: return ret; } @@ -1118,6 +1945,10 @@ int mem_cgroup_newpage_charge(struct page *page, MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL); } +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype); + int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { @@ -1154,16 +1985,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, unlock_page_cgroup(pc); } - if (do_swap_account && PageSwapCache(page)) { - mem = try_get_mem_cgroup_from_swapcache(page); - if (mem) - mm = NULL; - else - mem = NULL; - /* SwapCache may be still linked to LRU now. */ - mem_cgroup_lru_del_before_commit_swapcache(page); - } - if (unlikely(!mm && !mem)) mm = &init_mm; @@ -1171,29 +1992,23 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_CACHE, NULL); - ret = mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); - if (mem) - css_put(&mem->css); - if (PageSwapCache(page)) - mem_cgroup_lru_add_after_commit_swapcache(page); + /* shmem */ + if (PageSwapCache(page)) { + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, mem, + MEM_CGROUP_CHARGE_TYPE_SHMEM); + } else + ret = mem_cgroup_charge_common(page, mm, gfp_mask, + MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); - if (do_swap_account && !ret && PageSwapCache(page)) { - swp_entry_t ent = {.val = page_private(page)}; - /* avoid double counting */ - mem = swap_cgroup_record(ent, NULL); - if (mem) { - res_counter_uncharge(&mem->memsw, PAGE_SIZE); - mem_cgroup_put(mem); - } - } return ret; } /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without - * struct page_cgroup is aquired. This refcnt will be cumsumed by + * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, @@ -1210,12 +2025,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, goto charge_cur_mm; /* * A racing thread's fault, or swapoff, may have already updated - * the pte, and even removed page from swap cache: return success - * to go on to do_swap_page()'s pte_same() test, which should fail. + * the pte, and even removed page from swap cache: in those cases + * do_swap_page()'s pte_same() test will fail; but there's also a + * KSM case which does need to charge the page. */ if (!PageSwapCache(page)) - return 0; - mem = try_get_mem_cgroup_from_swapcache(page); + goto charge_cur_mm; + mem = try_get_mem_cgroup_from_page(page); if (!mem) goto charge_cur_mm; *ptr = mem; @@ -1229,7 +2045,9 @@ charge_cur_mm: return __mem_cgroup_try_charge(mm, mask, ptr, true); } -void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype) { struct page_cgroup *pc; @@ -1237,9 +2055,10 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) return; if (!ptr) return; + cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); - __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED); + __mem_cgroup_commit_charge(ptr, pc, ctype); mem_cgroup_lru_add_after_commit_swapcache(page); /* * Now swap is on-memory. This means this page may be @@ -1250,16 +2069,36 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) */ if (do_swap_account && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; + unsigned short id; struct mem_cgroup *memcg; - memcg = swap_cgroup_record(ent, NULL); + + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + /* + * This recorded memcg can be obsolete one. So, avoid + * calling css_tryget + */ + if (!mem_cgroup_is_root(memcg)) + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } - + rcu_read_unlock(); } - /* add this page(page_cgroup) to the LRU we want. */ + /* + * At swapin, we may charge account against cgroup which has no tasks. + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&ptr->css); +} +void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +{ + __mem_cgroup_commit_charge_swapin(page, ptr, + MEM_CGROUP_CHARGE_TYPE_MAPPED); } void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) @@ -1268,13 +2107,54 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) return; if (!mem) return; + mem_cgroup_cancel_charge(mem); +} + +static void +__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) +{ + struct memcg_batch_info *batch = NULL; + bool uncharge_memsw = true; + /* If swapout, usage of swap doesn't decrease */ + if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) + uncharge_memsw = false; + /* + * do_batch > 0 when unmapping pages or inode invalidate/truncate. + * In those cases, all pages freed continously can be expected to be in + * the same cgroup and we have chance to coalesce uncharges. + * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE) + * because we want to do uncharge as soon as possible. + */ + if (!current->memcg_batch.do_batch || test_thread_flag(TIF_MEMDIE)) + goto direct_uncharge; + + batch = ¤t->memcg_batch; + /* + * In usual, we do css_get() when we remember memcg pointer. + * But in this case, we keep res->usage until end of a series of + * uncharges. Then, it's ok to ignore memcg's refcnt. + */ + if (!batch->memcg) + batch->memcg = mem; + /* + * In typical case, batch->memcg == mem. This means we can + * merge a series of uncharges to an uncharge of res_counter. + * If not, we uncharge res_counter ony by one. + */ + if (batch->memcg != mem) + goto direct_uncharge; + /* remember freed charge and uncharge it later */ + batch->bytes += PAGE_SIZE; + if (uncharge_memsw) + batch->memsw_bytes += PAGE_SIZE; + return; +direct_uncharge: res_counter_uncharge(&mem->res, PAGE_SIZE); - if (do_swap_account) + if (uncharge_memsw) res_counter_uncharge(&mem->memsw, PAGE_SIZE); - css_put(&mem->css); + return; } - /* * uncharge if !page_mapped(page) */ @@ -1307,6 +2187,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_DROP: if (page_mapped(page)) goto unlock_out; break; @@ -1321,11 +2202,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - res_counter_uncharge(&mem->res, PAGE_SIZE); - if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); - + if (!mem_cgroup_is_root(mem)) + __do_uncharge(mem, ctype); + if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) + mem_cgroup_swap_statistics(mem, true); mem_cgroup_charge_statistics(mem, pc, false); + ClearPageCgroupUsed(pc); /* * pc->mem_cgroup is not cleared here. It will be accessed when it's @@ -1337,6 +2219,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); + memcg_check_events(mem, page); /* at swapout, this memcg will be accessed to record to swap */ if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) css_put(&mem->css); @@ -1366,23 +2249,74 @@ void mem_cgroup_uncharge_cache_page(struct page *page) } /* - * called from __delete_from_swap_cache() and drop "page" account. + * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate. + * In that cases, pages are freed continuously and we can expect pages + * are in the same memcg. All these calls itself limits the number of + * pages freed at once, then uncharge_start/end() is called properly. + * This may be called prural(2) times in a context, + */ + +void mem_cgroup_uncharge_start(void) +{ + current->memcg_batch.do_batch++; + /* We can do nest. */ + if (current->memcg_batch.do_batch == 1) { + current->memcg_batch.memcg = NULL; + current->memcg_batch.bytes = 0; + current->memcg_batch.memsw_bytes = 0; + } +} + +void mem_cgroup_uncharge_end(void) +{ + struct memcg_batch_info *batch = ¤t->memcg_batch; + + if (!batch->do_batch) + return; + + batch->do_batch--; + if (batch->do_batch) /* If stacked, do nothing. */ + return; + + if (!batch->memcg) + return; + /* + * This "batch->memcg" is valid without any css_get/put etc... + * bacause we hide charges behind us. + */ + if (batch->bytes) + res_counter_uncharge(&batch->memcg->res, batch->bytes); + if (batch->memsw_bytes) + res_counter_uncharge(&batch->memcg->memsw, batch->memsw_bytes); + /* forget this pointer (for sanity check) */ + batch->memcg = NULL; +} + +#ifdef CONFIG_SWAP +/* + * called after __delete_from_swap_cache() and drop "page" account. * memcg information is recorded to swap_cgroup of "ent" */ -void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) +void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) { struct mem_cgroup *memcg; + int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; + + if (!swapout) /* this was a swap cache but the swap is unused ! */ + ctype = MEM_CGROUP_CHARGE_TYPE_DROP; + + memcg = __mem_cgroup_uncharge_common(page, ctype); - memcg = __mem_cgroup_uncharge_common(page, - MEM_CGROUP_CHARGE_TYPE_SWAPOUT); /* record memcg information */ - if (do_swap_account && memcg) { - swap_cgroup_record(ent, memcg); + if (do_swap_account && swapout && memcg) { + swap_cgroup_record(ent, css_id(&memcg->css)); mem_cgroup_get(memcg); } - if (memcg) + if (swapout && memcg) css_put(&memcg->css); } +#endif #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP /* @@ -1392,15 +2326,83 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) void mem_cgroup_uncharge_swap(swp_entry_t ent) { struct mem_cgroup *memcg; + unsigned short id; if (!do_swap_account) return; - memcg = swap_cgroup_record(ent, NULL); + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + /* + * We uncharge this because swap is freed. + * This memcg can be obsolete one. We avoid calling css_tryget + */ + if (!mem_cgroup_is_root(memcg)) + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } + rcu_read_unlock(); +} + +/** + * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record. + * @entry: swap entry to be moved + * @from: mem_cgroup which the entry is moved from + * @to: mem_cgroup which the entry is moved to + * @need_fixup: whether we should fixup res_counters and refcounts. + * + * It succeeds only when the swap_cgroup's record for this entry is the same + * as the mem_cgroup's id of @from. + * + * Returns 0 on success, -EINVAL on failure. + * + * The caller must have charged to @to, IOW, called res_counter_charge() about + * both res and memsw, and called css_get(). + */ +static int mem_cgroup_move_swap_account(swp_entry_t entry, + struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup) +{ + unsigned short old_id, new_id; + + old_id = css_id(&from->css); + new_id = css_id(&to->css); + + if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { + mem_cgroup_swap_statistics(from, false); + mem_cgroup_swap_statistics(to, true); + /* + * This function is only called from task migration context now. + * It postpones res_counter and refcount handling till the end + * of task migration(mem_cgroup_clear_mc()) for performance + * improvement. But we cannot postpone mem_cgroup_get(to) + * because if the process that has been moved to @to does + * swap-in, the refcount of @to might be decreased to 0. + */ + mem_cgroup_get(to); + if (need_fixup) { + if (!mem_cgroup_is_root(from)) + res_counter_uncharge(&from->memsw, PAGE_SIZE); + mem_cgroup_put(from); + /* + * we charged both to->res and to->memsw, so we should + * uncharge to->res. + */ + if (!mem_cgroup_is_root(to)) + res_counter_uncharge(&to->res, PAGE_SIZE); + css_put(&to->css); + } + return 0; + } + return -EINVAL; +} +#else +static inline int mem_cgroup_move_swap_account(swp_entry_t entry, + struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup) +{ + return -EINVAL; } #endif @@ -1425,11 +2427,11 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) } unlock_page_cgroup(pc); + *ptr = mem; if (mem) { - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false); css_put(&mem->css); } - *ptr = mem; return ret; } @@ -1443,7 +2445,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, if (!mem) return; - + cgroup_exclude_rmdir(&mem->css); /* at migration success, oldpage->mapping is NULL. */ if (oldpage->mapping) { target = oldpage; @@ -1483,39 +2485,37 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, */ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) mem_cgroup_uncharge_page(target); + /* + * At migration, we may charge account against cgroup which has no tasks + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&mem->css); } /* - * A call to try to shrink memory usage under specified resource controller. - * This is typically used for page reclaiming for shmem for reducing side - * effect of page allocation from shmem, which is used by some mem_cgroup. + * A call to try to shrink memory usage on charge failure at shmem's swapin. + * Calling hierarchical_reclaim is not enough because we should update + * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM. + * Moreover considering hierarchy, we should reclaim from the mem_over_limit, + * not from the memcg which this page would be charged to. + * try_charge_swapin does all of these works properly. */ -int mem_cgroup_shrink_usage(struct page *page, +int mem_cgroup_shmem_charge_fallback(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { struct mem_cgroup *mem = NULL; - int progress = 0; - int retry = MEM_CGROUP_RECLAIM_RETRIES; + int ret; if (mem_cgroup_disabled()) return 0; - if (page) - mem = try_get_mem_cgroup_from_swapcache(page); - if (!mem && mm) - mem = try_get_mem_cgroup_from_mm(mm); - if (unlikely(!mem)) - return 0; - do { - progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true); - progress += mem_cgroup_check_under_limit(mem); - } while (!progress && --retry); + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + if (!ret) + mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */ - css_put(&mem->css); - if (!retry) - return -ENOMEM; - return 0; + return ret; } static DEFINE_MUTEX(set_limit_mutex); @@ -1523,11 +2523,20 @@ static DEFINE_MUTEX(set_limit_mutex); static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { - - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; - int progress; + int retry_count; u64 memswlimit; int ret = 0; + int children = mem_cgroup_count_children(memcg); + u64 curusage, oldusage; + + /* + * For keeping hierarchical_reclaim simple, how long we should retry + * is depends on callers. We set our retry-count to be function + * of # of children which we should visit in this loop. + */ + retry_count = MEM_CGROUP_RECLAIM_RETRIES * children; + + oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -1547,29 +2556,41 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, break; } ret = res_counter_set_limit(&memcg->res, val); + if (!ret) { + if (memswlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } mutex_unlock(&set_limit_mutex); if (!ret) break; - progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, - false); - if (!progress) retry_count--; + mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, + MEM_CGROUP_RECLAIM_SHRINK); + curusage = res_counter_read_u64(&memcg->res, RES_USAGE); + /* Usage is reduced ? */ + if (curusage >= oldusage) + retry_count--; + else + oldusage = curusage; } return ret; } -int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, - unsigned long long val) +static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, + unsigned long long val) { - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int retry_count; u64 memlimit, oldusage, curusage; - int ret; - - if (!do_swap_account) - return -EINVAL; + int children = mem_cgroup_count_children(memcg); + int ret = -EBUSY; + /* see mem_cgroup_resize_res_limit */ + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { ret = -EINTR; @@ -1588,20 +2609,121 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, break; } ret = res_counter_set_limit(&memcg->memsw, val); + if (!ret) { + if (memlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } mutex_unlock(&set_limit_mutex); if (!ret) break; - oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); - mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true); + mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, + MEM_CGROUP_RECLAIM_NOSWAP | + MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + /* Usage is reduced ? */ if (curusage >= oldusage) retry_count--; + else + oldusage = curusage; } return ret; } +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, + int zid) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_zone *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_zone *mctz; + unsigned long long excess; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node_zone(nid, zid); + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone, + gfp_mask, + MEM_CGROUP_RECLAIM_SOFT); + nr_reclaimed += reclaimed; + spin_lock(&mctz->lock); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) { + do { + /* + * Loop until we find yet another one. + * + * By the time we get the soft_limit lock + * again, someone might have aded the + * group back on the RB tree. Iterate to + * make sure we get a different mem. + * mem_cgroup_largest_soft_limit_node returns + * NULL if no other cgroup is present on + * the tree + */ + next_mz = + __mem_cgroup_largest_soft_limit_node(mctz); + if (next_mz == mz) { + css_put(&next_mz->mem->css); + next_mz = NULL; + } else /* next_mz == NULL or other memcg */ + break; + } while (1); + } + __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); + excess = res_counter_soft_limit_excess(&mz->mem->res); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + /* If excess == 0, no tree ops */ + __mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess); + spin_unlock(&mctz->lock); + css_put(&mz->mem->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->mem->css); + return nr_reclaimed; +} + /* * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. @@ -1634,7 +2756,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, pc = list_entry(list->prev, struct page_cgroup, lru); if (busy == pc) { list_move(&pc->lru, list); - busy = 0; + busy = NULL; spin_unlock_irqrestore(&zone->lru_lock, flags); continue; } @@ -1675,7 +2797,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all) if (free_all) goto try_to_free; move_account: - while (mem->res.usage > 0) { + do { ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; @@ -1684,6 +2806,7 @@ move_account: goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); + drain_all_stock_sync(); ret = 0; for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { @@ -1702,8 +2825,8 @@ move_account: if (ret == -ENOMEM) goto try_to_free; cond_resched(); - } - ret = 0; + /* "ret" should also be checked to ensure all lists are empty. */ + } while (mem->res.usage > 0 || ret); out: css_put(&mem->css); return ret; @@ -1730,16 +2853,13 @@ try_to_free: if (!progress) { nr_retries--; /* maybe some writeback is necessary */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } } lru_add_drain(); /* try move_account...there