diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 1813 |
1 files changed, 1527 insertions, 286 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 954032b80bed..20a8193a7af8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6,6 +6,10 @@ * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> * + * 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 @@ -21,6 +25,7 @@ #include <linux/memcontrol.h> #include <linux/cgroup.h> #include <linux/mm.h> +#include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/smp.h> #include <linux/page-flags.h> @@ -32,7 +37,10 @@ #include <linux/rbtree.h> #include <linux/slab.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/spinlock.h> +#include <linux/eventfd.h> +#include <linux/sort.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> @@ -55,7 +63,15 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/ #define do_swap_account (0) #endif -#define SOFTLIMIT_EVENTS_THRESH (1000) +/* + * 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. @@ -69,62 +85,16 @@ enum mem_cgroup_stat_index { 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_EVENTS, /* sum of pagein + pageout for internal use */ 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]; }; -static inline void -__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat, - enum mem_cgroup_stat_index idx) -{ - stat->count[idx] = 0; -} - -static inline s64 -__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat, - enum mem_cgroup_stat_index idx) -{ - return stat->count[idx]; -} - -/* - * 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; -} - -static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat) -{ - s64 ret; - - ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE); - ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS); - return ret; -} - /* * per-zone information in memory controller. */ @@ -174,6 +144,41 @@ struct mem_cgroup_tree { static struct mem_cgroup_tree soft_limit_tree __read_mostly; +struct mem_cgroup_threshold { + struct eventfd_ctx *eventfd; + u64 threshold; +}; + +/* For threshold */ +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below usage. */ + int current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +struct mem_cgroup_thresholds { + /* Primary thresholds array */ + struct mem_cgroup_threshold_ary *primary; + /* + * Spare threshold array. + * This is needed to make mem_cgroup_unregister_event() "never fail". + * It must be able to store at least primary->size - 1 entries. + */ + struct mem_cgroup_threshold_ary *spare; +}; + +/* for OOM */ +struct mem_cgroup_eventfd_list { + struct list_head list; + struct eventfd_ctx *eventfd; +}; + +static void mem_cgroup_threshold(struct mem_cgroup *mem); +static void mem_cgroup_oom_notify(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 @@ -217,20 +222,75 @@ struct mem_cgroup { * 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; + /* OOM-Killer disable */ + int oom_kill_disable; /* 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_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; /* - * statistics. This must be placed at the end of memcg. + * percpu counter. */ - struct mem_cgroup_stat stat; + 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 */ + MOVE_CHARGE_TYPE_FILE, /* file page(including tmpfs) 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), +}; + +static bool move_anon(void) +{ + return test_bit(MOVE_CHARGE_TYPE_ANON, + &mc.to->move_charge_at_immigrate); +} + +static bool move_file(void) +{ + return test_bit(MOVE_CHARGE_TYPE_FILE, + &mc.to->move_charge_at_immigrate); +} + /* * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft * limit reclaim to prevent infinite loops, if they ever occur. @@ -258,9 +318,12 @@ enum charge_type { /* for encoding cft->private value on file */ #define _MEM (0) #define _MEMSWAP (1) +#define _OOM_TYPE (2) #define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) #define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) +/* Used for OOM nofiier */ +#define OOM_CONTROL (0) /* * Reclaim flags for mem_cgroup_hierarchical_reclaim @@ -371,23 +434,6 @@ mem_cgroup_remove_exceeded(struct mem_cgroup *mem, spin_unlock(&mctz->lock); } -static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem) -{ - bool ret = false; - int cpu; - s64 val; - struct mem_cgroup_stat_cpu *cpustat; - - cpu = get_cpu(); - cpustat = &mem->stat.cpustat[cpu]; - val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS); - if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) { - __mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS); - ret = true; - } - put_cpu(); - return ret; -} static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) { @@ -481,17 +527,31 