aboutsummaryrefslogtreecommitdiffstats
path: root/net/sched/cls_cgroup.c
blob: f84fdc3a7f279219d8bf3e8e97683562d748f711 (plain) (blame)
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
/*
 * net/sched/cls_cgroup.c	Control Group Classifier
 *
 *		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.
 *
 * Authors:	Thomas Graf <tgraf@suug.ch>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/cgroup.h>
#include <linux/rcupdate.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
#include <net/cls_cgroup.h>

static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
					       struct cgroup *cgrp);
static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp);

struct cgroup_subsys net_cls_subsys = {
	.name		= "net_cls",
	.create		= cgrp_create,
	.destroy	= cgrp_destroy,
	.populate	= cgrp_populate,
#ifdef CONFIG_NET_CLS_CGROUP
	.subsys_id	= net_cls_subsys_id,
#endif
	.module		= THIS_MODULE,
};


static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp)
{
	return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id),
			    struct cgroup_cls_state, css);
}

static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
{
	return container_of(task_subsys_state(p, net_cls_subsys_id),
			    struct cgroup_cls_state, css);
}

static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
						 struct cgroup *cgrp)
{
	struct cgroup_cls_state *cs;

	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
	if (!cs)
		return ERR_PTR(-ENOMEM);

	if (cgrp->parent)
		cs->classid = cgrp_cls_state(cgrp->parent)->classid;

	return &cs->css;
}

static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	kfree(cgrp_cls_state(cgrp));
}

static u64 read_classid(struct cgroup *cgrp, struct cftype *cft)
{
	return cgrp_cls_state(cgrp)->classid;
}

static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value)
{
	cgrp_cls_state(cgrp)->classid = (u32) value;
	return 0;
}

static struct cftype ss_files[] = {
	{
		.name = "classid",
		.read_u64 = read_classid,
		.write_u64 = write_classid,
	},
};

static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
}

struct cls_cgroup_head {
	u32			handle;
	struct tcf_exts		exts;
	struct tcf_ematch_tree	ematches;
};

static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
			       struct tcf_result *res)
{
	struct cls_cgroup_head *head = tp->root;
	u32 classid;

	rcu_read_lock();
	classid = task_cls_state(current)->classid;
	rcu_read_unlock();

	/*
	 * Due to the nature of the classifier it is required to ignore all
	 * packets originating from softirq context as accessing `current'
	 * would lead to false results.
	 *
	 * This test assumes that all callers of dev_queue_xmit() explicitely
	 * disable bh. Knowing this, it is possible to detect softirq based
	 * calls by looking at the number of nested bh disable calls because
	 * softirqs always disables bh.
	 */
	if (in_serving_softirq()) {
		/* If there is an sk_classid we'll use that. */
		if (!skb->sk)
			return -1;
		classid = skb->sk->sk_classid;
	}

	if (!classid)
		return -1;

	if (!tcf_em_tree_match(skb, &head->ematches, NULL))
		return -1;

	res->classid = classid;
	res->class = 0;
	return tcf_exts_exec(skb, &head->exts, res);
}

static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
{
	return 0UL;
}

static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
{
}

static int cls_cgroup_init(struct tcf_proto *tp)
{
	return 0;
}

static const struct tcf_ext_map cgroup_ext_map = {
	.action = TCA_CGROUP_ACT,
	.police = TCA_CGROUP_POLICE,
};

static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
};

static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
			     u32 handle, struct nlattr **tca,
			     unsigned long *arg)
{
	struct nlattr *tb[TCA_CGROUP_MAX + 1];
	struct cls_cgroup_head *head = tp->root;
	struct tcf_ematch_tree t;
	struct tcf_exts e;
	int err;

	if (!tca[TCA_OPTIONS])
		return -EINVAL;

	if (head == NULL) {
		if (!handle)
			return -EINVAL;

		head = kzalloc(sizeof(*head), GFP_KERNEL);
		if (head == NULL)
			return -ENOBUFS;

		head->handle = handle;

		tcf_tree_lock(tp);
		tp->root = head;
		tcf_tree_unlock(tp);
	}

	if (handle != head->handle)
		return -ENOENT;

	err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
			       cgroup_policy);
	if (err < 0)
		return err;

	err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map);
	if (err < 0)
		return err;

	err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
	if (err < 0)
		return err;

	tcf_exts_change(tp, &head->exts, &e);
	tcf_em_tree_change(tp, &head->ematches, &t);

	return 0;
}

static void cls_cgroup_destroy(struct tcf_proto *tp)
{
	struct cls_cgroup_head *head = tp->root;

	if (head) {
		tcf_exts_destroy(tp, &head->exts);
		tcf_em_tree_destroy(tp, &head->ematches);
		kfree(head);
	}
}

static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
{
	return -EOPNOTSUPP;
}

static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
	struct cls_cgroup_head *head = tp->root;

	if (arg->count < arg->skip)
		goto skip;

	if (arg->fn(tp, (unsigned long) head, arg) < 0) {
		arg->stop = 1;
		return;
	}
skip:
	arg->count++;
}

static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
			   struct sk_buff *skb, struct tcmsg *t)
{
	struct cls_cgroup_head *head = tp->root;
	unsigned char *b = skb_tail_pointer(skb);
	struct nlattr *nest;

	t->tcm_handle = head->handle;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;

	if (tcf_exts_dump(skb, &head->exts, &cgroup_ext_map) < 0 ||
	    tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
		goto nla_put_failure;

	nla_nest_end(skb, nest);

	if (tcf_exts_dump_stats(skb, &head->exts, &cgroup_ext_map) < 0)
		goto nla_put_failure;

	return skb->len;

nla_put_failure:
	nlmsg_trim(skb, b);
	return -1;
}

static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
	.kind		=	"cgroup",
	.init		=	cls_cgroup_init,
	.change		=	cls_cgroup_change,
	.classify	=	cls_cgroup_classify,
	.destroy	=	cls_cgroup_destroy,
	.get		=	cls_cgroup_get,
	.put		=	cls_cgroup_put,
	.delete		=	cls_cgroup_delete,
	.walk		=	cls_cgroup_walk,
	.dump		=	cls_cgroup_dump,
	.owner		=	THIS_MODULE,
};

static int __init init_cgroup_cls(void)
{
	int ret;

	ret = cgroup_load_subsys(&net_cls_subsys);
	if (ret)
		goto out;

#ifndef CONFIG_NET_CLS_CGROUP
	/* We can't use rcu_assign_pointer because this is an int. */
	smp_wmb();
	net_cls_subsys_id = net_cls_subsys.subsys_id;
#endif

	ret = register_tcf_proto_ops(&cls_cgroup_ops);
	if (ret)
		cgroup_unload_subsys(&net_cls_subsys);

out:
	return ret;
}

static void __exit exit_cgroup_cls(void)
{
	unregister_tcf_proto_ops(&cls_cgroup_ops);

#ifndef CONFIG_NET_CLS_CGROUP
	net_cls_subsys_id = -1;
	synchronize_rcu();
#endif

	cgroup_unload_subsys(&net_cls_subsys);
}

module_init(init_cgroup_cls);
module_exit(exit_cgroup_cls);
MODULE_LICENSE("GPL");