memcontrol.c

	u64 memlimit, memswlimit, oldusage, curusage;
	int children = mem_cgroup_count_children(memcg);
	int ret = -EBUSY;
	int enlarge = 0;

	/* see mem_cgroup_resize_res_limit */
 	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
	while (retry_count) {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		/*
		 * Rather than hide all in some function, I do this in
		 * open coded manner. You see what this really does.
		 * We have to guarantee mem->res.limit < mem->memsw.limit.
		 */
		mutex_lock(&set_limit_mutex);
		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
		if (memlimit > val) {
			ret = -EINVAL;
			mutex_unlock(&set_limit_mutex);
			break;
		}
		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
		if (memswlimit < val)
			enlarge = 1;
		ret = res_counter_set_limit(&memcg->memsw, val);
		if (!ret) {
			if (memlimit == val)
				memcg->memsw_is_minimum = true;
			else
				memcg->memsw_is_minimum = false;
		}
		mutex_unlock(&set_limit_mutex);

		if (!ret)
			break;

		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
						MEM_CGROUP_RECLAIM_NOSWAP |
						MEM_CGROUP_RECLAIM_SHRINK);
		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
		/* Usage is reduced ? */
		if (curusage >= oldusage)
			retry_count--;
		else
			oldusage = curusage;
	}
	if (!ret && enlarge)
		memcg_oom_recover(memcg);
	return ret;
}

unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
					    gfp_t gfp_mask)
{
	unsigned long nr_reclaimed = 0;
	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
	unsigned long reclaimed;
	int loop = 0;
	struct mem_cgroup_tree_per_zone *mctz;
	unsigned long long excess;

	if (order > 0)
		return 0;

	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
	/*
	 * This loop can run a while, specially if mem_cgroup's continuously
	 * keep exceeding their soft limit and putting the system under
	 * pressure
	 */
	do {
		if (next_mz)
			mz = next_mz;
		else
			mz = mem_cgroup_largest_soft_limit_node(mctz);
		if (!mz)
			break;

		reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone,
						gfp_mask,
						MEM_CGROUP_RECLAIM_SOFT);
		nr_reclaimed += reclaimed;
		spin_lock(&mctz->lock);

		/*
		 * If we failed to reclaim anything from this memory cgroup
		 * it is time to move on to the next cgroup
		 */
		next_mz = NULL;
		if (!reclaimed) {
			do {
				/*
				 * Loop until we find yet another one.
				 *
				 * By the time we get the soft_limit lock
				 * again, someone might have aded the
				 * group back on the RB tree. Iterate to
				 * make sure we get a different mem.
				 * mem_cgroup_largest_soft_limit_node returns
				 * NULL if no other cgroup is present on
				 * the tree
				 */
				next_mz =
				__mem_cgroup_largest_soft_limit_node(mctz);
				if (next_mz == mz) {
					css_put(&next_mz->mem->css);
					next_mz = NULL;
				} else /* next_mz == NULL or other memcg */
					break;
			} while (1);
		}
		__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
		excess = res_counter_soft_limit_excess(&mz->mem->res);
		/*
		 * One school of thought says that we should not add
		 * back the node to the tree if reclaim returns 0.
		 * But our reclaim could return 0, simply because due
		 * to priority we are exposing a smaller subset of
		 * memory to reclaim from. Consider this as a longer
		 * term TODO.
		 */
		/* If excess == 0, no tree ops */
		__mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess);
		spin_unlock(&mctz->lock);
		css_put(&mz->mem->css);
		loop++;
		/*
		 * Could not reclaim anything and there are no more
		 * mem cgroups to try or we seem to be looping without
		 * reclaiming anything.
		 */
		if (!nr_reclaimed &&
			(next_mz == NULL ||
			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
			break;
	} while (!nr_reclaimed);
	if (next_mz)
		css_put(&next_mz->mem->css);
	return nr_reclaimed;
}

