memcontrol.c

	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 *memcg, *parent;
	long error = -ENOMEM;
	int node;

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

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

	/* root ? */
	if (cont->parent == NULL) {
		int cpu;
		enable_swap_cgroup();
		parent = NULL;
		root_mem_cgroup = memcg;
		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);
		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);
		res_counter_init(&memcg->kmem, &parent->kmem);
		/*
		 * 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);
		res_counter_init(&memcg->kmem, NULL);
	}
	memcg->last_scanned_child = 0;
	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);
	return &memcg->css;
free_out:
	__mem_cgroup_free(memcg);
	root_mem_cgroup = NULL;
	return ERR_PTR(error);
}

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

	mem_cgroup_put(memcg);
}

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);

	if (!ret)
		ret = register_kmem_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 *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 || !memcg)
			/* 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
 * @ptent: the pte to be checked
 * @target: the pointer the target page or swap ent will be stored(can be NULL)
 *
 * Returns
 *   0(MC_TARGET_NONE): if the pte is not a target for move charge.
 *   1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
 *     move charge. if @target is not NULL, the page is stored in target->page
 *     with extra refcnt got(Callers should handle it).
 *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
 *     target for charge migration. if @target is not NULL, the entry is stored
 *     in target->ent.
 *
 * Called with pte lock held.
 */
union mc_target {
	struct page	*page;
	swp_entry_t	ent;
};

enum mc_target_type {
	MC_TARGET_NONE,	/* not used */
	MC_TARGET_PAGE,
	MC_TARGET_SWAP,
};

static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
						unsigned long addr, pte_t ptent)
{
	struct page *page = vm_normal_page(vma, addr, ptent);

	if (!page || !page_mapped(page))
		return NULL;
	if (PageAnon(page)) {
		/* we don't move shared anon */
		if (!move_anon() || page_mapcount(page) > 2)
			return NULL;
	} else if (!move_file())
		/* we ignore mapcount for file pages */
		return NULL;
	if (!get_page_unless_zero(page))
		return NULL;

	return page;
}

static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
			unsigned long addr, pte_t ptent, swp_entry_t *entry)
{
	int usage_count;
	struct page *page = NULL;
	swp_entry_t ent = pte_to_swp_entry(ptent);

	if (!move_anon() || non_swap_entry(ent))
		return NULL;
	usage_count = mem_cgroup_count_swap_user(ent, &page);
	if (usage_count > 1) { /* we don't move shared anon */
		if (page)
			put_page(page);
		return NULL;
	}
	if (do_swap_account)
		entry->val = ent.val;

	return page;
}

static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
			unsigned long addr, pte_t ptent, swp_entry_t *entry)
{
	struct page *page = NULL;
	struct inode *inode;
	struct address_space *mapping;
	pgoff_t pgoff;

	if (!vma->vm_file) /* anonymous vma */
		return NULL;
	if (!move_file())
		return NULL;

	inode = vma->vm_file->f_path.dentry->d_inode;
	mapping = vma->vm_file->f_mapping;
	if (pte_none(ptent))
		pgoff = linear_page_index(vma, addr);
	else /* pte_file(ptent) is true */
		pgoff = pte_to_pgoff(ptent);

	/* page is moved even if it's not RSS of this task(page-faulted). */
	page = find_get_page(mapping, pgoff);

#ifdef CONFIG_SWAP
	/* shmem/tmpfs may report page out on swap: account for that too. */
	if (radix_tree_exceptional_entry(page)) {
		swp_entry_t swap = radix_to_swp_entry(page);
		if (do_swap_account)
			*entry = swap;
		page = find_get_page(&swapper_space, swap.val);
	}
#endif
	return page;
}

static int is_target_pte_for_mc(struct vm_area_struct *vma,
		unsigned long addr, pte_t ptent, union mc_target *target)
{
	struct page *page = NULL;
	struct page_cgroup *pc;
	int ret = 0;
	swp_entry_t ent = { .val = 0 };

	if (pte_present(ptent))
		page = mc_handle_present_pte(vma, addr, ptent);
	else if (is_swap_pte(ptent))
		page = mc_handle_swap_pte(vma, addr, ptent, &ent);
	else if (pte_none(ptent) || pte_file(ptent))
		page = mc_handle_file_pte(vma, addr, ptent, &ent);