may be some *locked* pages. */ - if (mem->res.usage) - goto move_account; - ret = 0; - goto out; + goto move_account; } int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) @@ -1766,7 +2886,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, cgroup_lock(); /* - * If parent's use_hiearchy is set, we can't make any modifications + * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can * occur, provided the current cgroup has no children. * @@ -1786,20 +2906,74 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, return retval; } +struct mem_cgroup_idx_data { + s64 val; + enum mem_cgroup_stat_index idx; +}; + +static int +mem_cgroup_get_idx_stat(struct mem_cgroup *mem, void *data) +{ + struct mem_cgroup_idx_data *d = data; + d->val += mem_cgroup_read_stat(mem, d->idx); + return 0; +} + +static void +mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem, + enum mem_cgroup_stat_index idx, s64 *val) +{ + struct mem_cgroup_idx_data d; + d.idx = idx; + d.val = 0; + mem_cgroup_walk_tree(mem, &d, mem_cgroup_get_idx_stat); + *val = d.val; +} + +static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap) +{ + u64 idx_val, val; + + if (!mem_cgroup_is_root(mem)) { + if (!swap) + return res_counter_read_u64(&mem->res, RES_USAGE); + else + return res_counter_read_u64(&mem->memsw, RES_USAGE); + } + + mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_CACHE, &idx_val); + val = idx_val; + mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_RSS, &idx_val); + val += idx_val; + + if (swap) { + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_SWAPOUT, &idx_val); + val += idx_val; + } + + return val << PAGE_SHIFT; +} + static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - u64 val = 0; + u64 val; int type, name; type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); switch (type) { case _MEM: - val = res_counter_read_u64(&mem->res, name); + if (name == RES_USAGE) + val = mem_cgroup_usage(mem, false); + else + val = res_counter_read_u64(&mem->res, name); break; case _MEMSWAP: - if (do_swap_account) + if (name == RES_USAGE) + val = mem_cgroup_usage(mem, true); + else val = res_counter_read_u64(&mem->memsw, name); break; default: @@ -1824,6 +2998,10 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, name = MEMFILE_ATTR(cft->private); switch (name) { case RES_LIMIT: + if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ + ret = -EINVAL; + break; + } /* This function does all necessary parse...reuse it */ ret = res_counter_memparse_write_strategy(buffer, &val); if (ret) @@ -1833,6 +3011,20 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, else ret = mem_cgroup_resize_memsw_limit(memcg, val); break; + case RES_SOFT_LIMIT: + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + /* + * For memsw, soft limits are hard to implement in terms + * of semantics, for now, we support soft limits for + * control without swap + */ + if (type == _MEM) + ret = res_counter_set_soft_limit(&memcg->res, val); + else + ret = -EINVAL; + break; default: ret = -EINVAL; /* should be BUG() ? */ break; @@ -1890,57 +3082,140 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) res_counter_reset_failcnt(&mem->memsw); break; } + + return 0; +} + +static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp, + struct cftype *cft) +{ + return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate; +} + +#ifdef CONFIG_MMU +static int mem_cgroup_move_charge_write(struct cgroup *cgrp, + struct cftype *cft, u64 val) +{ + struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + + if (val >= (1 << NR_MOVE_TYPE)) + return -EINVAL; + /* + * We check this value several times in both in can_attach() and + * attach(), so we need cgroup lock to prevent this value from being + * inconsistent. + */ + cgroup_lock(); + mem->move_charge_at_immigrate = val; + cgroup_unlock(); + return 0; } +#else +static int mem_cgroup_move_charge_write(struct cgroup *cgrp, + struct cftype *cft, u64 val) +{ + return -ENOSYS; +} +#endif + + +/* For read statistics */ +enum { + MCS_CACHE, + MCS_RSS, + MCS_FILE_MAPPED, + MCS_PGPGIN, + MCS_PGPGOUT, + MCS_SWAP, + MCS_INACTIVE_ANON, + MCS_ACTIVE_ANON, + MCS_INACTIVE_FILE, + MCS_ACTIVE_FILE, + MCS_UNEVICTABLE, + NR_MCS_STAT, +}; -static const struct mem_cgroup_stat_desc { - const char *msg; - u64 unit; -} mem_cgroup_stat_desc[] = { - [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, }, - [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, }, - [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, }, - [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, }, +struct mcs_total_stat { + s64 stat[NR_MCS_STAT]; }; +struct { + char *local_name; + char *total_name; +} memcg_stat_strings[NR_MCS_STAT] = { + {"cache", "total_cache"}, + {"rss", "total_rss"}, + {"mapped_file", "total_mapped_file"}, + {"pgpgin", "total_pgpgin"}, + {"pgpgout", "total_pgpgout"}, + {"swap", "total_swap"}, + {"inactive_anon", "total_inactive_anon"}, + {"active_anon", "total_active_anon"}, + {"inactive_file", "total_inactive_file"}, + {"active_file", "total_active_file"}, + {"unevictable", "total_unevictable"} +}; + + +static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) +{ + struct mcs_total_stat *s = data; + s64 val; + + /* per cpu stat */ + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); + s->stat[MCS_CACHE] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); + s->stat[MCS_RSS] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED); + s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT); + s->stat[MCS_PGPGIN] += val; + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGOUT_COUNT); + s->stat[MCS_PGPGOUT] += val; + if (do_swap_account) { + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT); + s->stat[MCS_SWAP] += val * PAGE_SIZE; + } + + /* per zone stat */ + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); + s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); + s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); + s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); + s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); + s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; + return 