summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/net_namespace.c
blob: 78cf061f817938560117a7a6bbed007b9660810e (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
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
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
// SPDX-License-Identifier: GPL-2.0

#include <linux/bpf.h>
#include <linux/filter.h>
#include <net/net_namespace.h>

/*
 * Functions to manage BPF programs attached to netns
 */

struct bpf_netns_link {
	struct bpf_link	link;
	enum bpf_attach_type type;
	enum netns_bpf_attach_type netns_type;

	/* We don't hold a ref to net in order to auto-detach the link
	 * when netns is going away. Instead we rely on pernet
	 * pre_exit callback to clear this pointer. Must be accessed
	 * with netns_bpf_mutex held.
	 */
	struct net *net;
};

/* Protects updates to netns_bpf */
DEFINE_MUTEX(netns_bpf_mutex);

/* Must be called with netns_bpf_mutex held. */
static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link)
{
	struct bpf_netns_link *net_link =
		container_of(link, struct bpf_netns_link, link);

	net_link->net = NULL;
}

static void bpf_netns_link_release(struct bpf_link *link)
{
	struct bpf_netns_link *net_link =
		container_of(link, struct bpf_netns_link, link);
	enum netns_bpf_attach_type type = net_link->netns_type;
	struct net *net;

	/* Link auto-detached by dying netns. */
	if (!net_link->net)
		return;

	mutex_lock(&netns_bpf_mutex);

	/* Recheck after potential sleep. We can race with cleanup_net
	 * here, but if we see a non-NULL struct net pointer pre_exit
	 * has not happened yet and will block on netns_bpf_mutex.
	 */
	net = net_link->net;
	if (!net)
		goto out_unlock;

	net->bpf.links[type] = NULL;
	RCU_INIT_POINTER(net->bpf.progs[type], NULL);

out_unlock:
	mutex_unlock(&netns_bpf_mutex);
}

static void bpf_netns_link_dealloc(struct bpf_link *link)
{
	struct bpf_netns_link *net_link =
		container_of(link, struct bpf_netns_link, link);

	kfree(net_link);
}

static int bpf_netns_link_update_prog(struct bpf_link *link,
				      struct bpf_prog *new_prog,
				      struct bpf_prog *old_prog)
{
	struct bpf_netns_link *net_link =
		container_of(link, struct bpf_netns_link, link);
	enum netns_bpf_attach_type type = net_link->netns_type;
	struct net *net;
	int ret = 0;

	if (old_prog && old_prog != link->prog)
		return -EPERM;
	if (new_prog->type != link->prog->type)
		return -EINVAL;

	mutex_lock(&netns_bpf_mutex);

	net = net_link->net;
	if (!net || !check_net(net)) {
		/* Link auto-detached or netns dying */
		ret = -ENOLINK;
		goto out_unlock;
	}

	old_prog = xchg(&link->prog, new_prog);
	rcu_assign_pointer(net->bpf.progs[type], new_prog);
	bpf_prog_put(old_prog);

out_unlock:
	mutex_unlock(&netns_bpf_mutex);
	return ret;
}

static int bpf_netns_link_fill_info(const struct bpf_link *link,
				    struct bpf_link_info *info)
{
	const struct bpf_netns_link *net_link =
		container_of(link, struct bpf_netns_link, link);
	unsigned int inum = 0;
	struct net *net;

	mutex_lock(&netns_bpf_mutex);
	net = net_link->net;
	if (net && check_net(net))
		inum = net->ns.inum;
	mutex_unlock(&netns_bpf_mutex);

	info->netns.netns_ino = inum;
	info->netns.attach_type = net_link->type;
	return 0;
}

static void bpf_netns_link_show_fdinfo(const struct bpf_link *link,
				       struct seq_file *seq)
{
	struct bpf_link_info info = {};

	bpf_netns_link_fill_info(link, &info);
	seq_printf(seq,
		   "netns_ino:\t%u\n"
		   "attach_type:\t%u\n",
		   info.netns.netns_ino,
		   info.netns.attach_type);
}

static const struct bpf_link_ops bpf_netns_link_ops = {
	.release = bpf_netns_link_release,
	.dealloc = bpf_netns_link_dealloc,
	.update_prog = bpf_netns_link_update_prog,
	.fill_link_info = bpf_netns_link_fill_info,
	.show_fdinfo = bpf_netns_link_show_fdinfo,
};

int netns_bpf_prog_query(const union bpf_attr *attr,
			 union bpf_attr __user *uattr)
{
	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
	u32 prog_id, prog_cnt = 0, flags = 0;
	enum netns_bpf_attach_type type;
	struct bpf_prog *attached;
	struct net *net;

	if (attr->query.query_flags)
		return -EINVAL;

	type = to_netns_bpf_attach_type(attr->query.attach_type);
	if (type < 0)
		return -EINVAL;

	net = get_net_ns_by_fd(attr->query.target_fd);
	if (IS_ERR(net))
		return PTR_ERR(net);

	rcu_read_lock();
	attached = rcu_dereference(net->bpf.progs[type]);
	if (attached) {
		prog_cnt = 1;
		prog_id = attached->aux->id;
	}
	rcu_read_unlock();

	put_net(net);

