memcontrol.c

 */
static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
{
	preempt_disable();
	/* threshold event is triggered in finer grain than soft limit */
	if (unlikely(mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_THRESH))) {
		bool do_softlimit;
		bool do_numainfo __maybe_unused;

		do_softlimit = mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_SOFTLIMIT);
#if MAX_NUMNODES > 1
		do_numainfo = mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_NUMAINFO);
#endif
		preempt_enable();

		mem_cgroup_threshold(memcg);
		if (unlikely(do_softlimit))
			mem_cgroup_update_tree(memcg, page);
#if MAX_NUMNODES > 1
		if (unlikely(do_numainfo))
			atomic_inc(&memcg->numainfo_events);
#endif
	} else
		preempt_enable();
}

struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
	return mem_cgroup_from_css(
		cgroup_subsys_state(cont, mem_cgroup_subsys_id));
}

struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
	/*
	 * mm_update_next_owner() may clear mm->owner to NULL
	 * if it races with swapoff, page migration, etc.
	 * So this can be called with p == NULL.
	 */
	if (unlikely(!p))
		return NULL;

	return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id));
}

struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
	struct mem_cgroup *memcg = NULL;

	if (!mm)
		return NULL;
	/*
	 * Because we have no locks, mm->owner's may be being moved to other
	 * cgroup. We use css_tryget() here even if this looks
	 * pessimistic (rather than adding locks here).
	 */
	rcu_read_lock();
	do {
		memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!memcg))
			break;
	} while (!css_tryget(&memcg->css));
	rcu_read_unlock();
	return memcg;
}

/**
 * mem_cgroup_iter - iterate over memory cgroup hierarchy
 * @root: hierarchy root
 * @prev: previously returned memcg, NULL on first invocation
 * @reclaim: cookie for shared reclaim walks, NULL for full walks
 *
 * Returns references to children of the hierarchy below @root, or
 * @root itself, or %NULL after a full round-trip.
 *
 * Caller must pass the return value in @prev on subsequent
 * invocations for reference counting, or use mem_cgroup_iter_break()
 * to cancel a hierarchy walk before the round-trip is complete.
 *
 * Reclaimers can specify a zone and a priority level in @reclaim to
 * divide up the memcgs in the hierarchy among all concurrent
 * reclaimers operating on the same zone and priority.
 */
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
				   struct mem_cgroup *prev,
				   struct mem_cgroup_reclaim_cookie *reclaim)
{
	struct mem_cgroup *memcg = NULL;
	int id = 0;

	if (mem_cgroup_disabled())
		return NULL;

	if (!root)
		root = root_mem_cgroup;

	if (prev && !reclaim)
		id = css_id(&prev->css);

	if (!root->use_hierarchy && root != root_mem_cgroup) {
		if (prev)
			goto out_css_put;
		return root;
	}

	while (!memcg) {
		struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
		struct cgroup_subsys_state *css;

		if (reclaim) {
			int nid = zone_to_nid(reclaim->zone);
			int zid = zone_idx(reclaim->zone);
			struct mem_cgroup_per_zone *mz;

			mz = mem_cgroup_zoneinfo(root, nid, zid);
			iter = &mz->reclaim_iter[reclaim->priority];
			if (prev && reclaim->generation != iter->generation)
				goto out_css_put;
			id = iter->position;
		}

		rcu_read_lock();
		css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id);
		if (css) {
			if (css == &root->css || css_tryget(css))
				memcg = mem_cgroup_from_css(css);
		} else
			id = 0;
		rcu_read_unlock();

		if (reclaim) {
			iter->position = id;
			if (!css)
				iter->generation++;
			else if (!prev && memcg)
				reclaim->generation = iter->generation;
		}

		if (prev && !css)
			goto out_css_put;
	}
out_css_put:
	if (prev && prev != root)
		css_put(&prev->css);

	return memcg;
}

/**
 * mem_cgroup_iter_break - abort a hierarchy walk prematurely
 * @root: hierarchy root
 * @prev: last visited hierarchy member as returned by mem_cgroup_iter()
 */
void mem_cgroup_iter_break(struct mem_cgroup *root,
			   struct mem_cgroup *prev)
{
	if (!root)
		root = root_mem_cgroup;
	if (prev && prev != root)
		css_put(&prev->css);
}

