+ if (mem_cgroup_disabled())
+ return;
+
+ pc = lookup_page_cgroup(page);
+ /*
+ * Used bit is set without atomic ops but after smp_wmb().
+ * For making pc->mem_cgroup visible, insert smp_rmb() here.
+ */
+ smp_rmb();
+ /* 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]);
+}
+
+void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
+{
+ struct page_cgroup *pc;
+ struct mem_cgroup_per_zone *mz;
+
+ 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.
+ */
+ smp_rmb();
+ if (!PageCgroupUsed(pc))
+ return;
+
+ 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]);
+}
+
+/*
+ * At handling SwapCache, pc->mem_cgroup may be changed while it's linked to
+ * lru because the page may.be reused after it's fully uncharged (because of
+ * SwapCache behavior).To handle that, unlink page_cgroup from LRU when charge
+ * it again. This function is only used to charge SwapCache. It's done under
+ * lock_page and expected that zone->lru_lock is never held.
+ */
+static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
+{
+ unsigned long flags;
+ struct zone *zone = page_zone(page);
+ struct page_cgroup *pc = lookup_page_cgroup(page);
+
+ spin_lock_irqsave(&zone->lru_lock, flags);
+ /*
+ * Forget old LRU when this page_cgroup is *not* used. This Used bit
+ * is guarded by lock_page() because the page is SwapCache.
+ */
+ if (!PageCgroupUsed(pc))
+ mem_cgroup_del_lru_list(page, page_lru(page));
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
+{
+ unsigned long flags;
+ struct zone *zone = page_zone(page);
+ struct page_cgroup *pc = lookup_page_cgroup(page);
+
+ spin_lock_irqsave(&zone->lru_lock, flags);
+ /* link when the page is linked to LRU but page_cgroup isn't */
+ if (PageLRU(page) && !PageCgroupAcctLRU(pc))
+ mem_cgroup_add_lru_list(page, page_lru(page));
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+
+void mem_cgroup_move_lists(struct page *page,
+ enum lru_list from, enum lru_list to)
+{
+ if (mem_cgroup_disabled())
+ return;
+ mem_cgroup_del_lru_list(page, from);
+ mem_cgroup_add_lru_list(page, to);
+}
+
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
+{
+ int ret;
+ struct mem_cgroup *curr = NULL;
+
+ task_lock(task);
+ rcu_read_lock();
+ curr = try_get_mem_cgroup_from_mm(task->mm);
+ rcu_read_unlock();
+ task_unlock(task);
+ if (!curr)
+ return 0;
+ /*
+ * 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").
+ */
+ if (mem->use_hierarchy)
+ ret = css_is_ancestor(&curr->css, &mem->css);
+ else
+ ret = (curr == mem);
+ css_put(&curr->css);
+ return ret;
+}
+
+/*
+ * prev_priority control...this will be used in memory reclaim path.
+ */
+int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
+{
+ int prev_priority;
+
+ spin_lock(&mem->reclaim_param_lock);
+ prev_priority = mem->prev_priority;
+ spin_unlock(&mem->reclaim_param_lock);
+
+ return prev_priority;
+}
+
+void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
+{
+ spin_lock(&mem->reclaim_param_lock);
+ if (priority < mem->prev_priority)
+ mem->prev_priority = priority;
+ spin_unlock(&mem->reclaim_param_lock);
+}
+
+void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
+{
+ spin_lock(&mem->reclaim_param_lock);
+ mem->prev_priority = priority;
+ spin_unlock(&mem->reclaim_param_lock);
+}
+
+static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
+{
+ unsigned long active;
+ unsigned long inactive;
+ unsigned long gb;
+ unsigned long inactive_ratio;
+
+ 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)
+ inactive_ratio = int_sqrt(10 * gb);
+ else
+ inactive_ratio = 1;
+
+ if (present_pages) {
+ present_pages[0] = inactive;
+ present_pages[1] = active;
+ }
+
+ return inactive_ratio;
+}
+
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+{
+ unsigned long active;
+ unsigned long inactive;
+ unsigned long present_pages[2];
+ unsigned long inactive_ratio;
+
+ inactive_ratio = calc_inactive_ratio(memcg, present_pages);
+
+ inactive = present_pages[0];
+ active = present_pages[1];
+
+ if (inactive * inactive_ratio < active)
+ return 1;
+
+ 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)
+{
+ int nid = zone->zone_pgdat->node_id;
+ int zid = zone_idx(zone);
+ struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+
+ return MEM_CGROUP_ZSTAT(mz, lru);
+}
+
+struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
+ struct zone *zone)
+{
+ int nid = zone->zone_pgdat->node_id;
+ int zid = zone_idx(zone);
+ struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+
+ return &mz->reclaim_stat;
+}
+
+struct zone_reclaim_stat *
+mem_cgroup_get_reclaim_stat_from_page(struct page *page)
+{
+ struct page_cgroup *pc;
+ struct mem_cgroup_per_zone *mz;
+
+ if (mem_cgroup_disabled())
+ return NULL;
+
+ pc = lookup_page_cgroup(page);
+ /*
+ * Used bit is set without atomic ops but after smp_wmb().
