aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_metrics.c
blob: 5a38a2d5a95ba41dc67aa82aefaf5f2dcddc88d9 (plain) (blame)
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
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/tcp.h>

#include <net/inet_connection_sock.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/dst.h>
#include <net/tcp.h>

int sysctl_tcp_nometrics_save __read_mostly;

enum tcp_metric_index {
	TCP_METRIC_RTT,
	TCP_METRIC_RTTVAR,
	TCP_METRIC_SSTHRESH,
	TCP_METRIC_CWND,
	TCP_METRIC_REORDERING,

	/* Always last.  */
	TCP_METRIC_MAX,
};

struct tcp_metrics_block {
	struct tcp_metrics_block __rcu	*tcpm_next;
	struct inetpeer_addr		tcpm_addr;
	unsigned long			tcpm_stamp;
	u32				tcpm_ts;
	u32				tcpm_ts_stamp;
	u32				tcpm_lock;
	u32				tcpm_vals[TCP_METRIC_MAX];
};

static bool tcp_metric_locked(struct tcp_metrics_block *tm,
			      enum tcp_metric_index idx)
{
	return tm->tcpm_lock & (1 << idx);
}

static u32 tcp_metric_get(struct tcp_metrics_block *tm,
			  enum tcp_metric_index idx)
{
	return tm->tcpm_vals[idx];
}

static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm,
				  enum tcp_metric_index idx)
{
	return msecs_to_jiffies(tm->tcpm_vals[idx]);
}

static void tcp_metric_set(struct tcp_metrics_block *tm,
			   enum tcp_metric_index idx,
			   u32 val)
{
	tm->tcpm_vals[idx] = val;
}

static void tcp_metric_set_msecs(struct tcp_metrics_block *tm,
				 enum tcp_metric_index idx,
				 u32 val)
{
	tm->tcpm_vals[idx] = jiffies_to_msecs(val);
}

static bool addr_same(const struct inetpeer_addr *a,
		      const struct inetpeer_addr *b)
{
	const struct in6_addr *a6, *b6;

	if (a->family != b->family)
		return false;
	if (a->family == AF_INET)
		return a->addr.a4 == b->addr.a4;

	a6 = (const struct in6_addr *) &a->addr.a6[0];
	b6 = (const struct in6_addr *) &b->addr.a6[0];

	return ipv6_addr_equal(a6, b6);
}

struct tcpm_hash_bucket {
	struct tcp_metrics_block __rcu	*chain;
};

static DEFINE_SPINLOCK(tcp_metrics_lock);

static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst)
{
	u32 val;

	val = 0;
	if (dst_metric_locked(dst, RTAX_RTT))
		val |= 1 << TCP_METRIC_RTT;
	if (dst_metric_locked(dst, RTAX_RTTVAR))
		val |= 1 << TCP_METRIC_RTTVAR;
	if (dst_metric_locked(dst, RTAX_SSTHRESH))
		val |= 1 << TCP_METRIC_SSTHRESH;
	if (dst_metric_locked(dst, RTAX_CWND))
		val |= 1 << TCP_METRIC_CWND;
	if (dst_metric_locked(dst, RTAX_REORDERING))
		val |= 1 << TCP_METRIC_REORDERING;
	tm->tcpm_lock = val;

	tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT);
	tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR);
	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
	tm->tcpm_ts = 0;
	tm->tcpm_ts_stamp = 0;
}

static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
					  struct inetpeer_addr *addr,
					  unsigned int hash,
					  bool reclaim)
{
	struct tcp_metrics_block *tm;
	struct net *net;

	spin_lock_bh(&tcp_metrics_lock);
	net = dev_net(dst->dev);
	if (unlikely(reclaim)) {
		struct tcp_metrics_block *oldest;

		oldest = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain);
		for (tm = rcu_dereference(oldest->tcpm_next); tm;
		     tm = rcu_dereference(tm->tcpm_next)) {
			if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp))
				oldest = tm;
		}
		tm = oldest;
	} else {
		tm = kmalloc(sizeof(*tm), GFP_ATOMIC);
		if (!tm)
			goto out_unlock;
	}
	tm->tcpm_addr = *addr;
	tm->tcpm_stamp = jiffies;

	tcpm_suck_dst(tm, dst);

	if (likely(!reclaim)) {
		tm->tcpm_next = net->ipv4.tcp_metrics_hash[hash].chain;
		rcu_assign_pointer(net->ipv4.tcp_metrics_hash[hash].chain, tm);
	}

out_unlock:
	spin_unlock_bh(&tcp_metrics_lock);
	return tm;
}

#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)

static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
{
	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
		tcpm_suck_dst(tm, dst);
}