/*
 * Iteration constructs for visiting all cgroups (under a tree).  If
 * loops are exited prematurely (break), mem_cgroup_iter_break() must
 * be used for reference counting.
 */
#define for_each_mem_cgroup_tree(iter, root)		\
	for (iter = mem_cgroup_iter(root, NULL, NULL);	\
	     iter != NULL;				\
	     iter = mem_cgroup_iter(root, iter, NULL))

#define for_each_mem_cgroup(iter)			\
	for (iter = mem_cgroup_iter(NULL, NULL, NULL);	\
	     iter != NULL;				\
	     iter = mem_cgroup_iter(NULL, iter, NULL))

void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
{
	struct mem_cgroup *memcg;

	rcu_read_lock();
	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (unlikely(!memcg))
		goto out;

	switch (idx) {
	case PGFAULT:
		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
		break;
	case PGMAJFAULT:
		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
		break;
	default:
		BUG();
	}
out:
	rcu_read_unlock();
}
EXPORT_SYMBOL(__mem_cgroup_count_vm_event);

/**
 * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
 * @zone: zone of the wanted lruvec
 * @memcg: memcg of the wanted lruvec
 *
 * Returns the lru list vector holding pages for the given @zone and
 * @mem.  This can be the global zone lruvec, if the memory controller
 * is disabled.
 */
struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
				      struct mem_cgroup *memcg)
{
	struct mem_cgroup_per_zone *mz;
	struct lruvec *lruvec;

	if (mem_cgroup_disabled()) {
		lruvec = &zone->lruvec;
		goto out;
	}

	mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
	lruvec = &mz->lruvec;
out:
	/*
	 * Since a node can be onlined after the mem_cgroup was created,
	 * we have to be prepared to initialize lruvec->zone here;
	 * and if offlined then reonlined, we need to reinitialize it.
	 */
	if (unlikely(lruvec->zone != zone))
		lruvec->zone = zone;
	return lruvec;
}

/*
 * Following LRU functions are allowed to be used without PCG_LOCK.
 * Operations are called by routine of global LRU independently from memcg.
 * What we have to take care of here is validness of pc->mem_cgroup.
 *
 * Changes to pc->mem_cgroup happens when
 * 1. charge
 * 2. moving account
 * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
 * It is added to LRU before charge.
 * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
 * When moving account, the page is not on LRU. It's isolated.
 */

/**
 * mem_cgroup_page_lruvec - return lruvec for adding an lru page
 * @page: the page
 * @zone: zone of the page
 */
struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
{
	struct mem_cgroup_per_zone *mz;
	struct mem_cgroup *memcg;
	struct page_cgroup *pc;
	struct lruvec *lruvec;

	if (mem_cgroup_disabled()) {
		lruvec = &zone->lruvec;
		goto out;
	}

	pc = lookup_page_cgroup(page);
	memcg = pc->mem_cgroup;

	/*
	 * Surreptitiously switch any uncharged offlist page to root:
	 * an uncharged page off lru does nothing to secure
	 * its former mem_cgroup from sudden removal.
	 *
	 * Our caller holds lru_lock, and PageCgroupUsed is updated
	 * under page_cgroup lock: between them, they make all uses
	 * of pc->mem_cgroup safe.
	 */
	if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup)
		pc->mem_cgroup = memcg = root_mem_cgroup;

	mz = page_cgroup_zoneinfo(memcg, page);
	lruvec = &mz->lruvec;
out:
	/*
	 * Since a node can be onlined after the mem_cgroup was created,
	 * we have to be prepared to initialize lruvec->zone here;
	 * and if offlined then reonlined, we need to reinitialize it.
	 */
	if (unlikely(lruvec->zone != zone))
		lruvec->zone = zone;
	return lruvec;
}

