summaryrefslogtreecommitdiff
path: root/datapath/linux/compat/ip_tunnel.c
blob: 81909370271cd5fe88b223c9230dada0038aecc3 (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
/*
 * Copyright (c) 2013 Nicira, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * 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.
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/kconfig.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/rculist.h>
#include <linux/err.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/udp.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif

#include "compat.h"

#ifndef HAVE_METADATA_DST
static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t)
{
	if (t->collect_md)
		rcu_assign_pointer(itn->collect_md_tun, t);
	else
		WARN_ONCE(1, "%s: collect md not set\n", t->dev->name);
}

static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t)
{
	if (t->collect_md)
		rcu_assign_pointer(itn->collect_md_tun, NULL);
}

static inline void init_tunnel_flow(struct flowi4 *fl4,
				    int proto,
				    __be32 daddr, __be32 saddr,
				    __be32 key, __u8 tos, int oif)
{
	memset(fl4, 0, sizeof(*fl4));
	fl4->flowi4_oif = oif;
	fl4->daddr = daddr;
	fl4->saddr = saddr;
	fl4->flowi4_tos = tos;
	fl4->flowi4_proto = proto;
	fl4->fl4_gre_key = key;
}

static int ip_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);

	iph = &tunnel->parms.iph;

	/* Guess output device to choose reasonable mtu and needed_headroom */
	if (iph->daddr) {
		struct flowi4 fl4;
		struct rtable *rt;

		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
				 iph->saddr, tunnel->parms.o_key,
				 RT_TOS(iph->tos), tunnel->parms.link);
		rt = ip_route_output_key(tunnel->net, &fl4);

		if (!IS_ERR(rt)) {
			tdev = rt_dst(rt).dev;
			ip_rt_put(rt);
		}
		if (dev->type != ARPHRD_ETHER)
			dev->flags |= IFF_POINTOPOINT;
	}

	if (!tdev && tunnel->parms.link)
		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);

	if (tdev) {
		hlen = tdev->hard_header_len + tdev->needed_headroom;
		mtu = tdev->mtu;
	}

	dev->needed_headroom = t_hlen + hlen;
	mtu -= (dev->hard_header_len + t_hlen);

	if (mtu < 68)
		mtu = 68;

	return mtu;
}

int rpl___ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;

	if (new_mtu < 68)
		return -EINVAL;

	if (new_mtu > max_mtu) {
		if (strict)
			return -EINVAL;

		new_mtu = max_mtu;
	}

	dev->mtu = new_mtu;
	return 0;
}

int rpl_ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	return rpl___ip_tunnel_change_mtu(dev, new_mtu, true);
}

static void ip_tunnel_dev_free(struct net_device *dev)
{
#ifdef HAVE_DEV_TSTATS
	free_percpu(dev->tstats);
#endif
	free_netdev(dev);
}

#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,39)
void rpl_ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
#else
void rpl_ip_tunnel_dellink(struct net_device *dev)
#endif
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct ip_tunnel_net *itn;

	itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);

	ip_tunnel_del(itn, netdev_priv(dev));
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,39)
	unregister_netdevice_queue(dev, head);
#endif
}

int rpl_ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
				  struct rtnl_link_ops *ops, char *devname)
{
	struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);

	itn->collect_md_tun = NULL;
	itn->rtnl_ops = ops;
	return 0;
}

static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
			      struct rtnl_link_ops *ops)
{
	struct ip_tunnel *t;

	t = rtnl_dereference(itn->collect_md_tun);
	if (!t)
		return;
	unregister_netdevice_queue(t->dev, head);
}

void rpl_ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
{
	LIST_HEAD(list);

	rtnl_lock();
	ip_tunnel_destroy(itn, &list, ops);
	unregister_netdevice_many(&list);
	rtnl_unlock();
}

int rpl_ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
		      struct ip_tunnel_parm *p)
{
	struct ip_tunnel *nt;
	struct net *net = dev_net(dev);
	struct ip_tunnel_net *itn;
	int mtu;
	int err;

	nt = netdev_priv(dev);
	itn = net_generic(net, nt->ip_tnl_net_id);

	if (nt->collect_md) {
		if (rtnl_dereference(itn->collect_md_tun))
			return -EEXIST;
	} else {
		return -EOPNOTSUPP;
	}

	nt->net = net;
	nt->parms = *p;
	err = register_netdevice(dev);
	if (err)
		goto out;

	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
		eth_hw_addr_random(dev);

	mtu = ip_tunnel_bind_dev(dev);
	if (!tb[IFLA_MTU])
		dev->mtu = mtu;

	ip_tunnel_add(itn, nt);
out:
	return err;
}

int rpl_ip_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	dev->destructor	= ip_tunnel_dev_free;
#ifdef HAVE_DEV_TSTATS
	dev->tstats = (typeof(dev->tstats)) netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
	if (!dev->tstats)
		return -ENOMEM;
#endif
	tunnel->dev = dev;
	tunnel->net = dev_net(dev);
	strcpy(tunnel->parms.name, dev->name);
	iph->version		= 4;
	iph->ihl		= 5;

	if (tunnel->collect_md)
		dev->features |= NETIF_F_NETNS_LOCAL;

	return 0;
}

void rpl_ip_tunnel_uninit(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct net *net = tunnel->net;
	struct ip_tunnel_net *itn;

	itn = net_generic(net, tunnel->ip_tnl_net_id);
	ip_tunnel_del(itn, netdev_priv(dev));
}

/* Do least required initialization, rest of init is done in tunnel_init call */
void rpl_ip_tunnel_setup(struct net_device *dev, int net_id)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	tunnel->ip_tnl_net_id = net_id;
}

int rpl_ip_tunnel_get_iflink(const struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	return tunnel->parms.link;
}

struct net *rpl_ip_tunnel_get_link_net(const struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	return tunnel->net;
}

#endif