summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_fastopen.c
blob: 78c192ee03a4fad5a43f91f693354e0889283632 (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
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
// SPDX-License-Identifier: GPL-2.0
#include <linux/crypto.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <net/inetpeer.h>
#include <net/tcp.h>

void tcp_fastopen_init_key_once(struct net *net)
{
	u8 key[TCP_FASTOPEN_KEY_LENGTH];
	struct tcp_fastopen_context *ctxt;

	rcu_read_lock();
	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
	if (ctxt) {
		rcu_read_unlock();
		return;
	}
	rcu_read_unlock();

	/* tcp_fastopen_reset_cipher publishes the new context
	 * atomically, so we allow this race happening here.
	 *
	 * All call sites of tcp_fastopen_cookie_gen also check
	 * for a valid cookie, so this is an acceptable risk.
	 */
	get_random_bytes(key, sizeof(key));
	tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
}

static void tcp_fastopen_ctx_free(struct rcu_head *head)
{
	struct tcp_fastopen_context *ctx =
	    container_of(head, struct tcp_fastopen_context, rcu);
	crypto_free_cipher(ctx->tfm);
	kfree(ctx);
}

void tcp_fastopen_destroy_cipher(struct sock *sk)
{
	struct tcp_fastopen_context *ctx;

	ctx = rcu_dereference_protected(
			inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1);
	if (ctx)
		call_rcu(&ctx->rcu, tcp_fastopen_ctx_free);
}

void tcp_fastopen_ctx_destroy(struct net *net)
{
	struct tcp_fastopen_context *ctxt;

	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);

	ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);

	if (ctxt)
		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
}

int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
			      void *key, unsigned int len)
{
	struct tcp_fastopen_context *ctx, *octx;
	struct fastopen_queue *q;
	int err;

	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;
	ctx->tfm = crypto_alloc_cipher("aes", 0, 0);

	if (IS_ERR(ctx->tfm)) {
		err = PTR_ERR(ctx->tfm);
error:		kfree(ctx);
		pr_err("TCP: TFO aes cipher alloc error: %d\n", err);
		return err;
	}
	err = crypto_cipher_setkey(ctx->tfm, key, len);
	if (err) {
		pr_err("TCP: TFO cipher key error: %d\n", err);
		crypto_free_cipher(ctx->tfm);
		goto error;
	}
	memcpy(ctx->key, key, len);


	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
	if (sk) {
		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
		octx = rcu_dereference_protected(q->ctx,
			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
		rcu_assign_pointer(q->ctx, ctx);
	} else {
		octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
		rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
	}
	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);

	if (octx)
		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
	return err;
}

static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
				      struct tcp_fastopen_cookie *foc)
{
	struct tcp_fastopen_context *ctx;
	bool ok = false;

	rcu_read_lock();

	ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
	if (!ctx)
		ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);

	if (ctx) {
		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
		ok = true;
	}
	rcu_read_unlock();
	return ok;
}

/* Generate the fastopen cookie by doing aes128 encryption on both
 * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
 * addresses. For the longer IPv6 addresses use CBC-MAC.
 *
 * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
 */
static bool tcp_fastopen_cookie_gen(struct sock *sk,
				    struct request_sock *req,
				    struct sk_buff *syn,
				    struct tcp_fastopen_cookie *foc)
{
	if (req->rsk_ops->family == AF_INET) {
		const struct iphdr *iph = ip_hdr(syn);

		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
		return __tcp_fastopen_cookie_gen(sk, path, foc);
	}

#if IS_ENABLED(CONFIG_IPV6)
	if (req->rsk_ops->family == AF_INET6) {
		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
		struct tcp_fastopen_cookie tmp;

		if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
			struct in6_addr *buf = &tmp.addr;
			int i;

			for (i = 0; i < 4; i++)
				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
			return __tcp_fastopen_cookie_gen(sk, buf, foc);
		}
	}
#endif
	return false;
}


/* If an incoming SYN or SYNACK frame contains a payload and/or FIN,
 * queue this additional data / FIN.
 */
void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt)
		return;

	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb)
		return;

	skb_dst_drop(skb);
	/* segs_in has been initialized to 1 in tcp_create_openreq_child().
	 * Hence, reset segs_in to 0 before calling tcp_segs_in()
	 * to avoid double counting.  Also, tcp_segs_in() expects
	 * skb->len to include the tcp_hdrlen.  Hence, it should
	 * be called before __skb_pull().
	 */
	tp->segs_in = 0;
	tcp_segs_in(tp, skb);
	__skb_pull(skb, tcp_hdrlen(skb));
	sk_forced_mem_schedule(sk, skb->truesize);
	skb_set_owner_r(skb, sk);