/**
 * mem_cgroup_update_lru_size - account for adding or removing an lru page
 * @lruvec: mem_cgroup per zone lru vector
 * @lru: index of lru list the page is sitting on
 * @nr_pages: positive when adding or negative when removing
 *
 * This function must be called when a page is added to or removed from an
 * lru list.
 */
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
				int nr_pages)
{
	struct mem_cgroup_per_zone *mz;
	unsigned long *lru_size;

	if (mem_cgroup_disabled())
		return;

	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
	lru_size = mz->lru_size + lru;
	*lru_size += nr_pages;
	VM_BUG_ON((long)(*lru_size) < 0);
}

/*
 * Checks whether given mem is same or in the root_mem_cgroup's
 * hierarchy subtree
 */
bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
				  struct mem_cgroup *memcg)
{
	if (root_memcg == memcg)
		return true;
	if (!root_memcg->use_hierarchy || !memcg)
		return false;
	return css_is_ancestor(&memcg->css, &root_memcg->css);
}

static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
				       struct mem_cgroup *memcg)
{
	bool ret;

	rcu_read_lock();
	ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
	rcu_read_unlock();
	return ret;
}

int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
{
	int ret;
	struct mem_cgroup *curr = NULL;
	struct task_struct *p;

	p = find_lock_task_mm(task);
	if (p) {
		curr = try_get_mem_cgroup_from_mm(p->mm);
		task_unlock(p);
	} else {
		/*
		 * All threads may have already detached their mm's, but the oom
		 * killer still needs to detect if they have already been oom
		 * killed to prevent needlessly killing additional tasks.
		 */
		task_lock(task);
		curr = mem_cgroup_from_task(task);
		if (curr)
			css_get(&curr->css);
		task_unlock(task);
	}
	if (!curr)
		return 0;
	/*
	 * We should check use_hierarchy of "memcg" 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 "memcg" in *cgroup*
	 * hierarchy(even if use_hierarchy is disabled in "memcg").
	 */
	ret = mem_cgroup_same_or_subtree(memcg, curr);
	css_put(&curr->css);
	return ret;
}

int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
{
	unsigned long inactive_ratio;
	unsigned long inactive;
	unsigned long active;
	unsigned long gb;

	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);

	gb = (inactive + active) >> (30 - PAGE_SHIFT);
	if (gb)
		inactive_ratio = int_sqrt(10 * gb);
	else
		inactive_ratio = 1;

	return inactive * inactive_ratio < active;
}

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

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

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

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

	return memcg->swappiness;
}

/*
 * memcg->moving_account is used for checking possibility that some thread is
 * calling move_account(). When a thread on CPU-A starts moving pages under
 * a memcg, other threads should check memcg->moving_account under
 * rcu_read_lock(), like this:
 *
 *         CPU-A                                    CPU-B
 *                                              rcu_read_lock()
 *         memcg->moving_account+1              if (memcg->mocing_account)
 *                                                   take heavy locks.
 *         synchronize_rcu()                    update something.
 *                                              rcu_read_unlock()
 *         start move here.
 */

/* for quick checking without looking up memcg */
atomic_t memcg_moving __read_mostly;

static void mem_cgroup_start_move(struct mem_cgroup *memcg)
{
	atomic_inc(&memcg_moving);
	atomic_inc(&memcg->moving_account);
	synchronize_rcu();
}

static void mem_cgroup_end_move(struct mem_cgroup *memcg)
{
	/*
	 * Now, mem_cgroup_clear_mc() may call this function with NULL.
	 * We check NULL in callee rather than caller.
	 */
	if (memcg) {
		atomic_dec(&memcg_moving);
		atomic_dec(&memcg->moving_account);
	}
}

