summaryrefslogtreecommitdiff
path: root/mm/memcontrol.c
blob: 4d4805eb37c77b06a98a9d06690982420734e077 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
/* 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>

struct cgroup_subsys mem_cgroup_subsys;

/*
 * 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.
 */
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.
	 * TODO: Consider making these lists per zone
	 */
	struct list_head active_list;
	struct list_head inactive_list;
};

/*
 * 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;
};


static inline
struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont,
				mem_cgroup_subsys_id), struct mem_cgroup,
				css);
}

static inline
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
				struct mem_cgroup, css);
}

void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
{
	struct mem_cgroup *mem;

	mem = mem_cgroup_from_task(p);
	css_get(&mem->css);
	mm->mem_cgroup = mem;
}

void mm_free_cgroup(struct mm_struct *mm)
{
	css_put(&mm->mem_cgroup->css);
}

void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
{
	page->page_cgroup = (unsigned long)pc;
}

struct page_cgroup *page_get_page_cgroup(struct page *page)
{
	return page->page_cgroup;
}

static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
			struct file *file, char __user *userbuf, size_t nbytes,
			loff_t *ppos)
{
	return res_counter_read(&mem_cgroup_from_cont(cont)->res,
				cft->private, userbuf, nbytes, ppos);
}

static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
				struct file *file, const char __user *userbuf,
				size_t nbytes, loff_t *ppos)
{
	return res_counter_write(&mem_cgroup_from_cont(cont)->res,
				cft->private, userbuf, nbytes, ppos);
}

static struct cftype mem_cgroup_files[] = {
	{
		.name = "usage",
		.private = RES_USAGE,
		.read = mem_cgroup_read,
	},
	{
		.name = "limit",
		.private = RES_LIMIT,
		.write = mem_cgroup_write,
		.read = mem_cgroup_read,
	},
	{
		.name = "failcnt",
		.private = RES_FAILCNT,
		.read = mem_cgroup_read,
	},
};

static struct mem_cgroup init_mem_cgroup;

static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct mem_cgroup *mem;

	if (unlikely((cont->parent) == NULL)) {
		mem = &init_mem_cgroup;
		init_mm.mem_cgroup = mem;
	} else
		mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);

	if (mem == NULL)
		return NULL;

	res_counter_init(&mem->res);
	return &mem->css;
}

static void mem_cgroup_destroy(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	kfree(mem_cgroup_from_cont(cont));
}

static int mem_cgroup_populate(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, mem_cgroup_files,
					ARRAY_SIZE(mem_cgroup_files));
}

struct cgroup_subsys mem_cgroup_subsys = {
	.name = "memory",
	.subsys_id = mem_cgroup_subsys_id,
	.create = mem_cgroup_create,
	.destroy = mem_cgroup_destroy,
	.populate = mem_cgroup_populate,
	.early_init = 1,
};