memcontrol.c

/* memcontrol.c - Memory Controller
 *
 * Copyright IBM Corporation, 2007
 * Author Balbir Singh <balbir@linux.vnet.ibm.com>
 *
 * Copyright 2007 OpenVZ SWsoft Inc
 * Author: Pavel Emelianov <xemul@openvz.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 */

#include <linux/res_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
#include "internal.h"

#include <asm/uaccess.h>

struct cgroup_subsys mem_cgroup_subsys __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES	5

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
int do_swap_account __read_mostly;
static int really_do_swap_account __initdata = 1; /* for remember boot option*/
#else
#define do_swap_account		(0)
#endif


/*
 * Statistics for memory cgroup.
 */
enum mem_cgroup_stat_index {
	/*
	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
	 */
	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as rss */
	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */

	MEM_CGROUP_STAT_NSTATS,
};

struct mem_cgroup_stat_cpu {
	s64 count[MEM_CGROUP_STAT_NSTATS];
} ____cacheline_aligned_in_smp;

struct mem_cgroup_stat {
	struct mem_cgroup_stat_cpu cpustat[0];
};

/*
 * For accounting under irq disable, no need for increment preempt count.
 */
static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat,
		enum mem_cgroup_stat_index idx, int val)
{
	stat->count[idx] += val;
}

static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
		enum mem_cgroup_stat_index idx)
{
	int cpu;
	s64 ret = 0;
	for_each_possible_cpu(cpu)
		ret += stat->cpustat[cpu].count[idx];
	return ret;
}

/*
 * per-zone information in memory controller.
 */
struct mem_cgroup_per_zone {
	/*
	 * spin_lock to protect the per cgroup LRU
	 */
	struct list_head	lists[NR_LRU_LISTS];
	unsigned long		count[NR_LRU_LISTS];

	struct zone_reclaim_stat reclaim_stat;
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])

struct mem_cgroup_per_node {
	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};

struct mem_cgroup_lru_info {
	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
};

/*
 * The memory controller data structure. The memory controller controls both
 * page cache and RSS per cgroup. We would eventually like to provide
 * statistics based on the statistics developed by Rik Van Riel for clock-pro,
 * to help the administrator determine what knobs to tune.
 *
 * TODO: Add a water mark for the memory controller. Reclaim will begin when
 * we hit the water mark. May be even add a low water mark, such that
 * no reclaim occurs from a cgroup at it's low water mark, this is
 * a feature that will be implemented much later in the future.
 */
struct mem_cgroup {
	struct cgroup_subsys_state css;
	/*
	 * the counter to account for memory usage
	 */
	struct res_counter res;
	/*
	 * the counter to account for mem+swap usage.
	 */
	struct res_counter memsw;
	/*
	 * Per cgroup active and inactive list, similar to the
	 * per zone LRU lists.
	 */
	struct mem_cgroup_lru_info info;

	/*
	  protect against reclaim related member.
	*/
	spinlock_t reclaim_param_lock;

	int	prev_priority;	/* for recording reclaim priority */

	/*
	 * While reclaiming in a hiearchy, we cache the last child we
	 * reclaimed from. Protected by cgroup_lock()
	 */
	struct mem_cgroup *last_scanned_child;
	/*
	 * Should the accounting and control be hierarchical, per subtree?
	 */
	bool use_hierarchy;
	unsigned long	last_oom_jiffies;
	int		obsolete;
	atomic_t	refcnt;

	unsigned int inactive_ratio;

	/*
	 * statistics. This must be placed at the end of memcg.
	 */
	struct mem_cgroup_stat stat;
};

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_MAPPED,
	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
	NR_CHARGE_TYPE,
};

/* only for here (for easy reading.) */
#define PCGF_CACHE	(1UL << PCG_CACHE)
#define PCGF_USED	(1UL << PCG_USED)
#define PCGF_LOCK	(1UL << PCG_LOCK)
static const unsigned long
pcg_default_flags[NR_CHARGE_TYPE] = {
	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */
	PCGF_USED | PCGF_LOCK, /* Anon */
	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
	0, /* FORCE */
};