0; +} + +static void +mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) +{ + mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat); +} + static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); - struct mem_cgroup_stat *stat = &mem_cont->stat; + struct mcs_total_stat mystat; int i; - for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) { - s64 val; + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_local_stat(mem_cont, &mystat); - val = mem_cgroup_read_stat(stat, i); - val *= mem_cgroup_stat_desc[i].unit; - cb->fill(cb, mem_cgroup_stat_desc[i].msg, val); + for (i = 0; i < NR_MCS_STAT; i++) { + if (i == MCS_SWAP && !do_swap_account) + continue; + cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]); } - /* showing # of active pages */ - { - unsigned long active_anon, inactive_anon; - unsigned long active_file, inactive_file; - unsigned long unevictable; - - inactive_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_ANON); - active_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_ANON); - inactive_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_FILE); - active_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_FILE); - unevictable = mem_cgroup_get_all_zonestat(mem_cont, - LRU_UNEVICTABLE); - - cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE); - cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE); - cb->fill(cb, "active_file", (active_file) * PAGE_SIZE); - cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE); - cb->fill(cb, "unevictable", unevictable * PAGE_SIZE); - } + /* Hierarchical information */ { unsigned long long limit, memsw_limit; memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit); @@ -1949,6 +3224,14 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, cb->fill(cb, "hierarchical_memsw_limit", memsw_limit); } + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_total_stat(mem_cont, &mystat); + for (i = 0; i < NR_MCS_STAT; i++) { + if (i == MCS_SWAP && !do_swap_account) + continue; + cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]); + } + #ifdef CONFIG_DEBUG_VM cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL)); @@ -2020,12 +3303,249 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, return 0; } +static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) +{ + struct mem_cgroup_threshold_ary *t; + u64 usage; + int i; + + rcu_read_lock(); + if (!swap) + t = rcu_dereference(memcg->thresholds); + else + t = rcu_dereference(memcg->memsw_thresholds); + + if (!t) + goto unlock; + + usage = mem_cgroup_usage(memcg, swap); + + /* + * current_threshold points to threshold just below usage. + * If it's not true, a threshold was crossed after last + * call of __mem_cgroup_threshold(). + */ + i = atomic_read(&t->current_threshold); + + /* + * Iterate backward over array of thresholds starting from + * current_threshold and check if a threshold is crossed. + * If none of thresholds below usage is crossed, we read + * only one element of the array here. + */ + for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--) + eventfd_signal(t->entries[i].eventfd, 1); + + /* i = current_threshold + 1 */ + i++; + + /* + * Iterate forward over array of thresholds starting from + * current_threshold+1 and check if a threshold is crossed. + * If none of thresholds above usage is crossed, we read + * only one element of the array here. + */ + for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++) + eventfd_signal(t->entries[i].eventfd, 1); + + /* Update current_threshold */ + atomic_set(&t->current_threshold, i - 1); +unlock: + rcu_read_unlock(); +} + +static void mem_cgroup_threshold(struct mem_cgroup *memcg) +{ + __mem_cgroup_threshold(memcg, false); + if (do_swap_account) + __mem_cgroup_threshold(memcg, true); +} + +static int compare_thresholds(const void *a, const void *b) +{ + const struct mem_cgroup_threshold *_a = a; + const struct mem_cgroup_threshold *_b = b; + + return _a->threshold - _b->threshold; +} + +static int mem_cgroup_register_event(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd, const char *args) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup_threshold_ary *thresholds, *thresholds_new; + int type = MEMFILE_TYPE(cft->private); + u64 threshold, usage; + int size; + int i, ret; + + ret = res_counter_memparse_write_strategy(args, &threshold); + if (ret) + return ret; + + mutex_lock(&memcg->thresholds_lock); + if (type == _MEM) + thresholds = memcg->thresholds; + else if (type == _MEMSWAP) + thresholds = memcg->memsw_thresholds; + else + BUG(); + + usage = mem_cgroup_usage(memcg, type == _MEMSWAP); + + /* Check if a threshold crossed before adding a new one */ + if (thresholds) + __mem_cgroup_threshold(memcg, type == _MEMSWAP); + + if (thresholds) + size = thresholds->size + 1; + else + size = 1; + + /* Allocate memory for new array of thresholds */ + thresholds_new = kmalloc(sizeof(*thresholds_new) + + size * sizeof(struct mem_cgroup_threshold), + GFP_KERNEL); + if (!thresholds_new) { + ret = -ENOMEM; + goto unlock; + } + thresholds_new->size = size; + + /* Copy thresholds (if any) to new array */ + if (thresholds) + memcpy(thresholds_new->entries, thresholds->entries, + thresholds->size * + sizeof(struct mem_cgroup_threshold)); + /* Add new threshold */ + thresholds_new->entries[size - 1].eventfd = eventfd; + thresholds_new->entries[size - 1].threshold = threshold; + + /* Sort thresholds. Registering of new threshold isn't time-critical */ + sort(thresholds_new->entries, size, + sizeof(struct mem_cgroup_threshold), + compare_thresholds, NULL); + + /* Find current threshold */ + atomic_set(&thresholds_new->current_threshold, -1); + for (i = 0; i < size; i++) { + if (thresholds_new->entries[i].threshold < usage) { + /* + * thresholds_new->current_threshold will not be used + * until rcu_assign_pointer(), so it's safe to increment + * it here. + */ + atomic_inc(&thresholds_new->current_threshold); + } + } + + if (type == _MEM) + rcu_assign_pointer(memcg->thresholds, thresholds_new); + else + rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new); + + /* To be