summaryrefslogtreecommitdiff
path: root/net/netfilter/nf_conntrack_proto_icmp.c
blob: b38b7164acd5ff466edf1876b6b338f3aed12857 (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
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
// SPDX-License-Identifier: GPL-2.0-only
/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
 * (C) 2006-2010 Patrick McHardy <kaber@trash.net>
 */

#include <linux/types.h>
#include <linux/timer.h>
#include <linux/netfilter.h>
#include <linux/in.h>
#include <linux/icmp.h>
#include <linux/seq_file.h>
#include <net/ip.h>
#include <net/checksum.h>
#include <linux/netfilter_ipv4.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_timeout.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_log.h>

#include "nf_internals.h"

static const unsigned int nf_ct_icmp_timeout = 30*HZ;

bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
		       struct net *net, struct nf_conntrack_tuple *tuple)
{
	const struct icmphdr *hp;
	struct icmphdr _hdr;

	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
	if (hp == NULL)
		return false;

	tuple->dst.u.icmp.type = hp->type;
	tuple->src.u.icmp.id = hp->un.echo.id;
	tuple->dst.u.icmp.code = hp->code;

	return true;
}

/* Add 1; spaces filled with 0. */
static const u_int8_t invmap[] = {
	[ICMP_ECHO] = ICMP_ECHOREPLY + 1,
	[ICMP_ECHOREPLY] = ICMP_ECHO + 1,
	[ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1,
	[ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1,
	[ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1,
	[ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1,
	[ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1,
	[ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1
};

bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple,
				    const struct nf_conntrack_tuple *orig)
{
	if (orig->dst.u.icmp.type >= sizeof(invmap) ||
	    !invmap[orig->dst.u.icmp.type])
		return false;

	tuple->src.u.icmp.id = orig->src.u.icmp.id;
	tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1;
	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
	return true;
}

/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_icmp_packet(struct nf_conn *ct,
			     struct sk_buff *skb,
			     enum ip_conntrack_info ctinfo,
			     const struct nf_hook_state *state)
{
	/* Do not immediately delete the connection after the first
	   successful reply to avoid excessive conntrackd traffic
	   and also to handle correctly ICMP echo reply duplicates. */
	unsigned int *timeout = nf_ct_timeout_lookup(ct);
	static const u_int8_t valid_new[] = {
		[ICMP_ECHO] = 1,
		[ICMP_TIMESTAMP] = 1,
		[ICMP_INFO_REQUEST] = 1,
		[ICMP_ADDRESS] = 1
	};

	if (state->pf != NFPROTO_IPV4)
		return -NF_ACCEPT;

	if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) ||
	    !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) {
		/* Can't create a new ICMP `conn' with this. */
		pr_debug("icmp: can't create new conn with type %u\n",
			 ct->tuplehash[0].tuple.dst.u.icmp.type);
		nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple);
		return -NF_ACCEPT;
	}

	if (!timeout)
		timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout;

	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
	return NF_ACCEPT;
}

/* Check inner header is related to any of the existing connections */
int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
			    unsigned int dataoff,
			    const struct nf_hook_state *state,
			    u8 l4proto, union nf_inet_addr *outer_daddr)
{
	struct nf_conntrack_tuple innertuple, origtuple;
	const struct nf_conntrack_tuple_hash *h;
	const struct nf_conntrack_zone *zone;
	enum ip_conntrack_info ctinfo;
	struct nf_conntrack_zone tmp;
	union nf_inet_addr *ct_daddr;
	enum ip_conntrack_dir dir;
	struct nf_conn *ct;

	WARN_ON(skb_nfct(skb));
	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);

	/* Are they talking about one of our connections? */
	if (!nf_ct_get_tuplepr(skb, dataoff,
			       state->pf, state->net, &origtuple))
		return -NF_ACCEPT;

	/* Ordinarily, we'd expect the inverted tupleproto, but it's
	   been preserved inside the ICMP. */
	if (!nf_ct_invert_tuple(&innertuple, &origtuple))
		return -NF_ACCEPT;

	h = nf_conntrack_find_get(state->net, zone, &innertuple);
	if (!h)
		return -NF_ACCEPT;

	/* Consider: A -> T (=This machine) -> B
	 *   Conntrack entry will look like this:
	 *      Original:  A->B
	 *      Reply:     B->T (SNAT case) OR A
	 *
	 * When this function runs, we got packet that looks like this:
	 * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..).
	 *
	 * Above nf_conntrack_find_get() makes lookup based on inner_hdr,
	 * so we should expect that destination of the found connection
	 * matches outer header destination address.
	 *
	 * In above example, we can consider these two cases:
	 *  1. Error coming in reply direction from B or M (middle box) to
	 *     T (SNAT case) or A.
	 *     Inner saddr will be B, dst will be T or A.
	 *     The found conntrack will be reply tuple (B->T/A).
	 *  2. Error coming in original direction from A or M to B.
	 *     Inner saddr will be A, inner daddr will be B.
	 *     The found conntrack will be original tuple (A->B).
	 *
	 * In both cases, conntrack[dir].dst == inner.dst.
	 *
	 * A bogus packet could look like this:
	 *   Inner: B->T
	 *   Outer: B->X (other machine reachable by T).
	 *
	 * In this case, lookup yields connection A->B and will
	 * set packet from B->X as *RELATED*, even though no connection
	 * from X was ever seen.
	 */
	ct = nf_ct_tuplehash_to_ctrack(h);
	dir = NF_CT_DIRECTION(h);
	ct_daddr = &ct->tuplehash[dir].tuple.dst.u3;
	if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) {
		if (state->pf == AF_INET) {
			nf_l4proto_log_invalid(skb, state,
					       l4proto,
					       "outer daddr %pI4 != inner %pI4",
					       &outer_daddr->ip, &ct_daddr->ip);
		} else if (state->pf == AF_INET6) {
			nf_l4proto_log_invalid(skb, state,
					       l4proto,
					       "outer daddr %pI6 != inner %pI6",
					       &outer_daddr->ip6, &ct_daddr->ip6);
		}
		nf_ct_put(ct);
		return -NF_ACCEPT;
	}

