memcontrol.c

	 * inconsistent.
	 */
	cgroup_lock();
	memcg->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

#ifdef CONFIG_NUMA
static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft,
				      struct seq_file *m)
{
	int nid;
	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
	unsigned long node_nr;
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);

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

	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
	seq_printf(m, "file=%lu", file_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
				LRU_ALL_FILE);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');

	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
	seq_printf(m, "anon=%lu", anon_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
				LRU_ALL_ANON);
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');

	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
	seq_printf(m, "unevictable=%lu", unevictable_nr);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
				BIT(LRU_UNEVICTABLE));
		seq_printf(m, " N%d=%lu", nid, node_nr);
	}
	seq_putc(m, '\n');
	return 0;
}
#endif /* CONFIG_NUMA */

static const char * const mem_cgroup_lru_names[] = {
	"inactive_anon",
	"active_anon",
	"inactive_file",
	"active_file",
	"unevictable",
};

static inline void mem_cgroup_lru_names_not_uptodate(void)
{
	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
}

static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
				 struct seq_file *m)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	struct mem_cgroup *mi;
	unsigned int i;

	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
			continue;
		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
	}

	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++)
		seq_printf(m, "%s %lu\n", mem_cgroup_events_names[i],
			   mem_cgroup_read_events(memcg, i));

	for (i = 0; i < NR_LRU_LISTS; i++)
		seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i],
			   mem_cgroup_nr_lru_pages(memcg, BIT(i)) * PAGE_SIZE);

	/* Hierarchical information */
	{
		unsigned long long limit, memsw_limit;
		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
		seq_printf(m, "hierarchical_memory_limit %llu\n", limit);
		if (do_swap_account)
			seq_printf(m, "hierarchical_memsw_limit %llu\n",
				   memsw_limit);
	}

	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
		long long val = 0;

		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
			continue;
		for_each_mem_cgroup_tree(mi, memcg)
			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
		seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
	}

	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
		unsigned long long val = 0;

		for_each_mem_cgroup_tree(mi, memcg)
			val += mem_cgroup_read_events(mi, i);
		seq_printf(m, "total_%s %llu\n",
			   mem_cgroup_events_names[i], val);
	}

	for (i = 0; i < NR_LRU_LISTS; i++) {
		unsigned long long val = 0;

		for_each_mem_cgroup_tree(mi, memcg)
			val += mem_cgroup_nr_lru_pages(mi, BIT(i)) * PAGE_SIZE;
		seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], val);
	}

#ifdef CONFIG_DEBUG_VM
	{
		int nid, zid;
		struct mem_cgroup_per_zone *mz;
		struct zone_reclaim_stat *rstat;
		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(memcg, nid, zid);
				rstat = &mz->lruvec.reclaim_stat;

				recent_rotated[0] += rstat->recent_rotated[0];
				recent_rotated[1] += rstat->recent_rotated[1];
				recent_scanned[0] += rstat->recent_scanned[0];
				recent_scanned[1] += rstat->recent_scanned[1];
			}
		seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]);
		seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]);
		seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]);
		seq_printf(m, "recent_scanned_file %lu\n", 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 mem_cgroup_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 or equal to 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 *memcg)
{
	struct mem_cgroup_eventfd_list *ev;

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

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

	for_each_mem_cgroup_tree(iter, memcg)
		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;
		} else
			break;
	}

	/* 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();

	if (!thresholds->primary)
		goto unlock;

	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;
	/* If all events are unregistered, free the spare array */
	if (!new) {
		kfree(thresholds->spare);
		thresholds->spare = NULL;
	}

	rcu_assign_pointer(thresholds->primary, new);

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

	spin_lock(&memcg_oom_lock);

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

	/* already in OOM ? */
	if (atomic_read(&memcg->under_oom))
		eventfd_signal(eventfd, 1);
	spin_unlock(&memcg_oom_lock);

	return 0;
}

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

	BUG_ON(type != _OOM_TYPE);

	spin_lock(&memcg_oom_lock);

	list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) {
		if (ev->eventfd == eventfd) {
			list_del(&ev->list);
			kfree(ev);
		}
	}

	spin_unlock(&memcg_oom_lock);
}

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

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

	if (atomic_read(&memcg->under_oom))
		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 *memcg = 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) ||
	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
		cgroup_unlock();
		return -EINVAL;
	}
	memcg->oom_kill_disable = val;
	if (!val)
		memcg_oom_recover(memcg);
	cgroup_unlock();
	return 0;
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
	return mem_cgroup_sockets_init(memcg, ss);
};

static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
{
	mem_cgroup_sockets_destroy(memcg);
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
	return 0;
}

static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
{
}
#endif

static struct cftype mem_cgroup_files[] = {
	{
		.name = "usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
		.read = 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 = mem_cgroup_read,
	},
	{
		.name = "limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
		.write_string = mem_cgroup_write,
		.read = mem_cgroup_read,
	},
	{
		.name = "soft_limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
		.write_string = mem_cgroup_write,
		.read = mem_cgroup_read,
	},
	{
		.name = "failcnt",
		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
		.trigger = mem_cgroup_reset,
		.read = mem_cgroup_read,
	},
	{
		.name = "stat",
		.read_seq_string = 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",
		.read_seq_string = mem_control_numa_stat_show,
	},
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
	{
		.name = "memsw.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
		.read = 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 = mem_cgroup_read,
	},
	{
		.name = "memsw.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
		.write_string = mem_cgroup_write,
		.read = mem_cgroup_read,
	},
	{
		.name = "memsw.failcnt",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
		.trigger = mem_cgroup_reset,
		.read = mem_cgroup_read,
	},
#endif
	{ },	/* terminate */
};

static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup_per_zone *mz;
	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;