/*
 * This routine traverse page_cgroup in given list and drop them all.
 * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
 */
static int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
				int node, int zid, enum lru_list lru)
{
	struct zone *zone;
	struct mem_cgroup_per_zone *mz;
	struct page_cgroup *pc, *busy;
	unsigned long flags, loop;
	struct list_head *list;
	int ret = 0;

	zone = &NODE_DATA(node)->node_zones[zid];
	mz = mem_cgroup_zoneinfo(mem, node, zid);
	list = &mz->lists[lru];

	loop = MEM_CGROUP_ZSTAT(mz, lru);
	/* give some margin against EBUSY etc...*/
	loop += 256;
	busy = NULL;
	while (loop--) {
		ret = 0;
		spin_lock_irqsave(&zone->lru_lock, flags);
		if (list_empty(list)) {
			spin_unlock_irqrestore(&zone->lru_lock, flags);
			break;
		}
		pc = list_entry(list->prev, struct page_cgroup, lru);
		if (busy == pc) {
			list_move(&pc->lru, list);
			busy = NULL;
			spin_unlock_irqrestore(&zone->lru_lock, flags);
			continue;
		}
		spin_unlock_irqrestore(&zone->lru_lock, flags);

		ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL);
		if (ret == -ENOMEM)
			break;

		if (ret == -EBUSY || ret == -EINVAL) {
			/* found lock contention or "pc" is obsolete. */
			busy = pc;
			cond_resched();
		} else
			busy = NULL;
	}

	if (!ret && !list_empty(list))
		return -EBUSY;
	return ret;
}

/*
 * make mem_cgroup's charge to be 0 if there is no task.
 * This enables deleting this mem_cgroup.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
{
	int ret;
	int node, zid, shrink;
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct cgroup *cgrp = mem->css.cgroup;

	css_get(&mem->css);

	shrink = 0;
	/* should free all ? */
	if (free_all)
		goto try_to_free;
move_account:
	do {
		ret = -EBUSY;
		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
			goto out;
		ret = -EINTR;
		if (signal_pending(current))
			goto out;
		/* This is for making all *used* pages to be on LRU. */
		lru_add_drain_all();
		drain_all_stock_sync();
		ret = 0;
		mem_cgroup_start_move(mem);
		for_each_node_state(node, N_HIGH_MEMORY) {
			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
				enum lru_list l;
				for_each_lru(l) {
					ret = mem_cgroup_force_empty_list(mem,
							node, zid, l);
					if (ret)
						break;
				}
			}
			if (ret)
				break;
		}
		mem_cgroup_end_move(mem);
		memcg_oom_recover(mem);
		/* it seems parent cgroup doesn't have enough mem */
		if (ret == -ENOMEM)
			goto try_to_free;
		cond_resched();
	/* "ret" should also be checked to ensure all lists are empty. */
	} while (mem->res.usage > 0 || ret);
out:
	css_put(&mem->css);
	return ret;

try_to_free:
	/* returns EBUSY if there is a task or if we come here twice. */
	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
		ret = -EBUSY;
		goto out;
	}
	/* we call try-to-free pages for make this cgroup empty */
	lru_add_drain_all();
	/* try to free all pages in this cgroup */
	shrink = 1;
	while (nr_retries && mem->res.usage > 0) {
		int progress;

		if (signal_pending(current)) {
			ret = -EINTR;
			goto out;
		}
		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
						false, get_swappiness(mem));
		if (!progress) {
			nr_retries--;
			/* maybe some writeback is necessary */
			congestion_wait(BLK_RW_ASYNC, HZ/10);
		}

	}
	lru_add_drain();
	/* try move_account...there may be some *locked* pages. */
	goto move_account;
}

int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
{
	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
}


static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
{
	return mem_cgroup_from_cont(cont)->use_hierarchy;
}

static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
					u64 val)
{
	int retval = 0;
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
	struct cgroup *parent = cont->parent;
	struct mem_cgroup *parent_mem = NULL;

	if (parent)
		parent_mem = mem_cgroup_from_cont(parent);

