Merge tag 'pm+acpi-3.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael...

[opensuse:kernel.git] / mm / 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/sort.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/vmpressure.h>
#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include <net/tcp_memcontrol.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;
        unsigned long 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;
};

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 tcp_memcontrol 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

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

static size_t memcg_size(void)
{
        return sizeof(struct mem_cgroup) +
                nr_node_ids * sizeof(struct mem_cgroup_per_node);
}

/* internal only representation about the status of kmem accounting. */
enum {
        KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
        KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */
        KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
};

/* We account when limit is on, but only after call sites are patched */
#define KMEM_ACCOUNTED_MASK \
                ((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED))

#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_set_activated(struct mem_cgroup *memcg)
{
        set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
}

static void memcg_kmem_clear_activated(struct mem_cgroup *memcg)
{
        clear_bit(KMEM_ACCOUNTED_ACTIVATED, &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;
}

struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css)
{
        return &mem_cgroup_from_css(css)->vmpressure;
}

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

/* 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.cg_proto;
}
EXPORT_SYMBOL(tcp_proto_cgroup);

static void disarm_sock_keys(struct mem_cgroup *memcg)
{
        if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
                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.
 * There are two main reasons for not using the css_id for this:
 *  1) 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.
 *
 *  2) In order not to violate the cgroup API, we would like to do all memory
 *     allocation in ->create(). At that point, we haven't yet allocated the
 *     css_id. Having a separate index prevents us from messing with the cgroup
 *     core for this
 *
 * 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 css_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
 * css_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 65535

/*
 * 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)
                total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask);
        return total;
}

static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
                                       enum mem_cgroup_events_target target)
{
        unsigned long val, next;

        val = __this_cpu_read(memcg->stat->nr_page_events);
        next = __this_cpu_read(memcg->stat->targets[target]);
        /* from time_after() in jiffies.h */
        if ((long)next - (long)val < 0) {
                switch (target) {
                case MEM_CGROUP_TARGET_THRESH:
                        next = val + THRESHOLDS_EVENTS_TARGET;
                        break;
                case MEM_CGROUP_TARGET_SOFTLIMIT:
                        next = val + SOFTLIMIT_EVENTS_TARGET;
                        break;
                case MEM_CGROUP_TARGET_NUMAINFO:
                        next = val + NUMAINFO_EVENTS_TARGET;
                        break;
                default:
                        break;
                }
                __this_cpu_write(memcg->stat->targets[target], next);
                return true;
        }
        return false;
}

/*
 * Check events in order.
 *
 */
static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
{
        preempt_disable();
        /* threshold event is triggered in finer grain than soft limit */
        if (unlikely(mem_cgroup_event_ratelimit(memcg,
                                                MEM_CGROUP_TARGET_THRESH))) {
                bool do_softlimit;
                bool do_numainfo __maybe_unused;

                do_softlimit = mem_cgroup_event_ratelimit(memcg,
                                                MEM_CGROUP_TARGET_SOFTLIMIT);
#if MAX_NUMNODES > 1
                do_numainfo = mem_cgroup_event_ratelimit(memcg,
                                                MEM_CGROUP_TARGET_NUMAINFO);
#endif
                preempt_enable();

                mem_cgroup_threshold(memcg);
                if (unlikely(do_softlimit))
                        mem_cgroup_update_tree(memcg, page);
#if MAX_NUMNODES > 1
                if (unlikely(do_numainfo))
                        atomic_inc(&memcg->numainfo_events);
#endif
        } else
                preempt_enable();
}

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 mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id));
}

struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
        struct mem_cgroup *memcg = 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 {
                memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
                if (unlikely(!memcg))
                        break;
        } while (!css_tryget(&memcg->css));
        rcu_read_unlock();
        return memcg;
}

/*
 * Returns a next (in a pre-order walk) alive memcg (with elevated css
 * ref. count) or NULL if the whole root's subtree has been visited.
 *
 * helper function to be used by mem_cgroup_iter
 */
static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
                struct mem_cgroup *last_visited)
{
        struct cgroup_subsys_state *prev_css, *next_css;

        prev_css = last_visited ? &last_visited->css : NULL;
skip_node:
        next_css = css_next_descendant_pre(prev_css, &root->css);

        /*
         * Even if we found a group we have to make sure it is
         * alive. css && !memcg means that the groups should be
         * skipped and we should continue the tree walk.
         * last_visited css is safe to use because it is
         * protected by css_get and the tree walk is rcu safe.
         */
        if (next_css) {
                struct mem_cgroup *mem = mem_cgroup_from_css(next_css);

                if (css_tryget(&mem->css))
                        return mem;
                else {
                        prev_css = next_css;
                        goto skip_node;
                }
        }

        return NULL;
}

static void mem_cgroup_iter_invalidate(struct mem_cgroup *root)
{
        /*
         * When a group in the hierarchy below root is destroyed, the
         * hierarchy iterator can no longer be trusted since it might
         * have pointed to the destroyed group.  Invalidate it.
         */
        atomic_inc(&root->dead_count);
}

static struct mem_cgroup *
mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
                     struct mem_cgroup *root,
                     int *sequence)
{
        struct mem_cgroup *position = NULL;
        /*
         * A cgroup destruction happens in two stages: offlining and
         * release.  They are separated by a RCU grace period.
         *
         * If the iterator is valid, we may still race with an
         * offlining.  The RCU lock ensures the object won't be
         * released, tryget will fail if we lost the race.
         */
        *sequence = atomic_read(&root->dead_count);
        if (iter->last_dead_count == *sequence) {
                smp_rmb();
                position = iter->last_visited;
                if (position && !css_tryget(&position->css))
                        position = NULL;
        }
        return position;
}

static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
                                   struct mem_cgroup *last_visited,
                                   struct mem_cgroup *new_position,
                                   int sequence)
{
        if (last_visited)
                css_put(&last_visited->css);
        /*
         * We store the sequence count from the time @last_visited was
         * loaded successfully instead of rereading it here so that we
         * don't lose destruction events in between.  We could have
         * raced with the destruction of @new_position after all.
         */
        iter->last_visited = new_position;
        smp_wmb();
        iter->last_dead_count = sequence;
}

/**
 * mem_cgroup_iter - iterate over memory cgroup hierarchy
 * @root: hierarchy root
 * @prev: previously returned memcg, NULL on first invocation
 * @reclaim: cookie for shared reclaim walks, NULL for full walks
 *
 * Returns references to children of the hierarchy below @root, or
 * @root itself, or %NULL after a full round-trip.
 *
 * Caller must pass the return value in @prev on subsequent
 * invocations for reference counting, or use mem_cgroup_iter_break()
 * to cancel a hierarchy walk before the round-trip is complete.
 *
 * Reclaimers can specify a zone and a priority level in @reclaim to
 * divide up the memcgs in the hierarchy among all concurrent
 * reclaimers operating on the same zone and priority.
 */
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
                                   struct mem_cgroup *prev,
                                   struct mem_cgroup_reclaim_cookie *reclaim)
{
        struct mem_cgroup *memcg = NULL;
        struct mem_cgroup *last_visited = NULL;

        if (mem_cgroup_disabled())
                return NULL;

        if (!root)
                root = root_mem_cgroup;

        if (prev && !reclaim)
                last_visited = prev;

        if (!root->use_hierarchy && root != root_mem_cgroup) {
                if (prev)
                        goto out_css_put;
                return root;
        }

        rcu_read_lock();
        while (!memcg) {
                struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
                int uninitialized_var(seq);

                if (reclaim) {
                        int nid = zone_to_nid(reclaim->zone);
                        int zid = zone_idx(reclaim->zone);
                        struct mem_cgroup_per_zone *mz;

                        mz = mem_cgroup_zoneinfo(root, nid, zid);
                        iter = &mz->reclaim_iter[reclaim->priority];
                        if (prev && reclaim->generation != iter->generation) {
                                iter->last_visited = NULL;
                                goto out_unlock;
                        }

                        last_visited = mem_cgroup_iter_load(iter, root, &seq);
                }

                memcg = __mem_cgroup_iter_next(root, last_visited);

                if (reclaim) {
                        mem_cgroup_iter_update(iter, last_visited, memcg, seq);

