aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/syncookies.c
blob: 307dc3c0d635da453e541c9056d60e484cd04b66 (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
/*
 *  Syncookies implementation for the Linux kernel
 *
 *  Copyright (C) 1997 Andi Kleen
 *  Based on ideas by D.J.Bernstein and Eric Schenk. 
 *
 *	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.
 * 
 *  $Id: syncookies.c,v 1.18 2002/02/01 22:01:04 davem Exp $
 *
 *  Missing: IPv6 support. 
 */

#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/cryptohash.h>
#include <linux/kernel.h>
#include <net/tcp.h>

extern int sysctl_tcp_syncookies;

static __u32 syncookie_secret[2][16-3+SHA_DIGEST_WORDS];

static __init int init_syncookies(void)
{
	get_random_bytes(syncookie_secret, sizeof(syncookie_secret));
	return 0;
}
module_init(init_syncookies);

#define COOKIEBITS 24	/* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)

static u32 cookie_hash(u32 saddr, u32 daddr, u32 sport, u32 dport,
		       u32 count, int c)
{
	__u32 tmp[16 + 5 + SHA_WORKSPACE_WORDS];

	memcpy(tmp + 3, syncookie_secret[c], sizeof(syncookie_secret[c]));
	tmp[0] = saddr;
	tmp[1] = daddr;
	tmp[2] = (sport << 16) + dport;
	tmp[3] = count;
	sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);

	return tmp[17];
}

static __u32 secure_tcp_syn_cookie(__u32 saddr, __u32 daddr, __u16 sport,
				   __u16 dport, __u32 sseq, __u32 count,
				   __u32 data)
{
	/*
	 * Compute the secure sequence number.
	 * The output should be:
   	 *   HASH(sec1,saddr,sport,daddr,dport,sec1) + sseq + (count * 2^24)
	 *      + (HASH(sec2,saddr,sport,daddr,dport,count,sec2) % 2^24).
	 * Where sseq is their sequence number and count increases every
	 * minute by 1.
	 * As an extra hack, we add a small "data" value that encodes the
	 * MSS into the second hash value.
	 */

	return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
		sseq + (count << COOKIEBITS) +
		((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
		 & COOKIEMASK));
}

/*
 * This retrieves the small "data" value from the syncookie.
 * If the syncookie is bad, the data returned will be out of
 * range.  This must be checked by the caller.
 *
 * The count value used to generate the cookie must be within
 * "maxdiff" if the current (passed-in) "count".  The return value
 * is (__u32)-1 if this test fails.
 */
static __u32 check_tcp_syn_cookie(__u32 cookie, __u32 saddr, __u32 daddr,
				  __u16 sport, __u16 dport, __u32 sseq,
				  __u32 count, __u32 maxdiff)
{
	__u32 diff;

	/* Strip away the layers from the cookie */
	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;

	/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
	if (diff >= maxdiff)
		return (__u32)-1;

	return (cookie -
		cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
		& COOKIEMASK;	/* Leaving the data behind */
}

/* 
 * This table has to be sorted and terminated with (__u16)-1.
 * XXX generate a better table.
 * Unresolved Issues: HIPPI with a 64k MSS is not well supported.
 */
static __u16 const msstab[] = {
	64 - 1,
	256 - 1,	
	512 - 1,
	536 - 1,
	1024 - 1,	
	1440 - 1,
	1460 - 1,
	4312 - 1,
	(__u16)-1
};
/* The number doesn't include the -1 terminator */
#define NUM_MSS (ARRAY_SIZE(msstab) - 1)

/*
 * Generate a syncookie.  mssp points to the mss, which is returned
 * rounded down to the value encoded in the cookie.
 */
__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int mssind;
	const __u16 mss = *mssp;

	
	tp->last_synq_overflow = jiffies;

	/* XXX sort msstab[] by probability?  Binary search? */
	for (mssind = 0; mss > msstab[mssind + 1]; mssind++)
		;
	*mssp = msstab[mssind] + 1;

	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESSENT);

	return secure_tcp_syn_cookie(skb->nh.iph->saddr, skb->nh.iph->daddr,
				     skb->h.th->source, skb->h.th->dest,
				     ntohl(skb->h.th->seq),
				     jiffies / (HZ * 60), mssind);
}