	cgroup_lock();
	/*
	 * If parent's use_hierarchy is set, we can't make any modifications
	 * in the child subtrees. If it is unset, then the change can
	 * occur, provided the current cgroup has no children.
	 *
	 * For the root cgroup, parent_mem is NULL, we allow value to be
	 * set if there are no children.
	 */
	if ((!parent_mem || !parent_mem->use_hierarchy) &&
				(val == 1 || val == 0)) {
		if (list_empty(&cont->children))
			mem->use_hierarchy = val;
		else
			retval = -EBUSY;
	} else
		retval = -EINVAL;
	cgroup_unlock();

	return retval;
}


static u64 mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem,
				enum mem_cgroup_stat_index idx)
{
	struct mem_cgroup *iter;
	s64 val = 0;

	/* each per cpu's value can be minus.Then, use s64 */
	for_each_mem_cgroup_tree(iter, mem)
		val += mem_cgroup_read_stat(iter, idx);

	if (val < 0) /* race ? */
		val = 0;
	return val;
}

static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap)
{
	u64 val;

	if (!mem_cgroup_is_root(mem)) {
		if (!swap)
			return res_counter_read_u64(&mem->res, RES_USAGE);
		else
			return res_counter_read_u64(&mem->memsw, RES_USAGE);
	}

	val = mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_CACHE);
	val += mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_RSS);

	if (swap)
		val += mem_cgroup_get_recursive_idx_stat(mem,
				MEM_CGROUP_STAT_SWAPOUT);

	return val << PAGE_SHIFT;
}

static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
	u64 val;
	int type, name;

	type = MEMFILE_TYPE(cft->private);
	name = MEMFILE_ATTR(cft->private);
	switch (type) {
	case _MEM:
		if (name == RES_USAGE)
			val = mem_cgroup_usage(mem, false);
		else
			val = res_counter_read_u64(&mem->res, name);
		break;
	case _MEMSWAP:
		if (name == RES_USAGE)
			val = mem_cgroup_usage(mem, true);
		else
			val = res_counter_read_u64(&mem->memsw, name);
		break;
	default:
		BUG();
		break;
	}
	return val;
}
/*
 * The user of this function is...
 * RES_LIMIT.
 */
static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
			    const char *buffer)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	int type, name;
	unsigned long long val;
	int ret;

	type = MEMFILE_TYPE(cft->private);
	name = MEMFILE_ATTR(cft->private);
	switch (name) {
	case RES_LIMIT:
		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
			ret = -EINVAL;
			break;
		}
		/* This function does all necessary parse...reuse it */
		ret = res_counter_memparse_write_strategy(buffer, &val);
		if (ret)
			break;
		if (type == _MEM)
			ret = mem_cgroup_resize_limit(memcg, val);
		else
			ret = mem_cgroup_resize_memsw_limit(memcg, val);
		break;
	case RES_SOFT_LIMIT:
		ret = res_counter_memparse_write_strategy(buffer, &val);
		if (ret)
			break;
		/*
		 * For memsw, soft limits are hard to implement in terms
		 * of semantics, for now, we support soft limits for
		 * control without swap
		 */
		if (type == _MEM)
			ret = res_counter_set_soft_limit(&memcg->res, val);
		else
			ret = -EINVAL;
		break;
	default:
		ret = -EINVAL; /* should be BUG() ? */
		break;
	}
	return ret;
}

static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
		unsigned long long *mem_limit, unsigned long long *memsw_limit)
{
	struct cgroup *cgroup;
	unsigned long long min_limit, min_memsw_limit, tmp;

	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
	cgroup = memcg->css.cgroup;
	if (!memcg->use_hierarchy)
		goto out;

	while (cgroup->parent) {
		cgroup = cgroup->parent;
		memcg = mem_cgroup_from_cont(cgroup);
		if (!memcg->use_hierarchy)
			break;
		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
		min_limit = min(min_limit, tmp);
		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
		min_memsw_limit = min(min_memsw_limit, tmp);
	}
out:
	*mem_limit = min_limit;
	*memsw_limit = min_memsw_limit;
	return;
}

static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
	struct mem_cgroup *mem;
	int type, name;

	mem = mem_cgroup_from_cont(cont);
	type = MEMFILE_TYPE(event);
	name = MEMFILE_ATTR(event);
	switch (name) {
	case RES_MAX_USAGE:
		if (type == _MEM)
			res_counter_reset_max(&mem->res);
		else
			res_counter_reset_max(&mem->memsw);
		break;
	case RES_FAILCNT:
		if (type == _MEM)
			res_counter_reset_failcnt(&mem->res);
		else
			res_counter_reset_failcnt(&mem->memsw);
		break;
	}

	return 0;
}

static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp,
					struct cftype *cft)
{
	return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate;
}

