summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_memcontrol.c
blob: 133eb5eac49f65eebc204b543058647a10720a33 (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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
#include <net/tcp.h>
#include <net/tcp_memcontrol.h>
#include <net/sock.h>
#include <net/ip.h>
#include <linux/nsproxy.h>
#include <linux/memcontrol.h>
#include <linux/module.h>

int tcp_init_cgroup(struct mem_cgroup *memcg)
{
	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
	struct page_counter *counter_parent = NULL;
	/*
	 * The root cgroup does not use page_counters, but rather,
	 * rely on the data already collected by the network
	 * subsystem
	 */
	if (memcg == root_mem_cgroup)
		return 0;

	memcg->tcp_mem.memory_pressure = 0;

	if (parent)
		counter_parent = &parent->tcp_mem.memory_allocated;

	page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent);

	return 0;
}

void tcp_destroy_cgroup(struct mem_cgroup *memcg)
{
	if (memcg == root_mem_cgroup)
		return;

	if (memcg->tcp_mem.active)
		static_branch_dec(&memcg_sockets_enabled_key);
}

static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
{
	int ret;

	if (memcg == root_mem_cgroup)
		return -EINVAL;

	ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages);
	if (ret)
		return ret;

	if (!memcg->tcp_mem.active) {
		/*
		 * The active flag needs to be written after the static_key
		 * update. This is what guarantees that the socket activation
		 * function is the last one to run. See sock_update_memcg() for
		 * details, and note that we don't mark any socket as belonging
		 * to this memcg until that flag is up.
		 *
		 * We need to do this, because static_keys will span multiple
		 * sites, but we can't control their order. If we mark a socket
		 * as accounted, but the accounting functions are not patched in
		 * yet, we'll lose accounting.
		 *
		 * We never race with the readers in sock_update_memcg(),
		 * because when this value change, the code to process it is not
		 * patched in yet.
		 */
		static_branch_inc(&memcg_sockets_enabled_key);
		memcg->tcp_mem.active = true;
	}

	return 0;
}

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

static DEFINE_MUTEX(tcp_limit_mutex);

static ssize_t tcp_cgroup_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));
	unsigned long nr_pages;
	int ret = 0;

	buf = strstrip(buf);

	switch (of_cft(of)->private) {
	case RES_LIMIT:
		/* see memcontrol.c */
		ret = page_counter_memparse(buf, "-1", &nr_pages);
		if (ret)
			break;
		mutex_lock(&tcp_limit_mutex);
		ret = tcp_update_limit(memcg, nr_pages);
		mutex_unlock(&tcp_limit_mutex);
		break;
	default:
		ret = -EINVAL;
		break;
	}
	return ret ?: nbytes;
}

static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	u64 val;

	switch (cft->private) {
	case RES_LIMIT:
		if (memcg == root_mem_cgroup)
			val = PAGE_COUNTER_MAX;
		else
			val = memcg->tcp_mem.memory_allocated.limit;
		val *= PAGE_SIZE;
		break;
	case RES_USAGE:
		if (memcg == root_mem_cgroup)
			val = atomic_long_read(&tcp_memory_allocated);
		else
			val = page_counter_read(&memcg->tcp_mem.memory_allocated);
		val *= PAGE_SIZE;
		break;
	case RES_FAILCNT:
		if (memcg == root_mem_cgroup)
			return 0;
		val = memcg->tcp_mem.memory_allocated.failcnt;
		break;
	case RES_MAX_USAGE:
		if (memcg == root_mem_cgroup)
			return 0;
		val = memcg->tcp_mem.memory_allocated.watermark;
		val *= PAGE_SIZE;
		break;
	default:
		BUG();
	}
	return val;
}

static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg;

	memcg = mem_cgroup_from_css(of_css(of));
	if (memcg == root_mem_cgroup)
		return nbytes;

	switch (of_cft(of)->private) {
	case RES_MAX_USAGE:
		page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated);
		break;
	case RES_FAILCNT:
		memcg->tcp_mem.memory_allocated.failcnt = 0;
		break;
	}

	return nbytes;
}

static struct cftype tcp_files[] = {
	{
		.name = "kmem.tcp.limit_in_bytes",
		.write = tcp_cgroup_write,
		.read_u64 = tcp_cgroup_read,
		.private = RES_LIMIT,
	},
	{
		.name = "kmem.tcp.usage_in_bytes",
		.read_u64 = tcp_cgroup_read,
		.private = RES_USAGE,
	},
	{
		.name = "kmem.tcp.failcnt",
		.private = RES_FAILCNT,
		.write = tcp_cgroup_reset,
		.read_u64 = tcp_cgroup_read,
	},
	{
		.name = "kmem.tcp.max_usage_in_bytes",
		.private = RES_MAX_USAGE,
		.write = tcp_cgroup_reset,
		.read_u64 = tcp_cgroup_read,
	},
	{ }	/* terminate */
};

static int __init tcp_memcontrol_init(void)
{
	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, tcp_files));
	return 0;
}
__initcall(tcp_memcontrol_init);