memcontrol.c

	for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
		s64 val;

		val = mem_cgroup_read_stat(stat, i);
		val *= mem_cgroup_stat_desc[i].unit;
		cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
	}
	/* showing # of active pages */
	{
		unsigned long active_anon, inactive_anon;
		unsigned long active_file, inactive_file;
		unsigned long unevictable;

		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_INACTIVE_ANON);
		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_ACTIVE_ANON);
		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_INACTIVE_FILE);
		active_file = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_ACTIVE_FILE);
		unevictable = mem_cgroup_get_all_zonestat(mem_cont,
							LRU_UNEVICTABLE);

		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);

	}
	return 0;
}

static struct cftype mem_cgroup_files[] = {
	{
		.name = "usage_in_bytes",
		.private = RES_USAGE,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "max_usage_in_bytes",
		.private = RES_MAX_USAGE,
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "limit_in_bytes",
		.private = RES_LIMIT,
		.write_string = mem_cgroup_write,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "failcnt",
		.private = RES_FAILCNT,
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "force_empty",
		.trigger = mem_force_empty_write,
	},
	{
		.name = "stat",
		.read_map = mem_control_stat_show,
	},
};

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 = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
	if (!pn)
		return 1;

	mem->info.nodeinfo[node] = pn;
	memset(pn, 0, sizeof(*pn));

	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
		mz = &pn->zoneinfo[zone];
		spin_lock_init(&mz->lru_lock);
		for_each_lru(l)
			INIT_LIST_HEAD(&mz->lists[l]);
	}
	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;

	if (sizeof(*mem) < PAGE_SIZE)
		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
	else
		mem = vmalloc(sizeof(*mem));

	if (mem)
		memset(mem, 0, sizeof(*mem));
	return mem;
}

static void mem_cgroup_free(struct mem_cgroup *mem)
{
	if (sizeof(*mem) < PAGE_SIZE)
		kfree(mem);
	else
		vfree(mem);
}


static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct mem_cgroup *mem;
	int node;

	if (unlikely((cont->parent) == NULL)) {
		mem = &init_mem_cgroup;
		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
	} else {
		mem = mem_cgroup_alloc();
		if (!mem)
			return ERR_PTR(-ENOMEM);
	}

	res_counter_init(&mem->res);

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

	return &mem->css;
free_out:
	for_each_node_state(node, N_POSSIBLE)
		free_mem_cgroup_per_zone_info(mem, node);
	if (cont->parent != NULL)
		mem_cgroup_free(mem);
	return ERR_PTR(-ENOMEM);
}

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

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

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

	mem_cgroup_free(mem_cgroup_from_cont(cont));
}

static int mem_cgroup_populate(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, mem_cgroup_files,
					ARRAY_SIZE(mem_cgroup_files));
}

static void mem_cgroup_move_task(struct cgroup_subsys *ss,
				struct cgroup *cont,
				struct cgroup *old_cont,
				struct task_struct *p)
{
	struct mm_struct *mm;
	struct mem_cgroup *mem, *old_mem;

	mm = get_task_mm(p);
	if (mm == NULL)
		return;

	mem = mem_cgroup_from_cont(cont);
	old_mem = mem_cgroup_from_cont(old_cont);

	/*
	 * Only thread group leaders are allowed to migrate, the mm_struct is
	 * in effect owned by the leader
	 */
	if (!thread_group_leader(p))
		goto out;

out:
	mmput(mm);
}

struct cgroup_subsys mem_cgroup_subsys = {
	.name = "memory",
	.subsys_id = mem_cgroup_subsys_id,
	.create = mem_cgroup_create,
	.pre_destroy = mem_cgroup_pre_destroy,
	.destroy = mem_cgroup_destroy,
	.populate = mem_cgroup_populate,
	.attach = mem_cgroup_move_task,
	.early_init = 0,
};