aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/xfrm4_policy.c
blob: 329825ca68fe71730387583c9d96129ee3770db2 (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
/*
 * xfrm4_policy.c
 *
 * Changes:
 *	Kazunori MIYAZAWA @USAGI
 * 	YOSHIFUJI Hideaki @USAGI
 *		Split up af-specific portion
 *
 */

#include <linux/compiler.h>
#include <linux/inetdevice.h>
#include <net/xfrm.h>
#include <net/ip.h>

static struct dst_ops xfrm4_dst_ops;
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;

static int xfrm4_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
{
	return __ip_route_output_key((struct rtable**)dst, fl);
}

static int xfrm4_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr)
{
	struct rtable *rt;
	struct flowi fl_tunnel = {
		.nl_u = {
			.ip4_u = {
				.daddr = daddr->a4,
			},
		},
	};

	if (!xfrm4_dst_lookup((struct xfrm_dst **)&rt, &fl_tunnel)) {
		saddr->a4 = rt->rt_src;
		dst_release(&rt->u.dst);
		return 0;
	}
	return -EHOSTUNREACH;
}

static struct dst_entry *
__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
{
	struct dst_entry *dst;

	read_lock_bh(&policy->lock);
	for (dst = policy->bundles; dst; dst = dst->next) {
		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
		if (xdst->u.rt.fl.oif == fl->oif &&	/*XXX*/
		    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
		    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
		    xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
		    xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
			dst_clone(dst);
			break;
		}
	}
	read_unlock_bh(&policy->lock);
	return dst;
}

/* Allocate chain of dst_entry's, attach known xfrm's, calculate
 * all the metrics... Shortly, bundle a bundle.
 */

static int
__xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx,
		      struct flowi *fl, struct dst_entry **dst_p)
{
	struct dst_entry *dst, *dst_prev;
	struct rtable *rt0 = (struct rtable*)(*dst_p);
	struct rtable *rt = rt0;
	struct flowi fl_tunnel = {
		.nl_u = {
			.ip4_u = {
				.saddr = fl->fl4_src,
				.daddr = fl->fl4_dst,
				.tos = fl->fl4_tos
			}
		}
	};
	int i;
	int err;
	int header_len = 0;
	int trailer_len = 0;

	dst = dst_prev = NULL;
	dst_hold(&rt->u.dst);

	for (i = 0; i < nx; i++) {
		struct dst_entry *dst1 = dst_alloc(&xfrm4_dst_ops);
		struct xfrm_dst *xdst;

		if (unlikely(dst1 == NULL)) {
			err = -ENOBUFS;
			dst_release(&rt->u.dst);
			goto error;
		}

		if (!dst)
			dst = dst1;
		else {
			dst_prev->child = dst1;
			dst1->flags |= DST_NOHASH;
			dst_clone(dst1);
		}

		xdst = (struct xfrm_dst *)dst1;
		xdst->route = &rt->u.dst;
		xdst->genid = xfrm[i]->genid;

		dst1->next = dst_prev;
		dst_prev = dst1;

		header_len += xfrm[i]->props.header_len;
		trailer_len += xfrm[i]->props.trailer_len;

		if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL) {
			unsigned short encap_family = xfrm[i]->props.family;
			switch (encap_family) {
			case AF_INET:
				fl_tunnel.fl4_dst = xfrm[i]->id.daddr.a4;
				fl_tunnel.fl4_src = xfrm[i]->props.saddr.a4;
				break;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
			case AF_INET6:
				ipv6_addr_copy(&fl_tunnel.fl6_dst, (struct in6_addr*)&xfrm[i]->id.daddr.a6);
				ipv6_addr_copy(&fl_tunnel.fl6_src, (struct in6_addr*)&xfrm[i]->props.saddr.a6);
				break;
#endif
			default:
				BUG_ON(1);
			}
			err = xfrm_dst_lookup((struct xfrm_dst **)&rt,
					      &fl_tunnel, encap_family);
			if (err)
				goto error;
		} else
			dst_hold(&rt->u.dst);
	}

	dst_prev->child = &rt->u.dst;
	dst->path = &rt->u.dst;

	*dst_p = dst;
	dst = dst_prev;

	dst_prev = *dst_p;
	i = 0;
	for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) {
		struct xfrm_dst *x = (struct xfrm_dst*)dst_prev;
		struct xfrm_state_afinfo *afinfo;
		x->u.rt.fl = *fl;

		dst_prev->xfrm = xfrm[i++];
		dst_prev->dev = rt->u.dst.dev;
		if (rt->u.dst.dev)
			dev_hold(rt->u.dst.dev);
		dst_prev->obsolete	= -1;
		dst_prev->flags	       |= DST_HOST;
		dst_prev->lastuse	= jiffies;
		dst_prev->header_len	= header_len;
		dst_prev->nfheader_len	= 0;
		dst_prev->trailer_len	= trailer_len;
		memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics));

