Free Electrons

Embedded Linux Experts

  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
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
/*
 *	Linux NET3:	IP/IP protocol decoder.
 *
 *	Authors:
 *		Sam Lantinga (slouken@cs.ucdavis.edu)  02/01/95
 *
 *	Fixes:
 *		Alan Cox	:	Merged and made usable non modular (its so tiny its silly as
 *					a module taking up 2 pages).
 *		Alan Cox	: 	Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph)
 *					to keep ip_forward happy.
 *		Alan Cox	:	More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8).
 *		Kai Schulte	:	Fixed #defines for IP_FIREWALL->FIREWALL
 *              David Woodhouse :       Perform some basic ICMP handling.
 *                                      IPIP Routing without decapsulation.
 *              Carlos Picoto   :       GRE over IP support
 *		Alexey Kuznetsov:	Reworked. Really, now it is truncated version of ipv4/ip_gre.c.
 *					I do not want to merge them together.
 *
 *	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.
 *
 */

/* tunnel.c: an IP tunnel driver

	The purpose of this driver is to provide an IP tunnel through
	which you can tunnel network traffic transparently across subnets.

	This was written by looking at Nick Holloway's dummy driver
	Thanks for the great code!

		-Sam Lantinga	(slouken@cs.ucdavis.edu)  02/01/95

	Minor tweaks:
		Cleaned up the code a little and added some pre-1.3.0 tweaks.
		dev->hard_header/hard_header_len changed to use no headers.
		Comments/bracketing tweaked.
		Made the tunnels use dev->name not tunnel: when error reporting.
		Added tx_dropped stat

		-Alan Cox	(alan@lxorguk.ukuu.org.uk) 21 March 95

	Reworked:
		Changed to tunnel to destination gateway in addition to the
			tunnel's pointopoint address
		Almost completely rewritten
		Note:  There is currently no firewall or ICMP handling done.

		-Sam Lantinga	(slouken@cs.ucdavis.edu) 02/13/96

*/

/* Things I wish I had known when writing the tunnel driver:

	When the tunnel_xmit() function is called, the skb contains the
	packet to be sent (plus a great deal of extra info), and dev
	contains the tunnel device that _we_ are.

	When we are passed a packet, we are expected to fill in the
	source address with our source IP address.

	What is the proper way to allocate, copy and free a buffer?
	After you allocate it, it is a "0 length" chunk of memory
	starting at zero.  If you want to add headers to the buffer
	later, you'll have to call "skb_reserve(skb, amount)" with
	the amount of memory you want reserved.  Then, you call
	"skb_put(skb, amount)" with the amount of space you want in
	the buffer.  skb_put() returns a pointer to the top (#0) of
	that buffer.  skb->len is set to the amount of space you have
	"allocated" with skb_put().  You can then write up to skb->len
	bytes to that buffer.  If you need more, you can call skb_put()
	again with the additional amount of space you need.  You can
	find out how much more space you can allocate by calling
	"skb_tailroom(skb)".
	Now, to add header space, call "skb_push(skb, header_len)".
	This creates space at the beginning of the buffer and returns
	a pointer to this new space.  If later you need to strip a
	header from a buffer, call "skb_pull(skb, header_len)".
	skb_headroom() will return how much space is left at the top
	of the buffer (before the main data).  Remember, this headroom
	space must be reserved before the skb_put() function is called.
	*/

/*
   This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c

   For comments look at net/ipv4/ip_gre.c --ANK
 */


#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <asm/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/netfilter_ipv4.h>
#include <linux/if_ether.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");

static int ipip_net_id __read_mostly;

static int ipip_tunnel_init(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;

static int ipip_err(struct sk_buff *skb, u32 info)
{

/* All the routers (except for Linux) return only
   8 bytes of packet payload. It means, that precise relaying of
   ICMP in the real Internet is absolutely infeasible.
 */
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	struct ip_tunnel *t;
	int err;
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;

	err = -ENOENT;
	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
			     iph->daddr, iph->saddr, 0);
	if (t == NULL)
		goto out;