                        if (!memcg)
                                iter->generation++;
                        else if (!prev && memcg)
                                reclaim->generation = iter->generation;
                }

                if (prev && !memcg)
                        goto out_unlock;
        }
out_unlock:
        rcu_read_unlock();
out_css_put:
        if (prev && prev != root)
                css_put(&prev->css);

        return memcg;
}

/**
 * mem_cgroup_iter_break - abort a hierarchy walk prematurely
 * @root: hierarchy root
 * @prev: last visited hierarchy member as returned by mem_cgroup_iter()
 */
void mem_cgroup_iter_break(struct mem_cgroup *root,
                           struct mem_cgroup *prev)
{
        if (!root)
                root = root_mem_cgroup;
        if (prev && prev != root)
                css_put(&prev->css);
}

/*
 * Iteration constructs for visiting all cgroups (under a tree).  If
 * loops are exited prematurely (break), mem_cgroup_iter_break() must
 * be used for reference counting.
 */
#define for_each_mem_cgroup_tree(iter, root)            \
        for (iter = mem_cgroup_iter(root, NULL, NULL);  \
             iter != NULL;                              \
             iter = mem_cgroup_iter(root, iter, NULL))

#define for_each_mem_cgroup(iter)                       \
        for (iter = mem_cgroup_iter(NULL, NULL, NULL);  \
             iter != NULL;                              \
             iter = mem_cgroup_iter(NULL, iter, NULL))

void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
{
        struct mem_cgroup *memcg;

        rcu_read_lock();
        memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
        if (unlikely(!memcg))
                goto out;

        switch (idx) {
        case PGFAULT:
                this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
                break;
        case PGMAJFAULT:
                this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
                break;
        default:
                BUG();
        }
out:
        rcu_read_unlock();
}
EXPORT_SYMBOL(__mem_cgroup_count_vm_event);

/**
 * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
 * @zone: zone of the wanted lruvec
 * @memcg: memcg of the wanted lruvec
 *
 * Returns the lru list vector holding pages for the given @zone and
 * @mem.  This can be the global zone lruvec, if the memory controller
 * is disabled.
 */
struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
                                      struct mem_cgroup *memcg)
{
        struct mem_cgroup_per_zone *mz;
        struct lruvec *lruvec;

        if (mem_cgroup_disabled()) {
                lruvec = &zone->lruvec;
                goto out;
        }

        mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
        lruvec = &mz->lruvec;
out:
        /*
         * Since a node can be onlined after the mem_cgroup was created,
         * we have to be prepared to initialize lruvec->zone here;
         * and if offlined then reonlined, we need to reinitialize it.
         */
        if (unlikely(lruvec->zone != zone))
                lruvec->zone = zone;
        return lruvec;
}

/*
 * 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.
 */

/**
 * mem_cgroup_page_lruvec - return lruvec for adding an lru page
 * @page: the page
 * @zone: zone of the page
 */
struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
{
        struct mem_cgroup_per_zone *mz;
        struct mem_cgroup *memcg;
        struct page_cgroup *pc;
        struct lruvec *lruvec;

        if (mem_cgroup_disabled()) {
                lruvec = &zone->lruvec;
                goto out;
        }

        pc = lookup_page_cgroup(page);
        memcg = pc->mem_cgroup;

        /*
         * Surreptitiously switch any uncharged offlist page to root:
         * an uncharged page off lru does nothing to secure
         * its former mem_cgroup from sudden removal.
         *
         * Our caller holds lru_lock, and PageCgroupUsed is updated
         * under page_cgroup lock: between them, they make all uses
         * of pc->mem_cgroup safe.
         */
        if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup)
                pc->mem_cgroup = memcg = root_mem_cgroup;

        mz = page_cgroup_zoneinfo(memcg, page);
        lruvec = &mz->lruvec;
out:
        /*
         * Since a node can be onlined after the mem_cgroup was created,
         * we have to be prepared to initialize lruvec->zone here;
         * and if offlined then reonlined, we need to reinitialize it.
         */
        if (unlikely(lruvec->zone != zone))
                lruvec->zone = zone;
        return lruvec;
}

/**
 * mem_cgroup_update_lru_size - account for adding or removing an lru page
 * @lruvec: mem_cgroup per zone lru vector
 * @lru: index of lru list the page is sitting on
 * @nr_pages: positive when adding or negative when removing
 *
 * This function must be called when a page is added to or removed from an
 * lru list.
 */
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
                                int nr_pages)
{
        struct mem_cgroup_per_zone *mz;
        unsigned long *lru_size;

        if (mem_cgroup_disabled())
                return;

        mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
        lru_size = mz->lru_size + lru;
        *lru_size += nr_pages;
        VM_BUG_ON((long)(*lru_size) < 0);
}

/*
 * Checks whether given mem is same or in the root_mem_cgroup's
 * hierarchy subtree
 */
bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
                                  struct mem_cgroup *memcg)
{
        if (root_memcg == memcg)
                return true;
        if (!root_memcg->use_hierarchy || !memcg)
                return false;
        return css_is_ancestor(&memcg->css, &root_memcg->css);
}

static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
                                       struct mem_cgroup *memcg)
{
        bool ret;

        rcu_read_lock();
        ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
        rcu_read_unlock();
        return ret;
}

bool task_in_mem_cgroup(struct task_struct *task,
                        const struct mem_cgroup *memcg)
{
        struct mem_cgroup *curr = NULL;
        struct task_struct *p;
        bool ret;

        p = find_lock_task_mm(task);
        if (p) {
                curr = try_get_mem_cgroup_from_mm(p->mm);
                task_unlock(p);
        } else {
                /*
                 * All threads may have already detached their mm's, but the oom
                 * killer still needs to detect if they have already been oom
                 * killed to prevent needlessly killing additional tasks.
                 */
                rcu_read_lock();
                curr = mem_cgroup_from_task(task);
                if (curr)
                        css_get(&curr->css);
                rcu_read_unlock();
        }
        if (!curr)
                return false;
        /*
         * We should check use_hierarchy of "memcg" 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 "memcg" in *cgroup*
         * hierarchy(even if use_hierarchy is disabled in "memcg").
         */
        ret = mem_cgroup_same_or_subtree(memcg, curr);
        css_put(&curr->css);
        return ret;
}

int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
{
        unsigned long inactive_ratio;
        unsigned long inactive;
        unsigned long active;
        unsigned long gb;

        inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
        active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);

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

        return inactive * inactive_ratio < active;
}

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

/**
 * mem_cgroup_margin - calculate chargeable space of a memory cgroup
 * @memcg: the memory cgroup
 *
 * Returns the maximum amount of memory @mem can be charged with, in
 * pages.
 */
static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
{
        unsigned long long margin;

        margin = res_counter_margin(&memcg->res);
        if (do_swap_account)
                margin = min(margin, res_counter_margin(&memcg->memsw));
        return margin >> PAGE_SHIFT;
}

int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
        /* root ? */
        if (!css_parent(&memcg->css))
                return vm_swappiness;

        return memcg->swappiness;
}

/*
 * memcg->moving_account is used for checking possibility that some thread is
 * calling move_account(). When a thread on CPU-A starts moving pages under
 * a memcg, other threads should check memcg->moving_account under
 * rcu_read_lock(), like this:
 *
 *         CPU-A                                    CPU-B
 *                                              rcu_read_lock()
 *         memcg->moving_account+1              if (memcg->mocing_account)
 *                                                   take heavy locks.
 *         synchronize_rcu()                    update something.
 *                                              rcu_read_unlock()
 *         start move here.
 */

/* for quick checking without looking up memcg */
atomic_t memcg_moving __read_mostly;

static void mem_cgroup_start_move(struct mem_cgroup *memcg)
{
        atomic_inc(&memcg_moving);
        atomic_inc(&memcg->moving_account);
        synchronize_rcu();
}

static void mem_cgroup_end_move(struct mem_cgroup *memcg)
{
        /*
         * Now, mem_cgroup_clear_mc() may call this function with NULL.
         * We check NULL in callee rather than caller.
         */
        if (memcg) {
                atomic_dec(&memcg_moving);
                atomic_dec(&memcg->moving_account);
        }
}

