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
 *
 * 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/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/sort.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 <linux/cpu.h>
#include <linux/oom.h>
#include "internal.h"

#include <asm/uaccess.h>

#include <trace/events/vmscan.h>

struct cgroup_subsys mem_cgroup_subsys __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES	5
struct mem_cgroup *root_mem_cgroup __read_mostly;

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_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_CGROUP_MEM_RES_CTLR_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

/*
 * Per memcg event counter is incremented at every pagein/pageout. This counter
 * is used for trigger some periodic events. This is straightforward and better
 * than using jiffies etc. to handle periodic memcg event.
 *
 * These values will be used as !((event) & ((1 <<(thresh)) - 1))
 */
#define THRESHOLDS_EVENTS_THRESH (7) /* once in 128 */
#define SOFTLIMIT_EVENTS_THRESH (10) /* once in 1024 */

/*
 * 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 anon rss */
	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
	MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
	/* incremented at every  pagein/pageout */
	MEM_CGROUP_EVENTS = MEM_CGROUP_STAT_DATA,
	MEM_CGROUP_ON_MOVE,	/* someone is moving account between groups */

	MEM_CGROUP_STAT_NSTATS,
};

struct mem_cgroup_stat_cpu {
	s64 count[MEM_CGROUP_STAT_NSTATS];
};

/*
 * 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;
	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	*mem;		/* Back pointer, we cannot */
						/* use container_of	   */
};
/* 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];
};

/*
 * 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 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;
};

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

/*
 * 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;

	/*
	 * While reclaiming in a hierarchy, we cache the last child we
	 * reclaimed from.
	 */
	int last_scanned_child;
	/*
	 * Should the accounting and control be hierarchical, per subtree?
	 */
	bool use_hierarchy;
	atomic_t	oom_lock;
	atomic_t	refcnt;

	unsigned 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;
	/*
	 * percpu counter.
	 */
	struct mem_cgroup_stat_cpu *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;
};

/* Stuffs for move charges at task migration. */
/*
 * Types of charges to be moved. "move_charge_at_immitgrate" is 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 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.to->move_charge_at_immigrate);
}

static bool move_file(void)
{
	return test_bit(MOVE_CHARGE_TYPE_FILE,
					&mc.to->move_charge_at_immigrate);
}

/*
 * 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_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 */
	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
	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)
/* Not used, but added here for completeness */
#define PCGF_ACCT	(1UL << PCG_ACCT)

/* for encoding cft->private value on file */
#define _MEM			(0)
#define _MEMSWAP		(1)
#define _OOM_TYPE		(2)
#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)
#define MEM_CGROUP_RECLAIM_SOFT_BIT	0x2
#define MEM_CGROUP_RECLAIM_SOFT		(1 << MEM_CGROUP_RECLAIM_SOFT_BIT)

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

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

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

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 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 *mem,
				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 *mem,
				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 *mem,
				struct mem_cgroup_per_zone *mz,
				struct mem_cgroup_tree_per_zone *mctz)
{
	spin_lock(&mctz->lock);
	__mem_cgroup_remove_exceeded(mem, mz, mctz);
	spin_unlock(&mctz->lock);
}


static void mem_cgroup_update_tree(struct mem_cgroup *mem, 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 (; mem; mem = parent_mem_cgroup(mem)) {
		mz = mem_cgroup_zoneinfo(mem, nid, zid);
		excess = res_counter_soft_limit_excess(&mem->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(mem, mz, mctz);
			/*
			 * Insert again. mz->usage_in_excess will be updated.
			 * If excess is 0, no tree ops.
			 */
			__mem_cgroup_insert_exceeded(mem, mz, mctz, excess);
			spin_unlock(&mctz->lock);
		}
	}
}

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

	for_each_node_state(node, N_POSSIBLE) {
		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
			mz = mem_cgroup_zoneinfo(mem, node, zone);
			mctz = soft_limit_tree_node_zone(node, zone);
			mem_cgroup_remove_exceeded(mem, mz, mctz);
		}
	}
}

static inline unsigned long mem_cgroup_get_excess(struct mem_cgroup *mem)
{
	return res_counter_soft_limit_excess(&mem->res) >> PAGE_SHIFT;
}

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->mem, mz, mctz);
	if (!res_counter_soft_limit_excess(&mz->mem->res) ||
		!css_tryget(&mz->mem->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 s64 mem_cgroup_read_stat(struct mem_cgroup *mem,
		enum mem_cgroup_stat_index idx)
{
	int cpu;
	s64 val = 0;

