path: root/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>
 *
 * 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/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>

#include <asm/uaccess.h>

struct cgroup_subsys mem_cgroup_subsys;
static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
static struct kmem_cache *page_cgroup_cache;

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

	MEM_CGROUP_STAT_NSTATS,
};

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

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

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

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

/*
 * per-zone information in memory controller.
 */

enum mem_cgroup_zstat_index {
	MEM_CGROUP_ZSTAT_ACTIVE,
	MEM_CGROUP_ZSTAT_INACTIVE,

	NR_MEM_CGROUP_ZSTAT,
};

struct mem_cgroup_per_zone {
	/*
	 * spin_lock to protect the per cgroup LRU
	 */
	spinlock_t		lru_lock;
	struct list_head	active_list;
	struct list_head	inactive_list;
	unsigned long count[NR_MEM_CGROUP_ZSTAT];
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])

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

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

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

	int	prev_priority;	/* for recording reclaim priority */
	/*
	 * statistics.
	 */
	struct mem_cgroup_stat stat;
};
static struct mem_cgroup init_mem_cgroup;

/*
 * We use the lower bit of the page->page_cgroup pointer as a bit spin
 * lock.  We need to ensure that page->page_cgroup is at least two
 * byte aligned (based on comments from Nick Piggin).  But since
 * bit_spin_lock doesn't actually set that lock bit in a non-debug
 * uniprocessor kernel, we should avoid setting it here too.
 */
#define PAGE_CGROUP_LOCK_BIT 	0x0
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
#else
#define PAGE_CGROUP_LOCK	0x0
#endif

/*
 * A page_cgroup page is associated with every page descriptor. The
 * page_cgroup helps us identify information about the cgroup
 */
struct page_cgroup {
	struct list_head lru;		/* per cgroup LRU list */
	struct page *page;
	struct mem_cgroup *mem_cgroup;
	int ref_cnt;			/* cached, mapped, migrating */
	int flags;
};
#define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */

static int page_cgroup_nid(struct page_cgroup *pc)
{
	return page_to_nid(pc->page);
}

static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
	return page_zonenum(pc->page);
}

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_MAPPED,
};

/*
 * Always modified under lru lock. Then, not necessary to preempt_disable()
 */
static void mem_cgroup_charge_statistics(struct