/*
 * 2 routines for checking "mem" is under move_account() or not.
 *
 * mem_cgroup_stolen() -  checking whether a cgroup is mc.from or not. This
 *			  is used for avoiding races 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_stolen(struct mem_cgroup *memcg)
{
	VM_BUG_ON(!rcu_read_lock_held());
	return atomic_read(&memcg->moving_account) > 0;
}

static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
{
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	bool ret = false;
	/*
	 * Unlike task_move routines, we access mc.to, mc.from not under
	 * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
	 */
	spin_lock(&mc.lock);
	from = mc.from;
	to = mc.to;
	if (!from)
		goto unlock;

	ret = mem_cgroup_same_or_subtree(memcg, from)
		|| mem_cgroup_same_or_subtree(memcg, to);
unlock:
	spin_unlock(&mc.lock);
	return ret;
}

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

/*
 * Take this lock when
 * - a code tries to modify page's memcg while it's USED.
 * - a code tries to modify page state accounting in a memcg.
 * see mem_cgroup_stolen(), too.
 */
static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
				  unsigned long *flags)
{
	spin_lock_irqsave(&memcg->move_lock, *flags);
}

static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
				unsigned long *flags)
{
	spin_unlock_irqrestore(&memcg->move_lock, *flags);
}

#define K(x) ((x) << (PAGE_SHIFT-10))
/**
 * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
 * @memcg: The memory cgroup that went over limit
 * @p: Task that is going to be killed
 *
 * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
 * enabled
 */
void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
	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;
	struct mem_cgroup *iter;
	unsigned int i;

	if (!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();

	pr_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
	 */
	pr_cont(" as a result of limit of %s\n", memcg_name);
done:

	pr_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));
	pr_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));
	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));

	for_each_mem_cgroup_tree(iter, memcg) {
		pr_info("Memory cgroup stats");

		rcu_read_lock();
		ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
		if (!ret)
			pr_cont(" for %s", memcg_name);
		rcu_read_unlock();
		pr_cont(":");

		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
				continue;
			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
				K(mem_cgroup_read_stat(iter, i)));
		}

		for (i = 0; i < NR_LRU_LISTS; i++)
			pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
				K(mem_cgroup_nr_lru_pages(iter, BIT(i))));

		pr_cont("\n");
	}
}

/*
 * This function returns the number of memcg under hierarchy tree. Returns
 * 1(self count) if no children.
 */
static int mem_cgroup_count_children(struct mem_cgroup *memcg)
{
	int num = 0;
	struct mem_cgroup *iter;

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

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

	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);

	/*
	 * Do not consider swap space if we cannot swap due to swappiness
	 */
	if (mem_cgroup_swappiness(memcg)) {
		u64 memsw;

		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.
		 */
		limit = min(limit, memsw);
	}

	return limit;
}

static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
				     int order)
{
	struct mem_cgroup *iter;
	unsigned long chosen_points = 0;
	unsigned long totalpages;
	unsigned int points = 0;
	struct task_struct *chosen = NULL;

	/*
	 * If current has a pending SIGKILL, then automatically select it.  The
	 * goal is to allow it to allocate so that it may quickly exit and free
	 * its memory.
	 */
	if (fatal_signal_pending(current)) {
		set_thread_flag(TIF_MEMDIE);
		return;
	}

	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
	for_each_mem_cgroup_tree(iter, memcg) {
		struct cgroup *cgroup = iter->css.cgroup;
		struct cgroup_iter it;
		struct task_struct *task;

		cgroup_iter_start(cgroup, &it);
		while ((task = cgroup_iter_next(cgroup, &it))) {
			switch (oom_scan_process_thread(task, totalpages, NULL,
							false)) {
			case OOM_SCAN_SELECT:
				if (chosen)
					put_task_struct(chosen);
				chosen = task;
				chosen_points = ULONG_MAX;
				get_task_struct(chosen);
				/* fall through */
			case OOM_SCAN_CONTINUE:
				continue;
			case OOM_SCAN_ABORT:
				cgroup_iter_end(cgroup, &it);
				mem_cgroup_iter_break(memcg, iter);
				if (chosen)
					put_task_struct(chosen);
				return;
			case OOM_SCAN_OK:
				break;
			};
			points = oom_badness(task, memcg, NULL, totalpages);
			if (points > chosen_points) {
				if (chosen)
					put_task_struct(chosen);
				chosen = task;
				chosen_points = points;
				get_task_struct(chosen);
			}
		}
		cgroup_iter_end(cgroup, &it);
	}