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
				 t->parms.link, 0, IPPROTO_IPIP, 0);
		err = 0;
		goto out;
	}

	if (type == ICMP_REDIRECT) {
		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
			      IPPROTO_IPIP, 0);
		err = 0;
		goto out;
	}

	if (t->parms.iph.daddr == 0)
		goto out;

	err = 0;
	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
		goto out;

	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
		t->err_count++;
	else
		t->err_count = 1;
	t->err_time = jiffies;

out:
	return err;
}

static const struct tnl_ptk_info tpi = {
	/* no tunnel info required for ipip. */
	.proto = htons(ETH_P_IP),
};

static int ipip_rcv(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
	struct ip_tunnel *tunnel;
	const struct iphdr *iph;

	iph = ip_hdr(skb);
	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
			iph->saddr, iph->daddr, 0);
	if (tunnel) {
		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto drop;
		if (iptunnel_pull_header(skb, 0, tpi.proto))
			goto drop;
		return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
	}

	return -1;

drop:
	kfree_skb(skb);
	return 0;
}

/*
 *	This function assumes it is being called from dev_queue_xmit()
 *	and that skb is filled properly by that function.
 */
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr  *tiph = &tunnel->parms.iph;

	if (unlikely(skb->protocol != htons(ETH_P_IP)))
		goto tx_error;

	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
	if (IS_ERR(skb))
		goto out;

	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
	return NETDEV_TX_OK;

tx_error:
	kfree_skb(skb);
out:
	dev->stats.tx_errors++;
	return NETDEV_TX_OK;
}

static int
ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip_tunnel_parm p;

	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
		return -EFAULT;

	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
			return -EINVAL;
	}

	p.i_key = p.o_key = 0;
	p.i_flags = p.o_flags = 0;
	if (p.iph.ttl)
		p.iph.frag_off |= htons(IP_DF);

	err = ip_tunnel_ioctl(dev, &p, cmd);
	if (err)
		return err;

	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
		return -EFAULT;

	return 0;
}

static const struct net_device_ops ipip_netdev_ops = {
	.ndo_init       = ipip_tunnel_init,
	.ndo_uninit     = ip_tunnel_uninit,
	.ndo_start_xmit	= ipip_tunnel_xmit,
	.ndo_do_ioctl	= ipip_tunnel_ioctl,
	.ndo_change_mtu = ip_tunnel_change_mtu,
	.ndo_get_stats64 = ip_tunnel_get_stats64,
};

#define IPIP_FEATURES (NETIF_F_SG |		\
		       NETIF_F_FRAGLIST |	\
		       NETIF_F_HIGHDMA |	\
		       NETIF_F_GSO_SOFTWARE |	\
		       NETIF_F_HW_CSUM)

static void ipip_tunnel_setup(struct net_device *dev)
{
	dev->netdev_ops		= &ipip_netdev_ops;

	dev->type		= ARPHRD_TUNNEL;
	dev->flags		= IFF_NOARP;
	dev->iflink		= 0;
	dev->addr_len		= 4;
	dev->features		|= NETIF_F_LLTX;
	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;

	dev->features		|= IPIP_FEATURES;
	dev->hw_features	|= IPIP_FEATURES;
	ip_tunnel_setup(dev, ipip_net_id);
}

static int ipip_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);

	tunnel->hlen = 0;
	tunnel->parms.iph.protocol = IPPROTO_IPIP;
	return ip_tunnel_init(dev);
}

static void ipip_netlink_parms(struct nlattr *data[],
			       struct ip_tunnel_parm *parms)
{
	memset(parms, 0, sizeof(*parms));

	parms->iph.version = 4;
	parms->iph.protocol = IPPROTO_IPIP;
	parms->iph.ihl = 5;

	if (!data)
		return;

	if (data[IFLA_IPTUN_LINK])
		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);

	if (data[IFLA_IPTUN_LOCAL])
		parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);

	if (data[IFLA_IPTUN_REMOTE])
		parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);

	if (data[IFLA_IPTUN_TTL]) {
		parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
		if (parms->iph.ttl)
			parms->iph.frag_off = htons(IP_DF);
	}