/* for encoding cft->private value on file */
#define _MEM			(0)
#define _MEMSWAP		(1)
#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
#define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)

static void mem_cgroup_get(struct mem_cgroup *mem);
static void mem_cgroup_put(struct mem_cgroup *mem);

static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
					 struct page_cgroup *pc,
					 bool charge)
{
	int val = (charge)? 1 : -1;
	struct mem_cgroup_stat *stat = &mem->stat;
	struct mem_cgroup_stat_cpu *cpustat;
	int cpu = get_cpu();

	cpustat = &stat->cpustat[cpu];
	if (PageCgroupCache(pc))
		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
	else
		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val);

	if (charge)
		__mem_cgroup_stat_add_safe(cpustat,
				MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
	else
		__mem_cgroup_stat_add_safe(cpustat,
				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
	put_cpu();
}

static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}

static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
	struct mem_cgroup *mem = pc->mem_cgroup;
	int nid = page_cgroup_nid(pc);
	int zid = page_cgroup_zid(pc);

	if (!mem)
		return NULL;

	return mem_cgroup_zoneinfo(mem, nid, zid);
}

static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
					enum lru_list idx)
{
	int nid, zid;
	struct mem_cgroup_per_zone *mz;
	u64 total = 0;

	for_each_online_node(nid)
		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
			mz = mem_cgroup_zoneinfo(mem, nid, zid);
			total += MEM_CGROUP_ZSTAT(mz, idx);
		}
	return total;
}

static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont,
				mem_cgroup_subsys_id), struct mem_cgroup,
				css);
}

struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
	/*
	 * mm_update_next_owner() may clear mm->owner to NULL
	 * if it races with swapoff, page migration, etc.
	 * So this can be called with p == NULL.
	 */
	if (unlikely(!p))
		return NULL;

	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
				struct mem_cgroup, css);
}

/*
 * Following LRU functions are allowed to be used without PCG_LOCK.
 * Operations are called by routine of global LRU independently from memcg.
 * What we have to take care of here is validness of pc->mem_cgroup.
 *
 * Changes to pc->mem_cgroup happens when
 * 1. charge
 * 2. moving account
 * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
 * It is added to LRU before charge.
 * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
 * When moving account, the page is not on LRU. It's isolated.
 */

void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
{
	struct page_cgroup *pc;
	struct mem_cgroup *mem;
	struct mem_cgroup_per_zone *mz;

	if (mem_cgroup_disabled())
		return;
	pc = lookup_page_cgroup(page);
	/* can happen while we handle swapcache. */
	if (list_empty(&pc->lru))
		return;
	mz = page_cgroup_zoneinfo(pc);
	mem = pc->mem_cgroup;
	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
	list_del_init(&pc->lru);
	return;
}

void mem_cgroup_del_lru(struct page *page)
{
	mem_cgroup_del_lru_list(page, page_lru(page));
}

void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
{
	struct mem_cgroup_per_zone *mz;
	struct page_cgroup *pc;

	if (mem_cgroup_disabled())
		return;

	pc = lookup_page_cgroup(page);
	smp_rmb();
	/* unused page is not rotated. */
	if (!PageCgroupUsed(pc))
		return;
	mz = page_cgroup_zoneinfo(pc);
	list_move(&pc->lru, &mz->lists[lru]);
}

void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
{
	struct page_cgroup *pc;
	struct mem_cgroup_per_zone *mz;

	if (mem_cgroup_disabled())
		return;
	pc = lookup_page_cgroup(page);
	/* barrier to sync with "charge" */
	smp_rmb();
	if (!PageCgroupUsed(pc))
		return;

	mz = page_cgroup_zoneinfo(pc);
	MEM_CGROUP_ZSTAT(mz, lru) += 1;
	list_add(&pc->lru, &mz->lists[lru]);
}
/*
 * To add swapcache into LRU. Be careful to all this function.
 * zone->lru_lock shouldn't be held and irq must not be disabled.
 */
static void mem_cgroup_lru_fixup(struct page *page)
{
	if (!isolate_lru_page(page))
		putback_lru_page(page);
}

void mem_cgroup_move_lists(struct page *page,
			   enum lru_list from, enum lru_list to)
{
	if (mem_cgroup_disabled())
		return;
	mem_cgroup_del_lru_list(page, from);
	mem_cgroup_add_lru_list(page, to);
}

int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
	int ret;

	task_lock(task);
	ret = task->mm && mm_match_cgroup(task->mm, mem);
	task_unlock(task);
	return ret;
}

