memcontrol.c

	},
	{
		.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 = memcg_stat_show,
	},
	{
		.name = "force_empty",
		.trigger = mem_cgroup_force_empty_write,
	},
	{
		.name = "use_hierarchy",
		.flags = CFTYPE_INSANE,
		.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),
	},
	{
		.name = "pressure_level",
		.register_event = vmpressure_register_event,
		.unregister_event = vmpressure_unregister_event,
	},
#ifdef CONFIG_NUMA
	{
		.name = "numa_stat",
		.read_seq_string = memcg_numa_stat_show,
	},
#endif
#ifdef CONFIG_MEMCG_KMEM
	{
		.name = "kmem.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
		.write_string = mem_cgroup_write,
		.read = mem_cgroup_read,
	},
	{
		.name = "kmem.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
		.read = mem_cgroup_read,
	},
	{
		.name = "kmem.failcnt",
		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
		.trigger = mem_cgroup_reset,
		.read = mem_cgroup_read,
	},
	{
		.name = "kmem.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
		.trigger = mem_cgroup_reset,
		.read = mem_cgroup_read,
	},
#ifdef CONFIG_SLABINFO
	{
		.name = "kmem.slabinfo",
		.read_seq_string = mem_cgroup_slabinfo_read,
	},
#endif
#endif
	{ },	/* terminate */
};

#ifdef CONFIG_MEMCG_SWAP
static struct cftype memsw_cgroup_files[] = {
	{
		.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,
	},
	{ },	/* terminate */
};
#endif
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);
		mz->usage_in_excess = 0;
		mz->on_tree = false;
		mz->memcg = memcg;
	}
	memcg->nodeinfo[node] = pn;
	return 0;
}

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

static struct mem_cgroup *mem_cgroup_alloc(void)
{
	struct mem_cgroup *memcg;
	size_t size = memcg_size();

	/* Can be very big if nr_node_ids 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;
}

/*
 * 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;
	size_t size = memcg_size();

	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);

	/*
	 * 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_static_keys(memcg);
	if (size < PAGE_SIZE)
		kfree(memcg);
	else
		vfree(memcg);
}

/*
 * 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);

static void __init 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);
		BUG_ON(!rtpn);

		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);
		}
	}
}

static struct cgroup_subsys_state * __ref
mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct mem_cgroup *memcg;
	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 (parent_css == NULL) {
		root_mem_cgroup = memcg;
		res_counter_init(&memcg->res, NULL);
		res_counter_init(&memcg->memsw, NULL);
		res_counter_init(&memcg->kmem, NULL);
	}

	memcg->last_scanned_node = MAX_NUMNODES;
	INIT_LIST_HEAD(&memcg->oom_notify);
	memcg->move_charge_at_immigrate = 0;
	mutex_init(&memcg->thresholds_lock);
	spin_lock_init(&memcg->move_lock);
	vmpressure_init(&memcg->vmpressure);

	return &memcg->css;

free_out:
	__mem_cgroup_free(memcg);
	return ERR_PTR(error);
}

static int
mem_cgroup_css_online(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
	int error = 0;

	if (!parent)
		return 0;

	mutex_lock(&memcg_create_mutex);

	memcg->use_hierarchy = parent->use_hierarchy;
	memcg->oom_kill_disable = parent->oom_kill_disable;
	memcg->swappiness = mem_cgroup_swappiness(parent);

	if (parent->use_hierarchy) {
		res_counter_init(&memcg->res, &parent->res);
		res_counter_init(&memcg->memsw, &parent->memsw);
		res_counter_init(&memcg->kmem, &parent->kmem);

		/*
		 * No need to take a reference to the parent because cgroup
		 * core guarantees its existence.
		 */
	} else {
		res_counter_init(&memcg->res, NULL);
		res_counter_init(&memcg->memsw, NULL);
		res_counter_init(&memcg->kmem, NULL);
		/*
		 * Deeper hierachy with use_hierarchy == false doesn't make
		 * much sense so let cgroup subsystem know about this
		 * unfortunate state in our controller.
		 */
		if (parent != root_mem_cgroup)
			mem_cgroup_subsys.broken_hierarchy = true;
	}

