memcontrol.c

	MCS_PGMAJFAULT,
	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"},
	{"pgfault", "total_pgfault"},
	{"pgmajfault", "total_pgmajfault"},
	{"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_events(mem, MEM_CGROUP_EVENTS_PGPGIN);
	s->stat[MCS_PGPGIN] += val;
	val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGOUT);
	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;
	}
	val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGFAULT);
	s->stat[MCS_PGFAULT] += val;
	val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGMAJFAULT);
	s->stat[MCS_PGMAJFAULT] += val;

	/* 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);
}

#ifdef CONFIG_NUMA
static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
{
	int nid;
	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
	unsigned long node_nr;
	struct cgroup *cont = m->private;
	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);

	total_nr = mem_cgroup_nr_lru_pages(mem_cont);
	seq_printf(m, "total=%lu", total_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');

	file_nr = mem_cgroup_nr_file_lru_pages(mem_cont);
	seq_printf(m, "file=%lu", file_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_file_lru_pages(mem_cont, nid);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');

	anon_nr = mem_cgroup_nr_anon_lru_pages(mem_cont);
	seq_printf(m, "anon=%lu", anon_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_anon_lru_pages(mem_cont, nid);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');

	unevictable_nr = mem_cgroup_nr_unevictable_lru_pages(mem_cont);
	seq_printf(m, "unevictable=%lu", unevictable_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_unevictable_lru_pages(mem_cont,
									nid);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');
	return 0;
}
#endif /* CONFIG_NUMA */

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;
	}

	memcg->swappiness = val;

	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) {
			list_del(&ev->list);
			kfree(ev);
		}
	}

	mutex_unlock(&memcg_oom_mutex);
}

static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
	struct cftype *cft,  struct cgroup_map_cb *cb)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);

	cb->fill(cb, "oom_kill_disable", mem->oom_kill_disable);

	if (atomic_read(&mem->oom_lock))
		cb->fill(cb, "under_oom", 1);
	else
		cb->fill(cb, "under_oom", 0);
	return 0;
}

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

	/* cannot set to root cgroup and only 0 and 1 are allowed */
	if (!cgrp->parent || !((val == 0) || (val == 1)))
		return -EINVAL;

	parent = mem_cgroup_from_cont(cgrp->parent);

	cgroup_lock();
	/* oom-kill-disable is a flag for subhierarchy. */
	if ((parent->use_hierarchy) ||
	    (mem->use_hierarchy && !list_empty(&cgrp->children))) {
		cgroup_unlock();
		return -EINVAL;
	}
	mem->oom_kill_disable = val;
	if (!val)
		memcg_oom_recover(mem);
	cgroup_unlock();
	return 0;
}

#ifdef CONFIG_NUMA
static const struct file_operations mem_control_numa_stat_file_operations = {
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
{
	struct cgroup *cont = file->f_dentry->d_parent->d_fsdata;

	file->f_op = &mem_control_numa_stat_file_operations;
	return single_open(file, mem_control_numa_stat_show, cont);
}
#endif /* CONFIG_NUMA */

static struct cftype mem_cgroup_files[] = {
	{
		.name = "usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
		.read_u64 = mem_cgroup_read,
		.register_event = mem_cgroup_usage_register_event,
		.unregister_event = mem_cgroup_usage_unregister_event,
	},
	{
		.name = "max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
		.write_string = mem_cgroup_write,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "soft_limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
		.write_string = mem_cgroup_write,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "failcnt",
		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "stat",
		.read_map = mem_control_stat_show,
	},
	{
		.name = "force_empty",
		.trigger = mem_cgroup_force_empty_write,
	},
	{
		.name = "use_hierarchy",
		.write_u64 = mem_cgroup_hierarchy_write,
		.read_u64 = mem_cgroup_hierarchy_read,
	},
	{
		.name = "swappiness",
		.read_u64 = mem_cgroup_swappiness_read,
		.write_u64 = mem_cgroup_swappiness_write,
	},
	{
		.name = "move_charge_at_immigrate",
		.read_u64 = mem_cgroup_move_charge_read,
		.write_u64 = mem_cgroup_move_charge_write,
	},
	{
		.name = "oom_control",
		.read_map = mem_cgroup_oom_control_read,
		.write_u64 = mem_cgroup_oom_control_write,
		.register_event = mem_cgroup_oom_register_event,
		.unregister_event = mem_cgroup_oom_unregister_event,
		.private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
	},
#ifdef CONFIG_NUMA
	{
		.name = "numa_stat",
		.open = mem_control_numa_stat_open,
	},
#endif
};

