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>
 *
 * Memory thresholds
 * Copyright (C) 2009 Nokia Corporation
 * Author: Kirill A. Shutemov
 *
 * Kernel Memory Controller
 * Copyright (C) 2012 Parallels Inc. and Google Inc.
 * Authors: Glauber Costa and Suleiman Souhlal
 *
 * 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/hugetlb.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/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/sort.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmpressure.h>
#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/file.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include <net/tcp_memcontrol.h>
#include "slab.h"

#include <asm/uaccess.h>

#include <trace/events/vmscan.h>

struct cgroup_subsys mem_cgroup_subsys __read_mostly;
EXPORT_SYMBOL(mem_cgroup_subsys);

#define MEM_CGROUP_RECLAIM_RETRIES	5
static struct mem_cgroup *root_mem_cgroup __read_mostly;

#ifdef CONFIG_MEMCG_SWAP
/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
int do_swap_account __read_mostly;

/* for remember boot option*/
#ifdef CONFIG_MEMCG_SWAP_ENABLED
static int really_do_swap_account __initdata = 1;
#else
static int really_do_swap_account __initdata = 0;
#endif

#else
#define do_swap_account		0
#endif


static const char * const mem_cgroup_stat_names[] = {
	"cache",
	"rss",
	"rss_huge",
	"mapped_file",
	"writeback",
	"swap",
};

enum mem_cgroup_events_index {
	MEM_CGROUP_EVENTS_PGPGIN,	/* # of pages paged in */
	MEM_CGROUP_EVENTS_PGPGOUT,	/* # of pages paged out */
	MEM_CGROUP_EVENTS_PGFAULT,	/* # of page-faults */
	MEM_CGROUP_EVENTS_PGMAJFAULT,	/* # of major page-faults */
	MEM_CGROUP_EVENTS_NSTATS,
};

static const char * const mem_cgroup_events_names[] = {
	"pgpgin",
	"pgpgout",
	"pgfault",
	"pgmajfault",
};

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

/*
 * Per memcg event counter is incremented at every pagein/pageout. With THP,
 * it will be incremated by the number of pages. This counter is used for
 * for trigger some periodic events. This is straightforward and better
 * than using jiffies etc. to handle periodic memcg event.
 */
enum mem_cgroup_events_target {
	MEM_CGROUP_TARGET_THRESH,
	MEM_CGROUP_TARGET_SOFTLIMIT,
	MEM_CGROUP_TARGET_NUMAINFO,
	MEM_CGROUP_NTARGETS,
};
#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
#define NUMAINFO_EVENTS_TARGET	1024

struct mem_cgroup_stat_cpu {
	long count[MEM_CGROUP_STAT_NSTATS];
	unsigned long events[MEM_CGROUP_EVENTS_NSTATS];
	unsigned long nr_page_events;
	unsigned long targets[MEM_CGROUP_NTARGETS];
};

struct mem_cgroup_reclaim_iter {
	/*
	 * last scanned hierarchy member. Valid only if last_dead_count
	 * matches memcg->dead_count of the hierarchy root group.
	 */
	struct mem_cgroup *last_visited;
	int last_dead_count;

	/* scan generation, increased every round-trip */
	unsigned int generation;
};

/*
 * per-zone information in memory controller.
 */
struct mem_cgroup_per_zone {
	struct lruvec		lruvec;
	unsigned long		lru_size[NR_LRU_LISTS];

	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];

	struct rb_node		tree_node;	/* RB tree node */
	unsigned long long	usage_in_excess;/* Set to the value by which */
						/* the soft limit is exceeded*/
	bool			on_tree;
	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
						/* use container_of	   */
};

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

/*
 * Cgroups above their limits are maintained in a RB-Tree, independent of
 * their hierarchy representation
 */

struct mem_cgroup_tree_per_zone {
	struct rb_root rb_root;
	spinlock_t lock;
};

struct mem_cgroup_tree_per_node {
	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
};

struct mem_cgroup_tree {
	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
};

static struct mem_cgroup_tree soft_limit_tree __read_mostly;

struct mem_cgroup_threshold {
	struct eventfd_ctx *eventfd;
	u64 threshold;
};

