memcontrol.c

	 * is safe. Because if page_cgroup's USED bit is unset, the page
	 * will not be added to any memcg's LRU. If page_cgroup's USED bit is
	 * set, the commit after this will fail, anyway.
	 * This all charge/uncharge is done under some mutual execustion.
	 * So, we don't need to taking care of changes in USED bit.
	 */
	if (likely(!PageLRU(page)))
		return;

	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(struct page *page)
{
	unsigned long flags;
	struct zone *zone = page_zone(page);
	struct page_cgroup *pc = lookup_page_cgroup(page);

	/* taking care of that the page is added to LRU while we commit it */
	if (likely(!PageLRU(page)))
		return;
	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;
	struct task_struct *p;

	p = find_lock_task_mm(task);
	if (!p)
		return 0;
	curr = try_get_mem_cgroup_from_mm(p->mm);
	task_unlock(p);
	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;
}

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_lru_pages(struct mem_cgroup *memcg,
						struct zone *zone,
						enum lru_list lru)
{
	int nid = zone_to_nid(zone);
	int zid = zone_idx(zone);
	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);

	return MEM_CGROUP_ZSTAT(mz, lru);
}

static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg,
							int nid)
{
	unsigned long ret;

	ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_FILE) +
		mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_FILE);

	return ret;
}

static unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *memcg,
							int nid)
{
	unsigned long ret;

	ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) +
		mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON);
	return ret;
}

#if MAX_NUMNODES > 1
static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg)
{
	u64 total = 0;
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY)
		total += mem_cgroup_node_nr_file_lru_pages(memcg, nid);

	return total;
}

static unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg)
{
	u64 total = 0;
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY)
		total += mem_cgroup_node_nr_anon_lru_pages(memcg, nid);

	return total;
}

static unsigned long
mem_cgroup_node_nr_unevictable_lru_pages(struct mem_cgroup *memcg, int nid)
{
	return mem_cgroup_get_zonestat_node(memcg, nid, LRU_UNEVICTABLE);
}

static unsigned long
mem_cgroup_nr_unevictable_lru_pages(struct mem_cgroup *memcg)
{
	u64 total = 0;
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY)
		total += mem_cgroup_node_nr_unevictable_lru_pages(memcg, nid);

	return total;
}

static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
							int nid)
{
	enum lru_list l;
	u64 total = 0;

	for_each_lru(l)
		total += mem_cgroup_get_zonestat_node(memcg, nid, l);

	return total;
}

static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg)
{
	u64 total = 0;
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY)
		total += mem_cgroup_node_nr_lru_pages(memcg, nid);

	return total;
}
#endif /* CONFIG_NUMA */

struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
						      struct zone *zone)
{
	int nid = zone_to_nid(zone);
	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);
	if (!PageCgroupUsed(pc))
		return NULL;
	/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
	smp_rmb();
	mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
	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 = zone_to_nid(z);
	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;

		if (unlikely(!PageCgroupUsed(pc)))
			continue;

		page = lookup_cgroup_page(pc);

		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 += hpage_nr_pages(page);
			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;

	trace_mm_vmscan_memcg_isolate(0, nr_to_scan, scan, nr_taken,
				      0, 0, 0, mode);

	return nr_taken;
}

#define mem_cgroup_from_res_counter(counter, member)	\
	container_of(counter, struct mem_cgroup, member)

/**
 * mem_cgroup_margin - calculate chargeable space of a memory cgroup
 * @mem: the memory cgroup
 *
 * Returns the maximum amount of memory @mem can be charged with, in
 * pages.
 */
static unsigned long mem_cgroup_margin(struct mem_cgroup *mem)
{
	unsigned long long margin;

	margin = res_counter_margin(&mem->res);
	if (do_swap_account)
		margin = min(margin, res_counter_margin(&mem->memsw));
	return margin >> PAGE_SHIFT;
}

static unsigned int get_swappiness(struct mem_cgroup *memcg)
{
	struct cgroup *cgrp = memcg->css.cgroup;

	/* root ? */
	if (cgrp->parent == NULL)
		return vm_swappiness;

	return memcg->swappiness;
}

static void mem_cgroup_start_move(struct mem_cgroup *mem)
{
	int cpu;

	get_online_cpus();
	spin_lock(&mem->pcp_counter_lock);
	for_each_online_cpu(cpu)
		per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
	mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
	spin_unlock(&mem->pcp_counter_lock);
	put_online_cpus();

	synchronize_rcu();
}

static void mem_cgroup_end_move(struct mem_cgroup *mem)
{
	int cpu;

	if (!mem)
		return;
	get_online_cpus();
	spin_lock(&mem->pcp_counter_lock);
	for_each_online_cpu(cpu)
		per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
	mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
	spin_unlock(&mem->pcp_counter_lock);
	put_online_cpus();
}
/*
 * 2 routines for checking "mem" is under move_account() or not.
 *
 * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used
 *			  for avoiding race in accounting. If true,
 *			  pc->mem_cgroup may be overwritten.
 *
 * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
 *			  under hierarchy of moving cgroups. This is for
 *			  waiting at hith-memory prressure caused by "move".
 */