#ifdef CONFIG_MMU
static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
					struct cftype *cft, u64 val)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);

	if (val >= (1 << NR_MOVE_TYPE))
		return -EINVAL;
	/*
	 * We check this value several times in both in can_attach() and
	 * attach(), so we need cgroup lock to prevent this value from being
	 * inconsistent.
	 */
	cgroup_lock();
	mem->move_charge_at_immigrate = val;
	cgroup_unlock();

	return 0;
}
#else
static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
					struct cftype *cft, u64 val)
{
	return -ENOSYS;
}
#endif


/* For read statistics */
enum {
	MCS_CACHE,
	MCS_RSS,
	MCS_FILE_MAPPED,
	MCS_PGPGIN,
	MCS_PGPGOUT,
	MCS_SWAP,
	MCS_INACTIVE_ANON,
	MCS_ACTIVE_ANON,
	MCS_INACTIVE_FILE,
	MCS_ACTIVE_FILE,
	MCS_UNEVICTABLE,
	NR_MCS_STAT,
};

struct mcs_total_stat {
	s64 stat[NR_MCS_STAT];
};

struct {
	char *local_name;
	char *total_name;
} memcg_stat_strings[NR_MCS_STAT] = {
	{"cache", "total_cache"},
	{"rss", "total_rss"},
	{"mapped_file", "total_mapped_file"},
	{"pgpgin", "total_pgpgin"},
	{"pgpgout", "total_pgpgout"},
	{"swap", "total_swap"},
	{"inactive_anon", "total_inactive_anon"},
	{"active_anon", "total_active_anon"},
	{"inactive_file", "total_inactive_file"},
	{"active_file", "total_active_file"},
	{"unevictable", "total_unevictable"}
};


static void
mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
{
	s64 val;

	/* per cpu stat */
	val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
	s->stat[MCS_CACHE] += val * PAGE_SIZE;
	val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
	s->stat[MCS_RSS] += val * PAGE_SIZE;
	val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED);
	s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE;
	val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT);
	s->stat[MCS_PGPGIN] += val;
	val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGOUT_COUNT);
	s->stat[MCS_PGPGOUT] += val;
	if (do_swap_account) {
		val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
		s->stat[MCS_SWAP] += val * PAGE_SIZE;
	}

	/* per zone stat */
	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
	s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE;
	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON);
	s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE;
	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE);
	s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE;
	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE);
	s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
	val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE);
	s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
}

static void
mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
{
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, mem)
		mem_cgroup_get_local_stat(iter, s);
}

static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
				 struct cgroup_map_cb *cb)
{
	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
	struct mcs_total_stat mystat;
	int i;

	memset(&mystat, 0, sizeof(mystat));
	mem_cgroup_get_local_stat(mem_cont, &mystat);

	for (i = 0; i < NR_MCS_STAT; i++) {
		if (i == MCS_SWAP && !do_swap_account)
			continue;
		cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]);
	}

	/* Hierarchical information */
	{
		unsigned long long limit, memsw_limit;
		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
		cb->fill(cb, "hierarchical_memory_limit", limit);
		if (do_swap_account)
			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
	}

	memset(&mystat, 0, sizeof(mystat));
	mem_cgroup_get_total_stat(mem_cont, &mystat);
	for (i = 0; i < NR_MCS_STAT; i++) {
		if (i == MCS_SWAP && !do_swap_account)
			continue;
		cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]);
	}

#ifdef CONFIG_DEBUG_VM
	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));