/* For threshold */
struct mem_cgroup_threshold_ary {
	/* An array index points to threshold just below or equal to usage. */
	int current_threshold;
	/* Size of entries[] */
	unsigned int size;
	/* Array of thresholds */
	struct mem_cgroup_threshold entries[0];
};

struct mem_cgroup_thresholds {
	/* Primary thresholds array */
	struct mem_cgroup_threshold_ary *primary;
	/*
	 * Spare threshold array.
	 * This is needed to make mem_cgroup_unregister_event() "never fail".
	 * It must be able to store at least primary->size - 1 entries.
	 */
	struct mem_cgroup_threshold_ary *spare;
};

/* for OOM */
struct mem_cgroup_eventfd_list {
	struct list_head list;
	struct eventfd_ctx *eventfd;
};

/*
 * cgroup_event represents events which userspace want to receive.
 */
struct mem_cgroup_event {
	/*
	 * memcg which the event belongs to.
	 */
	struct mem_cgroup *memcg;
	/*
	 * eventfd to signal userspace about the event.
	 */
	struct eventfd_ctx *eventfd;
	/*
	 * Each of these stored in a list by the cgroup.
	 */
	struct list_head list;
	/*
	 * register_event() callback will be used to add new userspace
	 * waiter for changes related to this event.  Use eventfd_signal()
	 * on eventfd to send notification to userspace.
	 */
	int (*register_event)(struct mem_cgroup *memcg,
			      struct eventfd_ctx *eventfd, const char *args);
	/*
	 * unregister_event() callback will be called when userspace closes
	 * the eventfd or on cgroup removing.  This callback must be set,
	 * if you want provide notification functionality.
	 */
	void (*unregister_event)(struct mem_cgroup *memcg,
				 struct eventfd_ctx *eventfd);
	/*
	 * All fields below needed to unregister event when
	 * userspace closes eventfd.
	 */
	poll_table pt;
	wait_queue_head_t *wqh;
	wait_queue_t wait;
	struct work_struct remove;
};

static void mem_cgroup_threshold(struct mem_cgroup *memcg);
static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);

/*
 * 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;

	/* vmpressure notifications */
	struct vmpressure vmpressure;

	/*
	 * the counter to account for mem+swap usage.
	 */
	struct res_counter memsw;

	/*
	 * the counter to account for kernel memory usage.
	 */
	struct res_counter kmem;
	/*
	 * Should the accounting and control be hierarchical, per subtree?
	 */
	bool use_hierarchy;
	unsigned long kmem_account_flags; /* See KMEM_ACCOUNTED_*, below */

	bool		oom_lock;
	atomic_t	under_oom;
	atomic_t	oom_wakeups;

	int	swappiness;
	/* OOM-Killer disable */
	int		oom_kill_disable;

	/* set when res.limit == memsw.limit */
	bool		memsw_is_minimum;

	/* protect arrays of thresholds */
	struct mutex thresholds_lock;

	/* thresholds for memory usage. RCU-protected */
	struct mem_cgroup_thresholds thresholds;

	/* thresholds for mem+swap usage. RCU-protected */
	struct mem_cgroup_thresholds memsw_thresholds;

	/* For oom notifier event fd */
	struct list_head oom_notify;

	/*
	 * Should we move charges of a task when a task is moved into this
	 * mem_cgroup ? And what type of charges should we move ?
	 */
	unsigned long move_charge_at_immigrate;
	/*
	 * set > 0 if pages under this cgroup are moving to other cgroup.
	 */
	atomic_t	moving_account;
	/* taken only while moving_account > 0 */
	spinlock_t	move_lock;
	/*
	 * percpu counter.
	 */
	struct mem_cgroup_stat_cpu __percpu *stat;
	/*
	 * used when a cpu is offlined or other synchronizations
	 * See mem_cgroup_read_stat().
	 */
	struct mem_cgroup_stat_cpu nocpu_base;
	spinlock_t pcp_counter_lock;