+ * For making pc->mem_cgroup visible, insert smp_rmb() here.
+ */
+ smp_rmb();
+ if (!PageCgroupUsed(pc))
+ return NULL;
+
+ mz = page_cgroup_zoneinfo(pc);
+ if (!mz)
+ return NULL;
+
+ return &mz->reclaim_stat;
+}
+
+unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
+ struct list_head *dst,
+ unsigned long *scanned, int order,
+ int mode, struct zone *z,
+ struct mem_cgroup *mem_cont,
+ int active, int file)
+{
+ unsigned long nr_taken = 0;
+ struct page *page;
+ unsigned long scan;
+ LIST_HEAD(pc_list);
+ struct list_head *src;
+ struct page_cgroup *pc, *tmp;
+ 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 ret;
+
+ BUG_ON(!mem_cont);
+ mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
+ src = &mz->lists[lru];
+
+ scan = 0;
+ list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
+ if (scan >= nr_to_scan)
+ break;
+
+ page = pc->page;
+ if (unlikely(!PageCgroupUsed(pc)))
+ continue;
+ if (unlikely(!PageLRU(page)))
+ continue;
+
+ scan++;
+ 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;
+ }
+ }
+
+ *scanned = scan;
+ return nr_taken;
+}
+
+#define mem_cgroup_from_res_counter(counter, member) \
+ container_of(counter, struct mem_cgroup, member)
+
+static bool mem_cgroup_check_under_limit(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;
+}
+
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+ struct cgroup *cgrp = memcg->css.cgroup;
+ unsigned int swappiness;
+
+ /* root ? */
+ if (cgrp->parent == NULL)
+ return vm_swappiness;
+
+ spin_lock(&memcg->reclaim_param_lock);
+ swappiness = memcg->swappiness;
+ spin_unlock(&memcg->reclaim_param_lock);
+
+ return swappiness;
+}
+
+static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+{
+ int *val = data;
+ (*val)++;
+ return 0;
+}
+
+/**
+ * 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
+ */
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+ struct cgroup *task_cgrp;
+ struct cgroup *mem_cgrp;
+ /*
+ * 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.
+ */
+ static char memcg_name[PATH_MAX];
+ int ret;
+
+ if (!memcg || !p)
+ return;
+
+
+ rcu_read_lock();
+
+ mem_cgrp = memcg->css.cgroup;
+ task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+ ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+ if (ret < 0) {
+ /*
+ * Unfortunately, we are unable to convert to a useful name
+ * But we'll still print out the usage information
+ */
+ rcu_read_unlock();
+ goto done;
+ }
+ rcu_read_unlock();
+
+ 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:
+
+ 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));
+}
+
+/*
+ * 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)
+{
+ int num = 0;
+ mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+ return num;
+}
+
+/*
+ * 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 mem_cgroup *ret = NULL;
+ struct cgroup_subsys_state *css;
+ int nextid, found;
+
+ if (!root_mem->use_hierarchy) {
+ css_get(&root_mem->css);
+ ret = root_mem;
+ }
+
+ 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 ret;
+}
+
+/*
+ * 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,
+ struct zone *zone,
+ gfp_t gfp_mask,
+ unsigned long reclaim_options)
+{
+ 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;
+ /*
+ * 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;
+
+ mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb);
+
+ 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);
+ }
+ 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;
+}
+
+/*
+ * 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)
+{
+ struct mem_cgroup *mem;
+ struct page_cgroup *pc;
+
+ 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)
+{
+ struct mem_cgroup *mem, *mem_over_limit;
+ int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct res_counter *fail_res;
+ int csize = CHARGE_SIZE;
+
+ /*
+ * 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.
+ * The mm_struct's mem_cgroup changes on task migration if the
+ * thread group leader migrates. It's possible that mm is not
+ * set, if so charge the init_mm (happens for pagecache usage).