	{
		int nid, zid;
		struct mem_cgroup_per_zone *mz;
		unsigned long recent_rotated[2] = {0, 0};
		unsigned long recent_scanned[2] = {0, 0};

		for_each_online_node(nid)
			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
				mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);

				recent_rotated[0] +=
					mz->reclaim_stat.recent_rotated[0];
				recent_rotated[1] +=
					mz->reclaim_stat.recent_rotated[1];
				recent_scanned[0] +=
					mz->reclaim_stat.recent_scanned[0];
				recent_scanned[1] +=
					mz->reclaim_stat.recent_scanned[1];
			}
		cb->fill(cb, "recent_rotated_anon", recent_rotated[0]);
		cb->fill(cb, "recent_rotated_file", recent_rotated[1]);
		cb->fill(cb, "recent_scanned_anon", recent_scanned[0]);
		cb->fill(cb, "recent_scanned_file", recent_scanned[1]);
	}
#endif

	return 0;
}

static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);

	return get_swappiness(memcg);
}

static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
				       u64 val)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
	struct mem_cgroup *parent;

	if (val > 100)
		return -EINVAL;

	if (cgrp->parent == NULL)
		return -EINVAL;

	parent = mem_cgroup_from_cont(cgrp->parent);

	cgroup_lock();

	/* If under hierarchy, only empty-root can set this value */
	if ((parent->use_hierarchy) ||
	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
		cgroup_unlock();
		return -EINVAL;
	}

	spin_lock(&memcg->reclaim_param_lock);
	memcg->swappiness = val;
	spin_unlock(&memcg->reclaim_param_lock);

	cgroup_unlock();

	return 0;
}

static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
{
	struct mem_cgroup_threshold_ary *t;
	u64 usage;
	int i;

	rcu_read_lock();
	if (!swap)
		t = rcu_dereference(memcg->thresholds.primary);
	else
		t = rcu_dereference(memcg->memsw_thresholds.primary);

	if (!t)
		goto unlock;

	usage = mem_cgroup_usage(memcg, swap);

	/*
	 * current_threshold points to threshold just below usage.
	 * If it's not true, a threshold was crossed after last
	 * call of __mem_cgroup_threshold().
	 */
	i = t->current_threshold;

	/*
	 * Iterate backward over array of thresholds starting from
	 * current_threshold and check if a threshold is crossed.
	 * If none of thresholds below usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
		eventfd_signal(t->entries[i].eventfd, 1);

	/* i = current_threshold + 1 */
	i++;

	/*
	 * Iterate forward over array of thresholds starting from
	 * current_threshold+1 and check if a threshold is crossed.
	 * If none of thresholds above usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
		eventfd_signal(t->entries[i].eventfd, 1);

	/* Update current_threshold */
	t->current_threshold = i - 1;
unlock:
	rcu_read_unlock();
}

static void mem_cgroup_threshold(struct mem_cgroup *memcg)
{
	while (memcg) {
		__mem_cgroup_threshold(memcg, false);
		if (do_swap_account)
			__mem_cgroup_threshold(memcg, true);

		memcg = parent_mem_cgroup(memcg);
	}
}

static int compare_thresholds(const void *a, const void *b)
{
	const struct mem_cgroup_threshold *_a = a;
	const struct mem_cgroup_threshold *_b = b;

	return _a->threshold - _b->threshold;
}

static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem)
{
	struct mem_cgroup_eventfd_list *ev;

	list_for_each_entry(ev, &mem->oom_notify, list)
		eventfd_signal(ev->eventfd, 1);
	return 0;
}

static void mem_cgroup_oom_notify(struct mem_cgroup *mem)
{
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, mem)
		mem_cgroup_oom_notify_cb(iter);
}

static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
	struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	int type = MEMFILE_TYPE(cft->private);
	u64 threshold, usage;
	int i, size, ret;

	ret = res_counter_memparse_write_strategy(args, &threshold);
	if (ret)
		return ret;

	mutex_lock(&memcg->thresholds_lock);

	if (type == _MEM)
		thresholds = &memcg->thresholds;
	else if (type == _MEMSWAP)
		thresholds = &memcg->memsw_thresholds;
	else
		BUG();