	atomic_t	dead_count;
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
	struct cg_proto tcp_mem;
#endif
#if defined(CONFIG_MEMCG_KMEM)
	/* analogous to slab_common's slab_caches list. per-memcg */
	struct list_head memcg_slab_caches;
	/* Not a spinlock, we can take a lot of time walking the list */
	struct mutex slab_caches_mutex;
        /* Index in the kmem_cache->memcg_params->memcg_caches array */
	int kmemcg_id;
#endif

	int last_scanned_node;
#if MAX_NUMNODES > 1
	nodemask_t	scan_nodes;
	atomic_t	numainfo_events;
	atomic_t	numainfo_updating;
#endif

	/* List of events which userspace want to receive */
	struct list_head event_list;
	spinlock_t event_list_lock;

	struct mem_cgroup_per_node *nodeinfo[0];
	/* WARNING: nodeinfo must be the last member here */
};

/* internal only representation about the status of kmem accounting. */
enum {
	KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */
	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
};

#ifdef CONFIG_MEMCG_KMEM
static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
{
	set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}

static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}

static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
{
	/*
	 * Our caller must use css_get() first, because memcg_uncharge_kmem()
	 * will call css_put() if it sees the memcg is dead.
	 */
	smp_wmb();
	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
}

static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
{
	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
				  &memcg->kmem_account_flags);
}
#endif

/* Stuffs for move charges at task migration. */
/*
 * Types of charges to be moved. "move_charge_at_immitgrate" and
 * "immigrate_flags" are treated as a left-shifted bitmap of these types.
 */
enum move_type {
	MOVE_CHARGE_TYPE_ANON,	/* private anonymous page and swap of it */
	MOVE_CHARGE_TYPE_FILE,	/* file page(including tmpfs) and swap of it */
	NR_MOVE_TYPE,
};

/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
	spinlock_t	  lock; /* for from, to */
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	unsigned long immigrate_flags;
	unsigned long precharge;
	unsigned long moved_charge;
	unsigned long moved_swap;
	struct task_struct *moving_task;	/* a task moving charges */
	wait_queue_head_t waitq;		/* a waitq for other context */
} mc = {
	.lock = __SPIN_LOCK_UNLOCKED(mc.lock),
	.waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
};

static bool move_anon(void)
{
	return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags);
}

static bool move_file(void)
{
	return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags);
}

/*
 * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
 * limit reclaim to prevent infinite loops, if they ever occur.
 */
#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_ANON,
	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
	NR_CHARGE_TYPE,
};

/* for encoding cft->private value on file */
enum res_type {
	_MEM,
	_MEMSWAP,
	_OOM_TYPE,
	_KMEM,
};

#define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
#define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)
/* Used for OOM nofiier */
#define OOM_CONTROL		(0)

/*
 * Reclaim flags for mem_cgroup_hierarchical_reclaim
 */
#define MEM_CGROUP_RECLAIM_NOSWAP_BIT	0x0
#define MEM_CGROUP_RECLAIM_NOSWAP	(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
#define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
#define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)

/*
 * The memcg_create_mutex will be held whenever a new cgroup is created.
 * As a consequence, any change that needs to protect against new child cgroups
 * appearing has to hold it as well.
 */
static DEFINE_MUTEX(memcg_create_mutex);

struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
{
	return s ? container_of(s, struct mem_cgroup, css) : NULL;
}

/* Some nice accessors for the vmpressure. */
struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
{
	if (!memcg)
		memcg = root_mem_cgroup;
	return &memcg->vmpressure;
}

struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
{
	return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
}

static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
	return (memcg == root_mem_cgroup);
}

/*
 * We restrict the id in the range of [1, 65535], so it can fit into
 * an unsigned short.
 */
#define MEM_CGROUP_ID_MAX	USHRT_MAX

static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
	/*
	 * The ID of the root cgroup is 0, but memcg treat 0 as an
	 * invalid ID, so we return (cgroup_id + 1).
	 */
	return memcg->css.cgroup->id + 1;
}

static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
	struct cgroup_subsys_state *css;

	css = css_from_id(id - 1, &mem_cgroup_subsys);
	return mem_cgroup_from_css(css);
}