	if (data[IFLA_IPTUN_TOS])
		parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);

	if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
		parms->iph.frag_off = htons(IP_DF);
}

static int ipip_newlink(struct net *src_net, struct net_device *dev,
			struct nlattr *tb[], struct nlattr *data[])
{
	struct ip_tunnel_parm p;

	ipip_netlink_parms(data, &p);
	return ip_tunnel_newlink(dev, tb, &p);
}

static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
			   struct nlattr *data[])
{
	struct ip_tunnel_parm p;

	ipip_netlink_parms(data, &p);

	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
		return -EINVAL;

	return ip_tunnel_changelink(dev, tb, &p);
}

static size_t ipip_get_size(const struct net_device *dev)
{
	return
		/* IFLA_IPTUN_LINK */
		nla_total_size(4) +
		/* IFLA_IPTUN_LOCAL */
		nla_total_size(4) +
		/* IFLA_IPTUN_REMOTE */
		nla_total_size(4) +
		/* IFLA_IPTUN_TTL */
		nla_total_size(1) +
		/* IFLA_IPTUN_TOS */
		nla_total_size(1) +
		/* IFLA_IPTUN_PMTUDISC */
		nla_total_size(1) +
		0;
}

static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct ip_tunnel_parm *parm = &tunnel->parms;

	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
		       !!(parm->iph.frag_off & htons(IP_DF))))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = {
	[IFLA_IPTUN_LINK]		= { .type = NLA_U32 },
	[IFLA_IPTUN_LOCAL]		= { .type = NLA_U32 },
	[IFLA_IPTUN_REMOTE]		= { .type = NLA_U32 },
	[IFLA_IPTUN_TTL]		= { .type = NLA_U8 },
	[IFLA_IPTUN_TOS]		= { .type = NLA_U8 },
	[IFLA_IPTUN_PMTUDISC]		= { .type = NLA_U8 },
};

static struct rtnl_link_ops ipip_link_ops __read_mostly = {
	.kind		= "ipip",
	.maxtype	= IFLA_IPTUN_MAX,
	.policy		= ipip_policy,
	.priv_size	= sizeof(struct ip_tunnel),
	.setup		= ipip_tunnel_setup,
	.newlink	= ipip_newlink,
	.changelink	= ipip_changelink,
	.dellink	= ip_tunnel_dellink,
	.get_size	= ipip_get_size,
	.fill_info	= ipip_fill_info,
};

static struct xfrm_tunnel ipip_handler __read_mostly = {
	.handler	=	ipip_rcv,
	.err_handler	=	ipip_err,
	.priority	=	1,
};

static int __net_init ipip_init_net(struct net *net)
{
	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}

static void __net_exit ipip_exit_net(struct net *net)
{
	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
	ip_tunnel_delete_net(itn, &ipip_link_ops);
}

static struct pernet_operations ipip_net_ops = {
	.init = ipip_init_net,
	.exit = ipip_exit_net,
	.id   = &ipip_net_id,
	.size = sizeof(struct ip_tunnel_net),
};

static int __init ipip_init(void)
{
	int err;

	pr_info("ipip: IPv4 over IPv4 tunneling driver\n");

	err = register_pernet_device(&ipip_net_ops);
	if (err < 0)
		return err;
	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
	if (err < 0) {
		pr_info("%s: can't register tunnel\n", __func__);
		goto xfrm_tunnel_failed;
	}
	err = rtnl_link_register(&ipip_link_ops);
	if (err < 0)
		goto rtnl_link_failed;

out:
	return err;

rtnl_link_failed:
	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_tunnel_failed:
	unregister_pernet_device(&ipip_net_ops);
	goto out;
}

static void __exit ipip_fini(void)
{
	rtnl_link_unregister(&ipip_link_ops);
	if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
		pr_info("%s: can't deregister tunnel\n", __func__);

	unregister_pernet_device(&ipip_net_ops);
}

module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("ipip");
MODULE_ALIAS_NETDEV("tunl0");