/*
 * Calculate mapped_ratio under memory controller. This will be used in
 * vmscan.c for deteremining we have to reclaim mapped pages.
 */
int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
{
	long total, rss;

	/*
	 * usage is recorded in bytes. But, here, we assume the number of
	 * physical pages can be represented by "long" on any arch.
	 */
	total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
	return (int)((rss * 100L) / total);
}

/*
 * prev_priority control...this will be used in memory reclaim path.
 */
int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
{
	int prev_priority;

	spin_lock(&mem->reclaim_param_lock);
	prev_priority = mem->prev_priority;
	spin_unlock(&mem->reclaim_param_lock);

	return prev_priority;
}

void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
{
	spin_lock(&mem->reclaim_param_lock);
	if (priority < mem->prev_priority)
		mem->prev_priority = priority;
	spin_unlock(&mem->reclaim_param_lock);
}

void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
{
	spin_lock(&mem->reclaim_param_lock);
	mem->prev_priority = priority;
	spin_unlock(&mem->reclaim_param_lock);
}

int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
{
	unsigned long active;
	unsigned long inactive;

	inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
	active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);

	if (inactive * memcg->inactive_ratio < active)
		return 1;

	return 0;
}

unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
				       struct zone *zone,
				       enum lru_list lru)
{
	int nid = zone->zone_pgdat->node_id;
	int zid = zone_idx(zone);
	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);

	return MEM_CGROUP_ZSTAT(mz, lru);
}

struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
						      struct zone *zone)
{
	int nid = zone->zone_pgdat->node_id;
	int zid = zone_idx(zone);
	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);

	return &mz->reclaim_stat;
}

struct zone_reclaim_stat *
mem_cgroup_get_reclaim_stat_from_page(struct page *page)
{
	struct page_cgroup *pc;
	struct mem_cgroup_per_zone *mz;

	if (mem_cgroup_disabled())
		return NULL;

	pc = lookup_page_cgroup(page);
	mz = page_cgroup_zoneinfo(pc);
	if (!mz)
		return NULL;

	return &mz->reclaim_stat;
}

unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
					struct list_head *dst,
					unsigned long *scanned, int order,
					int mode, struct zone *z,
					struct mem_cgroup *mem_cont,
					int active, int file)
{
	unsigned long nr_taken = 0;
	struct page *page;
	unsigned long scan;
	LIST_HEAD(pc_list);
	struct list_head *src;
	struct page_cgroup *pc, *tmp;
	int nid = z->zone_pgdat->node_id;
	int zid = zone_idx(z);
	struct mem_cgroup_per_zone *mz;
	int lru = LRU_FILE * !!file + !!active;

	BUG_ON(!mem_cont);
	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
	src = &mz->lists[lru];

	scan = 0;
	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
		if (scan >= nr_to_scan)
			break;

		page = pc->page;
		if (unlikely(!PageCgroupUsed(pc)))
			continue;
		if (unlikely(!PageLRU(page)))
			continue;

		scan++;
		if (__isolate_lru_page(page, mode, file) == 0) {
			list_move(&page->lru, dst);
			nr_taken++;
		}
	}

	*scanned = scan;
	return nr_taken;
}

#define mem_cgroup_from_res_counter(counter, member)	\
	container_of(counter, struct mem_cgroup, member)