	if (!page && !ent.val)
		return 0;
	if (page) {
		pc = lookup_page_cgroup(page);
		/*
		 * Do only loose check w/o page_cgroup lock.
		 * mem_cgroup_move_account() checks the pc is valid or not under
		 * the lock.
		 */
		if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
			ret = MC_TARGET_PAGE;
			if (target)
				target->page = page;
		}
		if (!ret || !target)
			put_page(page);
	}
	/* There is a swap entry and a page doesn't exist or isn't charged */
	if (ent.val && !ret &&
			css_id(&mc.from->css) == lookup_swap_cgroup(ent)) {
		ret = MC_TARGET_SWAP;
		if (target)
			target->ent = ent;
	}
	return ret;
}

static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
					unsigned long addr, unsigned long end,
					struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->private;
	pte_t *pte;
	spinlock_t *ptl;

	split_huge_page_pmd(walk->mm, pmd);

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE)
		if (is_target_pte_for_mc(vma, addr, *pte, NULL))
			mc.precharge++;	/* increment precharge temporarily */
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();

	return 0;
}

static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
{
	unsigned long precharge;
	struct vm_area_struct *vma;

	down_read(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		struct mm_walk mem_cgroup_count_precharge_walk = {
			.pmd_entry = mem_cgroup_count_precharge_pte_range,
			.mm = mm,
			.private = vma,
		};
		if (is_vm_hugetlb_page(vma))
			continue;
		walk_page_range(vma->vm_start, vma->vm_end,
					&mem_cgroup_count_precharge_walk);
	}
	up_read(&mm->mmap_sem);

	precharge = mc.precharge;
	mc.precharge = 0;

	return precharge;
}

static int mem_cgroup_precharge_mc(struct mm_struct *mm)
{
	unsigned long precharge = mem_cgroup_count_precharge(mm);

	VM_BUG_ON(mc.moving_task);
	mc.moving_task = current;
	return mem_cgroup_do_precharge(precharge);
}

/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */
static void __mem_cgroup_clear_mc(void)
{
	struct mem_cgroup *from = mc.from;
	struct mem_cgroup *to = mc.to;

	/* we must uncharge all the leftover precharges from mc.to */
	if (mc.precharge) {
		__mem_cgroup_cancel_charge(mc.to, mc.precharge);
		mc.precharge = 0;
	}
	/*
	 * we didn't uncharge from mc.from at mem_cgroup_move_account(), so
	 * we must uncharge here.
	 */
	if (mc.moved_charge) {
		__mem_cgroup_cancel_charge(mc.from, mc.moved_charge);
		mc.moved_charge = 0;
	}
	/* we must fixup refcnts and charges */
	if (mc.moved_swap) {
		/* uncharge swap account from the old cgroup */
		if (!mem_cgroup_is_root(mc.from))
			res_counter_uncharge(&mc.from->memsw,
						PAGE_SIZE * mc.moved_swap);
		__mem_cgroup_put(mc.from, mc.moved_swap);

		if (!mem_cgroup_is_root(mc.to)) {
			/*
			 * we charged both to->res and to->memsw, so we should
			 * uncharge to->res.
			 */
			res_counter_uncharge(&mc.to->res,
						PAGE_SIZE * mc.moved_swap);
		}
		/* we've already done mem_cgroup_get(mc.to) */
		mc.moved_swap = 0;
	}
	memcg_oom_recover(from);
	memcg_oom_recover(to);
	wake_up_all(&mc.waitq);
}

static void mem_cgroup_clear_mc(void)
{
	struct mem_cgroup *from = mc.from;

	/*
	 * we must clear moving_task before waking up waiters at the end of
	 * task migration.
	 */
	mc.moving_task = NULL;
	__mem_cgroup_clear_mc();
	spin_lock(&mc.lock);
	mc.from = NULL;
	mc.to = NULL;
	spin_unlock(&mc.lock);
	mem_cgroup_end_move(from);
}

static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
				struct cgroup *cgroup,
				struct task_struct *p)
{
	int ret = 0;
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);

	if (memcg->move_charge_at_immigrate) {
		struct mm_struct *mm;
		struct mem_cgroup *from = mem_cgroup_from_task(p);