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) 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; - struct mem_cgroup_stat *stat = &mem->stat; - struct mem_cgroup_stat_cpu *cpustat; - int cpu = get_cpu(); - - cpustat = &stat->cpustat[cpu]; - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_SWAPOUT, val); - put_cpu(); + this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); } static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, @@ -499,24 +559,21 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, 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]; + preempt_disable(); + if (PageCgroupCache(pc)) - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val); + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], val); else - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val); + __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], val); if (charge) - __mem_cgroup_stat_add_safe(cpustat, - MEM_CGROUP_STAT_PGPGIN_COUNT, 1); + __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]); else - __mem_cgroup_stat_add_safe(cpustat, - MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1); - put_cpu(); + __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, @@ -534,6 +591,29 @@ static unsigned long mem_cgroup_get_local_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, @@ -1000,7 +1080,7 @@ static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) } /** - * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode. + * 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 * @@ -1174,7 +1254,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, } } } - if (!mem_cgroup_local_usage(&victim->stat)) { + if (!mem_cgroup_local_usage(victim)) { /* this cgroup's local usage == 0 */ css_put(&victim->css); continue; @@ -1205,32 +1285,141 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, return total; } -bool mem_cgroup_oom_called(struct task_struct *task) +static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data) { - bool ret = false; - struct mem_cgroup *mem; - struct mm_struct *mm; + int *val = (int *)data; + int x; + /* + * 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. + */ + 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; - 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(); - return ret; + mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb); + + if (lock_count == 1) + return true; + return false; } -static int record_last_oom_cb(struct mem_cgroup *mem, void *data) +static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data) { - mem->last_oom_jiffies = jiffies; + /* + * 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 record_last_oom(struct mem_cgroup *mem) +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); + +struct oom_wait_info { + struct mem_cgroup *mem; + wait_queue_t wait; +}; + +static int memcg_oom_wake_function(wait_queue_t *wait, + unsigned mode, int sync, void *arg) +{ + struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg; + struct oom_wait_info *oom_wait_info; + + oom_wait_info = container_of(wait, struct oom_wait_info, wait); + + if (oom_wait_info->mem == wake_mem) + goto wakeup; + /* if no hierarchy, no match */ + if (!oom_wait_info->mem->use_hierarchy || !wake_mem->use_hierarchy) + return 0; + /* + * Both of oom_wait_info->mem and wake_mem are stable under us. + * Then we can use css_is_ancestor without taking care of RCU. + */ + if (!css_is_ancestor(&oom_wait_info->mem->css, &wake_mem->css) && + !css_is_ancestor(&wake_mem->css, &oom_wait_info->mem->css)) + return 0; + +wakeup: + return autoremove_wake_function(wait, mode, sync, arg); +} + +static void memcg_wakeup_oom(struct mem_cgroup *mem) { - mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb); + /* for filtering, pass "mem" as argument. */ + __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, mem); +} + +static void memcg_oom_recover(struct mem_cgroup *mem) +{ + if (atomic_read(&mem->oom_lock)) + memcg_wakeup_oom(mem); +} + +/* + * 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) +{ + struct oom_wait_info owait; + bool locked, need_to_kill; + + owait.mem = mem; + owait.wait.flags = 0; + owait.wait.func = memcg_oom_wake_function; + owait.wait.private = current; + INIT_LIST_HEAD(&owait.wait.task_list); + need_to_kill = true; + /* 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. + */ + prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); + if (!locked || mem->oom_kill_disable) + need_to_kill = false; + if (locked) + mem_cgroup_oom_notify(mem); + mutex_unlock(&memcg_oom_mutex); + + if (need_to_kill) { + finish_wait(&memcg_oom_waitq, &owait.wait); + mem_cgroup_out_of_memory(mem, mask); + } else { + schedule(); + finish_wait(&memcg_oom_waitq, &owait.wait); + } + mutex_lock(&memcg_oom_mutex); + mem_cgroup_oom_unlock(mem); + memcg_wakeup_oom(mem); + 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; } /* @@ -1240,9 +1429,6 @@ static void record_last_oom(struct mem_cgroup *mem) void mem_cgroup_update_file_mapped(struct page *page, int val) { struct mem_cgroup *mem; - struct mem_cgroup_stat *stat; - struct mem_cgroup_stat_cpu *cpustat; - int cpu; struct page_cgroup *pc; pc = lookup_page_cgroup(page); @@ -1251,20 +1437,20 @@ void mem_cgroup_update_file_mapped(struct page *page, int val) lock_page_cgroup(pc); mem = pc->mem_cgroup; - if (!mem) - goto done; - - if (!PageCgroupUsed(pc)) + if (!mem || !PageCgroupUsed(pc)) goto done; /* - * Preemption is already disabled, we don't need get_cpu() + * Preemption is already disabled. We can use __this_cpu_xxx */ - cpu = smp_processor_id(); - stat = &mem->stat; - cpustat = &stat->cpustat[cpu]; + 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); + } - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED, val); done: unlock_page_cgroup(pc); } @@ -1330,7 +1516,7 @@ static void drain_local_stock(struct work_struct *dummy) /* * Cache charges(val) which is from res_counter, to local per_cpu area. - * This will be consumed by consumt_stock() function, later. + * This will be consumed by consume_stock() function, later. */ static void refill_stock(struct mem_cgroup *mem, int val) { @@ -1401,19 +1587,21 @@ static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb, * 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, struct page *page) + 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. @@ -1440,7 +1628,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, unsigned long flags = 0; if (consume_stock(mem)) - goto charged; + goto done; ret = res_counter_charge(&mem->res, csize, &fail_res); if (likely(!ret)) { @@ -1483,28 +1671,68 @@ 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) { - mem_cgroup_out_of_memory(mem_over_limit, gfp_mask); - record_last_oom(mem_over_limit); + 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); -charged: - /* - * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. - * if they exceeds softlimit. - */ - if (mem_cgroup_soft_limit_check(mem)) - mem_cgroup_update_tree(mem, page); done: return 0; nomem: css_put(&mem->css); return -ENOMEM; +bypass: + *memcg = NULL; + return 0; } /* @@ -1512,14 +1740,23 @@ nomem: * 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) +static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem, + unsigned long count) { if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, PAGE_SIZE * count); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); + 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); } - css_put(&mem->css); + /* we don't need css_put for root */ +} + +static void mem_cgroup_cancel_charge(struct mem_cgroup *mem) +{ + __mem_cgroup_cancel_charge(mem, 1); } /* @@ -1615,6 +1852,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, 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); } /** @@ -1622,61 +1865,48 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, * @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. * - * 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 void __mem_cgroup_move_account(struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to) + struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) { - struct page *page; - int cpu; - struct mem_cgroup_stat *stat; - struct mem_cgroup_stat_cpu *cpustat; - VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); VM_BUG_ON(!PageCgroupLocked(pc)); VM_BUG_ON(!PageCgroupUsed(pc)); VM_BUG_ON(pc->mem_cgroup != from); - if (!mem_cgroup_is_root(from)) - res_counter_uncharge(&from->res, PAGE_SIZE); - mem_cgroup_charge_statistics(from, pc, false); - - page = pc->page; - if (page_mapped(page) && !PageAnon(page)) { - cpu = smp_processor_id(); - /* Update mapped_file data for mem_cgroup "from" */ - stat = &from->stat; - cpustat = &stat->cpustat[cpu]; - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED, - -1); - - /* Update mapped_file data for mem_cgroup "to" */ - stat = &to->stat; - cpustat = &stat->cpustat[cpu]; - __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED, - 1); + 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 (uncharge) + /* This is not "cancel", but cancel_charge does all we need. */ + mem_cgroup_cancel_charge(from); - if (do_swap_account && !mem_cgroup_is_root(from)) - res_counter_uncharge(&from->memsw, PAGE_SIZE); - css_put(&from->css); - - css_get(&to->css); + /* caller should have done css_get */ pc->mem_cgroup = to; mem_cgroup_charge_statistics(to, pc, true); /* * 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 it's garanteed