/*
 * This routine finds the DFS walk successor. This routine should be
 * called with cgroup_mutex held
 */
static struct mem_cgroup *
mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
{
	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;

	curr_cgroup = curr->css.cgroup;
	root_cgroup = root_mem->css.cgroup;

	if (!list_empty(&curr_cgroup->children)) {
		/*
		 * Walk down to children
		 */
		mem_cgroup_put(curr);
		cgroup = list_entry(curr_cgroup->children.next,
						struct cgroup, sibling);
		curr = mem_cgroup_from_cont(cgroup);
		mem_cgroup_get(curr);
		goto done;
	}

visit_parent:
	if (curr_cgroup == root_cgroup) {
		mem_cgroup_put(curr);
		curr = root_mem;
		mem_cgroup_get(curr);
		goto done;
	}

	/*
	 * Goto next sibling
	 */
	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
		mem_cgroup_put(curr);
		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
						sibling);
		curr = mem_cgroup_from_cont(cgroup);
		mem_cgroup_get(curr);
		goto done;
	}

	/*
	 * Go up to next parent and next parent's sibling if need be
	 */
	curr_cgroup = curr_cgroup->parent;
	goto visit_parent;

done:
	root_mem->last_scanned_child = curr;
	return curr;
}

/*
 * Visit the first child (need not be the first child as per the ordering
 * of the cgroup list, since we track last_scanned_child) of @mem and use
 * that to reclaim free pages from.
 */
static struct mem_cgroup *
mem_cgroup_get_first_node(struct mem_cgroup *root_mem)
{
	struct cgroup *cgroup;
	struct mem_cgroup *ret;
	bool obsolete = (root_mem->last_scanned_child &&
				root_mem->last_scanned_child->obsolete);

	/*
	 * Scan all children under the mem_cgroup mem
	 */
	cgroup_lock();
	if (list_empty(&root_mem->css.cgroup->children)) {
		ret = root_mem;
		goto done;
	}

	if (!root_mem->last_scanned_child || obsolete) {

		if (obsolete)
			mem_cgroup_put(root_mem->last_scanned_child);

		cgroup = list_first_entry(&root_mem->css.cgroup->children,
				struct cgroup, sibling);
		ret = mem_cgroup_from_cont(cgroup);
		mem_cgroup_get(ret);
	} else
		ret = mem_cgroup_get_next_node(root_mem->last_scanned_child,
						root_mem);

done:
	root_mem->last_scanned_child = ret;
	cgroup_unlock();
	return ret;
}

static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
{
	if (do_swap_account) {
		if (res_counter_check_under_limit(&mem->res) &&
			res_counter_check_under_limit(&mem->memsw))
			return true;
	} else
		if (res_counter_check_under_limit(&mem->res))
			return true;
	return false;
}

/*
 * Dance down the hierarchy if needed to reclaim memory. We remember the
 * last child we reclaimed from, so that we don't end up penalizing
 * one child extensively based on its position in the children list.
 *
 * root_mem is the original ancestor that we've been reclaim from.
 */
static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
						gfp_t gfp_mask, bool noswap)
{
	struct mem_cgroup *next_mem;
	int ret = 0;

	/*
	 * Reclaim unconditionally and don't check for return value.
	 * We need to reclaim in the current group and down the tree.
	 * One might think about checking for children before reclaiming,
	 * but there might be left over accounting, even after children
	 * have left.
	 */
	ret = try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap);
	if (mem_cgroup_check_under_limit(root_mem))
		return 0;
	if (!root_mem->use_hierarchy)
		return ret;

	next_mem = mem_cgroup_get_first_node(root_mem);

	while (next_mem != root_mem) {
		if (next_mem->obsolete) {
			mem_cgroup_put(next_mem);
			cgroup_lock();
			next_mem = mem_cgroup_get_first_node(root_mem);
			cgroup_unlock();
			continue;
		}
		ret = try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap);
		if (mem_cgroup_check_under_limit(root_mem))
			return 0;
		cgroup_lock();
		next_mem = mem_cgroup_get_next_node(next_mem, root_mem);
		cgroup_unlock();
	}
	return ret;
}

bool mem_cgroup_oom_called(struct task_struct *task)
{
	bool ret = false;
	struct mem_cgroup *mem;
	struct mm_struct *mm;

	rcu_read_lock();
	mm = task->mm;
	if (!mm)
		mm = &init_mm;
	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10))
		ret = true;
	rcu_read_unlock();
	return ret;
}
/*
 * Unlike exported interface, "oom" parameter is added. if oom==true,
 * oom-killer can be invoked.
 */
static int __mem_cgroup_try_charge(struct mm_struct *mm,
			gfp_t gfp_mask, struct mem_cgroup **memcg,
			bool oom)
{
	struct mem_cgroup *mem, *mem_over_limit;
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct res_counter *fail_res;

	if (unlikely(test_thread_flag(TIF_MEMDIE))) {
		/* Don't account this! */
		*memcg = NULL;
		return 0;
	}

