summaryrefslogtreecommitdiffstats
path: root/net/netfilter/xt_TCPMSS.c
blob: a75240f0d42b8da245035a8f8ee59b51895c445e (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
/*
 * This is a module which is used for setting the MSS option in TCP packets.
 *
 * Copyright (C) 2000 Marc Boucher <marc@mbsi.ca>
 * Copyright (C) 2007 Patrick McHardy <kaber@trash.net>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/gfp.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/ipv6.h>
#include <net/route.h>
#include <net/tcp.h>

#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_tcpudp.h>
#include <linux/netfilter/xt_TCPMSS.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>");
MODULE_DESCRIPTION("Xtables: TCP Maximum Segment Size (MSS) adjustment");
MODULE_ALIAS("ipt_TCPMSS");
MODULE_ALIAS("ip6t_TCPMSS");

static inline unsigned int
optlen(const u_int8_t *opt, unsigned int offset)
{
	/* Beware zero-length options: make finite progress */
	if (opt[offset] <= TCPOPT_NOP || opt[offset+1] == 0)
		return 1;
	else
		return opt[offset+1];
}

static int
tcpmss_mangle_packet(struct sk_buff *skb,
		     const struct xt_tcpmss_info *info,
		     unsigned int in_mtu,
		     unsigned int tcphoff,
		     unsigned int minlen)
{
	struct tcphdr *tcph;
	unsigned int tcplen, i;
	__be16 oldval;
	u16 newmss;
	u8 *opt;

	if (!skb_make_writable(skb, skb->len))
		return -1;

	tcplen = skb->len - tcphoff;
	tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);

	/* Header cannot be larger than the packet */
	if (tcplen < tcph->doff*4)
		return -1;

	if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
		if (dst_mtu(skb_dst(skb)) <= minlen) {
			net_err_ratelimited("unknown or invalid path-MTU (%u)\n",
					    dst_mtu(skb_dst(skb)));
			return -1;
		}
		if (in_mtu <= minlen) {
			net_err_ratelimited("unknown or invalid path-MTU (%u)\n",
					    in_mtu);
			return -1;
		}
		newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen;
	} else
		newmss = info->mss;

	opt = (u_int8_t *)tcph;
	for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) {
		if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS &&
		    opt[i+1] == TCPOLEN_MSS) {
			u_int16_t oldmss;

			oldmss = (opt[i+2] << 8) | opt[i+3];

			/* Never increase MSS, even when setting it, as
			 * doing so results in problems for hosts that rely
			 * on MSS being set correctly.
			 */
			if (oldmss <= newmss)
				return 0;

			opt[i+2] = (newmss & 0xff00) >> 8;
			opt[i+3] = newmss & 0x00ff;

			inet_proto_csum_replace2(&tcph->check, skb,
						 htons(oldmss), htons(newmss),
						 0);
			return 0;
		}
	}

	/* There is data after the header so the option can't be added
	   without moving it, and doing so may make the SYN packet
	   itself too large. Accept the packet unmodified instead. */
	if (tcplen > tcph->doff*4)
		return 0;

	/*
	 * MSS Option not found ?! add it..
	 */
	if (skb_tailroom(skb) < TCPOLEN_MSS) {
		if (pskb_expand_head(skb, 0,
				     TCPOLEN_MSS - skb_tailroom(skb),
				     GFP_ATOMIC))
			return -1;
		tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
	}

	skb_put(skb, TCPOLEN_MSS);

	opt = (u_int8_t *)tcph + sizeof(struct tcphdr);
	memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr));

	inet_proto_csum_replace2(&tcph->check, skb,
				 htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1);
	opt[0] = TCPOPT_MSS;
	opt[1] = TCPOLEN_MSS;
	opt[2] = (newmss & 0xff00) >> 8;
	opt[3] = newmss & 0x00ff;

	inet_proto_csum_replace4(&tcph->check, skb, 0, *((__be32 *)opt), 0);

	oldval = ((__be16 *)tcph)[6];
	tcph->doff += TCPOLEN_MSS/4;
	inet_proto_csum_replace2(&tcph->check, skb,
				 oldval, ((__be16 *)tcph)[6], 0);
	return TCPOLEN_MSS;
}

static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
				    unsigned int family)
{
	struct flowi fl;
	const struct nf_afinfo *ai;
	struct rtable *rt = NULL;
	u_int32_t mtu     = ~0U;

	if (family == PF_INET) {
		struct flowi4 *fl4 = &fl.u.ip4;
		memset(fl4, 0, sizeof(*fl4));
		fl4->daddr = ip_hdr(skb)->saddr;
	} else {
		struct flowi6 *fl6 = &fl.u.ip6;

		memset(fl6, 0, sizeof(*fl6));
		fl6->daddr = ipv6_hdr(skb)->saddr;
	}
	rcu_read_lock();
	ai = nf_get_afinfo(family);
	if (ai != NULL)
		ai->route(&init_net, (struct dst_entry **)&rt, &fl, false);
	rcu_read_unlock();