	TCP_SKB_CB(skb)->seq++;
	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;

	tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
	__skb_queue_tail(&sk->sk_receive_queue, skb);
	tp->syn_data_acked = 1;

	/* u64_stats_update_begin(&tp->syncp) not needed here,
	 * as we certainly are not changing upper 32bit value (0)
	 */
	tp->bytes_received = skb->len;

	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
		tcp_fin(sk);
}

static struct sock *tcp_fastopen_create_child(struct sock *sk,
					      struct sk_buff *skb,
					      struct request_sock *req)
{
	struct tcp_sock *tp;
	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
	struct sock *child;
	bool own_req;

	req->num_retrans = 0;
	req->num_timeout = 0;
	req->sk = NULL;

	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
							 NULL, &own_req);
	if (!child)
		return NULL;

	spin_lock(&queue->fastopenq.lock);
	queue->fastopenq.qlen++;
	spin_unlock(&queue->fastopenq.lock);

	/* Initialize the child socket. Have to fix some values to take
	 * into account the child is a Fast Open socket and is created
	 * only out of the bits carried in the SYN packet.
	 */
	tp = tcp_sk(child);

	tp->fastopen_rsk = req;
	tcp_rsk(req)->tfo_listener = true;

	/* RFC1323: The window in SYN & SYN/ACK segments is never
	 * scaled. So correct it appropriately.
	 */
	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
	tp->max_window = tp->snd_wnd;

	/* Activate the retrans timer so that SYNACK can be retransmitted.
	 * The request socket is not added to the ehash
	 * because it's been added to the accept queue directly.
	 */
	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);

	refcount_set(&req->rsk_refcnt, 2);

	/* Now finish processing the fastopen child socket. */
	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);

	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;

	tcp_fastopen_add_skb(child, skb);

	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
	tp->rcv_wup = tp->rcv_nxt;
	/* tcp_conn_request() is sending the SYNACK,
	 * and queues the child into listener accept queue.
	 */
	return child;
}

static bool tcp_fastopen_queue_check(struct sock *sk)
{
	struct fastopen_queue *fastopenq;

	/* Make sure the listener has enabled fastopen, and we don't
	 * exceed the max # of pending TFO requests allowed before trying
	 * to validating the cookie in order to avoid burning CPU cycles
	 * unnecessarily.
	 *
	 * XXX (TFO) - The implication of checking the max_qlen before
	 * processing a cookie request is that clients can't differentiate
	 * between qlen overflow causing Fast Open to be disabled
	 * temporarily vs a server not supporting Fast Open at all.
	 */
	fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
	if (fastopenq->max_qlen == 0)
		return false;

	if (fastopenq->qlen >= fastopenq->max_qlen) {
		struct request_sock *req1;
		spin_lock(&fastopenq->lock);
		req1 = fastopenq->rskq_rst_head;
		if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) {
			__NET_INC_STATS(sock_net(sk),
					LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
			spin_unlock(&fastopenq->lock);
			return false;
		}
		fastopenq->rskq_rst_head = req1->dl_next;
		fastopenq->qlen--;
		spin_unlock(&fastopenq->lock);
		reqsk_put(req1);
	}
	return true;
}

static bool tcp_fastopen_no_cookie(const struct sock *sk,
				   const struct dst_entry *dst,
				   int flag)
{
	return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
	       tcp_sk(sk)->fastopen_no_cookie ||
	       (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
}

/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
 * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
 * cookie request (foc->len == 0).
 */
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
			      struct request_sock *req,
			      struct tcp_fastopen_cookie *foc,
			      const struct dst_entry *dst)
{
	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
	struct sock *child;

	if (foc->len == 0) /* Client requests a cookie */
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);

	if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
	      (syn_data || foc->len >= 0) &&
	      tcp_fastopen_queue_check(sk))) {
		foc->len = -1;
		return NULL;
	}

	if (syn_data &&
	    tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
		goto fastopen;