/* Writing them here to avoid exposing memcg's inner layout */
#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)

void sock_update_memcg(struct sock *sk)
{
	if (mem_cgroup_sockets_enabled) {
		struct mem_cgroup *memcg;
		struct cg_proto *cg_proto;

		BUG_ON(!sk->sk_prot->proto_cgroup);

		/* Socket cloning can throw us here with sk_cgrp already
		 * filled. It won't however, necessarily happen from
		 * process context. So the test for root memcg given
		 * the current task's memcg won't help us in this case.
		 *
		 * Respecting the original socket's memcg is a better
		 * decision in this case.
		 */
		if (sk->sk_cgrp) {
			BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg));
			css_get(&sk->sk_cgrp->memcg->css);
			return;
		}

		rcu_read_lock();
		memcg = mem_cgroup_from_task(current);
		cg_proto = sk->sk_prot->proto_cgroup(memcg);
		if (!mem_cgroup_is_root(memcg) &&
		    memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) {
			sk->sk_cgrp = cg_proto;
		}
		rcu_read_unlock();
	}
}
EXPORT_SYMBOL(sock_update_memcg);

void sock_release_memcg(struct sock *sk)
{
	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct mem_cgroup *memcg;
		WARN_ON(!sk->sk_cgrp->memcg);
		memcg = sk->sk_cgrp->memcg;
		css_put(&sk->sk_cgrp->memcg->css);
	}
}

struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
{
	if (!memcg || mem_cgroup_is_root(memcg))
		return NULL;

	return &memcg->tcp_mem;
}
EXPORT_SYMBOL(tcp_proto_cgroup);

static void disarm_sock_keys(struct mem_cgroup *memcg)
{
	if (!memcg_proto_activated(&memcg->tcp_mem))
		return;
	static_key_slow_dec(&memcg_socket_limit_enabled);
}
#else
static void disarm_sock_keys(struct mem_cgroup *memcg)
{
}
#endif

#ifdef CONFIG_MEMCG_KMEM
/*
 * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
 * The main reason for not using cgroup id for this:
 *  this works better in sparse environments, where we have a lot of memcgs,
 *  but only a few kmem-limited. Or also, if we have, for instance, 200
 *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
 *  200 entry array for that.
 *
 * The current size of the caches array is stored in
 * memcg_limited_groups_array_size.  It will double each time we have to
 * increase it.
 */
static DEFINE_IDA(kmem_limited_groups);
int memcg_limited_groups_array_size;

/*
 * MIN_SIZE is different than 1, because we would like to avoid going through
 * the alloc/free process all the time. In a small machine, 4 kmem-limited
 * cgroups is a reasonable guess. In the future, it could be a parameter or
 * tunable, but that is strictly not necessary.
 *
 * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
 * this constant directly from cgroup, but it is understandable that this is
 * better kept as an internal representation in cgroup.c. In any case, the
 * cgrp_id space is not getting any smaller, and we don't have to necessarily
 * increase ours as well if it increases.
 */
#define MEMCG_CACHES_MIN_SIZE 4
#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX

/*
 * A lot of the calls to the cache allocation functions are expected to be
 * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
 * conditional to this static branch, we'll have to allow modules that does
 * kmem_cache_alloc and the such to see this symbol as well
 */
struct static_key memcg_kmem_enabled_key;
EXPORT_SYMBOL(memcg_kmem_enabled_key);

static void disarm_kmem_keys(struct mem_cgroup *memcg)
{
	if (memcg_kmem_is_active(memcg)) {
		static_key_slow_dec(&memcg_kmem_enabled_key);
		ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
	}
	/*
	 * This check can't live in kmem destruction function,
	 * since the charges will outlive the cgroup
	 */
	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
}
#else
static void disarm_kmem_keys(struct mem_cgroup *memcg)
{
}
#endif /* CONFIG_MEMCG_KMEM */

static void disarm_static_keys(struct mem_cgroup *memcg)
{
	disarm_sock_keys(memcg);
	disarm_kmem_keys(memcg);
}