	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
	mutex_unlock(&memcg_create_mutex);
	return error;
}

/*
 * Announce all parents that a group from their hierarchy is gone.
 */
static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
{
	struct mem_cgroup *parent = memcg;

	while ((parent = parent_mem_cgroup(parent)))
		mem_cgroup_iter_invalidate(parent);

	/*
	 * if the root memcg is not hierarchical we have to check it
	 * explicitely.
	 */
	if (!root_mem_cgroup->use_hierarchy)
		mem_cgroup_iter_invalidate(root_mem_cgroup);
}

static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	kmem_cgroup_css_offline(memcg);

	mem_cgroup_invalidate_reclaim_iterators(memcg);
	mem_cgroup_reparent_charges(memcg);
	mem_cgroup_destroy_all_caches(memcg);
	vmpressure_cleanup(&memcg->vmpressure);
}

static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	memcg_destroy_kmem(memcg);
	__mem_cgroup_free(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++;
	}
	return ret;
}

/**
 * get_mctgt_type - get target type of moving 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 = 0,
	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())
			return NULL;
	} else if (!move_file())
		/* we ignore mapcount for file pages */
		return NULL;
	if (!get_page_unless_zero(page))
		return NULL;

	return page;
}

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

	if (!move_anon() || non_swap_entry(ent))
		return NULL;
	/*
	 * Because lookup_swap_cache() updates some statistics counter,
	 * we call find_get_page() with swapper_space directly.
	 */
	page = find_get_page(swap_address_space(ent), ent.val);
	if (do_swap_account)
		entry->val = ent.val;

	return page;
}
#else
static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
			unsigned long addr, pte_t ptent, swp_entry_t *entry)
{
	return NULL;
}
#endif

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 address_space *mapping;
	pgoff_t pgoff;

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

	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(swap_address_space(swap), swap.val);
	}
#endif
	return page;
}

static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
		unsigned long addr, pte_t ptent, union mc_target *target)
{
	struct page *page = NULL;
	struct page_cgroup *pc;
	enum mc_target_type ret = MC_TARGET_NONE;
	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 ret;
	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_id(ent)) {
		ret = MC_TARGET_SWAP;
		if (target)
			target->ent = ent;
	}
	return ret;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * We don't consider swapping or file mapped pages because THP does not
 * support them for now.
 * Caller should make sure that pmd_trans_huge(pmd) is true.
 */
static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
		unsigned long addr, pmd_t pmd, union mc_target *target)
{
	struct page *page = NULL;
	struct page_cgroup *pc;
	enum mc_target_type ret = MC_TARGET_NONE;

	page = pmd_page(pmd);
	VM_BUG_ON(!page || !PageHead(page));
	if (!move_anon())
		return ret;
	pc = lookup_page_cgroup(page);
	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
		ret = MC_TARGET_PAGE;
		if (target) {
			get_page(page);
			target->page = page;
		}
	}
	return ret;
}
#else
static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
		unsigned long addr, pmd_t pmd, union mc_target *target)
{
	return MC_TARGET_NONE;
}
#endif

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;

	if (pmd_trans_huge_lock(pmd, vma) == 1) {
		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
			mc.precharge += HPAGE_PMD_NR;
		spin_unlock(&vma->vm_mm->page_table_lock);
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE)
		if (get_mctgt_type(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;
	int i;

	/* 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);

		for (i = 0; i < mc.moved_swap; i++)
			css_put(&mc.from->css);

		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 css_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_state *css,
				 struct cgroup_taskset *tset)
{
	struct task_struct *p = cgroup_taskset_first(tset);
	int ret = 0;
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	unsigned long move_charge_at_immigrate;