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

static s64 mem_cgroup_local_usage(struct mem_cgroup *mem)
{
	s64 ret;

	ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
	ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
	return ret;
}

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

static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
					 bool file, int nr_pages)
{
	preempt_disable();

	if (file)
		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages);
	else
		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages);

	/* pagein of a big page is an event. So, ignore page size */
	if (nr_pages > 0)
		__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]);
	else
		__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]);

	__this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages);

	preempt_enable();
}

static unsigned long mem_cgroup_get_local_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 bool __memcg_event_check(struct mem_cgroup *mem, int event_mask_shift)
{
	s64 val;

	val = this_cpu_read(mem->stat->count[MEM_CGROUP_EVENTS]);

	return !(val & ((1 << event_mask_shift) - 1));
}

/*
 * Check events in order.
 *
 */
static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
{
	/* threshold event is triggered in finer grain than soft limit */
	if (unlikely(__memcg_event_check(mem, THRESHOLDS_EVENTS_THRESH))) {
		mem_cgroup_threshold(mem);
		if (unlikely(__memcg_event_check(mem, SOFTLIMIT_EVENTS_THRESH)))
			mem_cgroup_update_tree(mem, page);
	}
}

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);
}

static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
	struct mem_cgroup *mem = NULL;

	if (!mm)
		return NULL;
	/*
	 * Because we have no locks, mm->owner's may be being moved to other
	 * cgroup. We use css_tryget() here even if this looks
	 * pessimistic (rather than adding locks here).
	 */
	rcu_read_lock();
	do {
		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!mem))
			break;
	} while (!css_tryget(&mem->css));
	rcu_read_unlock();
	return mem;
}

/* The caller has to guarantee "mem" exists before calling this */
static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem)
{
	struct cgroup_subsys_state *css;
	int found;

	if (!mem) /* ROOT cgroup has the smallest ID */
		return root_mem_cgroup; /*css_put/get against root is ignored*/
	if (!mem->use_hierarchy) {
		if (css_tryget(&mem->css))
			return mem;
		return NULL;
	}
	rcu_read_lock();
	/*
	 * searching a memory cgroup which has the smallest ID under given
	 * ROOT cgroup. (ID >= 1)
	 */
	css = css_get_next(&mem_cgroup_subsys, 1, &mem->css, &found);
	if (css && css_tryget(css))
		mem = container_of(css, struct mem_cgroup, css);
	else
		mem = NULL;
	rcu_read_unlock();
	return mem;
}

static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter,
					struct mem_cgroup *root,
					bool cond)
{
	int nextid = css_id(&iter->css) + 1;
	int found;
	int hierarchy_used;
	struct cgroup_subsys_state *css;

	hierarchy_used = iter->use_hierarchy;

	css_put(&iter->css);
	/* If no ROOT, walk all, ignore hierarchy */
	if (!cond || (root && !hierarchy_used))
		return NULL;

	if (!root)
		root = root_mem_cgroup;

	do {
		iter = NULL;
		rcu_read_lock();

		css = css_get_next(&mem_cgroup_subsys, nextid,
				&root->css, &found);
		if (css && css_tryget(css))
			iter = container_of(css, struct mem_cgroup, css);
		rcu_read_unlock();
		/* If css is NULL, no more cgroups will be found */
		nextid = found + 1;
	} while (css && !iter);

	return iter;
}
/*
 * for_eacn_mem_cgroup_tree() for visiting all cgroup under tree. Please
 * be careful that "break" loop is not allowed. We have reference count.
 * Instead of that modify "cond" to be false and "continue" to exit the loop.
 */
#define for_each_mem_cgroup_tree_cond(iter, root, cond)	\
	for (iter = mem_cgroup_start_loop(root);\
	     iter != NULL;\
	     iter = mem_cgroup_get_next(iter, root, cond))

#define for_each_mem_cgroup_tree(iter, root) \
	for_each_mem_cgroup_tree_cond(iter, root, true)

#define for_each_mem_cgroup_all(iter) \
	for_each_mem_cgroup_tree_cond(iter, NULL, true)