static void drain_all_stock_async(struct mem_cgroup *memcg);

static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
{
	VM_BUG_ON((unsigned)nid >= nr_node_ids);
	return &memcg->nodeinfo[nid]->zoneinfo[zid];
}

struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
{
	return &memcg->css;
}

static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
{
	int nid = page_to_nid(page);
	int zid = page_zonenum(page);

	return mem_cgroup_zoneinfo(memcg, nid, zid);
}

static struct mem_cgroup_tree_per_zone *
soft_limit_tree_node_zone(int nid, int zid)
{
	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
}

static struct mem_cgroup_tree_per_zone *
soft_limit_tree_from_page(struct page *page)
{
	int nid = page_to_nid(page);
	int zid = page_zonenum(page);

	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
}

static void
__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
				struct mem_cgroup_per_zone *mz,
				struct mem_cgroup_tree_per_zone *mctz,
				unsigned long long new_usage_in_excess)
{
	struct rb_node **p = &mctz->rb_root.rb_node;
	struct rb_node *parent = NULL;
	struct mem_cgroup_per_zone *mz_node;

	if (mz->on_tree)
		return;

	mz->usage_in_excess = new_usage_in_excess;
	if (!mz->usage_in_excess)
		return;
	while (*p) {
		parent = *p;
		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
					tree_node);
		if (mz->usage_in_excess < mz_node->usage_in_excess)
			p = &(*p)->rb_left;
		/*
		 * We can't avoid mem cgroups that are over their soft
		 * limit by the same amount
		 */
		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
			p = &(*p)->rb_right;
	}
	rb_link_node(&mz->tree_node, parent, p);
	rb_insert_color(&mz->tree_node, &mctz->rb_root);
	mz->on_tree = true;
}

static void
__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
				struct mem_cgroup_per_zone *mz,
				struct mem_cgroup_tree_per_zone *mctz)
{
	if (!mz->on_tree)
		return;
	rb_erase(&mz->tree_node, &mctz->rb_root);
	mz->on_tree = false;
}

static void
mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
				struct mem_cgroup_per_zone *mz,
				struct mem_cgroup_tree_per_zone *mctz)
{
	spin_lock(&mctz->lock);
	__mem_cgroup_remove_exceeded(memcg, mz, mctz);
	spin_unlock(&mctz->lock);
}


static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
{
	unsigned long long excess;
	struct mem_cgroup_per_zone *mz;
	struct mem_cgroup_tree_per_zone *mctz;
	int nid = page_to_nid(page);
	int zid = page_zonenum(page);
	mctz = soft_limit_tree_from_page(page);

	/*
	 * Necessary to update all ancestors when hierarchy is used.
	 * because their event counter is not touched.
	 */
	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
		mz = mem_cgroup_zoneinfo(memcg, nid, zid);
		excess = res_counter_soft_limit_excess(&memcg->res);
		/*
		 * We have to update the tree if mz is on RB-tree or
		 * mem is over its softlimit.
		 */
		if (excess || mz->on_tree) {
			spin_lock(&mctz->lock);
			/* if on-tree, remove it */
			if (mz->on_tree)
				__mem_cgroup_remove_exceeded(memcg, mz, mctz);
			/*
			 * Insert again. mz->usage_in_excess will be updated.
			 * If excess is 0, no tree ops.
			 */
			__mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
			spin_unlock(&mctz->lock);
		}
	}
}

static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
	int node, zone;
	struct mem_cgroup_per_zone *mz;
	struct mem_cgroup_tree_per_zone *mctz;

	for_each_node(node) {
		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
			mz = mem_cgroup_zoneinfo(memcg, node, zone);
			mctz = soft_limit_tree_node_zone(node, zone);
			mem_cgroup_remove_exceeded(memcg, mz, mctz);
		}
	}
}

static struct mem_cgroup_per_zone *
__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
{
	struct rb_node *rightmost = NULL;
	struct mem_cgroup_per_zone *mz;

retry:
	mz = NULL;
	rightmost = rb_last(&mctz->rb_root);
	if (!rightmost)
		goto done;		/* Nothing to reclaim from */