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static struct cftype memsw_cgroup_files[] = {
	{
		.name = "memsw.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
		.read_u64 = mem_cgroup_read,
		.register_event = mem_cgroup_usage_register_event,
		.unregister_event = mem_cgroup_usage_unregister_event,
	},
	{
		.name = "memsw.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "memsw.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
		.write_string = mem_cgroup_write,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "memsw.failcnt",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
};

static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
{
	if (!do_swap_account)
		return 0;
	return cgroup_add_files(cont, ss, memsw_cgroup_files,
				ARRAY_SIZE(memsw_cgroup_files));
};
#else
static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
{
	return 0;
}
#endif

static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup_per_zone *mz;
	enum lru_list l;
	int zone, tmp = node;
	/*
	 * This routine is called against possible nodes.
	 * But it's BUG to call kmalloc() against offline node.
	 *
	 * TODO: this routine can waste much memory for nodes which will
	 *       never be onlined. It's better to use memory hotplug callback
	 *       function.
	 */
	if (!node_state(node, N_NORMAL_MEMORY))
		tmp = -1;
	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
	if (!pn)
		return 1;

	mem->info.nodeinfo[node] = pn;
	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
		mz = &pn->zoneinfo[zone];
		for_each_lru(l)
			INIT_LIST_HEAD(&mz->lists[l]);
		mz->usage_in_excess = 0;
		mz->on_tree = false;
		mz->mem = mem;
	}
	return 0;
}

static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
	kfree(mem->info.nodeinfo[node]);
}

static struct mem_cgroup *mem_cgroup_alloc(void)
{
	struct mem_cgroup *mem;
	int size = sizeof(struct mem_cgroup);

	/* Can be very big if MAX_NUMNODES is very big */
	if (size < PAGE_SIZE)
		mem = kzalloc(size, GFP_KERNEL);
	else
		mem = vzalloc(size);

	if (!mem)
		return NULL;

	mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
	if (!mem->stat)
		goto out_free;
	spin_lock_init(&mem->pcp_counter_lock);
	return mem;

out_free:
	if (size < PAGE_SIZE)
		kfree(mem);
	else
		vfree(mem);
	return NULL;
}

/*
 * At destroying mem_cgroup, references from swap_cgroup can remain.
 * (scanning all at force_empty is too costly...)
 *
 * Instead of clearing all references at force_empty, we remember
 * the number of reference from swap_cgroup and free mem_cgroup when
 * it goes down to 0.
 *
 * Removal of cgroup itself succeeds regardless of refs from swap.
 */

static void __mem_cgroup_free(struct mem_cgroup *mem)
{
	int node;

	mem_cgroup_remove_from_trees(mem);
	free_css_id(&mem_cgroup_subsys, &mem->css);

	for_each_node_state(node, N_POSSIBLE)
		free_mem_cgroup_per_zone_info(mem, node);

	free_percpu(mem->stat);
	if (sizeof(struct mem_cgroup) < PAGE_SIZE)
		kfree(mem);
	else
		vfree(mem);
}

static void mem_cgroup_get(struct mem_cgroup *mem)
{
	atomic_inc(&mem->refcnt);
}

static void __mem_cgroup_put(struct mem_cgroup *mem, int count)
{
	if (atomic_sub_and_test(count, &mem->refcnt)) {
		struct mem_cgroup *parent = parent_mem_cgroup(mem);
		__mem_cgroup_free(mem);
		if (parent)
			mem_cgroup_put(parent);
	}
}

static void mem_cgroup_put(struct mem_cgroup *mem)
{
	__mem_cgroup_put(mem, 1);
}

/*
 * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
 */
static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
{
	if (!mem->res.parent)
		return NULL;
	return mem_cgroup_from_res_counter(mem->res.parent, res);
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static void __init enable_swap_cgroup(void)
{
	if (!mem_cgroup_disabled() && really_do_swap_account)
		do_swap_account = 1;
}
#else
static void __init enable_swap_cgroup(void)
{
}
#endif

static int mem_cgroup_soft_limit_tree_init(void)
{
	struct mem_cgroup_tree_per_node *rtpn;
	struct mem_cgroup_tree_per_zone *rtpz;
	int tmp, node, zone;

	for_each_node_state(node, N_POSSIBLE) {
		tmp = node;
		if (!node_state(node, N_NORMAL_MEMORY))
			tmp = -1;
		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
		if (!rtpn)
			return 1;

		soft_limit_tree.rb_tree_per_node[node] = rtpn;