+ */
+ mem = *memcg;
+ if (likely(!mem)) {
+ mem = try_get_mem_cgroup_from_mm(mm);
+ *memcg = mem;
+ } else {
+ css_get(&mem->css);
+ }
+ if (unlikely(!mem))
+ return 0;
+
+ VM_BUG_ON(css_is_removed(&mem->css));
+ if (mem_cgroup_is_root(mem))
+ goto done;
+
+ while (1) {
+ int ret = 0;
+ unsigned long flags = 0;
+
+ 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, csize, &fail_res);
+ if (likely(!ret))
+ break;
+ /* mem+swap counter fails */
+ res_counter_uncharge(&mem->res, csize);
+ flags |= MEM_CGROUP_RECLAIM_NOSWAP;
+ mem_over_limit = mem_cgroup_from_res_counter(fail_res,
+ memsw);
+ } else
+ /* mem counter fails */
+ 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, NULL,
+ gfp_mask, flags);
+ if (ret)
+ continue;
+
+ /*
+ * try_to_free_mem_cgroup_pages() might not give us a full
+ * picture of reclaim. Some pages are reclaimed and might be
+ * moved to swap cache or just unmapped from the cgroup.
+ * Check the limit again to see if the reclaim reduced the
+ * current usage of the cgroup before giving up
+ *
+ */
+ 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)
+ goto nomem;
+ if (mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) {
+ nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ continue;
+ }
+ /* 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;
+}
+
+/*
+ * 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)
+{
+ 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 */
+}
+
+static void mem_cgroup_cancel_charge(struct mem_cgroup *mem)
+{
+ __mem_cgroup_cancel_charge(mem, 1);
+}
+
+/*
+ * 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;
+ 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;
+}
+
+/*
+ * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
+ * USED state. If already USED, uncharge and return.
+ */
+
+static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
+ struct page_cgroup *pc,
+ enum charge_type ctype)
+{
+ /* try_charge() can return NULL to *memcg, taking care of it. */
+ if (!mem)
+ return;
+
+ lock_page_cgroup(pc);
+ if (unlikely(PageCgroupUsed(pc))) {
+ unlock_page_cgroup(pc);
+ 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();
+ 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
+ * @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 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, bool uncharge)
+{
+ 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 (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);
+
+ /* 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 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;
+}
+
+/*
+ * move charges to its parent.
+ */
+
+static int mem_cgroup_move_parent(struct page_cgroup *pc,
+ struct mem_cgroup *child,
+ gfp_t gfp_mask)
+{
+ struct page *page = pc->page;
+ struct cgroup *cg = child->css.cgroup;
+ struct cgroup *pcg = cg->parent;
+ struct mem_cgroup *parent;
+ int ret;
+
+ /* Is ROOT ? */
+ 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)
+ goto put_back;
+
+ ret = mem_cgroup_move_account(pc, child, parent, true);
+ if (ret)
+ mem_cgroup_cancel_charge(parent);
+put_back:
+ putback_lru_page(page);
+put:
+ put_page(page);
+out:
+ return ret;
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask, enum charge_type ctype,
+ struct mem_cgroup *memcg)
+{
+ struct mem_cgroup *mem;
+ struct page_cgroup *pc;
+ int ret;
+
+ pc = lookup_page_cgroup(page);
+ /* can happen at boot */
+ if (unlikely(!pc))
+ return 0;
+ prefetchw(pc);
+
+ mem = memcg;
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+ if (ret || !mem)
+ return ret;
+
+ __mem_cgroup_commit_charge(mem, pc, ctype);
+ return 0;
+}
+
+int mem_cgroup_newpage_charge(struct page *page,
+ struct mm_struct *mm, gfp_t gfp_mask)
+{
+ if (mem_cgroup_disabled())
+ return 0;
+ if (PageCompound(page))
+ return 0;
+ /*
+ * If already mapped, we don't have to account.
+ * If page cache, page->mapping has address_space.
+ * But page->mapping may have out-of-use anon_vma pointer,
+ * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
+ * is NULL.
+ */
+ if (page_mapped(page) || (page->mapping && !PageAnon(page)))
+ return 0;
+ if (unlikely(!mm))
+ mm = &init_mm;
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
+ 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)
+{
+ struct mem_cgroup *mem = NULL;
+ int ret;
+
+ if (mem_cgroup_disabled())
+ return 0;
+ if (PageCompound(page))
+ return 0;
+ /*
+ * Corner case handling. This is called from add_to_page_cache()
+ * in usual. But some FS (shmem) precharges this page before calling it
+ * and call add_to_page_cache() with GFP_NOWAIT.