static bool mem_cgroup_stealed(struct mem_cgroup *mem)
{
	VM_BUG_ON(!rcu_read_lock_held());
	return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
}

static bool mem_cgroup_under_move(struct mem_cgroup *mem)
{
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	bool ret = false;
	/*
	 * Unlike task_move routines, we access mc.to, mc.from not under
	 * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
	 */
	spin_lock(&mc.lock);
	from = mc.from;
	to = mc.to;
	if (!from)
		goto unlock;
	if (from == mem || to == mem
	    || (mem->use_hierarchy && css_is_ancestor(&from->css, &mem->css))
	    || (mem->use_hierarchy && css_is_ancestor(&to->css,	&mem->css)))
		ret = true;
unlock:
	spin_unlock(&mc.lock);
	return ret;
}

static bool mem_cgroup_wait_acct_move(struct mem_cgroup *mem)
{
	if (mc.moving_task && current != mc.moving_task) {
		if (mem_cgroup_under_move(mem)) {
			DEFINE_WAIT(wait);
			prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
			/* moving charge context might have finished. */
			if (mc.moving_task)
				schedule();
			finish_wait(&mc.waitq, &wait);
			return true;
		}
	}
	return false;
}

/**
 * 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;
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, mem)
		num++;
	return num;
}

/*
 * Return the memory (and swap, if configured) limit for a memcg.
 */
u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
{
	u64 limit;
	u64 memsw;

	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
	limit += total_swap_pages << PAGE_SHIFT;

	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
	/*
	 * If memsw is finite and limits the amount of swap space available
	 * to this memcg, return that limit.
	 */
	return min(limit, memsw);
}

/*
 * 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 */
		if (!css) {
			/* this means start scan from ID:1 */
			root_mem->last_scanned_child = 0;
		} else
			root_mem->last_scanned_child = found;
	}

	return ret;
}

/**
 * test_mem_cgroup_node_reclaimable
 * @mem: the target memcg
 * @nid: the node ID to be checked.
 * @noswap : specify true here if the user wants flle only information.
 *
 * This function returns whether the specified memcg contains any
 * reclaimable pages on a node. Returns true if there are any reclaimable
 * pages in the node.
 */
static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem,
		int nid, bool noswap)
{
	if (mem_cgroup_node_nr_file_lru_pages(mem, nid))
		return true;
	if (noswap || !total_swap_pages)
		return false;
	if (mem_cgroup_node_nr_anon_lru_pages(mem, nid))
		return true;
	return false;

}
#if MAX_NUMNODES > 1

/*
 * Always updating the nodemask is not very good - even if we have an empty
 * list or the wrong list here, we can start from some node and traverse all
 * nodes based on the zonelist. So update the list loosely once per 10 secs.
 *
 */
static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem)
{
	int nid;
	/*
	 * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
	 * pagein/pageout changes since the last update.
	 */
	if (!atomic_read(&mem->numainfo_events))
		return;
	if (atomic_inc_return(&mem->numainfo_updating) > 1)
		return;

	/* make a nodemask where this memcg uses memory from */
	mem->scan_nodes = node_states[N_HIGH_MEMORY];

	for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) {

		if (!test_mem_cgroup_node_reclaimable(mem, nid, false))
			node_clear(nid, mem->scan_nodes);
	}

	atomic_set(&mem->numainfo_events, 0);
	atomic_set(&mem->numainfo_updating, 0);
}

/*
 * Selecting a node where we start reclaim from. Because what we need is just
 * reducing usage counter, start from anywhere is O,K. Considering
 * memory reclaim from current node, there are pros. and cons.
 *
 * Freeing memory from current node means freeing memory from a node which
 * we'll use or we've used. So, it may make LRU bad. And if several threads
 * hit limits, it will see a contention on a node. But freeing from remote
 * node means more costs for memory reclaim because of memory latency.
 *
 * Now, we use round-robin. Better algorithm is welcomed.
 */
int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
{
	int node;

	mem_cgroup_may_update_nodemask(mem);
	node = mem->last_scanned_node;

	node = next_node(node, mem->scan_nodes);
	if (node == MAX_NUMNODES)
		node = first_node(mem->scan_nodes);
	/*
	 * We call this when we hit limit, not when pages are added to LRU.
	 * No LRU may hold pages because all pages are UNEVICTABLE or
	 * memcg is too small and all pages are not on LRU. In that case,
	 * we use curret node.
	 */
	if (unlikely(node == MAX_NUMNODES))
		node = numa_node_id();

	mem->last_scanned_node = node;
	return node;
}

/*
 * Check all nodes whether it contains reclaimable pages or not.
 * For quick scan, we make use of scan_nodes. This will allow us to skip
 * unused nodes. But scan_nodes is lazily updated and may not cotain
 * enough new information. We need to do double check.
 */
bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
{
	int nid;