		/* Copy neighbout for reachability confirmation */
		dst_prev->neighbour	= neigh_clone(rt->u.dst.neighbour);
		dst_prev->input		= rt->u.dst.input;
		/* XXX: When IPv6 module can be unloaded, we should manage reference
		 * to xfrm6_output in afinfo->output. Miyazawa
		 * */
		afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family);
		if (!afinfo) {
			dst = *dst_p;
			err = -EAFNOSUPPORT;
			goto error;
		}
		dst_prev->output = afinfo->output;
		xfrm_state_put_afinfo(afinfo);
		if (dst_prev->xfrm->props.family == AF_INET && rt->peer)
			atomic_inc(&rt->peer->refcnt);
		x->u.rt.peer = rt->peer;
		/* Sheit... I remember I did this right. Apparently,
		 * it was magically lost, so this code needs audit */
		x->u.rt.rt_flags = rt0->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL);
		x->u.rt.rt_type = rt->rt_type;
		x->u.rt.rt_src = rt0->rt_src;
		x->u.rt.rt_dst = rt0->rt_dst;
		x->u.rt.rt_gateway = rt->rt_gateway;
		x->u.rt.rt_spec_dst = rt0->rt_spec_dst;
		x->u.rt.idev = rt0->idev;
		in_dev_hold(rt0->idev);
		header_len -= x->u.dst.xfrm->props.header_len;
		trailer_len -= x->u.dst.xfrm->props.trailer_len;
	}

	xfrm_init_pmtu(dst);
	return 0;

error:
	if (dst)
		dst_free(dst);
	return err;
}

static void
_decode_session4(struct sk_buff *skb, struct flowi *fl)
{
	struct iphdr *iph = ip_hdr(skb);
	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;

	memset(fl, 0, sizeof(struct flowi));
	if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
		switch (iph->protocol) {
		case IPPROTO_UDP:
		case IPPROTO_UDPLITE:
		case IPPROTO_TCP:
		case IPPROTO_SCTP:
		case IPPROTO_DCCP:
			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
				__be16 *ports = (__be16 *)xprth;

				fl->fl_ip_sport = ports[0];
				fl->fl_ip_dport = ports[1];
			}
			break;

		case IPPROTO_ICMP:
			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
				u8 *icmp = xprth;

				fl->fl_icmp_type = icmp[0];
				fl->fl_icmp_code = icmp[1];
			}
			break;

		case IPPROTO_ESP:
			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
				__be32 *ehdr = (__be32 *)xprth;

				fl->fl_ipsec_spi = ehdr[0];
			}
			break;

		case IPPROTO_AH:
			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
				__be32 *ah_hdr = (__be32*)xprth;

				fl->fl_ipsec_spi = ah_hdr[1];
			}
			break;

		case IPPROTO_COMP:
			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
				__be16 *ipcomp_hdr = (__be16 *)xprth;

				fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
			}
			break;
		default:
			fl->fl_ipsec_spi = 0;
			break;
		}
	}
	fl->proto = iph->protocol;
	fl->fl4_dst = iph->daddr;
	fl->fl4_src = iph->saddr;
	fl->fl4_tos = iph->tos;
}

static inline int xfrm4_garbage_collect(void)
{
	xfrm4_policy_afinfo.garbage_collect();
	return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
}

static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
{
	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
	struct dst_entry *path = xdst->route;

	path->ops->update_pmtu(path, mtu);
}

static void xfrm4_dst_destroy(struct dst_entry *dst)
{
	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;

	if (likely(xdst->u.rt.idev))
		in_dev_put(xdst->u.rt.idev);
	if (dst->xfrm && dst->xfrm->props.family == AF_INET && likely(xdst->u.rt.peer))
		inet_putpeer(xdst->u.rt.peer);
	xfrm_dst_destroy(xdst);
}

static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			     int unregister)
{
	struct xfrm_dst *xdst;

	if (!unregister)
		return;

	xdst = (struct xfrm_dst *)dst;
	if (xdst->u.rt.idev->dev == dev) {
		struct in_device *loopback_idev = in_dev_get(init_net.loopback_dev);
		BUG_ON(!loopback_idev);

		do {
			in_dev_put(xdst->u.rt.idev);
			xdst->u.rt.idev = loopback_idev;
			in_dev_hold(loopback_idev);
			xdst = (struct xfrm_dst *)xdst->u.dst.child;
		} while (xdst->u.dst.xfrm);

		__in_dev_put(loopback_idev);
	}

	xfrm_dst_ifdown(dst, dev);
}

static struct dst_ops xfrm4_dst_ops = {
	.family =		AF_INET,
	.protocol =		__constant_htons(ETH_P_IP),
	.gc =			xfrm4_garbage_collect,
	.update_pmtu =		xfrm4_update_pmtu,
	.destroy =		xfrm4_dst_destroy,
	.ifdown =		xfrm4_dst_ifdown,
	.gc_thresh =		1024,
	.entry_size =		sizeof(struct xfrm_dst),
};

static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
	.family = 		AF_INET,
	.dst_ops =		&xfrm4_dst_ops,
	.dst_lookup =		xfrm4_dst_lookup,
	.get_saddr =		xfrm4_get_saddr,
	.find_bundle = 		__xfrm4_find_bundle,
	.bundle_create =	__xfrm4_bundle_create,
	.decode_session =	_decode_session4,
};

static void __init xfrm4_policy_init(void)
{
	xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
}

static void __exit xfrm4_policy_fini(void)
{
	xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
}

void __init xfrm4_init(void)
{
	xfrm4_state_init();
	xfrm4_policy_init();
}