+ *
+ * For GFP_NOWAIT case, the page may be pre-charged before calling
+ * add_to_page_cache(). (See shmem.c) check it here and avoid to call
+ * charge twice. (It works but has to pay a bit larger cost.)
+ * And when the page is SwapCache, it should take swap information
+ * into account. This is under lock_page() now.
+ */
+ if (!(gfp_mask & __GFP_WAIT)) {
+ struct page_cgroup *pc;
+
+
+ pc = lookup_page_cgroup(page);
+ if (!pc)
+ return 0;
+ lock_page_cgroup(pc);
+ if (PageCgroupUsed(pc)) {
+ unlock_page_cgroup(pc);
+ return 0;
+ }
+ unlock_page_cgroup(pc);
+ }
+
+ if (unlikely(!mm && !mem))
+ mm = &init_mm;
+
+ if (page_is_file_cache(page))
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
+ MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
+
+ /* 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);
+
+ 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 acquired. This refcnt will be consumed by
+ * "commit()" or removed by "cancel()"
+ */
+int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
+ struct page *page,
+ gfp_t mask, struct mem_cgroup **ptr)
+{
+ struct mem_cgroup *mem;
+ int ret;
+
+ if (mem_cgroup_disabled())
+ return 0;
+
+ if (!do_swap_account)
+ goto charge_cur_mm;
+ /*
+ * A racing thread's fault, or swapoff, may have already updated
+ * 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))
+ goto charge_cur_mm;
+ mem = try_get_mem_cgroup_from_page(page);
+ if (!mem)
+ goto charge_cur_mm;
+ *ptr = mem;
+ 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);
+}
+
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+ enum charge_type ctype)
+{
+ struct page_cgroup *pc;
+
+ if (mem_cgroup_disabled())
+ 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, ctype);
+ mem_cgroup_lru_add_after_commit_swapcache(page);
+ /*
+ * Now swap is on-memory. This means this page may be
+ * counted both as mem and swap....double count.
+ * Fix it by uncharging from memsw. Basically, this SwapCache is stable
+ * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
+ * may call delete_from_swap_cache() before reach here.
+ */
+ if (do_swap_account && PageSwapCache(page)) {
+ swp_entry_t ent = {.val = page_private(page)};
+ unsigned short id;
+ struct mem_cgroup *memcg;
+
+ id = swap_cgroup_record(ent, 0);
+ rcu_read_lock();
+ memcg = mem_cgroup_lookup(id);
+ if (memcg) {
+ /*
+ * 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();
+ }
+ /*
+ * 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)
+{
+ if (mem_cgroup_disabled())
+ 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 (uncharge_memsw)
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ return;
+}
+
+/*
+ * uncharge if !page_mapped(page)
+ */
+static struct mem_cgroup *
+__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
+{
+ struct page_cgroup *pc;
+ struct mem_cgroup *mem = NULL;
+ struct mem_cgroup_per_zone *mz;
+
+ if (mem_cgroup_disabled())
+ return NULL;
+
+ if (PageSwapCache(page))
+ return NULL;
+
+ /*
+ * Check if our page_cgroup is valid
+ */
+ pc = lookup_page_cgroup(page);
+ if (unlikely(!pc || !PageCgroupUsed(pc)))
+ return NULL;
+
+ lock_page_cgroup(pc);
+
+ mem = pc->mem_cgroup;
+
+ if (!PageCgroupUsed(pc))
+ goto unlock_out;
+
+ switch (ctype) {
+ case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ case MEM_CGROUP_CHARGE_TYPE_DROP:
+ if (page_mapped(page))
+ goto unlock_out;
+ break;
+ case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
+ if (!PageAnon(page)) { /* Shared memory */
+ if (page->mapping && !page_is_file_cache(page))
+ goto unlock_out;
+ } else if (page_mapped(page)) /* Anon */
+ goto unlock_out;
+ break;
+ default:
+ break;
+ }
+
+ 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
+ * freed from LRU. This is safe because uncharged page is expected not
+ * to be reused (freed soon). Exception is SwapCache, it's handled by
+ * special functions.
+ */
+
+ 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);
+
+ return mem;
+
+unlock_out:
+ unlock_page_cgroup(pc);
+ return NULL;
+}
+
+void mem_cgroup_uncharge_page(struct page *page)
+{
+ /* early check. */
+ if (page_mapped(page))
+ return;
+ if (page->mapping && !PageAnon(page))
+ return;
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
+void mem_cgroup_uncharge_cache_page(struct page *page)
+{
+ VM_BUG_ON(page_mapped(page));
+ VM_BUG_ON(page->mapping);
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
+}
+
+/*
+ * 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;
+ }
+}