	/*
	 * We are now commited to this value whatever it is. Changes in this
	 * tunable will only affect upcoming migrations, not the current one.
	 * So we need to save it, and keep it going.
	 */
	move_charge_at_immigrate  = memcg->move_charge_at_immigrate;
	if (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;
			mc.immigrate_flags = move_charge_at_immigrate;
			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_state *css,
				     struct cgroup_taskset *tset)
{
	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;
	enum mc_target_type target_type;
	union mc_target target;
	struct page *page;
	struct page_cgroup *pc;

	/*
	 * We don't take compound_lock() here but no race with splitting thp
	 * happens because:
	 *  - if pmd_trans_huge_lock() returns 1, the relevant thp is not
	 *    under splitting, which means there's no concurrent thp split,
	 *  - if another thread runs into split_huge_page() just after we
	 *    entered this if-block, the thread must wait for page table lock
	 *    to be unlocked in __split_huge_page_splitting(), where the main
	 *    part of thp split is not executed yet.
	 */
	if (pmd_trans_huge_lock(pmd, vma) == 1) {
		if (mc.precharge < HPAGE_PMD_NR) {
			spin_unlock(&vma->vm_mm->page_table_lock);
			return 0;
		}
		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
		if (target_type == MC_TARGET_PAGE) {
			page = target.page;
			if (!isolate_lru_page(page)) {
				pc = lookup_page_cgroup(page);
				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
							pc, mc.from, mc.to)) {
					mc.precharge -= HPAGE_PMD_NR;
					mc.moved_charge += HPAGE_PMD_NR;
				}
				putback_lru_page(page);
			}
			put_page(page);
		}
		spin_unlock(&vma->vm_mm->page_table_lock);
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
retry:
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; addr += PAGE_SIZE) {
		pte_t ptent = *(pte++);
		swp_entry_t ent;

		if (!mc.precharge)
			break;

		switch (get_mctgt_type(vma, addr, ptent, &target)) {
		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)) {
				mc.precharge--;
				/* we uncharge from mc.from later. */
				mc.moved_charge++;
			}
			putback_lru_page(page);
put:			/* get_mctgt_type() 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)) {
				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_state *css,
				 struct cgroup_taskset *tset)
{
	struct task_struct *p = cgroup_taskset_first(tset);
	struct mm_struct *mm = get_task_mm(p);

	if (mm) {
		if (mc.to)
			mem_cgroup_move_charge(mm);
		mmput(mm);
	}
	if (mc.to)
		mem_cgroup_clear_mc();
}
#else	/* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
				 struct cgroup_taskset *tset)
{
	return 0;
}
static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
				     struct cgroup_taskset *tset)
{
}
static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
				 struct cgroup_taskset *tset)
{
}
#endif

/*
 * Cgroup retains root cgroups across [un]mount cycles making it necessary
 * to verify sane_behavior flag on each mount attempt.
 */
static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
{
	/*
	 * use_hierarchy is forced with sane_behavior.  cgroup core
	 * guarantees that @root doesn't have any children, so turning it
	 * on for the root memcg is enough.
	 */
	if (cgroup_sane_behavior(root_css->cgroup))
		mem_cgroup_from_css(root_css)->use_hierarchy = true;
}

struct cgroup_subsys mem_cgroup_subsys = {
	.name = "memory",
	.subsys_id = mem_cgroup_subsys_id,
	.css_alloc = mem_cgroup_css_alloc,
	.css_online = mem_cgroup_css_online,
	.css_offline = mem_cgroup_css_offline,
	.css_free = mem_cgroup_css_free,
	.can_attach = mem_cgroup_can_attach,
	.cancel_attach = mem_cgroup_cancel_attach,
	.attach = mem_cgroup_move_task,
	.bind = mem_cgroup_bind,
	.base_cftypes = mem_cgroup_files,
	.early_init = 0,