aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/src/socket.c
blob: 663a462abb087bf6c2776089cdfec0a419041725 (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
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
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
/* SPDX-License-Identifier: GPL-2.0
 *
 * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
 */

#include "device.h"
#include "peer.h"
#include "socket.h"
#include "queueing.h"
#include "messages.h"

#include <linux/ctype.h>
#include <linux/net.h>
#include <linux/if_vlan.h>
#include <linux/if_ether.h>
#include <linux/inetdevice.h>
#include <net/udp_tunnel.h>
#include <net/ipv6.h>

static inline int send4(struct wireguard_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
{
	struct flowi4 fl = {
		.saddr = endpoint->src4.s_addr,
		.daddr = endpoint->addr4.sin_addr.s_addr,
		.fl4_dport = endpoint->addr4.sin_port,
		.flowi4_mark = wg->fwmark,
		.flowi4_proto = IPPROTO_UDP
	};
	struct rtable *rt = NULL;
	struct sock *sock;
	int ret = 0;

	skb->next = skb->prev = NULL;
	skb->dev = wg->dev;
	skb->mark = wg->fwmark;

	rcu_read_lock_bh();
	sock = rcu_dereference_bh(wg->sock4);

	if (unlikely(!sock)) {
		ret = -ENONET;
		goto err;
	}

	fl.fl4_sport = inet_sk(sock)->inet_sport;

	if (cache)
		rt = dst_cache_get_ip4(cache, &fl.saddr);

	if (!rt) {
		security_sk_classify_flow(sock, flowi4_to_flowi(&fl));
		if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, fl.saddr, RT_SCOPE_HOST))) {
			endpoint->src4.s_addr = *(__force __be32 *)&endpoint->src_if4 = fl.saddr = 0;
			if (cache)
				dst_cache_reset(cache);
		}
		rt = ip_route_output_flow(sock_net(sock), &fl, sock);
		if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && rt->dst.dev->ifindex != endpoint->src_if4)))) {
			endpoint->src4.s_addr = *(__force __be32 *)&endpoint->src_if4 = fl.saddr = 0;
			if (cache)
				dst_cache_reset(cache);
			if (!IS_ERR(rt))
				ip_rt_put(rt);
			rt = ip_route_output_flow(sock_net(sock), &fl, sock);
		}
		if (unlikely(IS_ERR(rt))) {
			ret = PTR_ERR(rt);
			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret);
			goto err;
		} else if (unlikely(rt->dst.dev == skb->dev)) {
			ip_rt_put(rt);
			ret = -ELOOP;
			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", wg->dev->name, &endpoint->addr);
			goto err;
		}
		if (cache)
			dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
	}
	udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds, ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, fl.fl4_dport, false, false);
	goto out;

err:
	kfree_skb(skb);
out:
	rcu_read_unlock_bh();
	return ret;
}

static inline int send6(struct wireguard_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
{
#if IS_ENABLED(CONFIG_IPV6)
	struct flowi6 fl = {
		.saddr = endpoint->src6,
		.daddr = endpoint->addr6.sin6_addr,
		.fl6_dport = endpoint->addr6.sin6_port,
		.flowi6_mark = wg->fwmark,
		.flowi6_oif = endpoint->addr6.sin6_scope_id,
		.flowi6_proto = IPPROTO_UDP
		/* TODO: addr->sin6_flowinfo */
	};
	struct dst_entry *dst = NULL;
	struct sock *sock;
	int ret = 0;

	skb->next = skb->prev = NULL;
	skb->dev = wg->dev;
	skb->mark = wg->fwmark;

	rcu_read_lock_bh();
	sock = rcu_dereference_bh(wg->sock6);

	if (unlikely(!sock)) {
		ret = -ENONET;
		goto err;
	}

	fl.fl6_sport = inet_sk(sock)->inet_sport;

	if (cache)
		dst = dst_cache_get_ip6(cache, &fl.saddr);

	if (!dst) {
		security_sk_classify_flow(sock, flowi6_to_flowi(&fl));
		if (unlikely(!ipv6_addr_any(&fl.saddr) && !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) {
			endpoint->src6 = fl.saddr = in6addr_any;
			if (cache)
				dst_cache_reset(cache);
		}
		ret = ipv6_stub->ipv6_dst_lookup(sock_net(sock), sock, &dst, &fl);
		if (unlikely(ret)) {
			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret);
			goto err;
		} else if (unlikely(dst->dev == skb->dev)) {
			dst_release(dst);
			ret = -ELOOP;
			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", wg->dev->name, &endpoint->addr);
			goto err;
		}
		if (cache)
			dst_cache_set_ip6(cache, dst, &fl.saddr);
	}

	udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds, ip6_dst_hoplimit(dst), 0, fl.fl6_sport, fl.fl6_dport, false);
	goto out;

err:
	kfree_skb(skb);
out:
	rcu_read_unlock_bh();
	return ret;
#else
	return -EAFNOSUPPORT;
#endif
}

int socket_send_skb_to_peer(struct wireguard_peer *peer, struct sk_buff *skb, u8 ds)
{
	size_t skb_len = skb->len;
	int ret = -EAFNOSUPPORT;

	read_lock_bh(&peer->endpoint_lock);
	if (peer->endpoint.addr.sa_family == AF_INET)
		ret = send4(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache);
	else if (peer->endpoint.addr.sa_family == AF_INET6)
		ret = send6(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache);
	else
		dev_kfree_skb(skb);
	if (likely(!ret))
		peer->tx_bytes += skb_len;
	read_unlock_bh(&peer->endpoint_lock);

	return ret;
}

int socket_send_buffer_to_peer(struct wireguard_peer *peer, void *buffer, size_t len, u8 ds)
{
	struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);

	if (unlikely(!skb))
		return -ENOMEM;

	skb_reserve(skb, SKB_HEADER_LEN);
	skb_set_inner_network_header(skb, 0);
	skb_put_data(skb, buffer, len);
	return socket_send_skb_to_peer(peer, skb, ds);
}

int socket_send_buffer_as_reply_to_skb(struct wireguard_device *wg, struct sk_buff *in_skb, void *buffer, size_t len)
{
	int ret = 0;
	struct sk_buff *skb;
	struct endpoint endpoint;

	if (unlikely(!in_skb))
		return -EINVAL;
	ret = socket_endpoint_from_skb(&endpoint, in_skb);
	if (unlikely(ret < 0))
		return ret;

	skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);
	if (unlikely(!skb))
		return -ENOMEM;
	skb_reserve(skb, SKB_HEADER_LEN);
	skb_set_inner_network_header(skb, 0);
	skb_put_data(skb, buffer, len);

	if (endpoint.addr.sa_family == AF_INET)
		ret = send4(wg, skb, &endpoint, 0, NULL);
	else if (endpoint.addr.sa_family == AF_INET6)
		ret = send6(wg, skb, &endpoint, 0, NULL);
	/* No other possibilities if the endpoint is valid, which it is, as we checked above. */

	return ret;
}

int socket_endpoint_from_skb(struct endpoint *endpoint, const struct sk_buff *skb)
{
	memset(endpoint, 0, sizeof(struct endpoint));
	if (skb->protocol == htons(ETH_P_IP)) {
		endpoint->addr4.sin_family = AF_INET;
		endpoint->addr4.sin_port = udp_hdr(skb)->source;
		endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr;
		endpoint->src4.s_addr = ip_hdr(skb)->daddr;
		endpoint->src_if4 = skb->skb_iif;
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		endpoint->addr6.sin6_family = AF_INET6;
		endpoint->addr6.sin6_port = udp_hdr(skb)->source;
		endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr;
		endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, skb->skb_iif);
		endpoint->src6 = ipv6_hdr(skb)->daddr;
	} else
		return -EINVAL;
	return 0;
}

static inline bool endpoint_eq(const struct endpoint *a, const struct endpoint *b)
{
	return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET &&
		a->addr4.sin_port == b->addr4.sin_port && a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr &&
		a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) ||
	       (a->addr.sa_family == AF_INET6 && b->addr.sa_family == AF_INET6 &&
		a->addr6.sin6_port == b->addr6.sin6_port && ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) &&
		a->addr6.sin6_scope_id == b->addr6.sin6_scope_id && ipv6_addr_equal(&a->src6, &b->src6)) ||
	       unlikely(!a->addr.sa_family && !b->addr.sa_family);
}