		VM_BUG_ON(from == memcg);

		mm = get_task_mm(p);
		if (!mm)
			return 0;
		/* We move charges only when we move a owner of the mm */
		if (mm->owner == p) {
			VM_BUG_ON(mc.from);
			VM_BUG_ON(mc.to);
			VM_BUG_ON(mc.precharge);
			VM_BUG_ON(mc.moved_charge);
			VM_BUG_ON(mc.moved_swap);
			mem_cgroup_start_move(from);
			spin_lock(&mc.lock);
			mc.from = from;
			mc.to = memcg;
			spin_unlock(&mc.lock);
			/* We set mc.moving_task later */

			ret = mem_cgroup_precharge_mc(mm);
			if (ret)
				mem_cgroup_clear_mc();
		}
		mmput(mm);
	}
	return ret;
}

static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
				struct cgroup *cgroup,
				struct task_struct *p)
{
	mem_cgroup_clear_mc();
}

static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct mm_walk *walk)
{
	int ret = 0;
	struct vm_area_struct *vma = walk->private;
	pte_t *pte;
	spinlock_t *ptl;

	split_huge_page_pmd(walk->mm, pmd);
retry:
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; addr += PAGE_SIZE) {
		pte_t ptent = *(pte++);
		union mc_target target;
		int type;
		struct page *page;
		struct page_cgroup *pc;
		swp_entry_t ent;

		if (!mc.precharge)
			break;

		type = is_target_pte_for_mc(vma, addr, ptent, &target);
		switch (type) {
		case MC_TARGET_PAGE:
			page = target.page;
			if (isolate_lru_page(page))
				goto put;
			pc = lookup_page_cgroup(page);
			if (!mem_cgroup_move_account(page, 1, pc,
						     mc.from, mc.to, false)) {
				mc.precharge--;
				/* we uncharge from mc.from later. */
				mc.moved_charge++;
			}
			putback_lru_page(page);
put:			/* is_target_pte_for_mc() gets the page */
			put_page(page);
			break;
		case MC_TARGET_SWAP:
			ent = target.ent;
			if (!mem_cgroup_move_swap_account(ent,
						mc.from, mc.to, false)) {
				mc.precharge--;
				/* we fixup refcnts and charges later. */
				mc.moved_swap++;
			}
			break;
		default:
			break;
		}
	}
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();

	if (addr != end) {
		/*
		 * We have consumed all precharges we got in can_attach().
		 * We try charge one by one, but don't do any additional
		 * charges to mc.to if we have failed in charge once in attach()
		 * phase.
		 */
		ret = mem_cgroup_do_precharge(1);
		if (!ret)
			goto retry;
	}

	return ret;
}

static void mem_cgroup_move_charge(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	lru_add_drain_all();
retry:
	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
		/*
		 * Someone who are holding the mmap_sem might be waiting in
		 * waitq. So we cancel all extra charges, wake up all waiters,
		 * and retry. Because we cancel precharges, we might not be able
		 * to move enough charges, but moving charge is a best-effort
		 * feature anyway, so it wouldn't be a big problem.
		 */
		__mem_cgroup_clear_mc();
		cond_resched();
		goto retry;
	}
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		int ret;
		struct mm_walk mem_cgroup_move_charge_walk = {
			.pmd_entry = mem_cgroup_move_charge_pte_range,
			.mm = mm,
			.private = vma,
		};
		if (is_vm_hugetlb_page(vma))
			continue;
		ret = walk_page_range(vma->vm_start, vma->vm_end,
						&mem_cgroup_move_charge_walk);
		if (ret)
			/*
			 * means we have consumed all precharges and failed in
			 * doing additional charge. Just abandon here.
			 */
			break;
	}
	up_read(&mm->mmap_sem);
}

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 = get_task_mm(p);

	if (mm) {
		if (mc.to)
			mem_cgroup_move_charge(mm);
		put_swap_token(mm);
		mmput(mm);
	}
	if (mc.to)
		mem_cgroup_clear_mc();
}
#else	/* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
				struct cgroup *cgroup,
				struct task_struct *p)
{
	return 0;
}
static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
				struct cgroup *cgroup,
				struct task_struct *p)
{
}
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
				struct cgroup *cont,
				struct cgroup *old_cont,
				struct task_struct *p)
{
}
#endif

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,
	.can_attach = mem_cgroup_can_attach,
	.cancel_attach = mem_cgroup_cancel_attach,
	.attach = mem_cgroup_move_task,
	.early_init = 0,
	.use_id = 1,
};

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static int __init enable_swap_account(char *s)
{
	/* consider enabled if no parameter or 1 is given */
	if (!strcmp(s, "1"))
		really_do_swap_account = 1;
	else if (!strcmp(s, "0"))
		really_do_swap_account = 0;
	return 1;
}
__setup("swapaccount=", enable_swap_account);

#endif