		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
			rtpz = &rtpn->rb_tree_per_zone[zone];
			rtpz->rb_root = RB_ROOT;
			spin_lock_init(&rtpz->lock);
		}
	}
	return 0;
}

static struct cgroup_subsys_state * __ref
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct mem_cgroup *mem, *parent;
	long error = -ENOMEM;
	int node;

	mem = mem_cgroup_alloc();
	if (!mem)
		return ERR_PTR(error);

	for_each_node_state(node, N_POSSIBLE)
		if (alloc_mem_cgroup_per_zone_info(mem, node))
			goto free_out;

	/* root ? */
	if (cont->parent == NULL) {
		int cpu;
		enable_swap_cgroup();
		parent = NULL;
		root_mem_cgroup = mem;
		if (mem_cgroup_soft_limit_tree_init())
			goto free_out;
		for_each_possible_cpu(cpu) {
			struct memcg_stock_pcp *stock =
						&per_cpu(memcg_stock, cpu);
			INIT_WORK(&stock->work, drain_local_stock);
		}
		hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
	} else {
		parent = mem_cgroup_from_cont(cont->parent);
		mem->use_hierarchy = parent->use_hierarchy;
		mem->oom_kill_disable = parent->oom_kill_disable;
	}

	if (parent && parent->use_hierarchy) {
		res_counter_init(&mem->res, &parent->res);
		res_counter_init(&mem->memsw, &parent->memsw);
		/*
		 * We increment refcnt of the parent to ensure that we can
		 * safely access it on res_counter_charge/uncharge.
		 * This refcnt will be decremented when freeing this
		 * mem_cgroup(see mem_cgroup_put).
		 */
		mem_cgroup_get(parent);
	} else {
		res_counter_init(&mem->res, NULL);
		res_counter_init(&mem->memsw, NULL);
	}
	mem->last_scanned_child = 0;
	mem->last_scanned_node = MAX_NUMNODES;
	INIT_LIST_HEAD(&mem->oom_notify);

	if (parent)
		mem->swappiness = get_swappiness(parent);
	atomic_set(&mem->refcnt, 1);
	mem->move_charge_at_immigrate = 0;
	mutex_init(&mem->thresholds_lock);
	return &mem->css;
free_out:
	__mem_cgroup_free(mem);
	root_mem_cgroup = NULL;
	return ERR_PTR(error);
}

static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
					struct cgroup *cont)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);

	return mem_cgroup_force_empty(mem, false);
}

static void mem_cgroup_destroy(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);

	mem_cgroup_put(mem);
}

static int mem_cgroup_populate(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	int ret;

	ret = cgroup_add_files(cont, ss, mem_cgroup_files,
				ARRAY_SIZE(mem_cgroup_files));

	if (!ret)
		ret = register_memsw_files(cont, ss);
	return ret;
}

#ifdef CONFIG_MMU
/* Handlers for move charge at task migration. */
#define PRECHARGE_COUNT_AT_ONCE	256
static int mem_cgroup_do_precharge(unsigned long count)
{
	int ret = 0;
	int batch_count = PRECHARGE_COUNT_AT_ONCE;
	struct mem_cgroup *mem = mc.to;

	if (mem_cgroup_is_root(mem)) {
		mc.precharge += count;
		/* we don't need css_get for root */
		return ret;
	}
	/* try to charge at once */
	if (count > 1) {
		struct res_counter *dummy;
		/*
		 * "mem" cannot be under rmdir() because we've already checked
		 * by cgroup_lock_live_cgroup() that it is not removed and we
		 * are still under the same cgroup_mutex. So we can postpone
		 * css_get().
		 */
		if (res_counter_charge(&mem->res, PAGE_SIZE * count, &dummy))
			goto one_by_one;
		if (do_swap_account && res_counter_charge(&mem->memsw,
						PAGE_SIZE * count, &dummy)) {
			res_counter_uncharge(&mem->res, PAGE_SIZE * count);
			goto one_by_one;
		}
		mc.precharge += count;
		return ret;
	}
one_by_one:
	/* fall back to one by one charge */
	while (count--) {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		if (!batch_count--) {
			batch_count = PRECHARGE_COUNT_AT_ONCE;
			cond_resched();
		}
		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, 1, &mem, false);
		if (ret || !mem)
			/* mem_cgroup_clear_mc() will do uncharge later */
			return -ENOMEM;
		mc.precharge++;
	}
	return ret;
}

/**
 * is_target_pte_for_mc - check a pte whether it is valid for move charge
 * @vma: the vma the pte to be checked belongs
 * @addr: the address corresponding to the pte to be checked