	/*
	 * We always charge the cgroup the mm_struct belongs to.
	 * The mm_struct's mem_cgroup changes on task migration if the
	 * thread group leader migrates. It's possible that mm is not
	 * set, if so charge the init_mm (happens for pagecache usage).
	 */
	if (likely(!*memcg)) {
		rcu_read_lock();
		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!mem)) {
			rcu_read_unlock();
			return 0;
		}
		/*
		 * For every charge from the cgroup, increment reference count
		 */
		css_get(&mem->css);
		*memcg = mem;
		rcu_read_unlock();
	} else {
		mem = *memcg;
		css_get(&mem->css);
	}

	while (1) {
		int ret;
		bool noswap = false;

		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
		if (likely(!ret)) {
			if (!do_swap_account)
				break;
			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
							&fail_res);
			if (likely(!ret))
				break;
			/* mem+swap counter fails */
			res_counter_uncharge(&mem->res, PAGE_SIZE);
			noswap = true;
			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
									memsw);
		} else
			/* mem counter fails */
			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
									res);

		if (!(gfp_mask & __GFP_WAIT))
			goto nomem;

		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
							noswap);

		/*
		 * try_to_free_mem_cgroup_pages() might not give us a full
		 * picture of reclaim. Some pages are reclaimed and might be
		 * moved to swap cache or just unmapped from the cgroup.
		 * Check the limit again to see if the reclaim reduced the
		 * current usage of the cgroup before giving up
		 *
		 */
		if (mem_cgroup_check_under_limit(mem_over_limit))
			continue;

		if (!nr_retries--) {
			if (oom) {
				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
				mem_over_limit->last_oom_jiffies = jiffies;
			}
			goto nomem;
		}
	}
	return 0;
nomem:
	css_put(&mem->css);
	return -ENOMEM;
}

/**
 * mem_cgroup_try_charge - get charge of PAGE_SIZE.
 * @mm: an mm_struct which is charged against. (when *memcg is NULL)
 * @gfp_mask: gfp_mask for reclaim.
 * @memcg: a pointer to memory cgroup which is charged against.
 *
 * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated
 * memory cgroup from @mm is got and stored in *memcg.
 *
 * Returns 0 if success. -ENOMEM at failure.
 * This call can invoke OOM-Killer.
 */

int mem_cgroup_try_charge(struct mm_struct *mm,
			  gfp_t mask, struct mem_cgroup **memcg)
{
	return __mem_cgroup_try_charge(mm, mask, memcg, true);
}

/*
 * commit a charge got by mem_cgroup_try_charge() and makes page_cgroup to be
 * USED state. If already USED, uncharge and return.
 */

static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
				     struct page_cgroup *pc,
				     enum charge_type ctype)
{
	/* try_charge() can return NULL to *memcg, taking care of it. */
	if (!mem)
		return;

	lock_page_cgroup(pc);
	if (unlikely(PageCgroupUsed(pc))) {
		unlock_page_cgroup(pc);
		res_counter_uncharge(&mem->res, PAGE_SIZE);
		if (do_swap_account)
			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
		css_put(&mem->css);
		return;
	}
	pc->mem_cgroup = mem;
	smp_wmb();
	pc->flags = pcg_default_flags[ctype];

	mem_cgroup_charge_statistics(mem, pc, true);

	unlock_page_cgroup(pc);
}

/**
 * mem_cgroup_move_account - move account of the page
 * @pc:	page_cgroup of the page.
 * @from: mem_cgroup which the page is moved from.
 * @to:	mem_cgroup which the page is moved to. @from != @to.
 *
 * The caller must confirm following.
 * - page is not on LRU (isolate_page() is useful.)
 *
 * returns 0 at success,
 * returns -EBUSY when lock is busy or "pc" is unstable.
 *
 * This function does "uncharge" from old cgroup but doesn't do "charge" to
 * new cgroup. It should be done by a caller.
 */

static int mem_cgroup_move_account(struct page_cgroup *pc,
	struct mem_cgroup *from, struct mem_cgroup *to)
{
	struct mem_cgroup_per_zone *from_mz, *to_mz;
	int nid, zid;
	int ret = -EBUSY;