	if (rt != NULL) {
		mtu = dst_mtu(&rt->dst);
		dst_release(&rt->dst);
	}
	return mtu;
}

static unsigned int
tcpmss_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
	struct iphdr *iph = ip_hdr(skb);
	__be16 newlen;
	int ret;

	ret = tcpmss_mangle_packet(skb, par->targinfo,
				   tcpmss_reverse_mtu(skb, PF_INET),
				   iph->ihl * 4,
				   sizeof(*iph) + sizeof(struct tcphdr));
	if (ret < 0)
		return NF_DROP;
	if (ret > 0) {
		iph = ip_hdr(skb);
		newlen = htons(ntohs(iph->tot_len) + ret);
		csum_replace2(&iph->check, iph->tot_len, newlen);
		iph->tot_len = newlen;
	}
	return XT_CONTINUE;
}

#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static unsigned int
tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
	u8 nexthdr;
	__be16 frag_off;
	int tcphoff;
	int ret;

	nexthdr = ipv6h->nexthdr;
	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
	if (tcphoff < 0)
		return NF_DROP;
	ret = tcpmss_mangle_packet(skb, par->targinfo,
				   tcpmss_reverse_mtu(skb, PF_INET6),
				   tcphoff,
				   sizeof(*ipv6h) + sizeof(struct tcphdr));
	if (ret < 0)
		return NF_DROP;
	if (ret > 0) {
		ipv6h = ipv6_hdr(skb);
		ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) + ret);
	}
	return XT_CONTINUE;
}
#endif

/* Must specify -p tcp --syn */
static inline bool find_syn_match(const struct xt_entry_match *m)
{
	const struct xt_tcp *tcpinfo = (const struct xt_tcp *)m->data;

	if (strcmp(m->u.kernel.match->name, "tcp") == 0 &&
	    tcpinfo->flg_cmp & TCPHDR_SYN &&
	    !(tcpinfo->invflags & XT_TCP_INV_FLAGS))
		return true;

	return false;
}

static int tcpmss_tg4_check(const struct xt_tgchk_param *par)
{
	const struct xt_tcpmss_info *info = par->targinfo;
	const struct ipt_entry *e = par->entryinfo;
	const struct xt_entry_match *ematch;

	if (info->mss == XT_TCPMSS_CLAMP_PMTU &&
	    (par->hook_mask & ~((1 << NF_INET_FORWARD) |
			   (1 << NF_INET_LOCAL_OUT) |
			   (1 << NF_INET_POST_ROUTING))) != 0) {
		pr_info("path-MTU clamping only supported in "
			"FORWARD, OUTPUT and POSTROUTING hooks\n");
		return -EINVAL;
	}
	xt_ematch_foreach(ematch, e)
		if (find_syn_match(ematch))
			return 0;
	pr_info("Only works on TCP SYN packets\n");
	return -EINVAL;
}

#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static int tcpmss_tg6_check(const struct xt_tgchk_param *par)
{
	const struct xt_tcpmss_info *info = par->targinfo;
	const struct ip6t_entry *e = par->entryinfo;
	const struct xt_entry_match *ematch;

	if (info->mss == XT_TCPMSS_CLAMP_PMTU &&
	    (par->hook_mask & ~((1 << NF_INET_FORWARD) |
			   (1 << NF_INET_LOCAL_OUT) |
			   (1 << NF_INET_POST_ROUTING))) != 0) {
		pr_info("path-MTU clamping only supported in "
			"FORWARD, OUTPUT and POSTROUTING hooks\n");
		return -EINVAL;
	}
	xt_ematch_foreach(ematch, e)
		if (find_syn_match(ematch))
			return 0;
	pr_info("Only works on TCP SYN packets\n");
	return -EINVAL;
}
#endif

static struct xt_target tcpmss_tg_reg[] __read_mostly = {
	{
		.family		= NFPROTO_IPV4,
		.name		= "TCPMSS",
		.checkentry	= tcpmss_tg4_check,
		.target		= tcpmss_tg4,
		.targetsize	= sizeof(struct xt_tcpmss_info),
		.proto		= IPPROTO_TCP,
		.me		= THIS_MODULE,
	},
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
	{
		.family		= NFPROTO_IPV6,
		.name		= "TCPMSS",
		.checkentry	= tcpmss_tg6_check,
		.target		= tcpmss_tg6,
		.targetsize	= sizeof(struct xt_tcpmss_info),
		.proto		= IPPROTO_TCP,
		.me		= THIS_MODULE,
	},
#endif
};

static int __init tcpmss_tg_init(void)
{
	return xt_register_targets(tcpmss_tg_reg, ARRAY_SIZE(tcpmss_tg_reg));
}

static void __exit tcpmss_tg_exit(void)
{
	xt_unregister_targets(tcpmss_tg_reg, ARRAY_SIZE(tcpmss_tg_reg));
}

module_init(tcpmss_tg_init);
module_exit(tcpmss_tg_exit);