	/*
	 * quick check...making use of scan_node.
	 * We can skip unused nodes.
	 */
	if (!nodes_empty(mem->scan_nodes)) {
		for (nid = first_node(mem->scan_nodes);
		     nid < MAX_NUMNODES;
		     nid = next_node(nid, mem->scan_nodes)) {

			if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
				return true;
		}
	}
	/*
	 * Check rest of nodes.
	 */
	for_each_node_state(nid, N_HIGH_MEMORY) {
		if (node_isset(nid, mem->scan_nodes))
			continue;
		if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
			return true;
	}
	return false;
}

#else
int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
{
	return 0;
}

bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
{
	return test_mem_cgroup_node_reclaimable(mem, 0, noswap);
}
#endif

/*
 * 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,
						unsigned long *total_scanned)
{
	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;
	unsigned long nr_scanned;

	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;

	/* If memsw_is_minimum==1, swap-out is of-no-use. */
	if (!check_soft && root_mem->memsw_is_minimum)
		noswap = true;

	while (1) {
		victim = mem_cgroup_select_victim(root_mem);
		if (victim == root_mem) {
			loop++;
			/*
			 * We are not draining per cpu cached charges during
			 * soft limit reclaim  because global reclaim doesn't
			 * care about charges. It tries to free some memory and
			 * charges will not give any.
			 */
			if (!check_soft && loop >= 1)
				drain_all_stock_async(root_mem);
			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 targeted reclaim.
				 * excess >> 2 is not to excessive so as to
				 * reclaim too much, nor too less that we keep
				 * coming back to reclaim from this cgroup
				 */
				if (total >= (excess >> 2) ||
					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) {
					css_put(&victim->css);
					break;
				}
			}
		}
		if (!mem_cgroup_reclaimable(victim, noswap)) {
			/* 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,
				&nr_scanned);
			*total_scanned += nr_scanned;
		} 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_soft_limit_excess(&root_mem->res))
				return total;
		} else if (mem_cgroup_margin(root_mem))
			return total;
	}
	return total;
}

/*
 * 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 x, lock_count = 0;
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, mem) {
		x = atomic_inc_return(&iter->oom_lock);
		lock_count = max(x, lock_count);
	}

	if (lock_count == 1)
		return true;
	return false;
}

static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)
{
	struct mem_cgroup *iter;

	/*
	 * When a new child is created while the hierarchy is under oom,
	 * mem_cgroup_oom_lock() may not be called. We have to use
	 * atomic_add_unless() here.
	 */
	for_each_mem_cgroup_tree(iter, mem)
		atomic_add_unless(&iter->oom_lock, -1, 0);
	return 0;
}


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)
{
	/* 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 (mem && 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;
}

/*
 * Currently used to update mapped file statistics, but the routine can be
 * generalized to update other statistics as well.
 *
 * Notes: Race condition
 *
 * We usually use page_cgroup_lock() for accessing page_cgroup member but
 * it tends to be costly. But considering some conditions, we doesn't need
 * to do so _always_.
 *
 * Considering "charge", lock_page_cgroup() is not required because all
 * file-stat operations happen after a page is attached to radix-tree. There
 * are no race with "charge".
 *
 * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
 * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
 * if there are race with "uncharge". Statistics itself is properly handled
 * by flags.
 *
 * Considering "move", this is an only case we see a race. To make the race
 * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
 * possibility of race condition. If there is, we take a lock.
 */

void mem_cgroup_update_page_stat(struct page *page,
				 enum mem_cgroup_page_stat_item idx, int val)
{
	struct mem_cgroup *mem;
	struct page_cgroup *pc = lookup_page_cgroup(page);
	bool need_unlock = false;
	unsigned long uninitialized_var(flags);

	if (unlikely(!pc))
		return;

	rcu_read_lock();
	mem = pc->mem_cgroup;
	if (unlikely(!mem || !PageCgroupUsed(pc)))
		goto out;
	/* pc->mem_cgroup is unstable ? */
	if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) {
		/* take a lock against to access pc->mem_cgroup */
		move_lock_page_cgroup(pc, &flags);
		need_unlock = true;
		mem = pc->mem_cgroup;
		if (!mem || !PageCgroupUsed(pc))
			goto out;
	}

	switch (idx) {
	case MEMCG_NR_FILE_MAPPED:
		if (val > 0)
			SetPageCgroupFileMapped(pc);
		else if (!page_mapped(page))
			ClearPageCgroupFileMapped(pc);
		idx = MEM_CGROUP_STAT_FILE_MAPPED;
		break;
	default:
		BUG();
	}

	this_cpu_add(mem->stat->count[idx], val);

out:
	if (unlikely(need_unlock))
		move_unlock_page_cgroup(pc, &flags);
	rcu_read_unlock();
	return;
}
EXPORT_SYMBOL(mem_cgroup_update_page_stat);