	VM_BUG_ON(from == to);
	VM_BUG_ON(PageLRU(pc->page));

	nid = page_cgroup_nid(pc);
	zid = page_cgroup_zid(pc);
	from_mz =  mem_cgroup_zoneinfo(from, nid, zid);
	to_mz =  mem_cgroup_zoneinfo(to, nid, zid);

	if (!trylock_page_cgroup(pc))
		return ret;

	if (!PageCgroupUsed(pc))
		goto out;

	if (pc->mem_cgroup != from)
		goto out;

	css_put(&from->css);
	res_counter_uncharge(&from->res, PAGE_SIZE);
	mem_cgroup_charge_statistics(from, pc, false);
	if (do_swap_account)
		res_counter_uncharge(&from->memsw, PAGE_SIZE);
	pc->mem_cgroup = to;
	mem_cgroup_charge_statistics(to, pc, true);
	css_get(&to->css);
	ret = 0;
out:
	unlock_page_cgroup(pc);
	return ret;
}

/*
 * move charges to its parent.
 */

static int mem_cgroup_move_parent(struct page_cgroup *pc,
				  struct mem_cgroup *child,
				  gfp_t gfp_mask)
{
	struct page *page = pc->page;
	struct cgroup *cg = child->css.cgroup;
	struct cgroup *pcg = cg->parent;
	struct mem_cgroup *parent;
	int ret;

	/* Is ROOT ? */
	if (!pcg)
		return -EINVAL;


	parent = mem_cgroup_from_cont(pcg);


	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
	if (ret || !parent)
		return ret;

	if (!get_page_unless_zero(page))
		return -EBUSY;

	ret = isolate_lru_page(page);

	if (ret)
		goto cancel;

	ret = mem_cgroup_move_account(pc, child, parent);

	/* drop extra refcnt by try_charge() (move_account increment one) */
	css_put(&parent->css);
	putback_lru_page(page);
	if (!ret) {
		put_page(page);
		return 0;
	}
	/* uncharge if move fails */
cancel:
	res_counter_uncharge(&parent->res, PAGE_SIZE);
	if (do_swap_account)
		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
	put_page(page);
	return ret;
}

/*
 * Charge the memory controller for page usage.
 * Return
 * 0 if the charge was successful
 * < 0 if the cgroup is over its limit
 */
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
				gfp_t gfp_mask, enum charge_type ctype,
				struct mem_cgroup *memcg)
{
	struct mem_cgroup *mem;
	struct page_cgroup *pc;
	int ret;

	pc = lookup_page_cgroup(page);
	/* can happen at boot */
	if (unlikely(!pc))
		return 0;
	prefetchw(pc);

	mem = memcg;
	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
	if (ret || !mem)
		return ret;

	__mem_cgroup_commit_charge(mem, pc, ctype);
	return 0;
}

int mem_cgroup_newpage_charge(struct page *page,
			      struct mm_struct *mm, gfp_t gfp_mask)
{
	if (mem_cgroup_disabled())
		return 0;
	if (PageCompound(page))
		return 0;
	/*
	 * If already mapped, we don't have to account.
	 * If page cache, page->mapping has address_space.
	 * But page->mapping may have out-of-use anon_vma pointer,
	 * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
	 * is NULL.
  	 */
	if (page_mapped(page) || (page->mapping && !PageAnon(page)))
		return 0;
	if (unlikely(!mm))
		mm = &init_mm;
	return mem_cgroup_charge_common(page, mm, gfp_mask,
				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);