summaryrefslogtreecommitdiff
path: root/net/ipv4/syncookies.c
blob: e037566315412a0aefea36b1c9b518f0e80983d5 (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
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  Syncookies implementation for the Linux kernel
 *
 *  Copyright (C) 1997 Andi Kleen
 *  Based on ideas by D.J.Bernstein and Eric Schenk.
 */

#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/siphash.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <net/secure_seq.h>
#include <net/tcp.h>
#include <net/route.h>

static siphash_key_t syncookie_secret[2] __read_mostly;

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

/* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK
 * stores TCP options:
 *
 * MSB                               LSB
 * | 31 ...   6 |  5  |  4   | 3 2 1 0 |
 * |  Timestamp | ECN | SACK | WScale  |
 *
 * When we receive a valid cookie-ACK, we look at the echoed tsval (if
 * any) to figure out which TCP options we should use for the rebuilt
 * connection.
 *
 * A WScale setting of '0xf' (which is an invalid scaling value)
 * means that original syn did not include the TCP window scaling option.
 */
#define TS_OPT_WSCALE_MASK	0xf
#define TS_OPT_SACK		BIT(4)
#define TS_OPT_ECN		BIT(5)
/* There is no TS_OPT_TIMESTAMP:
 * if ACK contains timestamp option, we already know it was
 * requested/supported by the syn/synack exchange.
 */
#define TSBITS	6
#define TSMASK	(((__u32)1 << TSBITS) - 1)

static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
		       u32 count, int c)
{
	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
	return siphash_4u32((__force u32)saddr, (__force u32)daddr,
			    (__force u32)sport << 16 | (__force u32)dport,
			    count, &syncookie_secret[c]);
}


/*
 * when syncookies are in effect and tcp timestamps are enabled we encode
 * tcp options in the lower bits of the timestamp value that will be
 * sent in the syn-ack.
 * Since subsequent timestamps use the normal tcp_time_stamp value, we
 * must make sure that the resulting initial timestamp is <= tcp_time_stamp.
 */
u64 cookie_init_timestamp(struct request_sock *req, u64 now)
{
	struct inet_request_sock *ireq;
	u32 ts, ts_now = tcp_ns_to_ts(now);
	u32 options = 0;

	ireq = inet_rsk(req);

	options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK;
	if (ireq->sack_ok)
		options |= TS_OPT_SACK;
	if (ireq->ecn_ok)
		options |= TS_OPT_ECN;

	ts = ts_now & ~TSMASK;
	ts |= options;
	if (ts > ts_now) {
		ts >>= TSBITS;
		ts--;
		ts <<= TSBITS;
		ts |= options;
	}
	return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ);
}


static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
				   __be16 dport, __u32 sseq, __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.
	 */
	u32 count = tcp_cookie_time();
	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 less than
 * MAX_SYNCOOKIE_AGE minutes in the past.
 * The return value (__u32)-1 if this test fails.
 */
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
				  __be16 sport, __be16 dport, __u32 sseq)
{
	u32 diff, count = tcp_cookie_time();

	/* 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 >= MAX_SYNCOOKIE_AGE)
		return (__u32)-1;

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

/*
 * MSS Values are chosen based on the 2011 paper
 * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
 * Values ..
 *  .. lower than 536 are rare (< 0.2%)
 *  .. between 537 and 1299 account for less than < 1.5% of observed values
 *  .. in the 1300-1349 range account for about 15 to 20% of observed mss values
 *  .. exceeding 1460 are very rare (< 0.04%)
 *
 *  1460 is the single most frequently announced mss value (30 to 46% depending
 *  on monitor location).  Table must be sorted.
 */
static __u16 const msstab[] = {
	536,
	1300,
	1440,	/* 1440, 1452: PPPoE */
	1460,
};

/*
 * 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(const struct iphdr *iph, const struct tcphdr *th,
			      u16 *mssp)
{
	int mssind;
	const __u16 mss = *mssp;

	for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--)
		if (mss >= msstab[mssind])
			break;
	*mssp = msstab[mssind];

	return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
				     th->source, th->dest, ntohl(th->seq),
				     mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);

__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
{
	const struct iphdr *iph = ip_hdr(skb);
	const struct tcphdr *th = tcp_hdr(skb);

	return __cookie_v4_init_sequence(iph, th, mssp);
}

/*
 * Check if a ack sequence number is a valid syncookie.
 * Return the decoded mss if it is, or 0 if not.
 */
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
		      u32 cookie)
{
	__u32 seq = ntohl(th->seq) - 1;
	__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
					    th->source, th->dest, seq);

	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
EXPORT_SYMBOL_GPL(__cookie_v4_check);

struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
				 struct request_sock *req,
				 struct dst_entry *dst, u32 tsoff)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sock *child;
	bool own_req;

	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
						 NULL, &own_req);
	if (child) {
		refcount_set(&req->rsk_refcnt, 1);
		tcp_sk(child)->tsoffset = tsoff;
		sock_rps_save_rxhash(child, skb);

		if (rsk_drop_req(req)) {
			reqsk_put(req);
			return child;
		}

		if (inet_csk_reqsk_queue_add(sk, req, child))
			return child;

		bh_unlock_sock(child);
		sock_put(child);
	}
	__reqsk_free(req);

	return NULL;
}
EXPORT_SYMBOL(tcp_get_cookie_sock);

