summaryrefslogtreecommitdiffstats
path: root/net/ipv4/xfrm4_policy.c
blob: 6074b694f118d117bd715c8468f5056203131bb1 (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
/*
 * xfrm4_policy.c
 *
 * Changes:
 *	Kazunori MIYAZAWA @USAGI
 * 	YOSHIFUJI Hideaki @USAGI
 *		Split up af-specific portion
 *
 */

#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/inetdevice.h>
#include <linux/if_tunnel.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>

static struct xfrm_policy_afinfo xfrm4_policy_afinfo;

static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
					    int tos,
					    const xfrm_address_t *saddr,
					    const xfrm_address_t *daddr)
{
	struct rtable *rt;

	memset(fl4, 0, sizeof(*fl4));
	fl4->daddr = daddr->a4;
	fl4->flowi4_tos = tos;
	if (saddr)
		fl4->saddr = saddr->a4;

	rt = __ip_route_output_key(net, fl4);
	if (!IS_ERR(rt))
		return &rt->dst;

	return ERR_CAST(rt);
}

static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
					  const xfrm_address_t *saddr,
					  const xfrm_address_t *daddr)
{
	struct flowi4 fl4;

	return __xfrm4_dst_lookup(net, &fl4, tos, saddr, daddr);
}

static int xfrm4_get_saddr(struct net *net,
			   xfrm_address_t *saddr, xfrm_address_t *daddr)
{
	struct dst_entry *dst;
	struct flowi4 fl4;

	dst = __xfrm4_dst_lookup(net, &fl4, 0, NULL, daddr);
	if (IS_ERR(dst))
		return -EHOSTUNREACH;

	saddr->a4 = fl4.saddr;
	dst_release(dst);
	return 0;
}

static int xfrm4_get_tos(const struct flowi *fl)
{
	return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
}

static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
			   int nfheader_len)
{
	return 0;
}

static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
			  const struct flowi *fl)
{
	struct rtable *rt = (struct rtable *)xdst->route;
	const struct flowi4 *fl4 = &fl->u.ip4;

	xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
	xdst->u.rt.rt_iif = fl4->flowi4_iif;
	xdst->u.rt.rt_oif = fl4->flowi4_oif;

	xdst->u.dst.dev = dev;
	dev_hold(dev);

	/* Sheit... I remember I did this right. Apparently,
	 * it was magically lost, so this code needs audit */
	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
					      RTCF_LOCAL);
	xdst->u.rt.rt_type = rt->rt_type;
	xdst->u.rt.rt_gateway = rt->rt_gateway;
	xdst->u.rt.rt_pmtu = rt->rt_pmtu;

	return 0;
}

static void
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
	const struct iphdr *iph = ip_hdr(skb);
	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
	struct flowi4 *fl4 = &fl->u.ip4;

	memset(fl4, 0, sizeof(struct flowi4));
	fl4->flowi4_mark = skb->mark;

	if (!ip_is_fragment(iph)) {
		switch (iph->protocol) {
		case IPPROTO_UDP:
		case IPPROTO_UDPLITE:
		case IPPROTO_TCP:
		case IPPROTO_SCTP:
		case IPPROTO_DCCP:
			if (xprth + 4 < skb->data ||
			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
				__be16 *ports = (__be16 *)xprth;

				fl4->fl4_sport = ports[!!reverse];
				fl4->fl4_dport = ports[!reverse];
			}
			break;

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

				fl4->fl4_icmp_type = icmp[0];
				fl4->fl4_icmp_code = icmp[1];
			}
			break;

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

				fl4->fl4_ipsec_spi = ehdr[0];
			}
			break;

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

				fl4->fl4_ipsec_spi = ah_hdr[1];
			}
			break;

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

				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
			}
			break;

		case IPPROTO_GRE:
			if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
				__be16 *greflags = (__be16 *)xprth;
				__be32 *gre_hdr = (__be32 *)xprth;

				if (greflags[0] & GRE_KEY) {
					if (greflags[0] & GRE_CSUM)
						gre_hdr++;
					fl4->fl4_gre_key = gre_hdr[1];
				}
			}
			break;

		default:
			fl4->fl4_ipsec_spi = 0;
			break;
		}
	}
	fl4->flowi4_proto = iph->protocol;
	fl4->daddr = reverse ? iph->saddr : iph->daddr;
	fl4->saddr = reverse ? iph->daddr : iph->saddr;
	fl4->flowi4_tos = iph->tos;
}

static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
	struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);

	xfrm4_policy_afinfo.garbage_collect(net);
	return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
}

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

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

static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
			   struct sk_buff *skb)
{
	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
	struct dst_entry *path = xdst->route;

	path->ops->redirect(path, sk, skb);
}

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

	dst_destroy_metrics_generic(dst);

	xfrm_dst_destroy(xdst);
}

static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			     int unregister)
{
	if (!unregister)
		return;

	xfrm_dst_ifdown(dst, dev);
}

static struct dst_ops xfrm4_dst_ops = {
	.family =		AF_INET,
	.protocol =		cpu_to_be16(ETH_P_IP),
	.gc =			xfrm4_garbage_collect,
	.update_pmtu =		xfrm4_update_pmtu,
	.redirect =		xfrm4_redirect,
	.cow_metrics =		dst_cow_metrics_generic,
	.destroy =		xfrm4_dst_destroy,
	.ifdown =		xfrm4_dst_ifdown,
	.local_out =		__ip_local_out,
	.gc_thresh =		1024,
};

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,
	.decode_session =	_decode_session4,
	.get_tos =		xfrm4_get_tos,
	.init_path =		xfrm4_init_path,
	.fill_dst =		xfrm4_fill_dst,
	.blackhole_route =	ipv4_blackhole_route,
};

#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm4_policy_table[] = {
	{
		.procname       = "xfrm4_gc_thresh",
		.data           = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
		.maxlen         = sizeof(int),
		.mode           = 0644,
		.proc_handler   = proc_dointvec,
	},
	{ }
};

static struct ctl_table_header *sysctl_hdr;
#endif

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

static void __exit xfrm4_policy_fini(void)
{
#ifdef CONFIG_SYSCTL
	if (sysctl_hdr)
		unregister_net_sysctl_table(sysctl_hdr);
#endif
	xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
}

void __init xfrm4_init(int rt_max_size)
{
	/*
	 * Select a default value for the gc_thresh based on the main route
	 * table hash size.  It seems to me the worst case scenario is when
	 * we have ipsec operating in transport mode, in which we create a
	 * dst_entry per socket.  The xfrm gc algorithm starts trying to remove
	 * entries at gc_thresh, and prevents new allocations as 2*gc_thresh
	 * so lets set an initial xfrm gc_thresh value at the rt_max_size/2.
	 * That will let us store an ipsec connection per route table entry,
	 * and start cleaning when were 1/2 full
	 */
	xfrm4_dst_ops.gc_thresh = rt_max_size/2;
	dst_entries_init(&xfrm4_dst_ops);

	xfrm4_state_init();
	xfrm4_policy_init();
#ifdef CONFIG_SYSCTL
	sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4",
					 xfrm4_policy_table);
#endif
}