	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
		return -EFAULT;
	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
		return -EFAULT;

	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
		return 0;

	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
		return -EFAULT;

	return 0;
}

int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
	enum netns_bpf_attach_type type;
	struct net *net;
	int ret;

	type = to_netns_bpf_attach_type(attr->attach_type);
	if (type < 0)
		return -EINVAL;

	net = current->nsproxy->net_ns;
	mutex_lock(&netns_bpf_mutex);

	/* Attaching prog directly is not compatible with links */
	if (net->bpf.links[type]) {
		ret = -EEXIST;
		goto out_unlock;
	}

	switch (type) {
	case NETNS_BPF_FLOW_DISSECTOR:
		ret = flow_dissector_bpf_prog_attach(net, prog);
		break;
	default:
		ret = -EINVAL;
		break;
	}
out_unlock:
	mutex_unlock(&netns_bpf_mutex);

	return ret;
}

/* Must be called with netns_bpf_mutex held. */
static int __netns_bpf_prog_detach(struct net *net,
				   enum netns_bpf_attach_type type)
{
	struct bpf_prog *attached;

	/* Progs attached via links cannot be detached */
	if (net->bpf.links[type])
		return -EINVAL;

	attached = rcu_dereference_protected(net->bpf.progs[type],
					     lockdep_is_held(&netns_bpf_mutex));
	if (!attached)
		return -ENOENT;
	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
	bpf_prog_put(attached);
	return 0;
}

int netns_bpf_prog_detach(const union bpf_attr *attr)
{
	enum netns_bpf_attach_type type;
	int ret;

	type = to_netns_bpf_attach_type(attr->attach_type);
	if (type < 0)
		return -EINVAL;

	mutex_lock(&netns_bpf_mutex);
	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type);
	mutex_unlock(&netns_bpf_mutex);

	return ret;
}

static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
				 enum netns_bpf_attach_type type)
{
	struct bpf_prog *prog;
	int err;

	mutex_lock(&netns_bpf_mutex);

	/* Allow attaching only one prog or link for now */
	if (net->bpf.links[type]) {
		err = -E2BIG;
		goto out_unlock;
	}
	/* Links are not compatible with attaching prog directly */
	prog = rcu_dereference_protected(net->bpf.progs[type],
					 lockdep_is_held(&netns_bpf_mutex));
	if (prog) {
		err = -EEXIST;
		goto out_unlock;
	}

	switch (type) {
	case NETNS_BPF_FLOW_DISSECTOR:
		err = flow_dissector_bpf_prog_attach(net, link->prog);
		break;
	default:
		err = -EINVAL;
		break;
	}
	if (err)
		goto out_unlock;

	net->bpf.links[type] = link;

out_unlock:
	mutex_unlock(&netns_bpf_mutex);
	return err;
}

int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
{
	enum netns_bpf_attach_type netns_type;
	struct bpf_link_primer link_primer;
	struct bpf_netns_link *net_link;
	enum bpf_attach_type type;
	struct net *net;
	int err;

	if (attr->link_create.flags)
		return -EINVAL;

	type = attr->link_create.attach_type;
	netns_type = to_netns_bpf_attach_type(type);
	if (netns_type < 0)
		return -EINVAL;

	net = get_net_ns_by_fd(attr->link_create.target_fd);
	if (IS_ERR(net))
		return PTR_ERR(net);

	net_link = kzalloc(sizeof(*net_link), GFP_USER);
	if (!net_link) {
		err = -ENOMEM;
		goto out_put_net;
	}
	bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS,
		      &bpf_netns_link_ops, prog);
	net_link->net = net;
	net_link->type = type;
	net_link->netns_type = netns_type;

	err = bpf_link_prime(&net_link->link, &link_primer);
	if (err) {
		kfree(net_link);
		goto out_put_net;
	}

	err = netns_bpf_link_attach(net, &net_link->link, netns_type);
	if (err) {
		bpf_link_cleanup(&link_primer);
		goto out_put_net;
	}

	put_net(net);
	return bpf_link_settle(&link_primer);

out_put_net:
	put_net(net);
	return err;
}

static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
{
	enum netns_bpf_attach_type type;
	struct bpf_link *link;

	mutex_lock(&netns_bpf_mutex);
	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
		link = net->bpf.links[type];
		if (link)
			bpf_netns_link_auto_detach(link);
		else
			__netns_bpf_prog_detach(net, type);
	}
	mutex_unlock(&netns_bpf_mutex);
}

static struct pernet_operations netns_bpf_pernet_ops __net_initdata = {
	.pre_exit = netns_bpf_pernet_pre_exit,
};

static int __init netns_bpf_init(void)
{
	return register_pernet_subsys(&netns_bpf_pernet_ops);
}

subsys_initcall(netns_bpf_init);