/*
 * 2 routines for checking "mem" is under move_account() or not.
 *
 * mem_cgroup_stolen() -  checking whether a cgroup is mc.from or not. This
 *                        is used for avoiding races in accounting.  If true,
 *                        pc->mem_cgroup may be overwritten.
 *
 * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
 *                        under hierarchy of moving cgroups. This is for
 *                        waiting at hith-memory prressure caused by "move".
 */

static bool mem_cgroup_stolen(struct mem_cgroup *memcg)
{
        VM_BUG_ON(!rcu_read_lock_held());
        return atomic_read(&memcg->moving_account) > 0;
}

static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
{
        struct mem_cgroup *from;
        struct mem_cgroup *to;
        bool ret = false;
        /*
         * Unlike task_move routines, we access mc.to, mc.from not under
         * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
         */
        spin_lock(&mc.lock);
        from = mc.from;
        to = mc.to;
        if (!from)
                goto unlock;

        ret = mem_cgroup_same_or_subtree(memcg, from)
                || mem_cgroup_same_or_subtree(memcg, to);
unlock:
        spin_unlock(&mc.lock);
        return ret;
}

static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
{
        if (mc.moving_task && current != mc.moving_task) {
                if (mem_cgroup_under_move(memcg)) {
                        DEFINE_WAIT(wait);
                        prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
                        /* moving charge context might have finished. */
                        if (mc.moving_task)
                                schedule();
                        finish_wait(&mc.waitq, &wait);
                        return true;
                }
        }
        return false;
}

/*
 * Take this lock when
 * - a code tries to modify page's memcg while it's USED.
 * - a code tries to modify page state accounting in a memcg.
 * see mem_cgroup_stolen(), too.
 */
static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
                                  unsigned long *flags)
{
        spin_lock_irqsave(&memcg->move_lock, *flags);
}

static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
                                unsigned long *flags)
{
        spin_unlock_irqrestore(&memcg->move_lock, *flags);
}

#define K(x) ((x) << (PAGE_SHIFT-10))
/**
 * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
 * @memcg: The memory cgroup that went over limit
 * @p: Task that is going to be killed
 *
 * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
 * enabled
 */
void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
        struct cgroup *task_cgrp;
        struct cgroup *mem_cgrp;
        /*
         * Need a buffer in BSS, can't rely on allocations. The code relies
         * on the assumption that OOM is serialized for memory controller.
         * If this assumption is broken, revisit this code.
         */
        static char memcg_name[PATH_MAX];
        int ret;
        struct mem_cgroup *iter;
        unsigned int i;

        if (!p)
                return;

        rcu_read_lock();

        mem_cgrp = memcg->css.cgroup;
        task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);

        ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
        if (ret < 0) {
                /*
                 * Unfortunately, we are unable to convert to a useful name
                 * But we'll still print out the usage information
                 */
                rcu_read_unlock();
                goto done;
        }
        rcu_read_unlock();

        pr_info("Task in %s killed", memcg_name);

        rcu_read_lock();
        ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
        if (ret < 0) {
                rcu_read_unlock();
                goto done;
        }
        rcu_read_unlock();

        /*
         * Continues from above, so we don't need an KERN_ level
         */
        pr_cont(" as a result of limit of %s\n", memcg_name);
done:

        pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
                res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
                res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
                res_counter_read_u64(&memcg->res, RES_FAILCNT));
        pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
                res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
                res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
                res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
        pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
                res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
                res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
                res_counter_read_u64(&memcg->kmem, RES_FAILCNT));

        for_each_mem_cgroup_tree(iter, memcg) {
                pr_info("Memory cgroup stats");

                rcu_read_lock();
                ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
                if (!ret)
                        pr_cont(" for %s", memcg_name);
                rcu_read_unlock();
                pr_cont(":");

                for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
                        if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
                                continue;
                        pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
                                K(mem_cgroup_read_stat(iter, i)));
                }

                for (i = 0; i < NR_LRU_LISTS; i++)
                        pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
                                K(mem_cgroup_nr_lru_pages(iter, BIT(i))));

                pr_cont("\n");
        }
}

/*
 * This function returns the number of memcg under hierarchy tree. Returns
 * 1(self count) if no children.
 */
static int mem_cgroup_count_children(struct mem_cgroup *memcg)
{
        int num = 0;
        struct mem_cgroup *iter;

        for_each_mem_cgroup_tree(iter, memcg)
                num++;
        return num;
}

/*
 * Return the memory (and swap, if configured) limit for a memcg.
 */
static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
{
        u64 limit;

        limit = res_counter_read_u64(&memcg->res, RES_LIMIT);

        /*
         * Do not consider swap space if we cannot swap due to swappiness
         */
        if (mem_cgroup_swappiness(memcg)) {
                u64 memsw;

                limit += total_swap_pages << PAGE_SHIFT;
                memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);

                /*
                 * If memsw is finite and limits the amount of swap space
                 * available to this memcg, return that limit.
                 */
                limit = min(limit, memsw);
        }

        return limit;
}

static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
                                     int order)
{
        struct mem_cgroup *iter;
        unsigned long chosen_points = 0;
        unsigned long totalpages;
        unsigned int points = 0;
        struct task_struct *chosen = NULL;

        /*
         * If current has a pending SIGKILL or is exiting, then automatically
         * select it.  The goal is to allow it to allocate so that it may
         * quickly exit and free its memory.
         */
        if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
                set_thread_flag(TIF_MEMDIE);
                return;
        }

        check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
        totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
        for_each_mem_cgroup_tree(iter, memcg) {
                struct css_task_iter it;
                struct task_struct *task;

                css_task_iter_start(&iter->css, &it);
                while ((task = css_task_iter_next(&it))) {
                        switch (oom_scan_process_thread(task, totalpages, NULL,
                                                        false)) {
                        case OOM_SCAN_SELECT:
                                if (chosen)
                                        put_task_struct(chosen);
                                chosen = task;
                                chosen_points = ULONG_MAX;
                                get_task_struct(chosen);
                                /* fall through */
                        case OOM_SCAN_CONTINUE:
                                continue;
                        case OOM_SCAN_ABORT:
                                css_task_iter_end(&it);
                                mem_cgroup_iter_break(memcg, iter);
                                if (chosen)
                                        put_task_struct(chosen);
                                return;
                        case OOM_SCAN_OK:
                                break;
                        };
                        points = oom_badness(task, memcg, NULL, totalpages);
                        if (points > chosen_points) {
                                if (chosen)
                                        put_task_struct(chosen);
                                chosen = task;
                                chosen_points = points;
                                get_task_struct(chosen);
                        }
                }
                css_task_iter_end(&it);
        }

        if (!chosen)
                return;
        points = chosen_points * 1000 / totalpages;
        oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
                         NULL, "Memory cgroup out of memory");
}

static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
                                        gfp_t gfp_mask,
                                        unsigned long flags)
{
        unsigned long total = 0;
        bool noswap = false;
        int loop;

        if (flags & MEM_CGROUP_RECLAIM_NOSWAP)
                noswap = true;
        if (!(flags & MEM_CGROUP_RECLAIM_SHRINK) && memcg->memsw_is_minimum)
                noswap = true;

        for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) {
                if (loop)
                        drain_all_stock_async(memcg);
                total += try_to_free_mem_cgroup_pages(memcg, gfp_mask, noswap);
                /*
                 * Allow limit shrinkers, which are triggered directly
                 * by userspace, to catch signals and stop reclaim
                 * after minimal progress, regardless of the margin.
                 */
                if (total && (flags & MEM_CGROUP_RECLAIM_SHRINK))
                        break;
                if (mem_cgroup_margin(memcg))
                        break;
                /*
                 * If nothing was reclaimed after two attempts, there
                 * may be no reclaimable pages in this hierarchy.
                 */
                if (loop && !total)
                        break;
        }
        return total;
}

/**
 * test_mem_cgroup_node_reclaimable
 * @memcg: the target memcg
 * @nid: the node ID to be checked.
 * @noswap : specify true here if the user wants flle only information.
 *
 * This function returns whether the specified memcg contains any
 * reclaimable pages on a node. Returns true if there are any reclaimable
 * pages in the node.
 */
static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
                int nid, bool noswap)
{
        if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE))
                return true;
        if (noswap || !total_swap_pages)
                return false;
        if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON))
                return true;
        return false;

}
#if MAX_NUMNODES > 1

/*
 * Always updating the nodemask is not very good - even if we have an empty
 * list or the wrong list here, we can start from some node and traverse all
 * nodes based on the zonelist. So update the list loosely once per 10 secs.
 *
 */
static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
{
        int nid;
        /*
         * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
         * pagein/pageout changes since the last update.
         */
        if (!atomic_read(&memcg->numainfo_events))
                return;
        if (atomic_inc_return(&memcg->numainfo_updating) > 1)
                return;

        /* make a nodemask where this memcg uses memory from */
        memcg->scan_nodes = node_states[N_MEMORY];

        for_each_node_mask(nid, node_states[N_MEMORY]) {

                if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
                        node_clear(nid, memcg->scan_nodes);
        }

        atomic_set(&memcg->numainfo_events, 0);
        atomic_set(&memcg->numainfo_updating, 0);
}

/*
 * Selecting a node where we start reclaim from. Because what we need is just
 * reducing usage counter, start from anywhere is O,K. Considering
 * memory reclaim from current node, there are pros. and cons.
 *
 * Freeing memory from current node means freeing memory from a node which
 * we'll use or we've used. So, it may make LRU bad. And if several threads
 * hit limits, it will see a contention on a node. But freeing from remote
 * node means more costs for memory reclaim because of memory latency.
 *
 * Now, we use round-robin. Better algorithm is welcomed.
 */
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
        int node;

        mem_cgroup_may_update_nodemask(memcg);
        node = memcg->last_scanned_node;

        node = next_node(node, memcg->scan_nodes);
        if (node == MAX_NUMNODES)
                node = first_node(memcg->scan_nodes);
        /*
         * We call this when we hit limit, not when pages are added to LRU.
         * No LRU may hold pages because all pages are UNEVICTABLE or
         * memcg is too small and all pages are not on LRU. In that case,
         * we use curret node.
         */
        if (unlikely(node == MAX_NUMNODES))
                node = numa_node_id();

        memcg->last_scanned_node = node;
        return node;
}

/*
 * Check all nodes whether it contains reclaimable pages or not.
 * For quick scan, we make use of scan_nodes. This will allow us to skip
 * unused nodes. But scan_nodes is lazily updated and may not cotain
 * enough new information. We need to do double check.
 */
static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
{
        int nid;

        /*
         * quick check...making use of scan_node.
         * We can skip unused nodes.
         */
        if (!nodes_empty(memcg->scan_nodes)) {
                for (nid = first_node(memcg->scan_nodes);
                     nid < MAX_NUMNODES;
                     nid = next_node(nid, memcg->scan_nodes)) {

                        if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
                                return true;
                }
        }
        /*
         * Check rest of nodes.
         */
        for_each_node_state(nid, N_MEMORY) {
                if (node_isset(nid, memcg->scan_nodes))
                        continue;
                if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
                        return true;
        }
        return false;
}

#else
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
        return 0;
}

static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
{
        return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
}
#endif

static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
                                   struct zone *zone,
                                   gfp_t gfp_mask,
                                   unsigned long *total_scanned)
{
        struct mem_cgroup *victim = NULL;
        int total = 0;
        int loop = 0;
        unsigned long excess;
        unsigned long nr_scanned;
        struct mem_cgroup_reclaim_cookie reclaim = {
                .zone = zone,
                .priority = 0,
        };

        excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;

        while (1) {
                victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
                if (!victim) {
                        loop++;
                        if (loop >= 2) {
                                /*
                                 * If we have not been able to reclaim
                                 * anything, it might because there are
                                 * no reclaimable pages under this hierarchy
                                 */
                                if (!total)
                                        break;
                                /*
                                 * We want to do more targeted reclaim.
                                 * excess >> 2 is not to excessive so as to
                                 * reclaim too much, nor too less that we keep
                                 * coming back to reclaim from this cgroup
                                 */
                                if (total >= (excess >> 2) ||
                                        (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
                                        break;
                        }
                        continue;
                }
                if (!mem_cgroup_reclaimable(victim, false))
                        continue;
                total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
                                                     zone, &nr_scanned);
                *total_scanned += nr_scanned;
                if (!res_counter_soft_limit_excess(&root_memcg->res))
                        break;
        }
        mem_cgroup_iter_break(root_memcg, victim);
        return total;
}

static DEFINE_SPINLOCK(memcg_oom_lock);

/*
 * Check OOM-Killer is already running under our hierarchy.
 * If someone is running, return false.
 */
static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
        struct mem_cgroup *iter, *failed = NULL;

        spin_lock(&memcg_oom_lock);

        for_each_mem_cgroup_tree(iter, memcg) {
                if (iter->oom_lock) {
                        /*
                         * this subtree of our hierarchy is already locked
                         * so we cannot give a lock.
                         */
                        failed = iter;
                        mem_cgroup_iter_break(memcg, iter);
                        break;
                } else
                        iter->oom_lock = true;
        }

        if (failed) {
                /*
                 * OK, we failed to lock the whole subtree so we have
                 * to clean up what we set up to the failing subtree
                 */
                for_each_mem_cgroup_tree(iter, memcg) {
                        if (iter == failed) {
                                mem_cgroup_iter_break(memcg, iter);
                                break;
                        }
                        iter->oom_lock = false;
                }
        }

        spin_unlock(&memcg_oom_lock);

        return !failed;
}

static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
        struct mem_cgroup *iter;

        spin_lock(&memcg_oom_lock);
        for_each_mem_cgroup_tree(iter, memcg)
                iter->oom_lock = false;
        spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
{
        struct mem_cgroup *iter;

        for_each_mem_cgroup_tree(iter, memcg)
                atomic_inc(&iter->under_oom);
}

static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
{
        struct mem_cgroup *iter;

        /*
         * When a new child is created while the hierarchy is under oom,
         * mem_cgroup_oom_lock() may not be called. We have to use
         * atomic_add_unless() here.
         */
        for_each_mem_cgroup_tree(iter, memcg)
                atomic_add_unless(&iter->under_oom, -1, 0);
}

static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);

struct oom_wait_info {
        struct mem_cgroup *memcg;
        wait_queue_t    wait;
};

static int memcg_oom_wake_function(wait_queue_t *wait,
        unsigned mode, int sync, void *arg)
{
        struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
        struct mem_cgroup *oom_wait_memcg;
        struct oom_wait_info *oom_wait_info;

        oom_wait_info = container_of(wait, struct oom_wait_info, wait);
        oom_wait_memcg = oom_wait_info->memcg;

        /*
         * Both of oom_wait_info->memcg and wake_memcg are stable under us.
         * Then we can use css_is_ancestor without taking care of RCU.
         */
        if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
                && !mem_cgroup_same_or_subtree(wake_memcg, oom_wait_memcg))
                return 0;
        return autoremove_wake_function(wait, mode, sync, arg);
}

static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
        atomic_inc(&memcg->oom_wakeups);
        /* for filtering, pass "memcg" as argument. */
        __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}

static void memcg_oom_recover(struct mem_cgroup *memcg)
{
        if (memcg && atomic_read(&memcg->under_oom))
                memcg_wakeup_oom(memcg);
}

static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
        if (!current->memcg_oom.may_oom)
                return;
        /*
         * We are in the middle of the charge context here, so we
         * don't want to block when potentially sitting on a callstack
         * that holds all kinds of filesystem and mm locks.
         *
         * Also, the caller may handle a failed allocation gracefully
         * (like optional page cache readahead) and so an OOM killer
         * invocation might not even be necessary.
         *
         * That's why we don't do anything here except remember the
         * OOM context and then deal with it at the end of the page
         * fault when the stack is unwound, the locks are released,
         * and when we know whether the fault was overall successful.
         */
        css_get(&memcg->css);
        current->memcg_oom.memcg = memcg;
        current->memcg_oom.gfp_mask = mask;
        current->memcg_oom.order = order;
}

/**
 * mem_cgroup_oom_synchronize - complete memcg OOM handling
 * @handle: actually kill/wait or just clean up the OOM state
 *
 * This has to be called at the end of a page fault if the memcg OOM
 * handler was enabled.
 *
 * Memcg supports userspace OOM handling where failed allocations must
 * sleep on a waitqueue until the userspace task resolves the
 * situation.  Sleeping directly in the charge context with all kinds
 * of locks held is not a good idea, instead we remember an OOM state
 * in the task and mem_cgroup_oom_synchronize() has to be called at
 * the end of the page fault to complete the OOM handling.
 *
 * Returns %true if an ongoing memcg OOM situation was detected and
 * completed, %false otherwise.
 */
bool mem_cgroup_oom_synchronize(bool handle)
{
        struct mem_cgroup *memcg = current->memcg_oom.memcg;
        struct oom_wait_info owait;
        bool locked;

        /* OOM is global, do not handle */
        if (!memcg)
                return false;

        if (!handle)
                goto cleanup;

        owait.memcg = memcg;
        owait.wait.flags = 0;
        owait.wait.func = memcg_oom_wake_function;
        owait.wait.private = current;
        INIT_LIST_HEAD(&owait.wait.task_list);

        prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
        mem_cgroup_mark_under_oom(memcg);

        locked = mem_cgroup_oom_trylock(memcg);

        if (locked)
                mem_cgroup_oom_notify(memcg);

        if (locked && !memcg->oom_kill_disable) {
                mem_cgroup_unmark_under_oom(memcg);
                finish_wait(&memcg_oom_waitq, &owait.wait);
                mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
                                         current->memcg_oom.order);
        } else {
                schedule();
                mem_cgroup_unmark_under_oom(memcg);
                finish_wait(&memcg_oom_waitq, &owait.wait);
        }

        if (locked) {
                mem_cgroup_oom_unlock(memcg);
                /*
                 * There is no guarantee that an OOM-lock contender
                 * sees the wakeups triggered by the OOM kill
                 * uncharges.  Wake any sleepers explicitely.
                 */
                memcg_oom_recover(memcg);
        }
cleanup:
        current->memcg_oom.memcg = NULL;
        css_put(&memcg->css);
        return true;
}

/*
 * Currently used to update mapped file statistics, but the routine can be
 * generalized to update other statistics as well.
 *
 * Notes: Race condition
 *
 * We usually use page_cgroup_lock() for accessing page_cgroup member but
 * it tends to be costly. But considering some conditions, we doesn't need
 * to do so _always_.
 *
 * Considering "charge", lock_page_cgroup() is not required because all
 * file-stat operations happen after a page is attached to radix-tree. There
 * are no race with "charge".
 *
 * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
 * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
 * if there are race with "uncharge". Statistics itself is properly handled
 * by flags.
 *
 * Considering "move", this is an only case we see a race. To make the race
 * small, we check mm->moving_account and detect there are possibility of race
 * If there is, we take a lock.
 */

void __mem_cgroup_begin_update_page_stat(struct page *page,
                                bool *locked, unsigned long *flags)
{
        struct mem_cgroup *memcg;
        struct page_cgroup *pc;

        pc = lookup_page_cgroup(page);
again:
        memcg = pc->mem_cgroup;
        if (unlikely(!memcg || !PageCgroupUsed(pc)))
                return;
        /*
         * If this memory cgroup is not under account moving, we don't
         * need to take move_lock_mem_cgroup(). Because we already hold
         * rcu_read_lock(), any calls to move_account will be delayed until
         * rcu_read_unlock() if mem_cgroup_stolen() == true.
         */
        if (!mem_cgroup_stolen(memcg))
                return;

        move_lock_mem_cgroup(memcg, flags);
        if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
                move_unlock_mem_cgroup(memcg, flags);
                goto again;
        }
        *locked = true;
}

void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
{
        struct page_cgroup *pc = lookup_page_cgroup(page);

        /*
         * It's guaranteed that pc->mem_cgroup never changes while
         * lock is held because a routine modifies pc->mem_cgroup
         * should take move_lock_mem_cgroup().
         */
        move_unlock_mem_cgroup(pc->mem_cgroup, flags);
}

void mem_cgroup_update_page_stat(struct page *page,
                                 enum mem_cgroup_stat_index idx, int val)
{
        struct mem_cgroup *memcg;
        struct page_cgroup *pc = lookup_page_cgroup(page);
        unsigned long uninitialized_var(flags);

        if (mem_cgroup_disabled())
                return;

        VM_BUG_ON(!rcu_read_lock_held());
        memcg = pc->mem_cgroup;
        if (unlikely(!memcg || !PageCgroupUsed(pc)))
                return;

        this_cpu_add(memcg->stat->count[idx], val);
}

/*
 * size of first charge trial. "32" comes from vmscan.c's magic value.
 * TODO: maybe necessary to use big numbers in big irons.
 */
#define CHARGE_BATCH    32U
struct memcg_stock_pcp {
        struct mem_cgroup *cached; /* this never be root cgroup */
        unsigned int nr_pages;
        struct work_struct work;
        unsigned long flags;
#define FLUSHING_CACHED_CHARGE  0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
static DEFINE_MUTEX(percpu_charge_mutex);

/**
 * consume_stock: Try to consume stocked charge on this cpu.
 * @memcg: memcg to consume from.
 * @nr_pages: how many pages to charge.
 *
 * The charges will only happen if @memcg matches the current cpu's memcg
 * stock, and at least @nr_pages are available in that stock.  Failure to
 * service an allocation will refill the stock.
 *
 * returns true if successful, false otherwise.
 */
static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
        struct memcg_stock_pcp *stock;
        bool ret = true;

        if (nr_pages > CHARGE_BATCH)
                return false;

        stock = &get_cpu_var(memcg_stock);
        if (memcg == stock->cached && stock->nr_pages >= nr_pages)
                stock->nr_pages -= nr_pages;
        else /* need to call res_counter_charge */
                ret = false;
        put_cpu_var(memcg_stock);
        return ret;
}

/*
 * Returns stocks cached in percpu to res_counter and reset cached information.
 */
static void drain_stock(struct memcg_stock_pcp *stock)
{
        struct mem_cgroup *old = stock->cached;

        if (stock->nr_pages) {
                unsigned long bytes = stock->nr_pages * PAGE_SIZE;

                res_counter_uncharge(&old->res, bytes);
                if (do_swap_account)
                        res_counter_uncharge(&old->memsw, bytes);
                stock->nr_pages = 0;
        }
        stock->cached = NULL;
}

/*
 * This must be called under preempt disabled or must be called by
 * a thread which is pinned to local cpu.
 */
static void drain_local_stock(struct work_struct *dummy)
{
        struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock);
        drain_stock(stock);
        clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
}

static void __init memcg_stock_init(void)
{
        int cpu;

        for_each_possible_cpu(cpu) {
                struct memcg_stock_pcp *stock =
                                        &per_cpu(memcg_stock, cpu);
                INIT_WORK(&stock->work, drain_local_stock);
        }
}

/*
 * Cache charges(val) which is from res_counter, to local per_cpu area.
 * This will be consumed by consume_stock() function, later.
 */
static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
        struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);

        if (stock->cached != memcg) { /* reset if necessary */
                drain_stock(stock);
                stock->cached = memcg;
        }
        stock->nr_pages += nr_pages;
        put_cpu_var(memcg_stock);
}

/*
 * Drains all per-CPU charge caches for given root_memcg resp. subtree
 * of the hierarchy under it. sync flag says whether we should block
 * until the work is done.
 */
static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
{
        int cpu, curcpu;

        /* Notify other cpus that system-wide "drain" is running */
        get_online_cpus();
        curcpu = get_cpu();
        for_each_online_cpu(cpu) {
                struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
                struct mem_cgroup *memcg;

                memcg = stock->cached;
                if (!memcg || !stock->nr_pages)
                        continue;
                if (!mem_cgroup_same_or_subtree(root_memcg, memcg))
                        continue;
                if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
                        if (cpu == curcpu)
                                drain_local_stock(&stock->work);
                        else
                                schedule_work_on(cpu, &stock->work);
                }
        }
        put_cpu();

        if (!sync)
                goto out;

        for_each_online_cpu(cpu) {
                struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
                if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
                        flush_work(&stock->work);
        }
out:
        put_online_cpus();
}

/*
 * Tries to drain stocked charges in other cpus. This function is asynchronous
 * and just put a work per cpu for draining localy on each cpu. Caller can
 * expects some charges will be back to res_counter later but cannot wait for
 * it.
 */
static void drain_all_stock_async(struct mem_cgroup *root_memcg)
{
        /*
         * If someone calls draining, avoid adding more kworker runs.
         */
        if (!mutex_trylock(&percpu_charge_mutex))
                return;
        drain_all_stock(root_memcg, false);
        mutex_unlock(&percpu_charge_mutex);
}

/* This is a synchronous drain interface. */
static void drain_all_stock_sync(struct mem_cgroup *root_memcg)
{
        /* called when force_empty is called */
        mutex_lock(&percpu_charge_mutex);
        drain_all_stock(root_memcg, true);
        mutex_unlock(&percpu_charge_mutex);
}

/*
 * This function drains percpu counter value from DEAD cpu and
 * move it to local cpu. Note that this function can be preempted.
 */
static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
{
        int i;

        spin_lock(&memcg->pcp_counter_lock);
        for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
                long x = per_cpu(memcg->stat->count[i], cpu);

                per_cpu(memcg->stat->count[i], cpu) = 0;
                memcg->nocpu_base.count[i] += x;
        }
        for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
                unsigned long x = per_cpu(memcg->stat->events[i], cpu);

                per_cpu(memcg->stat->events[i], cpu) = 0;
                memcg->nocpu_base.events[i] += x;
        }
        spin_unlock(&memcg->pcp_counter_lock);
}

static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
                                        unsigned long action,
                                        void *hcpu)
{
        int cpu = (unsigned long)hcpu;
        struct memcg_stock_pcp *stock;
        struct mem_cgroup *iter;

        if (action == CPU_ONLINE)
                return NOTIFY_OK;

        if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
                return NOTIFY_OK;

        for_each_mem_cgroup(iter)
                mem_cgroup_drain_pcp_counter(iter, cpu);

        stock = &per_cpu(memcg_stock, cpu);
        drain_stock(stock);
        return NOTIFY_OK;
}


/* See __mem_cgroup_try_charge() for details */
enum {
        CHARGE_OK,              /* success */
        CHARGE_RETRY,           /* need to retry but retry is not bad */
        CHARGE_NOMEM,           /* we can't do more. return -ENOMEM */
        CHARGE_WOULDBLOCK,      /* GFP_WAIT wasn't set and no enough res. */
};

static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
                                unsigned int nr_pages, unsigned int min_pages,
                                bool invoke_oom)
{
        unsigned long csize = nr_pages * PAGE_SIZE;
        struct mem_cgroup *mem_over_limit;
        struct res_counter *fail_res;
        unsigned long flags = 0;
        int ret;

        ret = res_counter_charge(&memcg->res, csize, &fail_res);

        if (likely(!ret)) {
                if (!do_swap_account)
                        return CHARGE_OK;
                ret = res_counter_charge(&memcg->memsw, csize, &fail_res);
                if (likely(!ret))
                        return CHARGE_OK;

                res_counter_uncharge(&memcg->res, csize);
                mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
                flags |= MEM_CGROUP_RECLAIM_NOSWAP;
        } else
                mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
        /*
         * Never reclaim on behalf of optional batching, retry with a
         * single page instead.
         */
        if (nr_pages > min_pages)
                return CHARGE_RETRY;

        if (!(gfp_mask & __GFP_WAIT))
                return CHARGE_WOULDBLOCK;

        if (gfp_mask & __GFP_NORETRY)
                return CHARGE_NOMEM;

        ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
        if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
                return CHARGE_RETRY;
        /*
         * Even though the limit is exceeded at this point, reclaim
         * may have been able to free some pages.  Retry the charge
         * before killing the task.
         *
         * Only for regular pages, though: huge pages are rather
         * unlikely to succeed so close to the limit, and we fall back
         * to regular pages anyway in case of failure.
         */
        if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret)
                return CHARGE_RETRY;

        /*
         * At task move, charge accounts can be doubly counted. So, it's
         * better to wait until the end of task_move if something is going on.
         */
        if (mem_cgroup_wait_acct_move(mem_over_limit))
                return CHARGE_RETRY;

        if (invoke_oom)
                mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));

        return CHARGE_NOMEM;
}

/*
 * __mem_cgroup_try_charge() does
 * 1. detect memcg to be charged against from passed *mm and *ptr,
 * 2. update res_counter
 * 3. call memory reclaim if necessary.
 *
 * In some special case, if the task is fatal, fatal_signal_pending() or
 * has TIF_MEMDIE, this function returns -EINTR while writing root_mem_cgroup
 * to *ptr. There are two reasons for this. 1: fatal threads should quit as soon
 * as possible without any hazards. 2: all pages should have a valid
 * pc->mem_cgroup. If mm is NULL and the caller doesn't pass a valid memcg
 * pointer, that is treated as a charge to root_mem_cgroup.
 *
 * So __mem_cgroup_try_charge() will return
 *  0       ...  on success, filling *ptr with a valid memcg pointer.
 *  -ENOMEM ...  charge failure because of resource limits.
 *  -EINTR  ...  if thread is fatal. *ptr is filled with root_mem_cgroup.
 *
 * Unlike the exported interface, an "oom" parameter is added. if oom==true,
 * the oom-killer can be invoked.
 */
static int __mem_cgroup_try_charge(struct mm_struct *mm,
                                   gfp_t gfp_mask,
                                   unsigned int nr_pages,
                                   struct mem_cgroup **ptr,
                                   bool oom)
{
        unsigned int batch = max(CHARGE_BATCH, nr_pages);
        int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
        struct mem_cgroup *memcg = NULL;
        int ret;

        /*
         * Unlike gloval-vm's OOM-kill, we're not in memory shortage
         * in system level. So, allow to go ahead dying process in addition to
         * MEMDIE process.
         */
        if (unlikely(test_thread_flag(TIF_MEMDIE)
                     || fatal_signal_pending(current)))
                goto bypass;

        if (unlikely(task_in_memcg_oom(current)))
                goto bypass;

        /*
         * 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 root memcg (happens for pagecache usage).
         */
        if (!*ptr && !mm)
                *ptr = root_mem_cgroup;
again:
        if (*ptr) { /* css should be a valid one */
                memcg = *ptr;
                if (mem_cgroup_is_root(memcg))
                        goto done;
                if (consume_stock(memcg, nr_pages))
                        goto done;
                css_get(&memcg->css);
        } else {
                struct task_struct *p;

                rcu_read_lock();
                p = rcu_dereference(mm->owner);
                /*
                 * Because we don't have task_lock(), "p" can exit.
                 * In that case, "memcg" can point to root or p can be NULL with
                 * race with swapoff. Then, we have small risk of mis-accouning.
                 * But such kind of mis-account by race always happens because
                 * we don't have cgroup_mutex(). It's overkill and we allo that
                 * small race, here.
                 * (*) swapoff at el will charge against mm-struct not against
                 * task-struct. So, mm->owner can be NULL.
                 */
                memcg = mem_cgroup_from_task(p);
                if (!memcg)
                        memcg = root_mem_cgroup;
                if (mem_cgroup_is_root(memcg)) {
                        rcu_read_unlock();
                        goto done;
                }
                if (consume_stock(memcg, nr_pages)) {
                        /*
                         * It seems dagerous to access memcg without css_get().
                         * But considering how consume_stok works, it's not
                         * necessary. If consume_stock success, some charges
                         * from this memcg are cached on this cpu. So, we
                         * don't need to call css_get()/css_tryget() before
                         * calling consume_stock().
                         */
                        rcu_read_unlock();
                        goto done;
                }
                /* after here, we may be blocked. we need to get refcnt */
                if (!css_tryget(&memcg->css)) {
                        rcu_read_unlock();
                        goto again;
                }
                rcu_read_unlock();
        }

        do {
                bool invoke_oom = oom && !nr_oom_retries;

                /* If killed, bypass charge */
                if (fatal_signal_pending(current)) {
                        css_put(&memcg->css);
                        goto bypass;
                }

                ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
                                           nr_pages, invoke_oom);
                switch (ret) {
                case CHARGE_OK:
                        break;
                case CHARGE_RETRY: /* not in OOM situation but retry */
                        batch = nr_pages;
                        css_put(&memcg->css);
                        memcg = NULL;
                        goto again;
                case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
                        css_put(&memcg->css);
                        goto nomem;
                case CHARGE_NOMEM: /* OOM routine works */
                        if (!oom || invoke_oom) {
                                css_put(&memcg->css);
                                goto nomem;
                        }
                        nr_oom_retries--;
                        break;
                }
        } while (ret != CHARGE_OK);

        if (batch > nr_pages)
                refill_stock(memcg, batch - nr_pages);
        css_put(&memcg->css);
done:
        *ptr = memcg;
        return 0;
nomem:
        *ptr = NULL;
        if (gfp_mask & __GFP_NOFAIL)
                return 0;
        return -ENOMEM;
bypass:
        *ptr = root_mem_cgroup;
        return -EINTR;
}

/*
 * Somemtimes we have to undo a charge we got by try_charge().
 * This function is for that and do uncharge, put css's refcnt.
 * gotten by try_charge().
 */
static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
                                       unsigned int nr_pages)
{
        if (!mem_cgroup_is_root(memcg)) {
                unsigned long bytes = nr_pages * PAGE_SIZE;

                res_counter_uncharge(&memcg->res, bytes);
                if (do_swap_account)
                        res_counter_uncharge(&memcg->memsw, bytes);
        }
}

/*
 * Cancel chrages in this cgroup....doesn't propagate to parent cgroup.
 * This is useful when moving usage to parent cgroup.
 */
static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
                                        unsigned int nr_pages)
{
        unsigned long bytes = nr_pages * PAGE_SIZE;

        if (mem_cgroup_is_root(memcg))
                return;

        res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
        if (do_swap_account)
                res_counter_uncharge_until(&memcg->memsw,
                                                memcg->memsw.parent, bytes);
}

/*
 * A helper function to get mem_cgroup from ID. must be called under
 * rcu_read_lock().  The caller is responsible for calling css_tryget if
 * the mem_cgroup is used for charging. (dropping refcnt from swap can be
 * called against removed memcg.)
 */
static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
{
        struct cgroup_subsys_state *css;

        /* ID 0 is unused ID */
        if (!id)
                return NULL;
        css = css_lookup(&mem_cgroup_subsys, id);
        if (!css)
                return NULL;
        return mem_cgroup_from_css(css);
}

struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
{
        struct mem_cgroup *memcg = NULL;
        struct page_cgroup *pc;
        unsigned short id;
        swp_entry_t ent;

        VM_BUG_ON(!PageLocked(page));

        pc = lookup_page_cgroup(page);
        lock_page_cgroup(pc);
        if (PageCgroupUsed(pc)) {
                memcg = pc->mem_cgroup;
                if (memcg && !css_tryget(&memcg->css))
                        memcg = NULL;
        } else if (PageSwapCache(page)) {
                ent.val = page_private(page);
                id = lookup_swap_cgroup_id(ent);
                rcu_read_lock();
                memcg = mem_cgroup_lookup(id);
                if (memcg && !css_tryget(&memcg->css))
                        memcg = NULL;
                rcu_read_unlock();
        }
        unlock_page_cgroup(pc);
        return memcg;
}

static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
                                       struct page *page,
                                       unsigned int nr_pages,
                                       enum charge_type ctype,
                                       bool lrucare)
{
        struct page_cgroup *pc = lookup_page_cgroup(page);
        struct zone *uninitialized_var(zone);
        struct lruvec *lruvec;
        bool was_on_lru = false;
        bool anon;

        lock_page_cgroup(pc);
        VM_BUG_ON(PageCgroupUsed(pc));
        /*
         * we don't need page_cgroup_lock about tail pages, becase they are not
         * accessed by any other context at this point.
         */

        /*
         * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
         * may already be on some other mem_cgroup's LRU.  Take care of it.
         */
        if (lrucare) {
                zone = page_zone(page);
                spin_lock_irq(&zone->lru_lock);
                if (PageLRU(page)) {
                        lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
                        ClearPageLRU(page);
                        del_page_from_lru_list(page, lruvec, page_lru(page));
                        was_on_lru = true;
                }
        }

        pc->mem_cgroup = memcg;
        /*
         * We access a page_cgroup asynchronously without lock_page_cgroup().
         * Especially when a page_cgroup is taken from a page, pc->mem_cgroup
         * is accessed after testing USED bit. To make pc->mem_cgroup visible
         * before USED bit, we need memory barrier here.
         * See mem_cgroup_add_lru_list(), etc.
         */
        smp_wmb();
        SetPageCgroupUsed(pc);

        if (lrucare) {
                if (was_on_lru) {
                        lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
                        VM_BUG_ON(PageLRU(page));
                        SetPageLRU(page);
                        add_page_to_lru_list(page, lruvec, page_lru(page));
                }
                spin_unlock_irq(&zone->lru_lock);
        }

        if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
                anon = true;
        else
                anon = false;

        mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
        unlock_page_cgroup(pc);

        /*
         * "charge_statistics" updated event counter. Then, check it.
         * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
         * if they exceeds softlimit.
         */
        memcg_check_events(memcg, page);
}

static DEFINE_MUTEX(set_limit_mutex);

#ifdef CONFIG_MEMCG_KMEM
static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
{
        return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
                (memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
}

/*
 * This is a bit cumbersome, but it is rarely used and avoids a backpointer
 * in the memcg_cache_params struct.
 */
static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
{
        struct kmem_cache *cachep;

        VM_BUG_ON(p->is_root_cache);
        cachep = p->root_cache;
        return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
}

#ifdef CONFIG_SLABINFO
static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css,
                                    struct cftype *cft, struct seq_file *m)
{
        struct mem_cgroup *memcg = mem_cgroup_from_css(css);
        struct memcg_cache_params *params;

        if (!memcg_can_account_kmem(memcg))
                return -EIO;

        print_slabinfo_header(m);

        mutex_lock(&memcg->slab_caches_mutex);
        list_for_each_entry(params, &memcg->memcg_slab_caches, list)
                cache_show(memcg_params_to_cache(params), m);
        mutex_unlock(&memcg->slab_caches_mutex);

        return 0;
}
#endif

static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
{
        struct res_counter *fail_res;
        struct mem_cgroup *_memcg;
        int ret = 0;
        bool may_oom;

        ret = res_counter_charge(&memcg->kmem, size, &fail_res);
        if (ret)
                return ret;

        /*
         * Conditions under which we can wait for the oom_killer. Those are
         * the same conditions tested by the core page allocator
         */
        may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);

        _memcg = memcg;
        ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
                                      &_memcg, may_oom);

        if (ret == -EINTR)  {
                /*
                 * __mem_cgroup_try_charge() chosed to bypass to root due to
                 * OOM kill or fatal signal.  Since our only options are to
                 * either fail the allocation or charge it to this cgroup, do
                 * it as a temporary condition. But we can't fail. From a
                 * kmem/slab perspective, the cache has already been selected,
                 * by mem_cgroup_kmem_get_cache(), so it is too late to change
                 * our minds.
                 *
                 * This condition will only trigger if the task entered
                 * memcg_charge_kmem in a sane state, but was OOM-killed during
                 * __mem_cgroup_try_charge() above. Tasks that were already
                 * dying when the allocation triggers should have been already
                 * directed to the root cgroup in memcontrol.h
                 */
                res_counter_charge_nofail(&memcg->res, size, &fail_res);
                if (do_swap_account)
                        res_counter_charge_nofail(&memcg->memsw, size,
                                                  &fail_res);
                ret = 0;
        } else if (ret)
                res_counter_uncharge(&memcg->kmem, size);

        return ret;
}

static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
{
        res_counter_uncharge(&memcg->res, size);
        if (do_swap_account)
                res_counter_uncharge(&memcg->memsw, size);

        /* Not down to 0 */
        if (res_counter_uncharge(&memcg->kmem, size))
                return;

        /*
         * Releases a reference taken in kmem_cgroup_css_offline in case
         * this last uncharge is racing with the offlining code or it is
         * outliving the memcg existence.
         *
         * The memory barrier imposed by test&clear is paired with the
         * explicit one in memcg_kmem_mark_dead().
         */
        if (memcg_kmem_test_and_clear_dead(memcg))
                css_put(&memcg->css);
}

void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
{
        if (!memcg)
                return;

        mutex_lock(&memcg->slab_caches_mutex);
        list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
        mutex_unlock(&memcg->slab_caches_mutex);
}

/*
 * helper for acessing a memcg's index. It will be used as an index in the
 * child cache array in kmem_cache, and also to derive its name. This function
 * will return -1 when this is not a kmem-limited memcg.
 */
int memcg_cache_id(struct mem_cgroup *memcg)
{
        return memcg ? memcg->kmemcg_id : -1;
}

/*
 * This ends up being protected by the set_limit mutex, during normal
 * operation, because that is its main call site.
 *
 * But when we create a new cache, we can call this as well if its parent
 * is kmem-limited. That will have to hold set_limit_mutex as well.
 */
int memcg_update_cache_sizes(struct mem_cgroup *memcg)
{
        int num, ret;

        num = ida_simple_get(&kmem_limited_groups,
                                0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
        if (num < 0)
                return num;
        /*
         * After this point, kmem_accounted (that we test atomically in
         * the beginning of this conditional), is no longer 0. This
         * guarantees only one process will set the following boolean
         * to true. We don't need test_and_set because we're protected
         * by the set_limit_mutex anyway.
         */
        memcg_kmem_set_activated(memcg);

        ret = memcg_update_all_caches(num+1);
        if (ret) {
                ida_simple_remove(&kmem_limited_groups, num);
                memcg_kmem_clear_activated(memcg);
                return ret;
        }

        memcg->kmemcg_id = num;
        INIT_LIST_HEAD(&memcg->memcg_slab_caches);
        mutex_init(&memcg->slab_caches_mutex);
        return 0;
}

static size_t memcg_caches_array_size(int num_groups)
{
        ssize_t size;
        if (num_groups <= 0)
                return 0;

        size = 2 * num_groups;
        if (size < MEMCG_CACHES_MIN_SIZE)
                size = MEMCG_CACHES_MIN_SIZE;
        else if (size > MEMCG_CACHES_MAX_SIZE)
                size = MEMCG_CACHES_MAX_SIZE;

        return size;
}

/*
 * We should update the current array size iff all caches updates succeed. This
 * can only be done from the slab side. The slab mutex needs to be held when
 * calling this.
 */
void memcg_update_array_size(int num)
{
        if (num > memcg_limited_groups_array_size)
                memcg_limited_groups_array_size = memcg_caches_array_size(num);
}

static void kmem_cache_destroy_work_func(struct work_struct *w);

int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
{
        struct memcg_cache_params *cur_params = s->memcg_params;

        VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);

        if (num_groups > memcg_limited_groups_array_size) {
                int i;
                ssize_t size = memcg_caches_array_size(num_groups);

                size *= sizeof(void *);
                size += offsetof(struct memcg_cache_params, memcg_caches);

                s->memcg_params = kzalloc(size, GFP_KERNEL);
                if (!s->memcg_params) {
                        s->memcg_params = cur_params;
                        return -ENOMEM;
                }

                s->memcg_params->is_root_cache = true;

                /*
                 * There is the chance it will be bigger than
                 * memcg_limited_groups_array_size, if we failed an allocation
                 * in a cache, in which case all caches updated before it, will
                 * have a bigger array.
                 *
                 * But if that is the case, the data after
                 * memcg_limited_groups_array_size is certainly unused
                 */
                for (i = 0; i < memcg_limited_groups_array_size; i++) {
                        if (!cur_params->memcg_caches[i])
                                continue;
                        s->memcg_params->memcg_caches[i] =
                                                cur_params->memcg_caches[i];
                }

                /*
                 * Ideally, we would wait until all caches succeed, and only
                 * then free the old one. But this is not worth the extra
                 * pointer per-cache we'd have to have for this.
                 *
                 * It is not a big deal if some caches are left with a size
                 * bigger than the others. And all updates will reset this
                 * anyway.
                 */
                kfree(cur_params);
        }
        return 0;
}

int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
                         struct kmem_cache *root_cache)
{
        size_t size;

        if (!memcg_kmem_enabled())
                return 0;

        if (!memcg) {
                size = offsetof(struct memcg_cache_params, memcg_caches);
                size += memcg_limited_groups_array_size * sizeof(void *);
        } else
                size = sizeof(struct memcg_cache_params);

        s->memcg_params = kzalloc(size, GFP_KERNEL);
        if (!s->memcg_params)
                return -ENOMEM;

        if (memcg) {
                s->memcg_params->memcg = memcg;
                s->memcg_params->root_cache = root_cache;
                INIT_WORK(&s->memcg_params->destroy,
                                kmem_cache_destroy_work_func);
        } else
                s->memcg_params->is_root_cache = true;

        return 0;
}

void memcg_release_cache(struct kmem_cache *s)
{
        struct kmem_cache *root;
        struct mem_cgroup *memcg;
        int id;

        /*
         * This happens, for instance, when a root cache goes away before we
         * add any memcg.
         */
        if (!s->memcg_params)
                return;

        if (s->memcg_params->is_root_cache)
                goto out;

        memcg = s->memcg_params->memcg;
        id  = memcg_cache_id(memcg);

        root = s->memcg_params->root_cache;
        root->memcg_params->memcg_caches[id] = NULL;

        mutex_lock(&memcg->slab_caches_mutex);
        list_del(&s->memcg_params->list);
        mutex_unlock(&memcg->slab_caches_mutex);

        css_put(&memcg->css);
out:
        kfree(s->memcg_params);
}

/*
 * During the creation a new cache, we need to disable our accounting mechanism
 * altogether. This is true even if we are not creating, but rather just
 * enqueing new caches to be created.
 *
 * This is because that process will trigger allocations; some visible, like
 * explicit kmallocs to auxiliary data structures, name strings and internal
 * cache structures; some well concealed, like INIT_WORK() that can allocate
 * objects during debug.
 *
 * If any allocation happens during memcg_kmem_get_cache, we will recurse back
 * to it. This may not be a bounded recursion: since the first cache creation
 * failed to complete (waiting on the allocation), we'll just try to create the
 * cache again, failing at the same point.
 *
 * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
 * memcg_kmem_skip_account. So we enclose anything that might allocate memory
 * inside the following two functions.
 */
static inline void memcg_stop_kmem_account(void)
{
        VM_BUG_ON(!current->mm);
        current->memcg_kmem_skip_account++;
}

static inline void memcg_resume_kmem_account(void)
{
        VM_BUG_ON(!current->mm);
        current->memcg_kmem_skip_account--;
}

static void kmem_cache_destroy_work_func(struct work_struct *w)
{
        struct kmem_cache *cachep;
        struct memcg_cache_params *p;

        p = container_of(w, struct memcg_cache_params, destroy);

        cachep = memcg_params_to_cache(p);

        /*
         * If we get down to 0 after shrink, we could delete right away.
         * However, memcg_release_pages() already puts us back in the workqueue
         * in that case. If we proceed deleting, we'll get a dangling
         * reference, and removing the object from the workqueue in that case
         * is unnecessary complication. We are not a fast path.
         *
         * Note that this case is fundamentally different from racing with
         * shrink_slab(): if memcg_cgroup_destroy_cache() is called in
         * kmem_cache_shrink, not only we would be reinserting a dead cache
         * into the queue, but doing so from inside the worker racing to
         * destroy it.
         *
         * So if we aren't down to zero, we'll just schedule a worker and try
         * again
         */
        if (atomic_read(&cachep->memcg_params->nr_pages) != 0) {
                kmem_cache_shrink(cachep);
                if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
                        return;