	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
	    tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
	    foc->len == valid_foc.len &&
	    !memcmp(foc->val, valid_foc.val, foc->len)) {
		/* Cookie is valid. Create a (full) child socket to accept
		 * the data in SYN before returning a SYN-ACK to ack the
		 * data. If we fail to create the socket, fall back and
		 * ack the ISN only but includes the same cookie.
		 *
		 * Note: Data-less SYN with valid cookie is allowed to send
		 * data in SYN_RECV state.
		 */
fastopen:
		child = tcp_fastopen_create_child(sk, skb, req);
		if (child) {
			foc->len = -1;
			NET_INC_STATS(sock_net(sk),
				      LINUX_MIB_TCPFASTOPENPASSIVE);
			return child;
		}
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
	} else if (foc->len > 0) /* Client presents an invalid cookie */
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);

	valid_foc.exp = foc->exp;
	*foc = valid_foc;
	return NULL;
}

bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
			       struct tcp_fastopen_cookie *cookie)
{
	unsigned long last_syn_loss = 0;
	const struct dst_entry *dst;
	int syn_loss = 0;

	tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);

	/* Recurring FO SYN losses: no cookie or data in SYN */
	if (syn_loss > 1 &&
	    time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) {
		cookie->len = -1;
		return false;
	}

	/* Firewall blackhole issue check */
	if (tcp_fastopen_active_should_disable(sk)) {
		cookie->len = -1;
		return false;
	}

	dst = __sk_dst_get(sk);

	if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) {
		cookie->len = -1;
		return true;
	}
	return cookie->len > 0;
}

/* This function checks if we want to defer sending SYN until the first
 * write().  We defer under the following conditions:
 * 1. fastopen_connect sockopt is set
 * 2. we have a valid cookie
 * Return value: return true if we want to defer until application writes data
 *               return false if we want to send out SYN immediately
 */
bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
{
	struct tcp_fastopen_cookie cookie = { .len = 0 };
	struct tcp_sock *tp = tcp_sk(sk);
	u16 mss;

	if (tp->fastopen_connect && !tp->fastopen_req) {
		if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) {
			inet_sk(sk)->defer_connect = 1;
			return true;
		}

		/* Alloc fastopen_req in order for FO option to be included
		 * in SYN
		 */
		tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req),
					   sk->sk_allocation);
		if (tp->fastopen_req)
			tp->fastopen_req->cookie = cookie;
		else
			*err = -ENOBUFS;
	}
	return false;
}
EXPORT_SYMBOL(tcp_fastopen_defer_connect);

/*
 * The following code block is to deal with middle box issues with TFO:
 * Middlebox firewall issues can potentially cause server's data being
 * blackholed after a successful 3WHS using TFO.
 * The proposed solution is to disable active TFO globally under the
 * following circumstances:
 *   1. client side TFO socket receives out of order FIN
 *   2. client side TFO socket receives out of order RST
 * We disable active side TFO globally for 1hr at first. Then if it
 * happens again, we disable it for 2h, then 4h, 8h, ...
 * And we reset the timeout back to 1hr when we see a successful active
 * TFO connection with data exchanges.
 */

/* Disable active TFO and record current jiffies and
 * tfo_active_disable_times
 */
void tcp_fastopen_active_disable(struct sock *sk)
{
	struct net *net = sock_net(sk);

	atomic_inc(&net->ipv4.tfo_active_disable_times);
	net->ipv4.tfo_active_disable_stamp = jiffies;
	NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}

/* Calculate timeout for tfo active disable
 * Return true if we are still in the active TFO disable period
 * Return false if timeout already expired and we should use active TFO
 */
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
	int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
	unsigned long timeout;
	int multiplier;

	if (!tfo_da_times)
		return false;

	/* Limit timout to max: 2^6 * initial timeout */
	multiplier = 1 << min(tfo_da_times - 1, 6);
	timeout = multiplier * tfo_bh_timeout * HZ;
	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
		return true;

	/* Mark check bit so we can check for successful active TFO
	 * condition and reset tfo_active_disable_times
	 */
	tcp_sk(sk)->syn_fastopen_ch = 1;
	return false;
}

/* Disable active TFO if FIN is the only packet in the ofo queue
 * and no data is received.
 * Also check if we can reset tfo_active_disable_times if data is
 * received successfully on a marked active TFO sockets opened on
 * a non-loopback interface
 */
void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst;
	struct sk_buff *skb;

	if (!tp->syn_fastopen)
		return;

	if (!tp->data_segs_in) {
		skb = skb_rb_first(&tp->out_of_order_queue);
		if (skb && !skb_rb_next(skb)) {
			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
				tcp_fastopen_active_disable(sk);
				return;
			}
		}
	} else if (tp->syn_fastopen_ch &&
		   atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
		dst = sk_dst_get(sk);
		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
			atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
		dst_release(dst);
	}
}