sure that nobody uses thresholds before freeing it */ + synchronize_rcu(); + + kfree(thresholds); +unlock: + mutex_unlock(&memcg->thresholds_lock); + + return ret; +} + +static int mem_cgroup_unregister_event(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup_threshold_ary *thresholds, *thresholds_new; + int type = MEMFILE_TYPE(cft->private); + u64 usage; + int size = 0; + int i, j, ret; + + mutex_lock(&memcg->thresholds_lock); + if (type == _MEM) + thresholds = memcg->thresholds; + else if (type == _MEMSWAP) + thresholds = memcg->memsw_thresholds; + else + BUG(); + + /* + * Something went wrong if we trying to unregister a threshold + * if we don't have thresholds + */ + BUG_ON(!thresholds); + + usage = mem_cgroup_usage(memcg, type == _MEMSWAP); + + /* Check if a threshold crossed before removing */ + __mem_cgroup_threshold(memcg, type == _MEMSWAP); + + /* Calculate new number of threshold */ + for (i = 0; i < thresholds->size; i++) { + if (thresholds->entries[i].eventfd != eventfd) + size++; + } + + /* Set thresholds array to NULL if we don't have thresholds */ + if (!size) { + thresholds_new = NULL; + goto assign; + } + + /* Allocate memory for new array of thresholds */ + thresholds_new = kmalloc(sizeof(*thresholds_new) + + size * sizeof(struct mem_cgroup_threshold), + GFP_KERNEL); + if (!thresholds_new) { + ret = -ENOMEM; + goto unlock; + } + thresholds_new->size = size; + + /* Copy thresholds and find current threshold */ + atomic_set(&thresholds_new->current_threshold, -1); + for (i = 0, j = 0; i < thresholds->size; i++) { + if (thresholds->entries[i].eventfd == eventfd) + continue; + + thresholds_new->entries[j] = thresholds->entries[i]; + if (thresholds_new->entries[j].threshold < usage) { + /* + * thresholds_new->current_threshold will not be used + * until rcu_assign_pointer(), so it's safe to increment + * it here. + */ + atomic_inc(&thresholds_new->current_threshold); + } + j++; + } + +assign: + if (type == _MEM) + rcu_assign_pointer(memcg->thresholds, thresholds_new); + else + rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new); + + /* To be sure that nobody uses thresholds before freeing it */ + synchronize_rcu(); + + kfree(thresholds); +unlock: + mutex_unlock(&memcg->thresholds_lock); + + return ret; +} static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), .read_u64 = mem_cgroup_read, + .register_event = mem_cgroup_register_event, + .unregister_event = mem_cgroup_unregister_event, }, { .name = "max_usage_in_bytes", @@ -2040,6 +3560,12 @@ static struct cftype mem_cgroup_files[] = { .read_u64 = mem_cgroup_read, }, { + .name = "soft_limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, + { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, @@ -2063,6 +3589,11 @@ static struct cftype mem_cgroup_files[] = { .read_u64 = mem_cgroup_swappiness_read, .write_u64 = mem_cgroup_swappiness_write, }, + { + .name = "move_charge_at_immigrate", + .read_u64 = mem_cgroup_move_charge_read, + .write_u64 = mem_cgroup_move_charge_write, + }, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP @@ -2071,6 +3602,8 @@ static struct cftype memsw_cgroup_files[] = { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), .read_u64 = mem_cgroup_read, + .register_event = mem_cgroup_register_event, + .unregister_event = mem_cgroup_unregister_event, }, { .name = "memsw.max_usage_in_bytes", @@ -2133,6 +3666,9 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) mz = &pn->zoneinfo[zone]; for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); + mz->usage_in_excess = 0; + mz->on_tree = false; + mz->mem = mem; } return 0; } @@ -2142,24 +3678,29 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) kfree(mem->info.nodeinfo[node]); } -static int mem_cgroup_size(void) -{ - int cpustat_size = nr_cpu_ids * sizeof(struct mem_cgroup_stat_cpu); - return sizeof(struct mem_cgroup) + cpustat_size; -} - static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *mem; - int size = mem_cgroup_size(); + int size = sizeof(struct mem_cgroup); + /* Can be very big if MAX_NUMNODES is very big */ if (size < PAGE_SIZE) mem = kmalloc(size, GFP_KERNEL); else mem = vmalloc(size); - if (mem) - memset(mem, 0, size); + if (!mem) + return NULL; + + memset(mem, 0, size); + mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu); + if (!mem->stat) { + if (size < PAGE_SIZE) + kfree(mem); + else + vfree(mem); + mem = NULL; + } return mem; } @@ -2178,10 +3719,14 @@ static void __mem_cgroup_free(struct mem_cgroup *mem) { int node; + mem_cgroup_remove_from_trees(mem); + free_css_id(&mem_cgroup_subsys, &mem->css); + for_each_node_state(node, N_POSSIBLE) free_mem_cgroup_per_zone_info(mem, node); - if (mem_cgroup_size() < PAGE_SIZE) + free_percpu(mem->stat); + if (sizeof(struct mem_cgroup) < PAGE_SIZE) kfree(mem); else vfree(mem); @@ -2192,9 +3737,9 @@ static void mem_cgroup_get(struct mem_cgroup *mem) atomic_inc(&mem->refcnt); } -static void mem_cgroup_put(struct mem_cgroup *mem) +static void __mem_cgroup_put(struct mem_cgroup *mem, int count) { - if (atomic_dec_and_test(&mem->refcnt)) { + if (atomic_sub_and_test(count, &mem->refcnt)) { struct mem_cgroup *parent = parent_mem_cgroup(mem); __mem_cgroup_free(mem); if (parent) @@ -2202,6 +3747,11 @@ static void mem_cgroup_put(struct mem_cgroup *mem) } } +static void mem_cgroup_put(struct mem_cgroup *mem) +{ + __mem_cgroup_put(mem, 1); +} + /* * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. */ @@ -2224,23 +3774,60 @@ static void __init enable_swap_cgroup(void) } #endif +static int mem_cgroup_soft_limit_tree_init(void) +{ + struct mem_cgroup_tree_per_node *rtpn; + struct mem_cgroup_tree_per_zone *rtpz; + int tmp, node, zone; + + for_each_node_state(node, N_POSSIBLE) { + tmp = node; + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); + if (!rtpn) + return 1; + + soft_limit_tree.rb_tree_per_node[node] = rtpn; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + } + return 0; +} + static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem, *parent; + long error = -ENOMEM; int node; mem = mem_cgroup_alloc(); if (!mem) - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; + /* root ? */ if (cont->parent == NULL) { + int cpu; enable_swap_cgroup(); parent = NULL; + root_mem_cgroup = mem; + if (mem_cgroup_soft_limit_tree_init()) + goto free_out; + for_each_possible_cpu(cpu) { + struct memcg_stock_pcp *stock = + &per_cpu(memcg_stock, cpu); + INIT_WORK(&stock->work, drain_local_stock); + } + hotcpu_notifier(memcg_stock_cpu_callback, 0); } else { parent = mem_cgroup_from_cont(cont->parent); mem->use_hierarchy = parent->use_hierarchy; @@ -2260,16 +3847,19 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) res_counter_init(&mem->res, NULL); res_counter_init(&mem->memsw, NULL); } - mem->last_scanned_child = NULL; + mem->last_scanned_child = 0; spin_lock_init(&mem->reclaim_param_lock); if (parent) mem->swappiness = get_swappiness(parent); atomic_set(&mem->refcnt, 1); + mem->move_charge_at_immigrate = 0; + mutex_init(&mem->thresholds_lock); return &mem->css; free_out: __mem_cgroup_free(mem); - return ERR_PTR(-ENOMEM); + root_mem_cgroup = NULL; + return ERR_PTR(error); } static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, @@ -2284,12 +3874,7 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - struct mem_cgroup *last_scanned_child = mem->last_scanned_child; - if (last_scanned_child) { - VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child)); - mem_cgroup_put(last_scanned_child); - } mem_cgroup_put(mem); } @@ -2306,18 +3891,445 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss, return ret; } +#ifdef CONFIG_MMU +/* Handlers for move charge at task migration. */ +#define PRECHARGE_COUNT_AT_ONCE 256 +static int mem_cgroup_do_precharge(unsigned long count) +{ + int ret = 0; + int batch_count = PRECHARGE_COUNT_AT_ONCE; + struct mem_cgroup *mem = mc.to; + + if (mem_cgroup_is_root(mem)) { + mc.precharge += count; + /* we don't need css_get for root */ + return ret; + } + /* try to charge at once */ + if (count > 1) { + struct res_counter *dummy; + /* + * "mem" cannot be under rmdir() because we've already checked + * by cgroup_lock_live_cgroup() that it is not removed and we + * are still under the same cgroup_mutex. So we can postpone + * css_get(). + */ + if (res_counter_charge(&mem->res, PAGE_SIZE * count, &dummy)) + goto one_by_one; + if (do_swap_account && res_counter_charge(&mem->memsw, + PAGE_SIZE * count, &dummy)) { + res_counter_uncharge(&mem->res, PAGE_SIZE * count); + goto one_by_one; + } + mc.precharge += count; + VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags)); + WARN_ON_ONCE(count > INT_MAX); + __css_get(&mem->css, (int)count); + return ret; + } +one_by_one: + /* fall back to one by one charge */ + while (count--) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (!batch_count--) { + batch_count = PRECHARGE_COUNT_AT_ONCE; + cond_resched(); + } + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); + if (ret || !mem) + /* mem_cgroup_clear_mc() will do uncharge later */ + return -ENOMEM; + mc.precharge++; + } + return ret; +} + +/** + * is_target_pte_for_mc - check a pte whether it is valid for move charge + * @vma: the vma the pte to be checked belongs + * @addr: the address corresponding to the pte to be checked + * @ptent: the pte to be checked + * @target: the pointer the target page or swap ent will be stored(can be NULL) + * + * Returns + * 0(MC_TARGET_NONE): if the pte is not a target for move charge. + * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for + * move charge. if @target is not NULL, the page is stored in target->page + * with extra refcnt got(Callers should handle it). + * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a + * target for charge migration. if @target is not NULL, the entry is stored + * in target->ent. + * + * Called with pte lock held. + */ +union mc_target { + struct page *page; + swp_entry_t ent; +}; + +enum mc_target_type { + MC_TARGET_NONE, /* not used */ + MC_TARGET_PAGE, + MC_TARGET_SWAP, +}; + +static int is_target_pte_for_mc(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, union mc_target *target) +{ + struct page *page = NULL; + struct page_cgroup *pc; + int ret = 0; + swp_entry_t ent = { .val = 0 }; + int usage_count = 0; + bool move_anon = test_bit(MOVE_CHARGE_TYPE_ANON, + &mc.to->move_charge_at_immigrate); + + if (!pte_present(ptent)) { + /* TODO: handle swap of shmes/tmpfs */ + if (pte_none(ptent) || pte_file(ptent)) + return 0; + else if (is_swap_pte(ptent)) { + ent = pte_to_swp_entry(ptent); + if (!move_anon || non_swap_entry(ent)) + return 0; + usage_count = mem_cgroup_count_swap_user(ent, &page); + } + } else { + page = vm_normal_page(vma, addr, ptent); + if (!page || !page_mapped(page)) + return 0; + /* + * TODO: We don't move charges of file(including shmem/tmpfs) + * pages for now. + */ + if (!move_anon || !PageAnon(page)) + return 0; + if (!get_page_unless_zero(page)) + return 0; + usage_count = page_mapcount(page); + } + if (usage_count > 1) { + /* + * TODO: We don't move charges of shared(used by multiple + * processes) pages for now. + */ + if (page) + put_page(page); + return 0; + } + if (page) { + pc = lookup_page_cgroup(page); + /* + * Do only loose check w/o page_cgroup lock. + * mem_cgroup_move_account() checks the pc is valid or not under + * the lock. + */ + if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { + ret = MC_TARGET_PAGE; + if (target) + target->page = page; + } + if (!ret || !target) + put_page(page); + } + /* throught */ + if (ent.val && do_swap_account && !ret && + css_id(&mc.from->css) == lookup_swap_cgroup(ent)) { + ret = MC_TARGET_SWAP; + if (target) + target->ent = ent; + } + return ret; +} + +static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->private; + pte_t *pte; + spinlock_t *ptl; + + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) + if (is_target_pte_for_mc(vma, addr, *pte, NULL)) + mc.precharge++; /* increment precharge temporarily */ + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + + return 0; +} + +static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) +{ + unsigned long precharge; + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + struct mm_walk mem_cgroup_count_precharge_walk = { + .pmd_entry = mem_cgroup_count_precharge_pte_range, + .mm = mm, + .private = vma, + }; + if (is_vm_hugetlb_page(vma)) + continue; + /* TODO: We don't move charges of shmem/tmpfs pages for now. */ + if (vma->vm_flags & VM_SHARED) + continue; + walk_page_range(vma->vm_start, vma->vm_end, + &mem_cgroup_count_precharge_walk); + } + up_read(&mm->mmap_sem); + + precharge = mc.precharge; + mc.precharge = 0; + + return precharge; +} + +static int mem_cgroup_precharge_mc(struct mm_struct *mm) +{ + return mem_cgroup_do_precharge(mem_cgroup_count_precharge(mm)); +} + +static void mem_cgroup_clear_mc(void) +{ + /* we must uncharge all the leftover precharges from mc.to */ + if (mc.precharge) { + __mem_cgroup_cancel_charge(mc.to, mc.precharge); + mc.precharge = 0; + } + /* + * we didn't uncharge from mc.from at mem_cgroup_move_account(), so + * we must uncharge here. + */ + if (mc.moved_charge) { + __mem_cgroup_cancel_charge(mc.from, mc.moved_charge); + mc.moved_charge = 0; + } + /* we must fixup refcnts and charges */ + if (mc.moved_swap) { + WARN_ON_ONCE(mc.moved_swap > INT_MAX); + /* uncharge swap account from the old cgroup */ + if (!mem_cgroup_is_root(mc.from)) + res_counter_uncharge(&mc.from->memsw, + PAGE_SIZE * mc.moved_swap); + __mem_cgroup_put(mc.from, mc.moved_swap); + + if (!mem_cgroup_is_root(mc.to)) { + /* + * we charged both to->res and to->memsw, so we should + * uncharge to->res. + */ + res_counter_uncharge(&mc.to->res, + PAGE_SIZE * mc.moved_swap); + VM_BUG_ON(test_bit(CSS_ROOT, &mc.to->css.flags)); + __css_put(&mc.to->css, mc.moved_swap); + } + /* we've already done mem_cgroup_get(mc.to) */ + + mc.moved_swap = 0; + } + mc.from = NULL; + mc.to = NULL; + mc.moving_task = NULL; + wake_up_all(&mc.waitq); +} + +static int mem_cgroup_can_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ + int ret = 0; + struct mem_cgroup *mem = mem_cgroup_from_cont(cgroup); + + if (mem->move_charge_at_immigrate) { + struct mm_struct *mm; + struct mem_cgroup *from = mem_cgroup_from_task(p); + + VM_BUG_ON(from == mem); + + mm = get_task_mm(p); + if (!mm) + return 0; + /* We move charges only when we move a owner of the mm */ + if (mm->owner == p) { + VM_BUG_ON(mc.from); + VM_BUG_ON(mc.to); + VM_BUG_ON(mc.precharge); + VM_BUG_ON(mc.moved_charge); + VM_BUG_ON(mc.moved_swap); + VM_BUG_ON(mc.moving_task); + mc.from = from; + mc.to = mem; + mc.precharge = 0; + mc.moved_charge = 0; + mc.moved_swap = 0; + mc.moving_task = current; + + ret = mem_cgroup_precharge_mc(mm); + if (ret) + mem_cgroup_clear_mc(); + } + mmput(mm); + } + return ret; +} + +static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ + mem_cgroup_clear_mc(); +} + +static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + int ret = 0; + struct vm_area_struct *vma = walk->private; + pte_t *pte; + spinlock_t *ptl; + +retry: + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; addr += PAGE_SIZE) { + pte_t ptent = *(pte++); + union mc_target target; + int type; + struct page *page; + struct page_cgroup *pc; + swp_entry_t ent; + + if (!mc.precharge) + break; + + type = is_target_pte_for_mc(vma, addr, ptent, &target); + switch (type) { + case MC_TARGET_PAGE: + page = target.page; + if (isolate_lru_page(page)) + goto put; + pc = lookup_page_cgroup(page); + if (!mem_cgroup_move_account(pc, + mc.from, mc.to, false)) { + mc.precharge--; + /* we uncharge from mc.from later. */ + mc.moved_charge++; + } + putback_lru_page(page); +put: /* is_target_pte_for_mc() gets the page */ + put_page(page); + break; + case MC_TARGET_SWAP: + ent = target.ent; + if (!mem_cgroup_move_swap_account(ent, + mc.from, mc.to, false)) { + mc.precharge--; + /* we fixup refcnts and charges later. */ + mc.moved_swap++; + } + break; + default: + break; + } + } + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + + if (addr != end) { + /* + * We have consumed all precharges we got in can_attach(). + * We try charge one by one, but don't do any additional + * charges to mc.to if we have failed in charge once in attach() + * phase. + */ + ret = mem_cgroup_do_precharge(1); + if (!ret) + goto retry; + } + + return ret; +} + +static void mem_cgroup_move_charge(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + lru_add_drain_all(); + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + int ret; + struct mm_walk mem_cgroup_move_charge_walk = { + .pmd_entry = mem_cgroup_move_charge_pte_range, + .mm = mm, + .private = vma, + }; + if (is_vm_hugetlb_page(vma)) + continue; + /* TODO: We don't move charges of shmem/tmpfs pages for now. */ + if (vma->vm_flags & VM_SHARED) + continue; + ret = walk_page_range(vma->vm_start, vma->vm_end, + &mem_cgroup_move_charge_walk); + if (ret) + /* + * means we have consumed all precharges and failed in + * doing additional charge. Just abandon here. + */ + break; + } + up_read(&mm->mmap_sem); +} + static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *old_cont, - struct task_struct *p) + struct task_struct *p, + bool threadgroup) { - mutex_lock(&memcg_tasklist); - /* - * FIXME: It's better to move charges of this process from old - * memcg to new memcg. But it's just on TODO-List now. - */ - mutex_unlock(&memcg_tasklist); + struct mm_struct *mm; + + if (!mc.to) + /* no need to move charge */ + return; + + mm = get_task_mm(p); + if (mm) { + mem_cgroup_move_charge(mm); + mmput(mm); + } + mem_cgroup_clear_mc(); +} +#else /* !CONFIG_MMU */ +static int mem_cgroup_can_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ + return 0; } +static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ +} +static void mem_cgroup_move_task(struct cgroup_subsys *ss, + struct cgroup *cont, + struct cgroup *old_cont, + struct task_struct *p, + bool threadgroup) +{ +} +#endif struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", @@ -2326,8 +4338,11 @@ struct cgroup_subsys mem_cgroup_subsys = { .pre_destroy = mem_cgroup_pre_destroy, .destroy = mem_cgroup_destroy, .populate = mem_cgroup_populate, + .can_attach = mem_cgroup_can_attach, + .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .early_init = 0, + .use_id = 1, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP