mm/memcontrol.c

// SPDX-License-Identifier: GPL-2.0-or-later
/* 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
 *
 * Native page reclaim
 * Charge lifetime sanitation
 * Lockless page tracking & accounting
 * Unified hierarchy configuration model
 * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
 */

#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/vm_event_item.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/sort.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmpressure.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/file.h>
#include <linux/tracehook.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include "slab.h"

#include <linux/uaccess.h>

#include <trace/events/vmscan.h>

struct cgroup_subsys memory_cgrp_subsys __read_mostly;
EXPORT_SYMBOL(memory_cgrp_subsys);

struct mem_cgroup *root_mem_cgroup __read_mostly;

#define MEM_CGROUP_RECLAIM_RETRIES	5

/* Socket memory accounting disabled? */
static bool cgroup_memory_nosocket;

/* Kernel memory accounting disabled? */
static bool cgroup_memory_nokmem;

/* Whether the swap controller is active */
#ifdef CONFIG_MEMCG_SWAP
bool cgroup_memory_noswap __read_mostly;
#else
#define cgroup_memory_noswap		1
#endif

#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif

/* Whether legacy memory+swap accounting is active */
static bool do_memsw_account(void)
{
	return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap;
}

#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024

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

struct mem_cgroup_tree_per_node {
	struct rb_root rb_root;
	struct rb_node *rb_rightmost;
	spinlock_t lock;
};

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;

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

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

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

/* Stuffs for move charges at task migration. */
/*
 * Types of charges to be moved.
 */
#define MOVE_ANON	0x1U
#define MOVE_FILE	0x2U
#define MOVE_MASK	(MOVE_ANON | MOVE_FILE)

/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
	spinlock_t	  lock; /* for from, to */
	struct mm_struct  *mm;
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	unsigned long 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),
};

/*
 * 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,
	_TCP,
};

#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)

/*
 * 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))

static inline bool should_force_charge(void)
{
	return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
		(current->flags & PF_EXITING);
}

/* 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;
}

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

/* Protects memcg_nr_cache_ids */
static DECLARE_RWSEM(memcg_cache_ids_sem);

void memcg_get_cache_ids(void)
{
	down_read(&memcg_cache_ids_sem);
}

void memcg_put_cache_ids(void)
{
	up_read(&memcg_cache_ids_sem);
}

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

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

struct workqueue_struct *memcg_kmem_cache_wq;
#endif

static int memcg_shrinker_map_size;
static DEFINE_MUTEX(memcg_shrinker_map_mutex);

static void memcg_free_shrinker_map_rcu(struct rcu_head *head)
{
	kvfree(container_of(head, struct memcg_shrinker_map, rcu));
}

static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg,
					 int size, int old_size)
{
	struct memcg_shrinker_map *new, *old;
	int nid;

	lockdep_assert_held(&memcg_shrinker_map_mutex);

	for_each_node(nid) {
		old = rcu_dereference_protected(
			mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
		/* Not yet online memcg */
		if (!old)
			return 0;

		new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
		if (!new)
			return -ENOMEM;

		/* Set all old bits, clear all new bits */
		memset(new->map, (int)0xff, old_size);
		memset((void *)new->map + old_size, 0, size - old_size);

		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new);
		call_rcu(&old->rcu, memcg_free_shrinker_map_rcu);
	}

	return 0;
}

static void memcg_free_shrinker_maps(struct mem_cgroup *memcg)
{
	struct mem_cgroup_per_node *pn;
	struct memcg_shrinker_map *map;
	int nid;

	if (mem_cgroup_is_root(memcg))
		return;

	for_each_node(nid) {
		pn = mem_cgroup_nodeinfo(memcg, nid);
		map = rcu_dereference_protected(pn->shrinker_map, true);
		if (map)
			kvfree(map);
		rcu_assign_pointer(pn->shrinker_map, NULL);
	}
}

static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg)
{
	struct memcg_shrinker_map *map;
	int nid, size, ret = 0;

	if (mem_cgroup_is_root(memcg))
		return 0;

	mutex_lock(&memcg_shrinker_map_mutex);
	size = memcg_shrinker_map_size;
	for_each_node(nid) {
		map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
		if (!map) {
			memcg_free_shrinker_maps(memcg);
			ret = -ENOMEM;
			break;
		}
		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
	}
	mutex_unlock(&memcg_shrinker_map_mutex);

	return ret;
}

int memcg_expand_shrinker_maps(int new_id)
{
	int size, old_size, ret = 0;
	struct mem_cgroup *memcg;

	size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long);
	old_size = memcg_shrinker_map_size;
	if (size <= old_size)
		return 0;

	mutex_lock(&memcg_shrinker_map_mutex);
	if (!root_mem_cgroup)
		goto unlock;

	for_each_mem_cgroup(memcg) {
		if (mem_cgroup_is_root(memcg))
			continue;
		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
		if (ret) {
			mem_cgroup_iter_break(NULL, memcg);
			goto unlock;
		}
	}
unlock:
	if (!ret)
		memcg_shrinker_map_size = size;
	mutex_unlock(&memcg_shrinker_map_mutex);
	return ret;
}

void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
{
	if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
		struct memcg_shrinker_map *map;

		rcu_read_lock();
		map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
		/* Pairs with smp mb in shrink_slab() */
		smp_mb__before_atomic();
		set_bit(shrinker_id, map->map);
		rcu_read_unlock();
	}
}

/**
 * mem_cgroup_css_from_page - css of the memcg associated with a page
 * @page: page of interest
 *
 * If memcg is bound to the default hierarchy, css of the memcg associated
 * with @page is returned.  The returned css remains associated with @page
 * until it is released.
 *
 * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
 * is returned.
 */
struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
{
	struct mem_cgroup *memcg;

	memcg = page->mem_cgroup;

	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
		memcg = root_mem_cgroup;

	return &memcg->css;
}

/**
 * page_cgroup_ino - return inode number of the memcg a page is charged to
 * @page: the page
 *
 * Look up the closest online ancestor of the memory cgroup @page is charged to
 * and return its inode number or 0 if @page is not charged to any cgroup. It
 * is safe to call this function without holding a reference to @page.
 *
 * Note, this function is inherently racy, because there is nothing to prevent
 * the cgroup inode from getting torn down and potentially reallocated a moment
 * after page_cgroup_ino() returns, so it only should be used by callers that
 * do not care (such as procfs interfaces).
 */
ino_t page_cgroup_ino(struct page *page)
{
	struct mem_cgroup *memcg;
	unsigned long ino = 0;

	rcu_read_lock();
	if (PageSlab(page) && !PageTail(page))
		memcg = memcg_from_slab_page(page);
	else
		memcg = READ_ONCE(page->mem_cgroup);
	while (memcg && !(memcg->css.flags & CSS_ONLINE))
		memcg = parent_mem_cgroup(memcg);
	if (memcg)
		ino = cgroup_ino(memcg->css.cgroup);
	rcu_read_unlock();
	return ino;
}

static struct mem_cgroup_per_node *
mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
{
	int nid = page_to_nid(page);

	return memcg->nodeinfo[nid];
}

static struct mem_cgroup_tree_per_node *
soft_limit_tree_node(int nid)
{
	return soft_limit_tree.rb_tree_per_node[nid];
}

static struct mem_cgroup_tree_per_node *
soft_limit_tree_from_page(struct page *page)
{
	int nid = page_to_nid(page);

	return soft_limit_tree.rb_tree_per_node[nid];
}

static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
					 struct mem_cgroup_tree_per_node *mctz,
					 unsigned long new_usage_in_excess)
{
	struct rb_node **p = &mctz->rb_root.rb_node;
	struct rb_node *parent = NULL;
	struct mem_cgroup_per_node *mz_node;
	bool rightmost = true;

	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_node,
					tree_node);
		if (mz->usage_in_excess < mz_node->usage_in_excess) {
			p = &(*p)->rb_left;
			rightmost = false;
		}

		/*
		 * 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;
	}

	if (rightmost)
		mctz->rb_rightmost = &mz->tree_node;

	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_per_node *mz,
					 struct mem_cgroup_tree_per_node *mctz)
{
	if (!mz->on_tree)
		return;

	if (&mz->tree_node == mctz->rb_rightmost)
		mctz->rb_rightmost = rb_prev(&mz->tree_node);

	rb_erase(&mz->tree_node, &mctz->rb_root);
	mz->on_tree = false;
}

static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
				       struct mem_cgroup_tree_per_node *mctz)
{
	unsigned long flags;

	spin_lock_irqsave(&mctz->lock, flags);
	__mem_cgroup_remove_exceeded(mz, mctz);
	spin_unlock_irqrestore(&mctz->lock, flags);
}

static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
{
	unsigned long nr_pages = page_counter_read(&memcg->memory);
	unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
	unsigned long excess = 0;

	if (nr_pages > soft_limit)
		excess = nr_pages - soft_limit;

	return excess;
}

static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
{
	unsigned long excess;
	struct mem_cgroup_per_node *mz;
	struct mem_cgroup_tree_per_node *mctz;

	mctz = soft_limit_tree_from_page(page);
	if (!mctz)
		return;
	/*
	 * 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_page_nodeinfo(memcg, page);
		excess = soft_limit_excess(memcg);
		/*
		 * We have to update the tree if mz is on RB-tree or
		 * mem is over its softlimit.
		 */
		if (excess || mz->on_tree) {
			unsigned long flags;

			spin_lock_irqsave(&mctz->lock, flags);
			/* if on-tree, remove it */
			if (mz->on_tree)
				__mem_cgroup_remove_exceeded(mz, mctz);
			/*
			 * Insert again. mz->usage_in_excess will be updated.
			 * If excess is 0, no tree ops.
			 */
			__mem_cgroup_insert_exceeded(mz, mctz, excess);
			spin_unlock_irqrestore(&mctz->lock, flags);
		}
	}
}

static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
	struct mem_cgroup_tree_per_node *mctz;
	struct mem_cgroup_per_node *mz;
	int nid;

	for_each_node(nid) {
		mz = mem_cgroup_nodeinfo(memcg, nid);
		mctz = soft_limit_tree_node(nid);
		if (mctz)
			mem_cgroup_remove_exceeded(mz, mctz);
	}
}

static struct mem_cgroup_per_node *
__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
	struct mem_cgroup_per_node *mz;

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

	mz = rb_entry(mctz->rb_rightmost,
		      struct mem_cgroup_per_node, 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, mctz);
	if (!soft_limit_excess(mz->memcg) ||
	    !css_tryget(&mz->memcg->css))
		goto retry;
done:
	return mz;
}

static struct mem_cgroup_per_node *
mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
	struct mem_cgroup_per_node *mz;

	spin_lock_irq(&mctz->lock);
	mz = __mem_cgroup_largest_soft_limit_node(mctz);
	spin_unlock_irq(&mctz->lock);
	return mz;
}

/**
 * __mod_memcg_state - update cgroup memory statistics
 * @memcg: the memory cgroup
 * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
 * @val: delta to add to the counter, can be negative
 */
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
{
	long x;

	if (mem_cgroup_disabled())
		return;

	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup *mi;

		/*
		 * Batch local counters to keep them in sync with
		 * the hierarchical ones.
		 */
		__this_cpu_add(memcg->vmstats_local->stat[idx], x);
		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
			atomic_long_add(x, &mi->vmstats[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->vmstats_percpu->stat[idx], x);
}

static struct mem_cgroup_per_node *
parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
{
	struct mem_cgroup *parent;

	parent = parent_mem_cgroup(pn->memcg);
	if (!parent)
		return NULL;
	return mem_cgroup_nodeinfo(parent, nid);
}

/**
 * __mod_lruvec_state - update lruvec memory statistics
 * @lruvec: the lruvec
 * @idx: the stat item
 * @val: delta to add to the counter, can be negative
 *
 * The lruvec is the intersection of the NUMA node and a cgroup. This
 * function updates the all three counters that are affected by a
 * change of state at this level: per-node, per-cgroup, per-lruvec.
 */
void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
			int val)
{
	pg_data_t *pgdat = lruvec_pgdat(lruvec);
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup *memcg;
	long x;

	/* Update node */
	__mod_node_page_state(pgdat, idx, val);

	if (mem_cgroup_disabled())
		return;

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	memcg = pn->memcg;

	/* Update memcg */
	__mod_memcg_state(memcg, idx, val);

	/* Update lruvec */
	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);

	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup_per_node *pi;

		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
			atomic_long_add(x, &pi->lruvec_stat[idx]);
		x = 0;
	}
	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}

void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
{
	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	rcu_read_lock();
	memcg = mem_cgroup_from_obj(p);

	/* Untracked pages have no memcg, no lruvec. Update only the node */
	if (!memcg || memcg == root_mem_cgroup) {
		__mod_node_page_state(pgdat, idx, val);
	} else {
		lruvec = mem_cgroup_lruvec(memcg, pgdat);
		__mod_lruvec_state(lruvec, idx, val);
	}
	rcu_read_unlock();
}

void mod_memcg_obj_state(void *p, int idx, int val)
{
	struct mem_cgroup *memcg;

	rcu_read_lock();
	memcg = mem_cgroup_from_obj(p);
	if (memcg)
		mod_memcg_state(memcg, idx, val);
	rcu_read_unlock();
}

/**
 * __count_memcg_events - account VM events in a cgroup
 * @memcg: the memory cgroup
 * @idx: the event item
 * @count: the number of events that occured
 */
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
			  unsigned long count)
{
	unsigned long x;

	if (mem_cgroup_disabled())
		return;

	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup *mi;

		/*
		 * Batch local counters to keep them in sync with
		 * the hierarchical ones.
		 */
		__this_cpu_add(memcg->vmstats_local->events[idx], x);
		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
			atomic_long_add(x, &mi->vmevents[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->vmstats_percpu->events[idx], x);
}

static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
{
	return atomic_long_read(&memcg->vmevents[event]);
}

static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
{
	long x = 0;
	int cpu;

	for_each_possible_cpu(cpu)
		x += per_cpu(memcg->vmstats_local->events[event], cpu);
	return x;
}

static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
					 struct page *page,
					 int nr_pages)
{
	/* pagein of a big page is an event. So, ignore page size */
	if (nr_pages > 0)
		__count_memcg_events(memcg, PGPGIN, 1);
	else {
		__count_memcg_events(memcg, PGPGOUT, 1);
		nr_pages = -nr_pages; /* for event */
	}

	__this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages);
}

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->vmstats_percpu->nr_page_events);
	next = __this_cpu_read(memcg->vmstats_percpu->targets[target]);
	/* from time_after() in jiffies.h */
	if ((long)(next - 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;
		default:
			break;
		}
		__this_cpu_write(memcg->vmstats_percpu->targets[target], next);
		return true;
	}
	return false;
}

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

		do_softlimit = mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_SOFTLIMIT);
		mem_cgroup_threshold(memcg);
		if (unlikely(do_softlimit))
			mem_cgroup_update_tree(memcg, page);
	}
}

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, memory_cgrp_id));
}
EXPORT_SYMBOL(mem_cgroup_from_task);

/**
 * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg.
 * @mm: mm from which memcg should be extracted. It can be NULL.
 *
 * Obtain a reference on mm->memcg and returns it if successful. Otherwise
 * root_mem_cgroup is returned. However if mem_cgroup is disabled, NULL is
 * returned.
 */
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return NULL;

	rcu_read_lock();
	do {
		/*
		 * Page cache insertions can happen withou an
		 * actual mm context, e.g. during disk probing
		 * on boot, loopback IO, acct() writes etc.
		 */
		if (unlikely(!mm))
			memcg = root_mem_cgroup;
		else {
			memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
			if (unlikely(!memcg))
				memcg = root_mem_cgroup;
		}
	} while (!css_tryget(&memcg->css));
	rcu_read_unlock();
	return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);

/**
 * get_mem_cgroup_from_page: Obtain a reference on given page's memcg.
 * @page: page from which memcg should be extracted.
 *
 * Obtain a reference on page->memcg and returns it if successful. Otherwise
 * root_mem_cgroup is returned.
 */
struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
{
	struct mem_cgroup *memcg = page->mem_cgroup;

	if (mem_cgroup_disabled())
		return NULL;

	rcu_read_lock();
	/* Page should not get uncharged and freed memcg under us. */
	if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css)))
		memcg = root_mem_cgroup;
	rcu_read_unlock();
	return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_page);

/**
 * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
 */
static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
{
	if (unlikely(current->active_memcg)) {
		struct mem_cgroup *memcg;

		rcu_read_lock();
		/* current->active_memcg must hold a ref. */
		if (WARN_ON_ONCE(!css_tryget(&current->active_memcg->css)))
			memcg = root_mem_cgroup;
		else
			memcg = current->active_memcg;
		rcu_read_unlock();
		return memcg;
	}
	return get_mem_cgroup_from_mm(current->mm);
}

/**
 * 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 node and a priority level in @reclaim to
 * divide up the memcgs in the hierarchy among all concurrent
 * reclaimers operating on the same node 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_reclaim_iter *uninitialized_var(iter);
	struct cgroup_subsys_state *css = NULL;
	struct mem_cgroup *memcg = NULL;
	struct mem_cgroup *pos = NULL;

	if (mem_cgroup_disabled())
		return NULL;

	if (!root)
		root = root_mem_cgroup;

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

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

	rcu_read_lock();

	if (reclaim) {
		struct mem_cgroup_per_node *mz;

		mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
		iter = &mz->iter;

		if (prev && reclaim->generation != iter->generation)
			goto out_unlock;

		while (1) {
			pos = READ_ONCE(iter->position);
			if (!pos || css_tryget(&pos->css))
				break;
			/*
			 * css reference reached zero, so iter->position will
			 * be cleared by ->css_released. However, we should not
			 * rely on this happening soon, because ->css_released
			 * is called from a work queue, and by busy-waiting we
			 * might block it. So we clear iter->position right
			 * away.
			 */
			(void)cmpxchg(&iter->position, pos, NULL);
		}
	}

	if (pos)
		css = &pos->css;

	for (;;) {
		css = css_next_descendant_pre(css, &root->css);
		if (!css) {
			/*
			 * Reclaimers share the hierarchy walk, and a
			 * new one might jump in right at the end of
			 * the hierarchy - make sure they see at least
			 * one group and restart from the beginning.
			 */
			if (!prev)
				continue;
			break;
		}

		/*
		 * Verify the css and acquire a reference.  The root
		 * is provided by the caller, so we know it's alive
		 * and kicking, and don't take an extra reference.
		 */
		memcg = mem_cgroup_from_css(css);

		if (css == &root->css)
			break;

		if (css_tryget(css))
			break;

		memcg = NULL;
	}

	if (reclaim) {
		/*
		 * The position could have already been updated by a competing
		 * thread, so check that the value hasn't changed since we read
		 * it to avoid reclaiming from the same cgroup twice.
		 */
		(void)cmpxchg(&iter->position, pos, memcg);

		if (pos)
			css_put(&pos->css);

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

out_unlock:
	rcu_read_unlock();
out:
	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);
}

static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
					struct mem_cgroup *dead_memcg)
{
	struct mem_cgroup_reclaim_iter *iter;
	struct mem_cgroup_per_node *mz;
	int nid;

	for_each_node(nid) {
		mz = mem_cgroup_nodeinfo(from, nid);
		iter = &mz->iter;
		cmpxchg(&iter->position, dead_memcg, NULL);
	}
}

static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
{
	struct mem_cgroup *memcg = dead_memcg;
	struct mem_cgroup *last;

	do {
		__invalidate_reclaim_iterators(memcg, dead_memcg);
		last = memcg;
	} while ((memcg = parent_mem_cgroup(memcg)));

	/*
	 * When cgruop1 non-hierarchy mode is used,
	 * parent_mem_cgroup() does not walk all the way up to the
	 * cgroup root (root_mem_cgroup). So we have to handle
	 * dead_memcg from cgroup root separately.
	 */
	if (last != root_mem_cgroup)
		__invalidate_reclaim_iterators(root_mem_cgroup,
						dead_memcg);
}

/**
 * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
 * @memcg: hierarchy root
 * @fn: function to call for each task
 * @arg: argument passed to @fn
 *
 * This function iterates over tasks attached to @memcg or to any of its
 * descendants and calls @fn for each task. If @fn returns a non-zero
 * value, the function breaks the iteration loop and returns the value.
 * Otherwise, it will iterate over all tasks and return 0.
 *
 * This function must not be called for the root memory cgroup.
 */
int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
			  int (*fn)(struct task_struct *, void *), void *arg)
{
	struct mem_cgroup *iter;
	int ret = 0;

	BUG_ON(memcg == root_mem_cgroup);

	for_each_mem_cgroup_tree(iter, memcg) {
		struct css_task_iter it;
		struct task_struct *task;

		css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
		while (!ret && (task = css_task_iter_next(&it)))
			ret = fn(task, arg);
		css_task_iter_end(&it);
		if (ret) {
			mem_cgroup_iter_break(memcg, iter);
			break;
		}
	}
	return ret;
}

/**
 * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
 * @page: the page
 * @pgdat: pgdat of the page
 *
 * This function relies on page->mem_cgroup being stable - see the
 * access rules in commit_charge().
 */
struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
{
	struct mem_cgroup_per_node *mz;
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

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

	memcg = page->mem_cgroup;
	/*
	 * Swapcache readahead pages are added to the LRU - and
	 * possibly migrated - before they are charged.
	 */
	if (!memcg)
		memcg = root_mem_cgroup;

	mz = mem_cgroup_page_nodeinfo(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->pgdat != pgdat))
		lruvec->pgdat = pgdat;
	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
 * @zid: zone id of the accounted pages
 * @nr_pages: positive when adding or negative when removing
 *
 * This function must be called under lru_lock, just before a page is added
 * to or just after a page is removed from an lru list (that ordering being
 * so as to allow it to check that lru_size 0 is consistent with list_empty).
 */
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
				int zid, int nr_pages)
{
	struct mem_cgroup_per_node *mz;
	unsigned long *lru_size;
	long size;

	if (mem_cgroup_disabled())
		return;

	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	lru_size = &mz->lru_zone_size[zid][lru];

	if (nr_pages < 0)
		*lru_size += nr_pages;

	size = *lru_size;
	if (WARN_ONCE(size < 0,
		"%s(%p, %d, %d): lru_size %ld\n",
		__func__, lruvec, lru, nr_pages, size)) {
		VM_BUG_ON(1);
		*lru_size = 0;
	}

	if (nr_pages > 0)
		*lru_size += nr_pages;
}

/**
 * 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 margin = 0;
	unsigned long count;
	unsigned long limit;

	count = page_counter_read(&memcg->memory);
	limit = READ_ONCE(memcg->memory.max);
	if (count < limit)
		margin = limit - count;

	if (do_memsw_account()) {
		count = page_counter_read(&memcg->memsw);
		limit = READ_ONCE(memcg->memsw.max);
		if (count < limit)
			margin = min(margin, limit - count);
		else
			margin = 0;
	}

	return margin;
}

/*
 * A routine for checking "mem" is under move_account() or not.
 *
 * Checking a cgroup is mc.from or mc.to or under hierarchy of
 * moving cgroups. This is for waiting at high-memory pressure
 * caused by "move".
 */
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_is_descendant(from, memcg) ||
		mem_cgroup_is_descendant(to, memcg);
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;
}

static char *memory_stat_format(struct mem_cgroup *memcg)
{
	struct seq_buf s;
	int i;

	seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE);
	if (!s.buffer)
		return NULL;

	/*
	 * Provide statistics on the state of the memory subsystem as
	 * well as cumulative event counters that show past behavior.
	 *
	 * This list is ordered following a combination of these gradients:
	 * 1) generic big picture -> specifics and details
	 * 2) reflecting userspace activity -> reflecting kernel heuristics
	 *
	 * Current memory state:
	 */

	seq_buf_printf(&s, "anon %llu\n",
		       (u64)memcg_page_state(memcg, NR_ANON_MAPPED) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file %llu\n",
		       (u64)memcg_page_state(memcg, NR_FILE_PAGES) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "kernel_stack %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
		       1024);
	seq_buf_printf(&s, "slab %llu\n",
		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "sock %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
		       PAGE_SIZE);

	seq_buf_printf(&s, "shmem %llu\n",
		       (u64)memcg_page_state(memcg, NR_SHMEM) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_mapped %llu\n",
		       (u64)memcg_page_state(memcg, NR_FILE_MAPPED) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_dirty %llu\n",
		       (u64)memcg_page_state(memcg, NR_FILE_DIRTY) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_writeback %llu\n",
		       (u64)memcg_page_state(memcg, NR_WRITEBACK) *
		       PAGE_SIZE);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	seq_buf_printf(&s, "anon_thp %llu\n",
		       (u64)memcg_page_state(memcg, NR_ANON_THPS) *
		       HPAGE_PMD_SIZE);
#endif

	for (i = 0; i < NR_LRU_LISTS; i++)
		seq_buf_printf(&s, "%s %llu\n", lru_list_name(i),
			       (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
			       PAGE_SIZE);

	seq_buf_printf(&s, "slab_reclaimable %llu\n",
		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "slab_unreclaimable %llu\n",
		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
		       PAGE_SIZE);

	/* Accumulated memory events */

	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT),
		       memcg_events(memcg, PGFAULT));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT),
		       memcg_events(memcg, PGMAJFAULT));

	seq_buf_printf(&s, "workingset_refault %lu\n",
		       memcg_page_state(memcg, WORKINGSET_REFAULT));
	seq_buf_printf(&s, "workingset_activate %lu\n",
		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
	seq_buf_printf(&s, "workingset_restore %lu\n",
		       memcg_page_state(memcg, WORKINGSET_RESTORE));
	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));

	seq_buf_printf(&s, "%s %lu\n",  vm_event_name(PGREFILL),
		       memcg_events(memcg, PGREFILL));
	seq_buf_printf(&s, "pgscan %lu\n",
		       memcg_events(memcg, PGSCAN_KSWAPD) +
		       memcg_events(memcg, PGSCAN_DIRECT));
	seq_buf_printf(&s, "pgsteal %lu\n",
		       memcg_events(memcg, PGSTEAL_KSWAPD) +
		       memcg_events(memcg, PGSTEAL_DIRECT));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE),
		       memcg_events(memcg, PGACTIVATE));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE),
		       memcg_events(memcg, PGDEACTIVATE));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE),
		       memcg_events(memcg, PGLAZYFREE));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED),
		       memcg_events(memcg, PGLAZYFREED));

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC),
		       memcg_events(memcg, THP_FAULT_ALLOC));
	seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC),
		       memcg_events(memcg, THP_COLLAPSE_ALLOC));
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

	/* The above should easily fit into one page */
	WARN_ON_ONCE(seq_buf_has_overflowed(&s));

	return s.buffer;
}

#define K(x) ((x) << (PAGE_SHIFT-10))
/**
 * mem_cgroup_print_oom_context: 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_context(struct mem_cgroup *memcg, struct task_struct *p)
{
	rcu_read_lock();

	if (memcg) {
		pr_cont(",oom_memcg=");
		pr_cont_cgroup_path(memcg->css.cgroup);
	} else
		pr_cont(",global_oom");
	if (p) {
		pr_cont(",task_memcg=");
		pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
	}
	rcu_read_unlock();
}

/**
 * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
 * memory controller.
 * @memcg: The memory cgroup that went over limit
 */
void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{
	char *buf;

	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
		K((u64)page_counter_read(&memcg->memory)),
		K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt);
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->swap)),
			K((u64)READ_ONCE(memcg->swap.max)), memcg->swap.failcnt);
	else {
		pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->memsw)),
			K((u64)memcg->memsw.max), memcg->memsw.failcnt);
		pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->kmem)),
			K((u64)memcg->kmem.max), memcg->kmem.failcnt);
	}

	pr_info("Memory cgroup stats for ");
	pr_cont_cgroup_path(memcg->css.cgroup);
	pr_cont(":");
	buf = memory_stat_format(memcg);
	if (!buf)
		return;
	pr_info("%s", buf);
	kfree(buf);
}

/*
 * Return the memory (and swap, if configured) limit for a memcg.
 */
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
	unsigned long max;

	max = READ_ONCE(memcg->memory.max);
	if (mem_cgroup_swappiness(memcg)) {
		unsigned long memsw_max;
		unsigned long swap_max;

		memsw_max = memcg->memsw.max;
		swap_max = READ_ONCE(memcg->swap.max);
		swap_max = min(swap_max, (unsigned long)total_swap_pages);
		max = min(max + swap_max, memsw_max);
	}
	return max;
}

unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
{
	return page_counter_read(&memcg->memory);
}

static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
				     int order)
{
	struct oom_control oc = {
		.zonelist = NULL,
		.nodemask = NULL,
		.memcg = memcg,
		.gfp_mask = gfp_mask,
		.order = order,
	};
	bool ret;

	if (mutex_lock_killable(&oom_lock))
		return true;
	/*
	 * A few threads which were not waiting at mutex_lock_killable() can
	 * fail to bail out. Therefore, check again after holding oom_lock.
	 */
	ret = should_force_charge() || out_of_memory(&oc);
	mutex_unlock(&oom_lock);
	return ret;
}

static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
				   pg_data_t *pgdat,
				   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 = {
		.pgdat = pgdat,
	};

	excess = soft_limit_excess(root_memcg);

	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;
		}
		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
					pgdat, &nr_scanned);
		*total_scanned += nr_scanned;
		if (!soft_limit_excess(root_memcg))
			break;
	}
	mem_cgroup_iter_break(root_memcg, victim);
	return total;
}

#ifdef CONFIG_LOCKDEP
static struct lockdep_map memcg_oom_lock_dep_map = {
	.name = "memcg_oom_lock",
};
#endif

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;
		}
	} else
		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);

	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);
	mutex_release(&memcg_oom_lock_dep_map, _RET_IP_);
	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;

	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		iter->under_oom++;
	spin_unlock(&memcg_oom_lock);
}

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. Watch for underflow.
	 */
	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		if (iter->under_oom > 0)
			iter->under_oom--;
	spin_unlock(&memcg_oom_lock);
}

static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);

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

static int memcg_oom_wake_function(wait_queue_entry_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;

	if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
	    !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
		return 0;
	return autoremove_wake_function(wait, mode, sync, arg);
}

static void memcg_oom_recover(struct mem_cgroup *memcg)
{
	/*
	 * For the following lockless ->under_oom test, the only required
	 * guarantee is that it must see the state asserted by an OOM when
	 * this function is called as a result of userland actions
	 * triggered by the notification of the OOM.  This is trivially
	 * achieved by invoking mem_cgroup_mark_under_oom() before
	 * triggering notification.
	 */
	if (memcg && memcg->under_oom)
		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}

enum oom_status {
	OOM_SUCCESS,
	OOM_FAILED,
	OOM_ASYNC,
	OOM_SKIPPED
};

static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
	enum oom_status ret;
	bool locked;

	if (order > PAGE_ALLOC_COSTLY_ORDER)
		return OOM_SKIPPED;

	memcg_memory_event(memcg, MEMCG_OOM);

	/*
	 * 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.
	 *
	 * cgroup1 allows disabling the OOM killer and waiting for outside
	 * handling until the charge can succeed; remember the context and put
	 * the task to sleep at the end of the page fault when all locks are
	 * released.
	 *
	 * On the other hand, in-kernel OOM killer allows for an async victim
	 * memory reclaim (oom_reaper) and that means that we are not solely
	 * relying on the oom victim to make a forward progress and we can
	 * invoke the oom killer here.
	 *
	 * Please note that mem_cgroup_out_of_memory might fail to find a
	 * victim and then we have to bail out from the charge path.
	 */
	if (memcg->oom_kill_disable) {
		if (!current->in_user_fault)
			return OOM_SKIPPED;
		css_get(&memcg->css);
		current->memcg_in_oom = memcg;
		current->memcg_oom_gfp_mask = mask;
		current->memcg_oom_order = order;

		return OOM_ASYNC;
	}

	mem_cgroup_mark_under_oom(memcg);

	locked = mem_cgroup_oom_trylock(memcg);

	if (locked)
		mem_cgroup_oom_notify(memcg);

	mem_cgroup_unmark_under_oom(memcg);
	if (mem_cgroup_out_of_memory(memcg, mask, order))
		ret = OOM_SUCCESS;
	else
		ret = OOM_FAILED;

	if (locked)
		mem_cgroup_oom_unlock(memcg);

	return ret;
}

/**
 * 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_in_oom;
	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.entry);

	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_in_oom = NULL;
	css_put(&memcg->css);
	return true;
}

/**
 * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM
 * @victim: task to be killed by the OOM killer
 * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM
 *
 * Returns a pointer to a memory cgroup, which has to be cleaned up
 * by killing all belonging OOM-killable tasks.
 *
 * Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
 */
struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
					    struct mem_cgroup *oom_domain)
{
	struct mem_cgroup *oom_group = NULL;
	struct mem_cgroup *memcg;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return NULL;

	if (!oom_domain)
		oom_domain = root_mem_cgroup;

	rcu_read_lock();

	memcg = mem_cgroup_from_task(victim);
	if (memcg == root_mem_cgroup)
		goto out;

	/*
	 * If the victim task has been asynchronously moved to a different
	 * memory cgroup, we might end up killing tasks outside oom_domain.
	 * In this case it's better to ignore memory.group.oom.
	 */
	if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain)))
		goto out;

	/*
	 * Traverse the memory cgroup hierarchy from the victim task's
	 * cgroup up to the OOMing cgroup (or root) to find the
	 * highest-level memory cgroup with oom.group set.
	 */
	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
		if (memcg->oom_group)
			oom_group = memcg;

		if (memcg == oom_domain)
			break;
	}

	if (oom_group)
		css_get(&oom_group->css);
out:
	rcu_read_unlock();

	return oom_group;
}

void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
{
	pr_info("Tasks in ");
	pr_cont_cgroup_path(memcg->css.cgroup);
	pr_cont(" are going to be killed due to memory.oom.group set\n");
}

/**
 * lock_page_memcg - lock a page->mem_cgroup binding
 * @page: the page
 *
 * This function protects unlocked LRU pages from being moved to
 * another cgroup.
 *
 * It ensures lifetime of the returned memcg. Caller is responsible
 * for the lifetime of the page; __unlock_page_memcg() is available
 * when @page might get freed inside the locked section.
 */
struct mem_cgroup *lock_page_memcg(struct page *page)
{
	struct page *head = compound_head(page); /* rmap on tail pages */
	struct mem_cgroup *memcg;
	unsigned long flags;

	/*
	 * The RCU lock is held throughout the transaction.  The fast
	 * path can get away without acquiring the memcg->move_lock
	 * because page moving starts with an RCU grace period.
	 *
	 * The RCU lock also protects the memcg from being freed when
	 * the page state that is going to change is the only thing
	 * preventing the page itself from being freed. E.g. writeback
	 * doesn't hold a page reference and relies on PG_writeback to
	 * keep off truncation, migration and so forth.
         */
	rcu_read_lock();

	if (mem_cgroup_disabled())
		return NULL;
again:
	memcg = head->mem_cgroup;
	if (unlikely(!memcg))
		return NULL;

	if (atomic_read(&memcg->moving_account) <= 0)
		return memcg;

	spin_lock_irqsave(&memcg->move_lock, flags);
	if (memcg != head->mem_cgroup) {
		spin_unlock_irqrestore(&memcg->move_lock, flags);
		goto again;
	}

	/*
	 * When charge migration first begins, we can have locked and
	 * unlocked page stat updates happening concurrently.  Track
	 * the task who has the lock for unlock_page_memcg().
	 */
	memcg->move_lock_task = current;
	memcg->move_lock_flags = flags;

	return memcg;
}
EXPORT_SYMBOL(lock_page_memcg);

/**
 * __unlock_page_memcg - unlock and unpin a memcg
 * @memcg: the memcg
 *
 * Unlock and unpin a memcg returned by lock_page_memcg().
 */
void __unlock_page_memcg(struct mem_cgroup *memcg)
{
	if (memcg && memcg->move_lock_task == current) {
		unsigned long flags = memcg->move_lock_flags;

		memcg->move_lock_task = NULL;
		memcg->move_lock_flags = 0;

		spin_unlock_irqrestore(&memcg->move_lock, flags);
	}

	rcu_read_unlock();
}

/**
 * unlock_page_memcg - unlock a page->mem_cgroup binding
 * @page: the page
 */
void unlock_page_memcg(struct page *page)
{
	struct page *head = compound_head(page);

	__unlock_page_memcg(head->mem_cgroup);
}
EXPORT_SYMBOL(unlock_page_memcg);

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;
	unsigned long flags;
	bool ret = false;

	if (nr_pages > MEMCG_CHARGE_BATCH)
		return ret;

	local_irq_save(flags);

	stock = this_cpu_ptr(&memcg_stock);
	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
		stock->nr_pages -= nr_pages;
		ret = true;
	}

	local_irq_restore(flags);

	return ret;
}

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

	if (stock->nr_pages) {
		page_counter_uncharge(&old->memory, stock->nr_pages);
		if (do_memsw_account())
			page_counter_uncharge(&old->memsw, stock->nr_pages);
		css_put_many(&old->css, stock->nr_pages);
		stock->nr_pages = 0;
	}
	stock->cached = NULL;
}

static void drain_local_stock(struct work_struct *dummy)
{
	struct memcg_stock_pcp *stock;
	unsigned long flags;

	/*
	 * The only protection from memory hotplug vs. drain_stock races is
	 * that we always operate on local CPU stock here with IRQ disabled
	 */
	local_irq_save(flags);

	stock = this_cpu_ptr(&memcg_stock);
	drain_stock(stock);
	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);

	local_irq_restore(flags);
}

/*
 * Cache charges(val) 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;
	unsigned long flags;

	local_irq_save(flags);

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

	if (stock->nr_pages > MEMCG_CHARGE_BATCH)
		drain_stock(stock);

	local_irq_restore(flags);
}

/*
 * Drains all per-CPU charge caches for given root_memcg resp. subtree
 * of the hierarchy under it.
 */
static void drain_all_stock(struct mem_cgroup *root_memcg)
{
	int cpu, curcpu;

	/* If someone's already draining, avoid adding running more workers. */
	if (!mutex_trylock(&percpu_charge_mutex))
		return;
	/*
	 * Notify other cpus that system-wide "drain" is running
	 * We do not care about races with the cpu hotplug because cpu down
	 * as well as workers from this path always operate on the local
	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
	 */
	curcpu = get_cpu();
	for_each_online_cpu(cpu) {
		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
		struct mem_cgroup *memcg;
		bool flush = false;

		rcu_read_lock();
		memcg = stock->cached;
		if (memcg && stock->nr_pages &&
		    mem_cgroup_is_descendant(memcg, root_memcg))
			flush = true;
		rcu_read_unlock();

		if (flush &&
		    !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();
	mutex_unlock(&percpu_charge_mutex);
}

static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
	struct memcg_stock_pcp *stock;
	struct mem_cgroup *memcg, *mi;

	stock = &per_cpu(memcg_stock, cpu);
	drain_stock(stock);

	for_each_mem_cgroup(memcg) {
		int i;

		for (i = 0; i < MEMCG_NR_STAT; i++) {
			int nid;
			long x;

			x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0);
			if (x)
				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
					atomic_long_add(x, &memcg->vmstats[i]);

			if (i >= NR_VM_NODE_STAT_ITEMS)
				continue;

			for_each_node(nid) {
				struct mem_cgroup_per_node *pn;

				pn = mem_cgroup_nodeinfo(memcg, nid);
				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
				if (x)
					do {
						atomic_long_add(x, &pn->lruvec_stat[i]);
					} while ((pn = parent_nodeinfo(pn, nid)));
			}
		}

		for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
			long x;

			x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0);
			if (x)
				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
					atomic_long_add(x, &memcg->vmevents[i]);
		}
	}

	return 0;
}

static void reclaim_high(struct mem_cgroup *memcg,
			 unsigned int nr_pages,
			 gfp_t gfp_mask)
{
	do {
		if (page_counter_read(&memcg->memory) <=
		    READ_ONCE(memcg->memory.high))
			continue;
		memcg_memory_event(memcg, MEMCG_HIGH);
		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));
}

static void high_work_func(struct work_struct *work)
{
	struct mem_cgroup *memcg;

	memcg = container_of(work, struct mem_cgroup, high_work);
	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}

/*
 * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
 * enough to still cause a significant slowdown in most cases, while still
 * allowing diagnostics and tracing to proceed without becoming stuck.
 */
#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)

/*
 * When calculating the delay, we use these either side of the exponentiation to
 * maintain precision and scale to a reasonable number of jiffies (see the table
 * below.
 *
 * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
 *   overage ratio to a delay.
 * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down down the
 *   proposed penalty in order to reduce to a reasonable number of jiffies, and
 *   to produce a reasonable delay curve.
 *
 * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
 * reasonable delay curve compared to precision-adjusted overage, not
 * penalising heavily at first, but still making sure that growth beyond the
 * limit penalises misbehaviour cgroups by slowing them down exponentially. For
 * example, with a high of 100 megabytes:
 *
 *  +-------+------------------------+
 *  | usage | time to allocate in ms |
 *  +-------+------------------------+
 *  | 100M  |                      0 |
 *  | 101M  |                      6 |
 *  | 102M  |                     25 |
 *  | 103M  |                     57 |
 *  | 104M  |                    102 |
 *  | 105M  |                    159 |
 *  | 106M  |                    230 |
 *  | 107M  |                    313 |
 *  | 108M  |                    409 |
 *  | 109M  |                    518 |
 *  | 110M  |                    639 |
 *  | 111M  |                    774 |
 *  | 112M  |                    921 |
 *  | 113M  |                   1081 |
 *  | 114M  |                   1254 |
 *  | 115M  |                   1439 |
 *  | 116M  |                   1638 |
 *  | 117M  |                   1849 |
 *  | 118M  |                   2000 |
 *  | 119M  |                   2000 |
 *  | 120M  |                   2000 |
 *  +-------+------------------------+
 */
 #define MEMCG_DELAY_PRECISION_SHIFT 20
 #define MEMCG_DELAY_SCALING_SHIFT 14

static u64 calculate_overage(unsigned long usage, unsigned long high)
{
	u64 overage;

	if (usage <= high)
		return 0;

	/*
	 * Prevent division by 0 in overage calculation by acting as if
	 * it was a threshold of 1 page
	 */
	high = max(high, 1UL);

	overage = usage - high;
	overage <<= MEMCG_DELAY_PRECISION_SHIFT;
	return div64_u64(overage, high);
}

static u64 mem_find_max_overage(struct mem_cgroup *memcg)
{
	u64 overage, max_overage = 0;

	do {
		overage = calculate_overage(page_counter_read(&memcg->memory),
					    READ_ONCE(memcg->memory.high));
		max_overage = max(overage, max_overage);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));

	return max_overage;
}

static u64 swap_find_max_overage(struct mem_cgroup *memcg)
{
	u64 overage, max_overage = 0;

	do {
		overage = calculate_overage(page_counter_read(&memcg->swap),
					    READ_ONCE(memcg->swap.high));
		if (overage)
			memcg_memory_event(memcg, MEMCG_SWAP_HIGH);
		max_overage = max(overage, max_overage);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));

	return max_overage;
}

/*
 * Get the number of jiffies that we should penalise a mischievous cgroup which
 * is exceeding its memory.high by checking both it and its ancestors.
 */
static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
					  unsigned int nr_pages,
					  u64 max_overage)
{
	unsigned long penalty_jiffies;

	if (!max_overage)
		return 0;

	/*
	 * We use overage compared to memory.high to calculate the number of
	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
	 * fairly lenient on small overages, and increasingly harsh when the
	 * memcg in question makes it clear that it has no intention of stopping
	 * its crazy behaviour, so we exponentially increase the delay based on
	 * overage amount.
	 */
	penalty_jiffies = max_overage * max_overage * HZ;
	penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
	penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;

	/*
	 * Factor in the task's own contribution to the overage, such that four
	 * N-sized allocations are throttled approximately the same as one
	 * 4N-sized allocation.
	 *
	 * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
	 * larger the current charge patch is than that.
	 */
	return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
}

/*
 * Scheduled by try_charge() to be executed from the userland return path
 * and reclaims memory over the high limit.
 */
void mem_cgroup_handle_over_high(void)
{
	unsigned long penalty_jiffies;
	unsigned long pflags;
	unsigned int nr_pages = current->memcg_nr_pages_over_high;
	struct mem_cgroup *memcg;

	if (likely(!nr_pages))
		return;

	memcg = get_mem_cgroup_from_mm(current->mm);
	reclaim_high(memcg, nr_pages, GFP_KERNEL);
	current->memcg_nr_pages_over_high = 0;

	/*
	 * memory.high is breached and reclaim is unable to keep up. Throttle
	 * allocators proactively to slow down excessive growth.
	 */
	penalty_jiffies = calculate_high_delay(memcg, nr_pages,
					       mem_find_max_overage(memcg));

	penalty_jiffies += calculate_high_delay(memcg, nr_pages,
						swap_find_max_overage(memcg));

	/*
	 * Clamp the max delay per usermode return so as to still keep the
	 * application moving forwards and also permit diagnostics, albeit
	 * extremely slowly.
	 */
	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);

	/*
	 * Don't sleep if the amount of jiffies this memcg owes us is so low
	 * that it's not even worth doing, in an attempt to be nice to those who
	 * go only a small amount over their memory.high value and maybe haven't
	 * been aggressively reclaimed enough yet.
	 */
	if (penalty_jiffies <= HZ / 100)
		goto out;

	/*
	 * If we exit early, we're guaranteed to die (since
	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
	 * need to account for any ill-begotten jiffies to pay them off later.
	 */
	psi_memstall_enter(&pflags);
	schedule_timeout_killable(penalty_jiffies);
	psi_memstall_leave(&pflags);

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

static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
		      unsigned int nr_pages)
{
	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct mem_cgroup *mem_over_limit;
	struct page_counter *counter;
	unsigned long nr_reclaimed;
	bool may_swap = true;
	bool drained = false;
	enum oom_status oom_status;

	if (mem_cgroup_is_root(memcg))
		return 0;
retry:
	if (consume_stock(memcg, nr_pages))
		return 0;

	if (!do_memsw_account() ||
	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
		if (page_counter_try_charge(&memcg->memory, batch, &counter))
			goto done_restock;
		if (do_memsw_account())
			page_counter_uncharge(&memcg->memsw, batch);
		mem_over_limit = mem_cgroup_from_counter(counter, memory);
	} else {
		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
		may_swap = false;
	}

	if (batch > nr_pages) {
		batch = nr_pages;
		goto retry;
	}

	/*
	 * Memcg doesn't have a dedicated reserve for atomic
	 * allocations. But like the global atomic pool, we need to
	 * put the burden of reclaim on regular allocation requests
	 * and let these go through as privileged allocations.
	 */
	if (gfp_mask & __GFP_ATOMIC)
		goto force;

	/*
	 * Unlike in global OOM situations, memcg is not in a physical
	 * memory shortage.  Allow dying and OOM-killed tasks to
	 * bypass the last charges so that they can exit quickly and
	 * free their memory.
	 */
	if (unlikely(should_force_charge()))
		goto force;

	/*
	 * Prevent unbounded recursion when reclaim operations need to
	 * allocate memory. This might exceed the limits temporarily,
	 * but we prefer facilitating memory reclaim and getting back
	 * under the limit over triggering OOM kills in these cases.
	 */
	if (unlikely(current->flags & PF_MEMALLOC))
		goto force;

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

	if (!gfpflags_allow_blocking(gfp_mask))
		goto nomem;

	memcg_memory_event(mem_over_limit, MEMCG_MAX);

	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
						    gfp_mask, may_swap);

	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
		goto retry;

	if (!drained) {
		drain_all_stock(mem_over_limit);
		drained = true;
		goto retry;
	}

	if (gfp_mask & __GFP_NORETRY)
		goto nomem;
	/*
	 * 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_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER))
		goto 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))
		goto retry;

	if (nr_retries--)
		goto retry;

	if (gfp_mask & __GFP_RETRY_MAYFAIL)
		goto nomem;

	if (gfp_mask & __GFP_NOFAIL)
		goto force;

	if (fatal_signal_pending(current))
		goto force;

	/*
	 * keep retrying as long as the memcg oom killer is able to make
	 * a forward progress or bypass the charge if the oom killer
	 * couldn't make any progress.
	 */
	oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask,
		       get_order(nr_pages * PAGE_SIZE));
	switch (oom_status) {
	case OOM_SUCCESS:
		nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
		goto retry;
	case OOM_FAILED:
		goto force;
	default:
		goto nomem;
	}
nomem:
	if (!(gfp_mask & __GFP_NOFAIL))
		return -ENOMEM;
force:
	/*
	 * The allocation either can't fail or will lead to more memory
	 * being freed very soon.  Allow memory usage go over the limit
	 * temporarily by force charging it.
	 */
	page_counter_charge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_charge(&memcg->memsw, nr_pages);
	css_get_many(&memcg->css, nr_pages);

	return 0;

done_restock:
	css_get_many(&memcg->css, batch);
	if (batch > nr_pages)
		refill_stock(memcg, batch - nr_pages);

	/*
	 * If the hierarchy is above the normal consumption range, schedule
	 * reclaim on returning to userland.  We can perform reclaim here
	 * if __GFP_RECLAIM but let's always punt for simplicity and so that
	 * GFP_KERNEL can consistently be used during reclaim.  @memcg is
	 * not recorded as it most likely matches current's and won't
	 * change in the meantime.  As high limit is checked again before
	 * reclaim, the cost of mismatch is negligible.
	 */
	do {
		bool mem_high, swap_high;

		mem_high = page_counter_read(&memcg->memory) >
			READ_ONCE(memcg->memory.high);
		swap_high = page_counter_read(&memcg->swap) >
			READ_ONCE(memcg->swap.high);

		/* Don't bother a random interrupted task */
		if (in_interrupt()) {
			if (mem_high) {
				schedule_work(&memcg->high_work);
				break;
			}
			continue;
		}

		if (mem_high || swap_high) {
			/*
			 * The allocating tasks in this cgroup will need to do
			 * reclaim or be throttled to prevent further growth
			 * of the memory or swap footprints.
			 *
			 * Target some best-effort fairness between the tasks,
			 * and distribute reclaim work and delay penalties
			 * based on how much each task is actually allocating.
			 */
			current->memcg_nr_pages_over_high += batch;
			set_notify_resume(current);
			break;
		}
	} while ((memcg = parent_mem_cgroup(memcg)));

	return 0;
}

#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU)
static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	if (mem_cgroup_is_root(memcg))
		return;

	page_counter_uncharge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_uncharge(&memcg->memsw, nr_pages);

	css_put_many(&memcg->css, nr_pages);
}
#endif

static void commit_charge(struct page *page, struct mem_cgroup *memcg)
{
	VM_BUG_ON_PAGE(page->mem_cgroup, page);
	/*
	 * Any of the following ensures page->mem_cgroup stability:
	 *
	 * - the page lock
	 * - LRU isolation
	 * - lock_page_memcg()
	 * - exclusive reference
	 */
	page->mem_cgroup = memcg;
}