	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
	/*
	 * Remove the node now but someone else can add it back,
	 * we will to add it back at the end of reclaim to its correct
	 * position in the tree.
	 */
	__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
		!css_tryget(&mz->memcg->css))
		goto retry;
done:
	return mz;
}

static struct mem_cgroup_per_zone *
mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
{
	struct mem_cgroup_per_zone *mz;

	spin_lock(&mctz->lock);
	mz = __mem_cgroup_largest_soft_limit_node(mctz);
	spin_unlock(&mctz->lock);
	return mz;
}

/*
 * Implementation Note: reading percpu statistics for memcg.
 *
 * Both of vmstat[] and percpu_counter has threshold and do periodic
 * synchronization to implement "quick" read. There are trade-off between
 * reading cost and precision of value. Then, we may have a chance to implement
 * a periodic synchronizion of counter in memcg's counter.
 *
 * But this _read() function is used for user interface now. The user accounts
 * memory usage by memory cgroup and he _always_ requires exact value because
 * he accounts memory. Even if we provide quick-and-fuzzy read, we always
 * have to visit all online cpus and make sum. So, for now, unnecessary
 * synchronization is not implemented. (just implemented for cpu hotplug)
 *
 * If there are kernel internal actions which can make use of some not-exact
 * value, and reading all cpu value can be performance bottleneck in some
 * common workload, threashold and synchonization as vmstat[] should be
 * implemented.
 */
static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
				 enum mem_cgroup_stat_index idx)
{
	long val = 0;
	int cpu;

	get_online_cpus();
	for_each_online_cpu(cpu)
		val += per_cpu(memcg->stat->count[idx], cpu);
#ifdef CONFIG_HOTPLUG_CPU
	spin_lock(&memcg->pcp_counter_lock);
	val += memcg->nocpu_base.count[idx];
	spin_unlock(&memcg->pcp_counter_lock);
#endif
	put_online_cpus();
	return val;
}

static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
					 bool charge)
{
	int val = (charge) ? 1 : -1;
	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
}

static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
					    enum mem_cgroup_events_index idx)
{
	unsigned long val = 0;
	int cpu;

	get_online_cpus();
	for_each_online_cpu(cpu)
		val += per_cpu(memcg->stat->events[idx], cpu);
#ifdef CONFIG_HOTPLUG_CPU
	spin_lock(&memcg->pcp_counter_lock);
	val += memcg->nocpu_base.events[idx];
	spin_unlock(&memcg->pcp_counter_lock);
#endif
	put_online_cpus();
	return val;
}

static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
					 struct page *page,
					 bool anon, int nr_pages)
{
	preempt_disable();

	/*
	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
	 * counted as CACHE even if it's on ANON LRU.
	 */
	if (anon)
		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
				nr_pages);
	else
		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
				nr_pages);

	if (PageTransHuge(page))
		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
				nr_pages);

	/* pagein of a big page is an event. So, ignore page size */
	if (nr_pages > 0)
		__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
	else {
		__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
		nr_pages = -nr_pages; /* for event */
	}

	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);

	preempt_enable();
}

unsigned long
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
	struct mem_cgroup_per_zone *mz;

	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
	return mz->lru_size[lru];
}

static unsigned long
mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
			unsigned int lru_mask)
{
	struct mem_cgroup_per_zone *mz;
	enum lru_list lru;
	unsigned long ret = 0;

	mz = mem_cgroup_zoneinfo(memcg, nid, zid);

	for_each_lru(lru) {
		if (BIT(lru) & lru_mask)
			ret += mz->lru_size[lru];
	}
	return ret;
}

static unsigned long
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
			int nid, unsigned int lru_mask)
{
	u64 total = 0;
	int zid;

	for (zid = 0; zid < MAX_NR_ZONES; zid++)
		total += mem_cgroup_zone_nr_lru_pages(memcg,
						nid, zid, lru_mask);

	return total;
}

static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
			unsigned int lru_mask)
{
	int nid;
	u64 total = 0;

	for_each_node_state(nid, N_MEMORY)