that - * "to" is never removed. So, we don't check rmdir status here. + * 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. */ } @@ -1685,15 +1915,20 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc, * __mem_cgroup_move_account() */ static int mem_cgroup_move_account(struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to) + 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); + __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; } @@ -1722,15 +1957,13 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, goto put; parent = mem_cgroup_from_cont(pcg); - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page); + ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); if (ret || !parent) goto put_back; - ret = mem_cgroup_move_account(pc, child, parent); - if (!ret) - css_put(&parent->css); /* drop extra refcnt by try_charge() */ - else - mem_cgroup_cancel_charge(parent); /* does css_put */ + ret = mem_cgroup_move_account(pc, child, parent, true); + if (ret) + mem_cgroup_cancel_charge(parent); put_back: putback_lru_page(page); put: @@ -1760,7 +1993,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, prefetchw(pc); mem = memcg; - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); if (ret || !mem) return ret; @@ -1880,14 +2113,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, if (!mem) goto charge_cur_mm; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page); + ret = __mem_cgroup_try_charge(NULL, mask, ptr, true); /* drop extra refcnt from tryget */ css_put(&mem->css); return ret; charge_cur_mm: if (unlikely(!mm)) mm = &init_mm; - return __mem_cgroup_try_charge(mm, mask, ptr, true, page); + return __mem_cgroup_try_charge(mm, mask, ptr, true); } static void @@ -1963,15 +2196,6 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) /* 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; /* @@ -1982,6 +2206,17 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) if (!batch->memcg) batch->memcg = mem; /* + * 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 (!batch->do_batch || test_thread_flag(TIF_MEMDIE)) + goto direct_uncharge; + + /* * 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. @@ -1997,6 +2232,8 @@ direct_uncharge: res_counter_uncharge(&mem->res, PAGE_SIZE); if (uncharge_memsw) res_counter_uncharge(&mem->memsw, PAGE_SIZE); + if (unlikely(batch->memcg != mem)) + memcg_oom_recover(mem); return; } @@ -2033,7 +2270,8 @@ __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)) + /* See mem_cgroup_prepare_migration() */ + if (page_mapped(page) || PageCgroupMigration(pc)) goto unlock_out; break; case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: @@ -2064,8 +2302,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); - if (mem_cgroup_soft_limit_check(mem)) - mem_cgroup_update_tree(mem, page); + 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); @@ -2134,6 +2371,7 @@ void mem_cgroup_uncharge_end(void) res_counter_uncharge(&batch->memcg->res, batch->bytes); if (batch->memsw_bytes) res_counter_uncharge(&batch->memcg->memsw, batch->memsw_bytes); + memcg_oom_recover(batch->memcg); /* forget this pointer (for sanity check) */ batch->memcg = NULL; } @@ -2192,16 +2430,76 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) } 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 /* * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. */ -int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) +int mem_cgroup_prepare_migration(struct page *page, + struct page *newpage, struct mem_cgroup **ptr) { struct page_cgroup *pc; struct mem_cgroup *mem = NULL; + enum charge_type ctype; int ret = 0; if (mem_cgroup_disabled()) @@ -2212,70 +2510,125 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) if (PageCgroupUsed(pc)) { mem = pc->mem_cgroup; css_get(&mem->css); + /* + * At migrating an anonymous page, its mapcount goes down + * to 0 and uncharge() will be called. But, even if it's fully + * unmapped, migration may fail and this page has to be + * charged again. We set MIGRATION flag here and delay uncharge + * until end_migration() is called + * + * Corner Case Thinking + * A) + * When the old page was mapped as Anon and it's unmap-and-freed + * while migration was ongoing. + * If unmap finds the old page, uncharge() of it will be delayed + * until end_migration(). If unmap finds a new page, it's + * uncharged when it make mapcount to be 1->0. If unmap code + * finds swap_migration_entry, the new page will not be mapped + * and end_migration() will find it(mapcount==0). + * + * B) + * When the old page was mapped but migraion fails, the kernel + * remaps it. A charge for it is kept by MIGRATION flag even + * if mapcount goes down to 0. We can do remap successfully + * without charging it again. + * + * C) + * The "old" page is under lock_page() until the end of + * migration, so, the old page itself will not be swapped-out. + * If the new page is swapped out before end_migraton, our + * hook to usual swap-out path will catch the event. + */ + if (PageAnon(page)) + SetPageCgroupMigration(pc); } unlock_page_cgroup(pc); + /* + * If the page is not charged at this point, + * we return here. + */ + if (!mem) + return 0; - if (mem) { - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, - page); - css_put(&mem->css); - } *ptr = mem; + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false); + css_put(&mem->css);/* drop extra refcnt */ + if (ret || *ptr == NULL) { + if (PageAnon(page)) { + lock_page_cgroup(pc); + ClearPageCgroupMigration(pc); + unlock_page_cgroup(pc); + /* + * The old page may be fully unmapped while we kept it. + */ + mem_cgroup_uncharge_page(page); + } + return -ENOMEM; + } + /* + * We charge new page before it's used/mapped. So, even if unlock_page() + * is called before end_migration, we can catch all events on this new + * page. In the case new page is migrated but not remapped, new page's + * mapcount will be finally 0 and we call uncharge in end_migration(). + */ + pc = lookup_page_cgroup(newpage); + if (PageAnon(page)) + ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; + else if (page_is_file_cache(page)) + ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + else + ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; + __mem_cgroup_commit_charge(mem, pc, ctype); return ret; } /* remove redundant charge if migration failed*/ void mem_cgroup_end_migration(struct mem_cgroup *mem, - struct page *oldpage, struct page *newpage) + struct page *oldpage, struct page *newpage) { - struct page *target, *unused; + struct page *used, *unused; struct page_cgroup *pc; - enum charge_type ctype; if (!mem) return; + /* blocks rmdir() */ cgroup_exclude_rmdir(&mem->css); /* at migration success, oldpage->mapping is NULL. */ if (oldpage->mapping) { - target = oldpage; - unused = NULL; + used = oldpage; + unused = newpage; } else { - target = newpage; + used = newpage; unused = oldpage; } - - if (PageAnon(target)) - ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; - else if (page_is_file_cache(target)) - ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; - else - ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - - /* unused page is not on radix-tree now. */ - if (unused) - __mem_cgroup_uncharge_common(unused, ctype); - - pc = lookup_page_cgroup(target); /* - * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup. - * So, double-counting is effectively avoided. + * We disallowed uncharge of pages under migration because mapcount + * of the page goes down to zero, temporarly. + * Clear the flag and check the page should be charged. */ - __mem_cgroup_commit_charge(mem, pc, ctype); + pc = lookup_page_cgroup(oldpage); + lock_page_cgroup(pc); + ClearPageCgroupMigration(pc); + unlock_page_cgroup(pc); + + if (unused != oldpage) + pc = lookup_page_cgroup(unused); + __mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE); + pc = lookup_page_cgroup(used); /* - * Both of oldpage and newpage are still under lock_page(). - * Then, we don't have to care about race in radix-tree. - * But we have to be careful that this page is unmapped or not. - * - * There is a case for !page_mapped(). At the start of - * migration, oldpage was mapped. But now, it's zapped. - * But we know *target* page is not freed/reused under us. - * mem_cgroup_uncharge_page() does all necessary checks. + * If a page is a file cache, radix-tree replacement is very atomic + * and we can skip this check. When it was an Anon page, its mapcount + * goes down to 0. But because we added MIGRATION flage, it's not + * uncharged yet. There are several case but page->mapcount check + * and USED bit check in mem_cgroup_uncharge_page() will do enough + * check. (see prepare_charge() also) */ - if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) - mem_cgroup_uncharge_page(target); + if (PageAnon(used)) + mem_cgroup_uncharge_page(used); /* - * At migration, we may charge account against cgroup which has no tasks + * 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. */ @@ -2313,10 +2666,11 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; - u64 memswlimit; + u64 memswlimit, memlimit; int ret = 0; int children = mem_cgroup_count_children(memcg); u64 curusage, oldusage; + int enlarge; /* * For keeping hierarchical_reclaim simple, how long we should retry @@ -2327,6 +2681,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); + enlarge = 0; while (retry_count) { if (signal_pending(current)) { ret = -EINTR; @@ -2344,6 +2699,11 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, mutex_unlock(&set_limit_mutex); break; } + + memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); + if (memlimit < val) + enlarge = 1; + ret = res_counter_set_limit(&memcg->res, val); if (!ret) { if (memswlimit == val) @@ -2365,6 +2725,8 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, else oldusage = curusage; } + if (!ret && enlarge) + memcg_oom_recover(memcg); return ret; } @@ -2373,9 +2735,10 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; - u64 memlimit, oldusage, curusage; + u64 memlimit, memswlimit, oldusage, curusage; int children = mem_cgroup_count_children(memcg); int ret = -EBUSY; + int enlarge = 0; /* see mem_cgroup_resize_res_limit */ retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; @@ -2397,6 +2760,9 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, mutex_unlock(&set_limit_mutex); break; } + memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); + if (memswlimit < val) + enlarge = 1; ret = res_counter_set_limit(&memcg->memsw, val); if (!ret) { if (memlimit == val) @@ -2419,6 +2785,8 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, else oldusage = curusage; } + if (!ret && enlarge) + memcg_oom_recover(memcg); return ret; } @@ -2545,7 +2913,7 @@ 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; } @@ -2610,6 +2978,7 @@ move_account: if (ret) break; } + memcg_oom_recover(mem); /* it seems parent cgroup doesn't have enough mem */ if (ret == -ENOMEM) goto try_to_free; @@ -2704,7 +3073,7 @@ 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->stat, d->idx); + d->val += mem_cgroup_read_stat(mem, d->idx); return 0; } @@ -2719,40 +3088,50 @@ mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem, *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 idx_val, val; + u64 val; int type, name; type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); switch (type) { case _MEM: - if (name == RES_USAGE && mem_cgroup_is_root(mem)) { - 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; - val <<= PAGE_SHIFT; - } else + if (name == RES_USAGE) + val = mem_cgroup_usage(mem, false); + else val = res_counter_read_u64(&mem->res, name); break; case _MEMSWAP: - if (name == RES_USAGE && mem_cgroup_is_root(mem)) { - 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; - mem_cgroup_get_recursive_idx_stat(mem, - MEM_CGROUP_STAT_SWAPOUT, &idx_val); - val += idx_val; - val <<= PAGE_SHIFT; - } else + if (name == RES_USAGE) + val = mem_cgroup_usage(mem, true); + else val = res_counter_read_u64(&mem->memsw, name); break; default: @@ -2865,6 +3244,39 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) 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 { @@ -2910,18 +3322,18 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) s64 val; /* per cpu stat */ - val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE); + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); s->stat[MCS_CACHE] += val * PAGE_SIZE; - val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); s->stat[MCS_RSS] += val * PAGE_SIZE; - val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_FILE_MAPPED); + 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->stat, MEM_CGROUP_STAT_PGPGIN_COUNT); + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT); s->stat[MCS_PGPGIN] += val; - val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT); + 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->stat, MEM_CGROUP_STAT_SWAPOUT); + val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT); s->stat[MCS_SWAP] += val * PAGE_SIZE; } @@ -3049,12 +3461,339 @@ 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.primary); + else + t = rcu_dereference(memcg->memsw_thresholds.primary); + + 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 = 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 */ + 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_oom_notify_cb(struct mem_cgroup *mem, void *data) +{ + struct mem_cgroup_eventfd_list *ev; + + list_for_each_entry(ev, &mem->oom_notify, list) + eventfd_signal(ev->eventfd, 1); + return 0; +} + +static void mem_cgroup_oom_notify(struct mem_cgroup *mem) +{ + mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_notify_cb); +} + +static int mem_cgroup_usage_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_thresholds *thresholds; + struct mem_cgroup_threshold_ary *new; + int type = MEMFILE_TYPE(cft->private); + u64 threshold, usage; + int i, size, 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->primary) + __mem_cgroup_threshold(memcg, type == _MEMSWAP); + + size = thresholds->primary ? thresholds->primary->size + 1 : 1; + + /* Allocate memory for new array of thresholds */ + new = kmalloc(sizeof(*new) + size * sizeof(struct mem_cgroup_threshold), + GFP_KERNEL); + if (!new) { + ret = -ENOMEM; + goto unlock; + } + new->size = size; + + /* Copy thresholds (if any) to new array */ + if (thresholds->primary) { + memcpy(new->entries, thresholds->primary->entries, (size - 1) * + sizeof(struct mem_cgroup_threshold)); + } + + /* Add new threshold */ + new->entries[size - 1].eventfd = eventfd; + new->entries[size - 1].threshold = threshold; + + /* Sort thresholds. Registering of new threshold isn't time-critical */ + sort(new->entries, size, sizeof(struct mem_cgroup_threshold), + compare_thresholds, NULL); + + /* Find current threshold */ + new->current_threshold = -1; + for (i = 0; i < size; i++) { + if (new->entries[i].threshold < usage) { + /* + * new->current_threshold will not be used until + * rcu_assign_pointer(), so it's safe to increment + * it here. + */ + ++new->current_threshold; + } + } + + /* Free old spare buffer and save old primary buffer as spare */ + kfree(thresholds->spare); + thresholds->spare = thresholds->primary; + + rcu_assign_pointer(thresholds->primary, new); + + /* To be sure that nobody uses thresholds */ + synchronize_rcu(); + +unlock: + mutex_unlock(&memcg->thresholds_lock); + + return ret; +} + +static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp, + struct cftype *cft, struct eventfd_ctx *eventfd) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup_thresholds *thresholds; + struct mem_cgroup_threshold_ary *new; + int type = MEMFILE_TYPE(cft->private); + u64 usage; + int i, j, size; + + 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 */ + size = 0; + for (i = 0; i < thresholds->primary->size; i++) { + if (thresholds->primary->entries[i].eventfd != eventfd) + size++; + } + + new = thresholds->spare; + + /* Set thresholds array to NULL if we don't have thresholds */ + if (!size) { + kfree(new); + new = NULL; + goto swap_buffers; + } + + new->size = size; + + /* Copy thresholds and find current threshold */ + new->current_threshold = -1; + for (i = 0, j = 0; i < thresholds->primary->size; i++) { + if (thresholds->primary->entries[i].eventfd == eventfd) + continue; + + new->entries[j] = thresholds->primary->entries[i]; + if (new->entries[j].threshold < usage) { + /* + * new->current_threshold will not be used + * until rcu_assign_pointer(), so it's safe to increment + * it here. + */ + ++new->current_threshold; + } + j++; + } + +swap_buffers: + /* Swap primary and spare array */ + thresholds->spare = thresholds->primary; + rcu_assign_pointer(thresholds->primary, new); + + /* To be sure that nobody uses thresholds */ + synchronize_rcu(); + + mutex_unlock(&memcg->thresholds_lock); +} + +static int mem_cgroup_oom_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_eventfd_list *event; + int type = MEMFILE_TYPE(cft->private); + + BUG_ON(type != _OOM_TYPE); + event = kmalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + mutex_lock(&memcg_oom_mutex); + + event->eventfd = eventfd; + list_add(&event->list, &memcg->oom_notify); + + /* already in OOM ? */ + if (atomic_read(&memcg->oom_lock)) + eventfd_signal(eventfd, 1); + mutex_unlock(&memcg_oom_mutex); + + return 0; +} + +static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, + struct cftype *cft, struct eventfd_ctx *eventfd) +{ + struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup_eventfd_list *ev, *tmp; + int type = MEMFILE_TYPE(cft->private); + + BUG_ON(type != _OOM_TYPE); + + mutex_lock(&memcg_oom_mutex); + + list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) { + if (ev->eventfd == eventfd) { + list_del(&ev->list); + kfree(ev); + } + } + + mutex_unlock(&memcg_oom_mutex); +} + +static int mem_cgroup_oom_control_read(struct cgroup *cgrp, + struct cftype *cft, struct cgroup_map_cb *cb) +{ + struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + + cb->fill(cb, "oom_kill_disable", mem->oom_kill_disable); + + if (atomic_read(&mem->oom_lock)) + cb->fill(cb, "under_oom", 1); + else + cb->fill(cb, "under_oom", 0); + return 0; +} + +/* + */ +static int mem_cgroup_oom_control_write(struct cgroup *cgrp, + struct cftype *cft, u64 val) +{ + struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent; + + /* cannot set to root cgroup and only 0 and 1 are allowed */ + if (!cgrp->parent || !((val == 0) || (val == 1))) + return -EINVAL; + + parent = mem_cgroup_from_cont(cgrp->parent); + + cgroup_lock(); + /* oom-kill-disable is a flag for subhierarchy. */ + if ((parent->use_hierarchy) || + (mem->use_hierarchy && !list_empty(&cgrp->children))) { + cgroup_unlock(); + return -EINVAL; + } + mem->oom_kill_disable = val; + if (!val) + memcg_oom_recover(mem); + cgroup_unlock(); + return 0; +} 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_usage_register_event, + .unregister_event = mem_cgroup_usage_unregister_event, }, { .name = "max_usage_in_bytes", @@ -3098,6 +3837,19 @@ 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, + }, + { + .name = "oom_control", + .read_map = mem_cgroup_oom_control_read, + .write_u64 = mem_cgroup_oom_control_write, + .register_event = mem_cgroup_oom_register_event, + .unregister_event = mem_cgroup_oom_unregister_event, + .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), + }, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP @@ -3106,6 +3858,8 @@ 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_usage_register_event, + .unregister_event = mem_cgroup_usage_unregister_event, }, { .name = "memsw.max_usage_in_bytes", @@ -3180,24 +3934,29 @@ 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; } @@ -3222,7 +3981,8 @@ static void __mem_cgroup_free(struct mem_cgroup *mem) 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); @@ -3233,9 +3993,9 @@ 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) @@ -3243,6 +4003,11 @@ 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. */ @@ -3319,10 +4084,10 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) 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; + mem->oom_kill_disable = parent->oom_kill_disable; } if (parent && parent->use_hierarchy) { @@ -3341,10 +4106,13 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) } mem->last_scanned_child = 0; spin_lock_init(&mem->reclaim_param_lock); + INIT_LIST_HEAD(&mem->oom_notify); 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); @@ -3381,17 +4149,488 @@ 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 struct page *mc_handle_present_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent) +{ + struct page *page = vm_normal_page(vma, addr, ptent); + + if (!page || !page_mapped(page)) + return NULL; + if (PageAnon(page)) { + /* we don't move shared anon */ + if (!move_anon() || page_mapcount(page) > 2) + return NULL; + } else if (!move_file()) + /* we ignore mapcount for file pages */ + return NULL; + if (!get_page_unless_zero(page)) + return NULL; + + return page; +} + +static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, swp_entry_t *entry) +{ + int usage_count; + struct page *page = NULL; + swp_entry_t ent = pte_to_swp_entry(ptent); + + if (!move_anon() || non_swap_entry(ent)) + return NULL; + usage_count = mem_cgroup_count_swap_user(ent, &page); + if (usage_count > 1) { /* we don't move shared anon */ + if (page) + put_page(page); + return NULL; + } + if (do_swap_account) + entry->val = ent.val; + + return page; +} + +static struct page *mc_handle_file_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, swp_entry_t *entry) +{ + struct page *page = NULL; + struct inode *inode; + struct address_space *mapping; + pgoff_t pgoff; + + if (!vma->vm_file) /* anonymous vma */ + return NULL; + if (!move_file()) + return NULL; + + inode = vma->vm_file->f_path.dentry->d_inode; + mapping = vma->vm_file->f_mapping; + if (pte_none(ptent)) + pgoff = linear_page_index(vma, addr); + else /* pte_file(ptent) is true */ + pgoff = pte_to_pgoff(ptent); + + /* page is moved even if it's not RSS of this task(page-faulted). */ + if (!mapping_cap_swap_backed(mapping)) { /* normal file */ + page = find_get_page(mapping, pgoff); + } else { /* shmem/tmpfs file. we should take account of swap too. */ + swp_entry_t ent; + mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent); + if (do_swap_account) + entry->val = ent.val; + } + + return page; +} + +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 }; + + if (pte_present(ptent)) + page = mc_handle_present_pte(vma, addr, ptent); + else if (is_swap_pte(ptent)) + page = mc_handle_swap_pte(vma, addr, ptent, &ent); + else if (pte_none(ptent) || pte_file(ptent)) + page = mc_handle_file_pte(vma, addr, ptent, &ent); + + if (!page && !ent.val) + 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); + } + /* There is a swap entry and a page doesn't exist or isn't charged */ + if (ent.val && !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; + 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; + memcg_oom_recover(mc.to); + } + /* + * 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; + memcg_oom_recover(mc.from); + } + /* 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; + 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, bool threadgroup) { - /* - * FIXME: It's better to move charges of this process from old - * memcg to new memcg. But it's just on TODO-List now. - */ + 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", @@ -3400,6 +4639,8 @@ 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, |