/*
 * when syncookies are in effect and tcp timestamps are enabled we stored
 * additional tcp options in the timestamp.
 * This extracts these options from the timestamp echo.
 *
 * return false if we decode a tcp option that is disabled
 * on the host.
 */
bool cookie_timestamp_decode(const struct net *net,
			     struct tcp_options_received *tcp_opt)
{
	/* echoed timestamp, lowest bits contain options */
	u32 options = tcp_opt->rcv_tsecr;

	if (!tcp_opt->saw_tstamp)  {
		tcp_clear_options(tcp_opt);
		return true;
	}

	if (!net->ipv4.sysctl_tcp_timestamps)
		return false;

	tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;

	if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack)
		return false;

	if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
		return true; /* no window scaling */

	tcp_opt->wscale_ok = 1;
	tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;

	return net->ipv4.sysctl_tcp_window_scaling != 0;
}
EXPORT_SYMBOL(cookie_timestamp_decode);

bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
		   const struct net *net, const struct dst_entry *dst)
{
	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;

	if (!ecn_ok)
		return false;

	if (net->ipv4.sysctl_tcp_ecn)
		return true;

	return dst_feature(dst, RTAX_FEATURE_ECN);
}
EXPORT_SYMBOL(cookie_ecn_ok);

struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
					    struct sock *sk,
					    struct sk_buff *skb)
{
	struct request_sock *req;

#ifdef CONFIG_MPTCP
	struct tcp_request_sock *treq;

	if (sk_is_mptcp(sk))
		ops = &mptcp_subflow_request_sock_ops;
#endif

	req = inet_reqsk_alloc(ops, sk, false);
	if (!req)
		return NULL;

#if IS_ENABLED(CONFIG_MPTCP)
	treq = tcp_rsk(req);
	treq->is_mptcp = sk_is_mptcp(sk);
	if (treq->is_mptcp) {
		int err = mptcp_subflow_init_cookie_req(req, sk, skb);

		if (err) {
			reqsk_free(req);
			return NULL;
		}
	}
#endif

	return req;
}
EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);

/* On input, sk is a listener.
 * Output is listener if incoming packet would not create a child
 *           NULL if memory could not be allocated.
 */
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
{
	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
	struct tcp_options_received tcp_opt;
	struct inet_request_sock *ireq;
	struct tcp_request_sock *treq;
	struct tcp_sock *tp = tcp_sk(sk);
	const struct tcphdr *th = tcp_hdr(skb);
	__u32 cookie = ntohl(th->ack_seq) - 1;
	struct sock *ret = sk;
	struct request_sock *req;
	int mss;
	struct rtable *rt;
	__u8 rcv_wscale;
	struct flowi4 fl4;
	u32 tsoff = 0;

	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
		goto out;

	if (tcp_synq_no_recent_overflow(sk))
		goto out;

	mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
	if (mss == 0) {
		__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
		goto out;
	}

	__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);

	/* check for timestamp cookie support */
	memset(&tcp_opt, 0, sizeof(tcp_opt));
	tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL);

	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
		tsoff = secure_tcp_ts_off(sock_net(sk),
					  ip_hdr(skb)->daddr,
					  ip_hdr(skb)->saddr);
		tcp_opt.rcv_tsecr -= tsoff;
	}

	if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
		goto out;

	ret = NULL;
	req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
	if (!req)
		goto out;

	ireq = inet_rsk(req);
	treq = tcp_rsk(req);
	treq->rcv_isn		= ntohl(th->seq) - 1;
	treq->snt_isn		= cookie;
	treq->ts_off		= 0;
	treq->txhash		= net_tx_rndhash();
	req->mss		= mss;
	ireq->ir_num		= ntohs(th->dest);
	ireq->ir_rmt_port	= th->source;
	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
	ireq->ir_mark		= inet_request_mark(sk, skb);
	ireq->snd_wscale	= tcp_opt.snd_wscale;
	ireq->sack_ok		= tcp_opt.sack_ok;
	ireq->wscale_ok		= tcp_opt.wscale_ok;
	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
	treq->snt_synack	= 0;
	treq->tfo_listener	= false;

	if (IS_ENABLED(CONFIG_SMC))
		ireq->smc_ok = 0;

	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);

	/* 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)
	 */
	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));

	if (security_inet_conn_request(sk, skb, req)) {
		reqsk_free(req);
		goto out;
	}

	req->num_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.
	 */
	flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark,
			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
			   inet_sk_flowi_flags(sk),
			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
			   ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
	rt = ip_route_output_key(sock_net(sk), &fl4);
	if (IS_ERR(rt)) {
		reqsk_free(req);
		goto out;
	}

	/* Try to redo what tcp_v4_send_synack did. */
	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);

	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
				  ireq->wscale_ok, &rcv_wscale,
				  dst_metric(&rt->dst, RTAX_INITRWND));

	ireq->rcv_wscale  = rcv_wscale;
	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);

	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
	/* ip_queue_xmit() depends on our flow being setup
	 * Normal sockets get it right from inet_csk_route_child_sock()
	 */
	if (ret)
		inet_sk(ret)->cork.fl.u.ip4 = fl4;
out:	return ret;
}