	if (!chosen)
		return;
	points = chosen_points * 1000 / totalpages;
	oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
			 NULL, "Memory cgroup out of memory");
}

static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
					gfp_t gfp_mask,
					unsigned long flags)
{
	unsigned long total = 0;
	bool noswap = false;
	int loop;

	if (flags & MEM_CGROUP_RECLAIM_NOSWAP)
		noswap = true;
	if (!(flags & MEM_CGROUP_RECLAIM_SHRINK) && memcg->memsw_is_minimum)
		noswap = true;

	for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) {
		if (loop)
			drain_all_stock_async(memcg);
		total += try_to_free_mem_cgroup_pages(memcg, gfp_mask, noswap);
		/*
		 * Allow limit shrinkers, which are triggered directly
		 * by userspace, to catch signals and stop reclaim
		 * after minimal progress, regardless of the margin.
		 */
		if (total && (flags & MEM_CGROUP_RECLAIM_SHRINK))
			break;
		if (mem_cgroup_margin(memcg))
			break;
		/*
		 * If nothing was reclaimed after two attempts, there
		 * may be no reclaimable pages in this hierarchy.
		 */
		if (loop && !total)
			break;
	}
	return total;
}

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

}
#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 *memcg)
{
	int nid;
	/*
	 * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
	 * pagein/pageout changes since the last update.
	 */
	if (!atomic_read(&memcg->numainfo_events))
		return;
	if (atomic_inc_return(&memcg->numainfo_updating) > 1)
		return;

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

	for_each_node_mask(nid, node_states[N_MEMORY]) {

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

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

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

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

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

	memcg->last_scanned_node = node;
	return node;
}

/*
 * 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.
 */
static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
{
	int nid;

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

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

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

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

static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
				   struct zone *zone,
				   gfp_t gfp_mask,
				   unsigned long *total_scanned)
{
	struct mem_cgroup *victim = NULL;
	int total = 0;
	int loop = 0;
	unsigned long excess;
	unsigned long nr_scanned;
	struct mem_cgroup_reclaim_cookie reclaim = {
		.zone = zone,
		.priority = 0,
	};

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

	while (1) {
		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
		if (!victim) {
			loop++;
			if (loop >= 2) {
				/*
				 * If we have not been able to reclaim
				 * anything, it might because there are
				 * no reclaimable pages under this hierarchy
				 */
				if (!total)
					break;
				/*
				 * We want to do more targeted reclaim.
				 * excess >> 2 is not to excessive so as to
				 * reclaim too much, nor too less that we keep
				 * coming back to reclaim from this cgroup
				 */
				if (total >= (excess >> 2) ||
					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
					break;
			}
			continue;
		}
		if (!mem_cgroup_reclaimable(victim, false))
			continue;
		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
						     zone, &nr_scanned);
		*total_scanned += nr_scanned;
		if (!res_counter_soft_limit_excess(&root_memcg->res))
			break;
	}
	mem_cgroup_iter_break(root_memcg, victim);
	return total;
}

/*
 * Check OOM-Killer is already running under our hierarchy.
 * If someone is running, return false.
 * Has to be called with memcg_oom_lock
 */
static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter, *failed = NULL;

	for_each_mem_cgroup_tree(iter, memcg) {
		if (iter->oom_lock) {
			/*
			 * this subtree of our hierarchy is already locked
			 * so we cannot give a lock.
			 */
			failed = iter;
			mem_cgroup_iter_break(memcg, iter);
			break;
		} else
			iter->oom_lock = true;
	}

	if (!failed)
		return true;

	/*
	 * OK, we failed to lock the whole subtree so we have to clean up
	 * what we set up to the failing subtree