	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);

	/* Check if a threshold crossed before adding a new one */
	if (thresholds->primary)
		__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	size = thresholds->primary ? thresholds->primary->size + 1 : 1;

	/* Allocate memory for new array of thresholds */
	new = kmalloc(sizeof(*new) + size * sizeof(struct mem_cgroup_threshold),
			GFP_KERNEL);
	if (!new) {
		ret = -ENOMEM;
		goto unlock;
	}
	new->size = size;

	/* Copy thresholds (if any) to new array */
	if (thresholds->primary) {
		memcpy(new->entries, thresholds->primary->entries, (size - 1) *
				sizeof(struct mem_cgroup_threshold));
	}

	/* Add new threshold */
	new->entries[size - 1].eventfd = eventfd;
	new->entries[size - 1].threshold = threshold;

	/* Sort thresholds. Registering of new threshold isn't time-critical */
	sort(new->entries, size, sizeof(struct mem_cgroup_threshold),
			compare_thresholds, NULL);

	/* Find current threshold */
	new->current_threshold = -1;
	for (i = 0; i < size; i++) {
		if (new->entries[i].threshold < usage) {
			/*
			 * new->current_threshold will not be used until
			 * rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		}
	}

	/* Free old spare buffer and save old primary buffer as spare */
	kfree(thresholds->spare);
	thresholds->spare = thresholds->primary;

	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

unlock:
	mutex_unlock(&memcg->thresholds_lock);

	return ret;
}

static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
	struct cftype *cft, struct eventfd_ctx *eventfd)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	int type = MEMFILE_TYPE(cft->private);
	u64 usage;
	int i, j, size;

	mutex_lock(&memcg->thresholds_lock);
	if (type == _MEM)
		thresholds = &memcg->thresholds;
	else if (type == _MEMSWAP)
		thresholds = &memcg->memsw_thresholds;
	else
		BUG();

	/*
	 * Something went wrong if we trying to unregister a threshold
	 * if we don't have thresholds
	 */
	BUG_ON(!thresholds);

	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);

	/* Check if a threshold crossed before removing */
	__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	/* Calculate new number of threshold */
	size = 0;
	for (i = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd != eventfd)
			size++;
	}

	new = thresholds->spare;

	/* Set thresholds array to NULL if we don't have thresholds */
	if (!size) {
		kfree(new);
		new = NULL;
		goto swap_buffers;
	}

	new->size = size;

	/* Copy thresholds and find current threshold */
	new->current_threshold = -1;
	for (i = 0, j = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd == eventfd)
			continue;

		new->entries[j] = thresholds->primary->entries[i];
		if (new->entries[j].threshold < usage) {
			/*
			 * new->current_threshold will not be used
			 * until rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		}
		j++;
	}

swap_buffers:
	/* Swap primary and spare array */
	thresholds->spare = thresholds->primary;
	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

	mutex_unlock(&memcg->thresholds_lock);
}

static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
	struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
	struct mem_cgroup_eventfd_list *event;
	int type = MEMFILE_TYPE(cft->private);

	BUG_ON(type != _OOM_TYPE);
	event = kmalloc(sizeof(*event),	GFP_KERNEL);
	if (!event)
		return -ENOMEM;

	mutex_lock(&memcg_oom_mutex);

	event->eventfd = eventfd;
	list_add(&event->list, &memcg->oom_notify);

	/* already in OOM ? */
	if (atomic_read(&memcg->oom_lock))
		eventfd_signal(eventfd, 1);
	mutex_unlock(&memcg_oom_mutex);

	return 0;
}

static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
	struct cftype *cft, struct eventfd_ctx *eventfd)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
	struct mem_cgroup_eventfd_list *ev, *tmp;
	int type = MEMFILE_TYPE(cft->private);

	BUG_ON(type != _OOM_TYPE);

	mutex_lock(&memcg_oom_mutex);

	list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) {
		if (ev->eventfd == eventfd) {