#ifdef CONFIG_MEMCG_KMEM
/*
 * Returns a pointer to the memory cgroup to which the kernel object is charged.
 *
 * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
 * cgroup_mutex, etc.
 */
struct mem_cgroup *mem_cgroup_from_obj(void *p)
{
	struct page *page;

	if (mem_cgroup_disabled())
		return NULL;

	page = virt_to_head_page(p);

	/*
	 * Slab pages don't have page->mem_cgroup set because corresponding
	 * kmem caches can be reparented during the lifetime. That's why
	 * memcg_from_slab_page() should be used instead.
	 */
	if (PageSlab(page))
		return memcg_from_slab_page(page);

	/* All other pages use page->mem_cgroup */
	return page->mem_cgroup;
}

static int memcg_alloc_cache_id(void)
{
	int id, size;
	int err;

	id = ida_simple_get(&memcg_cache_ida,
			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
	if (id < 0)
		return id;

	if (id < memcg_nr_cache_ids)
		return id;

	/*
	 * There's no space for the new id in memcg_caches arrays,
	 * so we have to grow them.
	 */
	down_write(&memcg_cache_ids_sem);

	size = 2 * (id + 1);
	if (size < MEMCG_CACHES_MIN_SIZE)
		size = MEMCG_CACHES_MIN_SIZE;
	else if (size > MEMCG_CACHES_MAX_SIZE)
		size = MEMCG_CACHES_MAX_SIZE;

	err = memcg_update_all_caches(size);
	if (!err)
		err = memcg_update_all_list_lrus(size);
	if (!err)
		memcg_nr_cache_ids = size;

	up_write(&memcg_cache_ids_sem);

	if (err) {
		ida_simple_remove(&memcg_cache_ida, id);
		return err;
	}
	return id;
}

static void memcg_free_cache_id(int id)
{
	ida_simple_remove(&memcg_cache_ida, id);
}

struct memcg_kmem_cache_create_work {
	struct mem_cgroup *memcg;
	struct kmem_cache *cachep;
	struct work_struct work;
};

static void memcg_kmem_cache_create_func(struct work_struct *w)
{
	struct memcg_kmem_cache_create_work *cw =
		container_of(w, struct memcg_kmem_cache_create_work, work);
	struct mem_cgroup *memcg = cw->memcg;
	struct kmem_cache *cachep = cw->cachep;

	memcg_create_kmem_cache(memcg, cachep);

	css_put(&memcg->css);
	kfree(cw);
}

/*
 * Enqueue the creation of a per-memcg kmem_cache.
 */
static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
					       struct kmem_cache *cachep)
{
	struct memcg_kmem_cache_create_work *cw;

	if (!css_tryget_online(&memcg->css))
		return;

	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
	if (!cw)
		return;

	cw->memcg = memcg;
	cw->cachep = cachep;
	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);

	queue_work(memcg_kmem_cache_wq, &cw->work);
}

static inline bool memcg_kmem_bypass(void)
{
	if (in_interrupt())
		return true;

	/* Allow remote memcg charging in kthread contexts. */
	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
	     !current->active_memcg)
		return true;
	return false;
}

/**
 * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
 * @cachep: the original global kmem cache
 *
 * Return the kmem_cache we're supposed to use for a slab allocation.
 * We try to use the current memcg's version of the cache.
 *
 * If the cache does not exist yet, if we are the first user of it, we
 * create it asynchronously in a workqueue and let the current allocation
 * go through with the original cache.
 *
 * This function takes a reference to the cache it returns to assure it
 * won't get destroyed while we are working with it. Once the caller is
 * done with it, memcg_kmem_put_cache() must be called to release the
 * reference.
 */
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
{
	struct mem_cgroup *memcg;
	struct kmem_cache *memcg_cachep;
	struct memcg_cache_array *arr;
	int kmemcg_id;

	VM_BUG_ON(!is_root_cache(cachep));

	if (memcg_kmem_bypass())
		return cachep;

	rcu_read_lock();

	if (unlikely(current->active_memcg))
		memcg = current->active_memcg;
	else
		memcg = mem_cgroup_from_task(current);

	if (!memcg || memcg == root_mem_cgroup)
		goto out_unlock;

	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
	if (kmemcg_id < 0)
		goto out_unlock;

	arr = rcu_dereference(cachep->memcg_params.memcg_caches);

	/*
	 * Make sure we will access the up-to-date value. The code updating
	 * memcg_caches issues a write barrier to match the data dependency
	 * barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
	 */
	memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);

	/*
	 * If we are in a safe context (can wait, and not in interrupt
	 * context), we could be be predictable and return right away.
	 * This would guarantee that the allocation being performed
	 * already belongs in the new cache.
	 *
	 * However, there are some clashes that can arrive from locking.
	 * For instance, because we acquire the slab_mutex while doing
	 * memcg_create_kmem_cache, this means no further allocation
	 * could happen with the slab_mutex held. So it's better to
	 * defer everything.
	 *
	 * If the memcg is dying or memcg_cache is about to be released,
	 * don't bother creating new kmem_caches. Because memcg_cachep
	 * is ZEROed as the fist step of kmem offlining, we don't need
	 * percpu_ref_tryget_live() here. css_tryget_online() check in
	 * memcg_schedule_kmem_cache_create() will prevent us from
	 * creation of a new kmem_cache.
	 */
	if (unlikely(!memcg_cachep))
		memcg_schedule_kmem_cache_create(memcg, cachep);
	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
		cachep = memcg_cachep;
out_unlock:
	rcu_read_unlock();
	return cachep;
}

/**
 * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
 * @cachep: the cache returned by memcg_kmem_get_cache
 */
void memcg_kmem_put_cache(struct kmem_cache *cachep)
{
	if (!is_root_cache(cachep))
		percpu_ref_put(&cachep->memcg_params.refcnt);
}

/**
 * __memcg_kmem_charge: charge a number of kernel pages to a memcg
 * @memcg: memory cgroup to charge
 * @gfp: reclaim mode
 * @nr_pages: number of pages to charge
 *
 * Returns 0 on success, an error code on failure.
 */
int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
			unsigned int nr_pages)
{
	struct page_counter *counter;
	int ret;

	ret = try_charge(memcg, gfp, nr_pages);
	if (ret)
		return ret;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
	    !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {

		/*
		 * Enforce __GFP_NOFAIL allocation because callers are not
		 * prepared to see failures and likely do not have any failure
		 * handling code.
		 */
		if (gfp & __GFP_NOFAIL) {
			page_counter_charge(&memcg->kmem, nr_pages);
			return 0;
		}
		cancel_charge(memcg, nr_pages);
		return -ENOMEM;
	}
	return 0;
}

/**
 * __memcg_kmem_uncharge: uncharge a number of kernel pages from a memcg
 * @memcg: memcg to uncharge
 * @nr_pages: number of pages to uncharge
 */
void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		page_counter_uncharge(&memcg->kmem, nr_pages);

	page_counter_uncharge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_uncharge(&memcg->memsw, nr_pages);
}

/**
 * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup
 * @page: page to charge
 * @gfp: reclaim mode
 * @order: allocation order
 *
 * Returns 0 on success, an error code on failure.
 */
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
{
	struct mem_cgroup *memcg;
	int ret = 0;

	if (memcg_kmem_bypass())
		return 0;

	memcg = get_mem_cgroup_from_current();
	if (!mem_cgroup_is_root(memcg)) {
		ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
		if (!ret) {
			page->mem_cgroup = memcg;
			__SetPageKmemcg(page);
		}
	}
	css_put(&memcg->css);
	return ret;
}

/**
 * __memcg_kmem_uncharge_page: uncharge a kmem page
 * @page: page to uncharge
 * @order: allocation order
 */
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
	struct mem_cgroup *memcg = page->mem_cgroup;
	unsigned int nr_pages = 1 << order;

	if (!memcg)
		return;

	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
	__memcg_kmem_uncharge(memcg, nr_pages);
	page->mem_cgroup = NULL;

	/* slab pages do not have PageKmemcg flag set */
	if (PageKmemcg(page))
		__ClearPageKmemcg(page);

	css_put_many(&memcg->css, nr_pages);
}
#endif /* CONFIG_MEMCG_KMEM */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE

/*
 * Because tail pages are not marked as "used", set it. We're under
 * pgdat->lru_lock and migration entries setup in all page mappings.
 */
void mem_cgroup_split_huge_fixup(struct page *head)
{
	int i;

	if (mem_cgroup_disabled())
		return;

	for (i = 1; i < HPAGE_PMD_NR; i++)
		head[i].mem_cgroup = head->mem_cgroup;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifdef CONFIG_MEMCG_SWAP
/**
 * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
 * @entry: swap entry to be moved
 * @from:  mem_cgroup which the entry is moved from
 * @to:  mem_cgroup which the entry is moved to
 *
 * It succeeds only when the swap_cgroup's record for this entry is the same
 * as the mem_cgroup's id of @from.
 *
 * Returns 0 on success, -EINVAL on failure.
 *
 * The caller must have charged to @to, IOW, called page_counter_charge() about
 * both res and memsw, and called css_get().
 */
static int mem_cgroup_move_swap_account(swp_entry_t entry,
				struct mem_cgroup *from, struct mem_cgroup *to)
{
	unsigned short old_id, new_id;

	old_id = mem_cgroup_id(from);
	new_id = mem_cgroup_id(to);

	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
		mod_memcg_state(from, MEMCG_SWAP, -1);
		mod_memcg_state(to, MEMCG_SWAP, 1);
		return 0;
	}
	return -EINVAL;
}
#else
static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
				struct mem_cgroup *from, struct mem_cgroup *to)
{
	return -EINVAL;
}
#endif

static DEFINE_MUTEX(memcg_max_mutex);

static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
				 unsigned long max, bool memsw)
{
	bool enlarge = false;
	bool drained = false;
	int ret;
	bool limits_invariant;
	struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;

	do {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		mutex_lock(&memcg_max_mutex);
		/*
		 * Make sure that the new limit (memsw or memory limit) doesn't
		 * break our basic invariant rule memory.max <= memsw.max.
		 */
		limits_invariant = memsw ? max >= READ_ONCE(memcg->memory.max) :
					   max <= memcg->memsw.max;
		if (!limits_invariant) {
			mutex_unlock(&memcg_max_mutex);
			ret = -EINVAL;
			break;
		}
		if (max > counter->max)
			enlarge = true;
		ret = page_counter_set_max(counter, max);
		mutex_unlock(&memcg_max_mutex);

		if (!ret)
			break;

		if (!drained) {
			drain_all_stock(memcg);
			drained = true;
			continue;
		}

		if (!try_to_free_mem_cgroup_pages(memcg, 1,
					GFP_KERNEL, !memsw)) {
			ret = -EBUSY;
			break;
		}
	} while (true);

	if (!ret && enlarge)
		memcg_oom_recover(memcg);

	return ret;
}

unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
					    gfp_t gfp_mask,
					    unsigned long *total_scanned)
{
	unsigned long nr_reclaimed = 0;
	struct mem_cgroup_per_node *mz, *next_mz = NULL;
	unsigned long reclaimed;
	int loop = 0;
	struct mem_cgroup_tree_per_node *mctz;
	unsigned long excess;
	unsigned long nr_scanned;

	if (order > 0)
		return 0;

	mctz = soft_limit_tree_node(pgdat->node_id);

	/*
	 * Do not even bother to check the largest node if the root
	 * is empty. Do it lockless to prevent lock bouncing. Races
	 * are acceptable as soft limit is best effort anyway.
	 */
	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
		return 0;

	/*
	 * This loop can run a while, specially if mem_cgroup's continuously
	 * keep exceeding their soft limit and putting the system under
	 * pressure
	 */
	do {
		if (next_mz)
			mz = next_mz;
		else
			mz = mem_cgroup_largest_soft_limit_node(mctz);
		if (!mz)
			break;

		nr_scanned = 0;
		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
						    gfp_mask, &nr_scanned);
		nr_reclaimed += reclaimed;
		*total_scanned += nr_scanned;
		spin_lock_irq(&mctz->lock);
		__mem_cgroup_remove_exceeded(mz, mctz);

		/*
		 * If we failed to reclaim anything from this memory cgroup
		 * it is time to move on to the next cgroup
		 */
		next_mz = NULL;
		if (!reclaimed)
			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);

		excess = soft_limit_excess(mz->memcg);
		/*
		 * One school of thought says that we should not add
		 * back the node to the tree if reclaim returns 0.
		 * But our reclaim could return 0, simply because due
		 * to priority we are exposing a smaller subset of
		 * memory to reclaim from. Consider this as a longer
		 * term TODO.
		 */
		/* If excess == 0, no tree ops */
		__mem_cgroup_insert_exceeded(mz, mctz, excess);
		spin_unlock_irq(&mctz->lock);
		css_put(&mz->memcg->css);
		loop++;
		/*
		 * Could not reclaim anything and there are no more
		 * mem cgroups to try or we seem to be looping without
		 * reclaiming anything.
		 */
		if (!nr_reclaimed &&
			(next_mz == NULL ||
			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
			break;
	} while (!nr_reclaimed);
	if (next_mz)
		css_put(&next_mz->memcg->css);
	return nr_reclaimed;
}

/*
 * Test whether @memcg has children, dead or alive.  Note that this
 * function doesn't care whether @memcg has use_hierarchy enabled and
 * returns %true if there are child csses according to the cgroup
 * hierarchy.  Testing use_hierarchy is the caller's responsibility.
 */
static inline bool memcg_has_children(struct mem_cgroup *memcg)
{
	bool ret;

	rcu_read_lock();
	ret = css_next_child(NULL, &memcg->css);
	rcu_read_unlock();
	return ret;
}

/*
 * Reclaims as many pages from the given memcg as possible.
 *
 * Caller is responsible for holding css reference for memcg.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
{
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;

	/* we call try-to-free pages for make this cgroup empty */
	lru_add_drain_all();

	drain_all_stock(memcg);

	/* try to free all pages in this cgroup */
	while (nr_retries && page_counter_read(&memcg->memory)) {
		int progress;

		if (signal_pending(current))
			return -EINTR;

		progress = try_to_free_mem_cgroup_pages(memcg, 1,
							GFP_KERNEL, true);
		if (!progress) {
			nr_retries--;
			/* maybe some writeback is necessary */
			congestion_wait(BLK_RW_ASYNC, HZ/10);
		}

	}

	return 0;
}

static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
					    char *buf, size_t nbytes,
					    loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));

	if (mem_cgroup_is_root(memcg))
		return -EINVAL;
	return mem_cgroup_force_empty(memcg) ?: nbytes;
}

static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
				     struct cftype *cft)
{
	return mem_cgroup_from_css(css)->use_hierarchy;
}

static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
				      struct cftype *cft, u64 val)
{
	int retval = 0;
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);

	if (memcg->use_hierarchy == val)
		return 0;

	/*
	 * If parent's use_hierarchy is set, we can't make any modifications
	 * in the child subtrees. If it is unset, then the change can
	 * occur, provided the current cgroup has no children.
	 *
	 * For the root cgroup, parent_mem is NULL, we allow value to be
	 * set if there are no children.
	 */
	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
				(val == 1 || val == 0)) {
		if (!memcg_has_children(memcg))
			memcg->use_hierarchy = val;
		else
			retval = -EBUSY;
	} else
		retval = -EINVAL;

	return retval;
}

static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
	unsigned long val;

	if (mem_cgroup_is_root(memcg)) {
		val = memcg_page_state(memcg, NR_FILE_PAGES) +
			memcg_page_state(memcg, NR_ANON_MAPPED);
		if (swap)
			val += memcg_page_state(memcg, MEMCG_SWAP);
	} else {
		if (!swap)
			val = page_counter_read(&memcg->memory);
		else
			val = page_counter_read(&memcg->memsw);
	}
	return val;
}

enum {
	RES_USAGE,
	RES_LIMIT,
	RES_MAX_USAGE,
	RES_FAILCNT,
	RES_SOFT_LIMIT,
};

static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct page_counter *counter;

	switch (MEMFILE_TYPE(cft->private)) {
	case _MEM:
		counter = &memcg->memory;
		break;
	case _MEMSWAP:
		counter = &memcg->memsw;
		break;
	case _KMEM:
		counter = &memcg->kmem;
		break;
	case _TCP:
		counter = &memcg->tcpmem;
		break;
	default:
		BUG();
	}

	switch (MEMFILE_ATTR(cft->private)) {
	case RES_USAGE:
		if (counter == &memcg->memory)
			return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
		if (counter == &memcg->memsw)
			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
		return (u64)page_counter_read(counter) * PAGE_SIZE;
	case RES_LIMIT:
		return (u64)counter->max * PAGE_SIZE;
	case RES_MAX_USAGE:
		return (u64)counter->watermark * PAGE_SIZE;
	case RES_FAILCNT:
		return counter->failcnt;
	case RES_SOFT_LIMIT:
		return (u64)memcg->soft_limit * PAGE_SIZE;
	default:
		BUG();
	}
}

static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
{
	unsigned long stat[MEMCG_NR_STAT] = {0};