/* 
 * This (misnamed) value is the age of syncookie which is permitted.
 * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
 * sysctl_tcp_retries1. It's a rather complicated formula (exponential
 * backoff) to compute at runtime so it's currently hardcoded here.
 */
#define COUNTER_TRIES 4
/*  
 * Check if a ack sequence number is a valid syncookie. 
 * Return the decoded mss if it is, or 0 if not.
 */
static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
{
	__u32 seq; 
	__u32 mssind;

	seq = ntohl(skb->h.th->seq)-1; 
	mssind = check_tcp_syn_cookie(cookie,
				      skb->nh.iph->saddr, skb->nh.iph->daddr,
				      skb->h.th->source, skb->h.th->dest,
				      seq, jiffies / (HZ * 60), COUNTER_TRIES);

	return mssind < NUM_MSS ? msstab[mssind] + 1 : 0;
}

static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
					   struct request_sock *req,
					   struct dst_entry *dst)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sock *child;

	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
	if (child)
		inet_csk_reqsk_queue_add(sk, req, child);
	else
		reqsk_free(req);

	return child;
}

struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
			     struct ip_options *opt)
{
	struct inet_request_sock *ireq;
	struct tcp_request_sock *treq;
	struct tcp_sock *tp = tcp_sk(sk);
	__u32 cookie = ntohl(skb->h.th->ack_seq) - 1; 
	struct sock *ret = sk;
	struct request_sock *req; 
	int mss; 
	struct rtable *rt; 
	__u8 rcv_wscale;

	if (!sysctl_tcp_syncookies || !skb->h.th->ack)
		goto out;

  	if (time_after(jiffies, tp->last_synq_overflow + TCP_TIMEOUT_INIT) ||
	    (mss = cookie_check(skb, cookie)) == 0) {
	 	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESFAILED);
		goto out;
	}

	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV);

	ret = NULL;
	req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */
	if (!req)
		goto out;

	ireq = inet_rsk(req);
	treq = tcp_rsk(req);
	treq->rcv_isn		= htonl(skb->h.th->seq) - 1;
	treq->snt_isn		= cookie; 
	req->mss		= mss;
 	ireq->rmt_port		= skb->h.th->source;
	ireq->loc_addr		= skb->nh.iph->daddr;
	ireq->rmt_addr		= skb->nh.iph->saddr;
	ireq->opt		= NULL;

	/* We throwed the options of the initial SYN away, so we hope
	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
	 */
	if (opt && opt->optlen) {
		int opt_size = sizeof(struct ip_options) + opt->optlen;

		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
		if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) {
			kfree(ireq->opt);
			ireq->opt = NULL;
		}
	}

	ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0;
	ireq->wscale_ok	 = ireq->sack_ok = 0; 
	req->expires	= 0UL; 
	req->retrans	= 0; 
	
	/*
	 * We need to lookup the route here to get at the correct
	 * window size. We should better make sure that the window size
	 * hasn't changed since we received the original syn, but I see
	 * no easy way to do this. 
	 */
	{
		struct flowi fl = { .nl_u = { .ip4_u =
					      { .daddr = ((opt && opt->srr) ?
							  opt->faddr :
							  ireq->rmt_addr),
						.saddr = ireq->loc_addr,
						.tos = RT_CONN_FLAGS(sk) } },
				    .proto = IPPROTO_TCP,
				    .uli_u = { .ports =
					       { .sport = skb->h.th->dest,
						 .dport = skb->h.th->source } } };
		security_sk_classify_flow(sk, &fl);
		if (ip_route_output_key(&rt, &fl)) {
			reqsk_free(req);
			goto out; 
		}
	}

	/* Try to redo what tcp_v4_send_synack did. */
	req->window_clamp = dst_metric(&rt->u.dst, RTAX_WINDOW);
	tcp_select_initial_window(tcp_full_space(sk), req->mss,
				  &req->rcv_wnd, &req->window_clamp, 
				  0, &rcv_wscale);
	/* BTW win scale with syncookies is 0 by definition */
	ireq->rcv_wscale  = rcv_wscale; 

	ret = get_cookie_sock(sk, skb, req, &rt->u.dst);
out:	return ret;
}