	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
		mz = &pn->zoneinfo[zone];
		lruvec_init(&mz->lruvec, &NODE_DATA(node)->node_zones[zone]);
		mz->usage_in_excess = 0;
		mz->on_tree = false;
		mz->memcg = memcg;
	}
	memcg->info.nodeinfo[node] = pn;
	return 0;
}

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

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

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

	if (!memcg)
		return NULL;

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

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

/*
 * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
 * but in process context.  The work_freeing structure is overlaid
 * on the rcu_freeing structure, which itself is overlaid on memsw.
 */
static void free_work(struct work_struct *work)
{
	struct mem_cgroup *memcg;
	int size = sizeof(struct mem_cgroup);

	memcg = container_of(work, struct mem_cgroup, work_freeing);
	/*
	 * We need to make sure that (at least for now), the jump label
	 * destruction code runs outside of the cgroup lock. This is because
	 * get_online_cpus(), which is called from the static_branch update,
	 * can't be called inside the cgroup_lock. cpusets are the ones
	 * enforcing this dependency, so if they ever change, we might as well.
	 *
	 * schedule_work() will guarantee this happens. Be careful if you need
	 * to move this code around, and make sure it is outside
	 * the cgroup_lock.
	 */
	disarm_sock_keys(memcg);
	if (size < PAGE_SIZE)
		kfree(memcg);
	else
		vfree(memcg);
}

static void free_rcu(struct rcu_head *rcu_head)
{
	struct mem_cgroup *memcg;

	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
	INIT_WORK(&memcg->work_freeing, free_work);
	schedule_work(&memcg->work_freeing);
}

/*
 * 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 *memcg)
{
	int node;

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

	for_each_node(node)
		free_mem_cgroup_per_zone_info(memcg, node);

	free_percpu(memcg->stat);
	call_rcu(&memcg->rcu_freeing, free_rcu);
}

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

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

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

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

#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(node) {
		tmp = node;
		if (!node_state(node, N_NORMAL_MEMORY))
			tmp = -1;
		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
		if (!rtpn)
			goto err_cleanup;

		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;

err_cleanup:
	for_each_node(node) {
		if (!soft_limit_tree.rb_tree_per_node[node])
			break;
		kfree(soft_limit_tree.rb_tree_per_node[node]);
		soft_limit_tree.rb_tree_per_node[node] = NULL;
	}
	return 1;

}

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

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

	for_each_node(node)
		if (alloc_mem_cgroup_per_zone_info(memcg, node))
			goto free_out;

	/* root ? */
	if (cont->parent == NULL) {
		int cpu;
		enable_swap_cgroup();
		parent = NULL;
		if (mem_cgroup_soft_limit_tree_init())
			goto free_out;
		root_mem_cgroup = memcg;
		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);
		memcg->use_hierarchy = parent->use_hierarchy;
		memcg->oom_kill_disable = parent->oom_kill_disable;
	}

	if (parent && parent->use_hierarchy) {
		res_counter_init(&memcg->res, &parent->res);
		res_counter_init(&memcg->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(&memcg->res, NULL);
		res_counter_init(&memcg->memsw, NULL);
	}
	memcg->last_scanned_node = MAX_NUMNODES;
	INIT_LIST_HEAD(&memcg->oom_notify);

	if (parent)
		memcg->swappiness = mem_cgroup_swappiness(parent);
	atomic_set(&memcg->refcnt, 1);
	memcg->move_charge_at_immigrate = 0;
	mutex_init(&memcg->thresholds_lock);
	spin_lock_init(&memcg->move_lock);

	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
	if (error) {
		/*
		 * We call put now because our (and parent's) refcnts
		 * are already in place. mem_cgroup_put() will internally
		 * call __mem_cgroup_free, so return directly
		 */
		mem_cgroup_put(memcg);
		return ERR_PTR(error);
	}
	return &memcg->css;
free_out:
	__mem_cgroup_free(memcg);
	return ERR_PTR(error);
}

static int mem_cgroup_pre_destroy(struct cgroup *cont)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);

	return mem_cgroup_force_empty(memcg, false);
}

static void mem_cgroup_destroy(struct cgroup *cont)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);

	kmem_cgroup_destroy(memcg);

	mem_cgroup_put(memcg);
}

#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 *memcg = mc.to;

	if (mem_cgroup_is_root(memcg)) {
		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;
		/*
		 * "memcg" 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(&memcg->res, PAGE_SIZE * count, &dummy))
			goto one_by_one;
		if (do_swap_account && res_counter_charge(&memcg->memsw,
						PAGE_SIZE * count, &dummy)) {
			res_counter_uncharge(&memcg->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, &memcg, false);
		if (ret)
			/* mem_cgroup_clear_mc() will do uncharge later */
			return ret;
		mc.precharge++;