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

/*
 * 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_per_zone *mz;

	if (mem_cgroup_disabled())
		return;
	pc = lookup_page_cgroup(page);
	/* can happen while we handle swapcache. */
	if (!TestClearPageCgroupAcctLRU(pc))
		return;
	VM_BUG_ON(!pc->mem_cgroup);
	/*
	 * We don't check PCG_USED bit. It's cleared when the "page" is finally
	 * removed from global LRU.
	 */
	mz = page_cgroup_zoneinfo(pc);
	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
	if (mem_cgroup_is_root(pc->mem_cgroup))
		return;
	VM_BUG_ON(list_empty(&pc->lru));
	list_del_init(&pc->lru);
}

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);
	/*
	 * Used bit is set without atomic ops but after smp_wmb().
	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
	 */
	smp_rmb();
	/* unused or root page is not rotated. */
	if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup))
		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);
	VM_BUG_ON(PageCgroupAcctLRU(pc));
	/*
	 * Used bit is set without atomic ops but after smp_wmb().
	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
	 */
	smp_rmb();
	if (!PageCgroupUsed(pc))
		return;

	mz = page_cgroup_zoneinfo(pc);
	MEM_CGROUP_ZSTAT(mz, lru) += 1;
	SetPageCgroupAcctLRU(pc);
	if (mem_cgroup_is_root(pc->mem_cgroup))
		return;
	list_add(&pc->lru, &mz->lists[lru]);
}

/*
 * At handling SwapCache, pc->mem_cgroup may be changed while it's linked to
 * lru because the page may.be reused after it's fully uncharged (because of
 * SwapCache behavior).To handle that, unlink page_cgroup from LRU when charge
 * it again. This function is only used to charge SwapCache. It's done under
 * lock_page and expected that zone->lru_lock is never held.
 */
static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
{
	unsigned long flags;
	struct zone *zone = page_zone(page);
	struct page_cgroup *pc = lookup_page_cgroup(page);

	spin_lock_irqsave(&zone->lru_lock, flags);
	/*
	 * Forget old LRU when this page_cgroup is *not* used. This Used bit
	 * is guarded by lock_page() because the page is SwapCache.
	 */
	if (!PageCgroupUsed(pc))
		mem_cgroup_del_lru_list(page, page_lru(page));
	spin_unlock_irqrestore(&zone->lru_lock, flags);
}

static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
{
	unsigned long flags;
	struct zone *zone = page_zone(page);
	struct page_cgroup *pc = lookup_page_cgroup(page);

	spin_lock_irqsave(&zone->lru_lock, flags);
	/* link when the page is linked to LRU but page_cgroup isn't */
	if (PageLRU(page) && !PageCgroupAcctLRU(pc))
		mem_cgroup_add_lru_list(page, page_lru(page));
	spin_unlock_irqrestore(&zone->lru_lock, flags);
}


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;
	struct mem_cgroup *curr = NULL;
	struct task_struct *p;

	p = find_lock_task_mm(task);
	if (!p)
		return 0;
	curr = try_get_mem_cgroup_from_mm(p->mm);
	task_unlock(p);
	if (!curr)
		return 0;
	/*
	 * We should check use_hierarchy of "mem" not "curr". Because checking
	 * use_hierarchy of "curr" here make this function true if hierarchy is
	 * enabled in "curr" and "curr" is a child of "mem" in *cgroup*
	 * hierarchy(even if use_hierarchy is disabled in "mem").
	 */
	if (mem->use_hierarchy)
		ret = css_is_ancestor(&curr->css, &mem->css);
	else
		ret = (curr == mem);
	css_put(&curr->css);
	return ret;
}

static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
{
	unsigned long active;
	unsigned long inactive;
	unsigned long gb;
	unsigned long inactive_ratio;

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

	gb = (inactive + active) >> (30 - PAGE_SHIFT);
	if (gb)
		inactive_ratio = int_sqrt(10 * gb);
	else
		inactive_ratio = 1;

	if (present_pages) {
		present_pages[0] = inactive;
		present_pages[1] = active;
	}

	return inactive_ratio;
}

int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
{
	unsigned long active;
	unsigned long inactive;
	unsigned long present_pages[2];
	unsigned long inactive_ratio;

	inactive_ratio = calc_inactive_ratio(memcg, present_pages);

	inactive = present_pages[0];
	active = present_pages[1];

	if (inactive * inactive_ratio < active)
		return 1;

	return 0;
}

int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
{
	unsigned long active;
	unsigned long inactive;

	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE);
	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE);

	return (active > inactive);
}