void socket_set_peer_endpoint(struct wireguard_peer *peer, const struct endpoint *endpoint)
{
	/* First we check unlocked, in order to optimize, since it's pretty rare
	 * that an endpoint will change. If we happen to be mid-write, and two
	 * CPUs wind up writing the same thing or something slightly different,
	 * it doesn't really matter much either.
	 */
	if (endpoint_eq(endpoint, &peer->endpoint))
		return;
	write_lock_bh(&peer->endpoint_lock);
	if (endpoint->addr.sa_family == AF_INET) {
		peer->endpoint.addr4 = endpoint->addr4;
		peer->endpoint.src4 = endpoint->src4;
		peer->endpoint.src_if4 = endpoint->src_if4;
	} else if (endpoint->addr.sa_family == AF_INET6) {
		peer->endpoint.addr6 = endpoint->addr6;
		peer->endpoint.src6 = endpoint->src6;
	} else
		goto out;
	dst_cache_reset(&peer->endpoint_cache);
out:
	write_unlock_bh(&peer->endpoint_lock);
}

void socket_set_peer_endpoint_from_skb(struct wireguard_peer *peer, const struct sk_buff *skb)
{
	struct endpoint endpoint;

	if (!socket_endpoint_from_skb(&endpoint, skb))
		socket_set_peer_endpoint(peer, &endpoint);
}

void socket_clear_peer_endpoint_src(struct wireguard_peer *peer)
{
	write_lock_bh(&peer->endpoint_lock);
	memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6));
	dst_cache_reset(&peer->endpoint_cache);
	write_unlock_bh(&peer->endpoint_lock);
}

static int receive(struct sock *sk, struct sk_buff *skb)
{
	struct wireguard_device *wg;

	if (unlikely(!sk))
		goto err;
	wg = sk->sk_user_data;
	if (unlikely(!wg))
		goto err;
	packet_receive(wg, skb);
	return 0;

err:
	kfree_skb(skb);
	return 0;
}

static inline void sock_free(struct sock *sock)
{
	if (unlikely(!sock))
		return;
	sk_clear_memalloc(sock);
	udp_tunnel_sock_release(sock->sk_socket);
}

static inline void set_sock_opts(struct socket *sock)
{
	sock->sk->sk_allocation = GFP_ATOMIC;
	sock->sk->sk_sndbuf = INT_MAX;
	sk_set_memalloc(sock->sk);
}

int socket_init(struct wireguard_device *wg, u16 port)
{
	int ret;
	struct udp_tunnel_sock_cfg cfg = {
		.sk_user_data = wg,
		.encap_type = 1,
		.encap_rcv = receive
	};
	struct socket *new4 = NULL, *new6 = NULL;
	struct udp_port_cfg port4 = {
		.family = AF_INET,
		.local_ip.s_addr = htonl(INADDR_ANY),
		.local_udp_port = htons(port),
		.use_udp_checksums = true
	};
#if IS_ENABLED(CONFIG_IPV6)
	int retries = 0;
	struct udp_port_cfg port6 = {
		.family = AF_INET6,
		.local_ip6 = IN6ADDR_ANY_INIT,
		.use_udp6_tx_checksums = true,
		.use_udp6_rx_checksums = true,
		.ipv6_v6only = true
	};
#endif

#if IS_ENABLED(CONFIG_IPV6)
retry:
#endif

	ret = udp_sock_create(wg->creating_net, &port4, &new4);
	if (ret < 0) {
		pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
		return ret;
	}
	set_sock_opts(new4);
	setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);

#if IS_ENABLED(CONFIG_IPV6)
	if (ipv6_mod_enabled()) {
		port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
		ret = udp_sock_create(wg->creating_net, &port6, &new6);
		if (ret < 0) {
			udp_tunnel_sock_release(new4);
			if (ret == -EADDRINUSE && !port && retries++ < 100)
				goto retry;
			pr_err("%s: Could not create IPv6 socket\n", wg->dev->name);
			return ret;
		}
		set_sock_opts(new6);
		setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
	}
#endif

	socket_reinit(wg, new4 ? new4->sk : NULL, new6 ? new6->sk : NULL);
	return 0;
}

void socket_reinit(struct wireguard_device *wg, struct sock *new4, struct sock *new6)
{
	struct sock *old4, *old6;

	mutex_lock(&wg->socket_update_lock);
	old4 = rcu_dereference_protected(wg->sock4, lockdep_is_held(&wg->socket_update_lock));
	old6 = rcu_dereference_protected(wg->sock6, lockdep_is_held(&wg->socket_update_lock));
	rcu_assign_pointer(wg->sock4, new4);
	rcu_assign_pointer(wg->sock6, new6);
	if (new4)
		wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
	mutex_unlock(&wg->socket_update_lock);
	synchronize_rcu_bh();
	synchronize_net();
	sock_free(old4);
	sock_free(old6);
}