	ctinfo = IP_CT_RELATED;
	if (dir == IP_CT_DIR_REPLY)
		ctinfo += IP_CT_IS_REPLY;

	/* Update skb to refer to this connection */
	nf_ct_set(skb, ct, ctinfo);
	return NF_ACCEPT;
}

static void icmp_error_log(const struct sk_buff *skb,
			   const struct nf_hook_state *state,
			   const char *msg)
{
	nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg);
}

/* Small and modified version of icmp_rcv */
int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
			      struct sk_buff *skb, unsigned int dataoff,
			      const struct nf_hook_state *state)
{
	union nf_inet_addr outer_daddr;
	const struct icmphdr *icmph;
	struct icmphdr _ih;

	/* Not enough header? */
	icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
	if (icmph == NULL) {
		icmp_error_log(skb, state, "short packet");
		return -NF_ACCEPT;
	}

	/* See nf_conntrack_proto_tcp.c */
	if (state->net->ct.sysctl_checksum &&
	    state->hook == NF_INET_PRE_ROUTING &&
	    nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) {
		icmp_error_log(skb, state, "bad hw icmp checksum");
		return -NF_ACCEPT;
	}

	/*
	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
	 *
	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
	 *		  discarded.
	 */
	if (icmph->type > NR_ICMP_TYPES) {
		icmp_error_log(skb, state, "invalid icmp type");
		return -NF_ACCEPT;
	}

	/* Need to track icmp error message? */
	if (!icmp_is_err(icmph->type))
		return NF_ACCEPT;

	memset(&outer_daddr, 0, sizeof(outer_daddr));
	outer_daddr.ip = ip_hdr(skb)->daddr;

	dataoff += sizeof(*icmph);
	return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
				       IPPROTO_ICMP, &outer_daddr);
}

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

static int icmp_tuple_to_nlattr(struct sk_buff *skb,
				const struct nf_conntrack_tuple *t)
{
	if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) ||
	    nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) ||
	    nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -1;
}

static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = {
	[CTA_PROTO_ICMP_TYPE]	= { .type = NLA_U8 },
	[CTA_PROTO_ICMP_CODE]	= { .type = NLA_U8 },
	[CTA_PROTO_ICMP_ID]	= { .type = NLA_U16 },
};

static int icmp_nlattr_to_tuple(struct nlattr *tb[],
				struct nf_conntrack_tuple *tuple,
				u_int32_t flags)
{
	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) {
		if (!tb[CTA_PROTO_ICMP_TYPE])
			return -EINVAL;

		tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]);
		if (tuple->dst.u.icmp.type >= sizeof(invmap) ||
		    !invmap[tuple->dst.u.icmp.type])
			return -EINVAL;
	}

	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) {
		if (!tb[CTA_PROTO_ICMP_CODE])
			return -EINVAL;

		tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]);
	}

	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) {
		if (!tb[CTA_PROTO_ICMP_ID])
			return -EINVAL;

		tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]);
	}

	return 0;
}

static unsigned int icmp_nlattr_tuple_size(void)
{
	static unsigned int size __read_mostly;

	if (!size)
		size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);

	return size;
}
#endif

#ifdef CONFIG_NF_CONNTRACK_TIMEOUT

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_cttimeout.h>

static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
				      struct net *net, void *data)
{
	unsigned int *timeout = data;
	struct nf_icmp_net *in = nf_icmp_pernet(net);

	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
		if (!timeout)
			timeout = &in->timeout;
		*timeout =
			ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
	} else if (timeout) {
		/* Set default ICMP timeout. */
		*timeout = in->timeout;
	}
	return 0;
}

static int
icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
{
	const unsigned int *timeout = data;

	if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -ENOSPC;
}

static const struct nla_policy
icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = {
	[CTA_TIMEOUT_ICMP_TIMEOUT]	= { .type = NLA_U32 },
};
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */

void nf_conntrack_icmp_init_net(struct net *net)
{
	struct nf_icmp_net *in = nf_icmp_pernet(net);

	in->timeout = nf_ct_icmp_timeout;
}

const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp =
{
	.l4proto		= IPPROTO_ICMP,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.tuple_to_nlattr	= icmp_tuple_to_nlattr,
	.nlattr_tuple_size	= icmp_nlattr_tuple_size,
	.nlattr_to_tuple	= icmp_nlattr_to_tuple,
	.nla_policy		= icmp_nla_policy,
#endif
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
	.ctnl_timeout		= {
		.nlattr_to_obj	= icmp_timeout_nlattr_to_obj,
		.obj_to_nlattr	= icmp_timeout_obj_to_nlattr,
		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
		.obj_size	= sizeof(unsigned int),
		.nla_policy	= icmp_timeout_nla_policy,
	},
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
};