#define TCP_METRICS_RECLAIM_DEPTH	5
#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL

static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
{
	if (tm)
		return tm;
	if (depth > TCP_METRICS_RECLAIM_DEPTH)
		return TCP_METRICS_RECLAIM_PTR;
	return NULL;
}

static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
						   struct net *net, unsigned int hash)
{
	struct tcp_metrics_block *tm;
	int depth = 0;

	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
	     tm = rcu_dereference(tm->tcpm_next)) {
		if (addr_same(&tm->tcpm_addr, addr))
			break;
		depth++;
	}
	return tcp_get_encode(tm, depth);
}

static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
						       struct dst_entry *dst)
{
	struct tcp_metrics_block *tm;
	struct inetpeer_addr addr;
	unsigned int hash;
	struct net *net;

	addr.family = req->rsk_ops->family;
	switch (addr.family) {
	case AF_INET:
		addr.addr.a4 = inet_rsk(req)->rmt_addr;
		hash = (__force unsigned int) addr.addr.a4;
		break;
	case AF_INET6:
		*(struct in6_addr *)addr.addr.a6 = inet6_rsk(req)->rmt_addr;
		hash = ((__force unsigned int) addr.addr.a6[0] ^
			(__force unsigned int) addr.addr.a6[1] ^
			(__force unsigned int) addr.addr.a6[2] ^
			(__force unsigned int) addr.addr.a6[3]);
		break;
	default:
		return NULL;
	}

	hash ^= (hash >> 24) ^ (hash >> 16) ^ (hash >> 8);

	net = dev_net(dst->dev);
	hash &= net->ipv4.tcp_metrics_hash_mask;

	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
	     tm = rcu_dereference(tm->tcpm_next)) {
		if (addr_same(&tm->tcpm_addr, &addr))
			break;
	}
	tcpm_check_stamp(tm, dst);
	return tm;
}

static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
{
	struct inet6_timewait_sock *tw6;
	struct tcp_metrics_block *tm;
	struct inetpeer_addr addr;
	unsigned int hash;
	struct net *net;

	addr.family = tw->tw_family;
	switch (addr.family) {
	case AF_INET:
		addr.addr.a4 = tw->tw_daddr;
		hash = (__force unsigned int) addr.addr.a4;
		break;
	case AF_INET6:
		tw6 = inet6_twsk((struct sock *)tw);
		*(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr;
		hash = ((__force unsigned int) addr.addr.a6[0] ^
			(__force unsigned int) addr.addr.a6[1] ^
			(__force unsigned int) addr.addr.a6[2] ^
			(__force unsigned int) addr.addr.a6[3]);
		break;
	default:
		return NULL;
	}

	hash ^= (hash >> 24) ^ (hash >> 16) ^ (hash >> 8);

	net = twsk_net(tw);
	hash &= net->ipv4.tcp_metrics_hash_mask;

	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
	     tm = rcu_dereference(tm->tcpm_next)) {
		if (addr_same(&tm->tcpm_addr, &addr))
			break;
	}
	return tm;
}

static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
						 struct dst_entry *dst,
						 bool create)
{
	struct tcp_metrics_block *tm;
	struct inetpeer_addr addr;
	unsigned int hash;
	struct net *net;
	bool reclaim;

	addr.family = sk->sk_family;
	switch (addr.family) {
	case AF_INET:
		addr.addr.a4 = inet_sk(sk)->inet_daddr;
		hash = (__force unsigned int) addr.addr.a4;
		break;
	case AF_INET6:
		*(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr;
		hash = ((__force unsigned int) addr.addr.a6[0] ^
			(__force unsigned int) addr.addr.a6[1] ^
			(__force unsigned int) addr.addr.a6[2] ^
			(__force unsigned int) addr.addr.a6[3]);
		break;
	default:
		return NULL;
	}

	hash ^= (hash >> 24) ^ (hash >> 16) ^ (hash >> 8);

	net = dev_net(dst->dev);
	hash &= net->ipv4.tcp_metrics_hash_mask;

	tm = __tcp_get_metrics(&addr, net, hash);
	reclaim = false;
	if (tm == TCP_METRICS_RECLAIM_PTR) {
		reclaim = true;
		tm = NULL;
	}
	if (!tm && create)
		tm = tcpm_new(dst, &addr, hash, reclaim);
	else
		tcpm_check_stamp(tm, dst);

	return tm;
}

/* Save metrics learned by this TCP session.  This function is called
 * only, when TCP finishes successfully i.e. when it enters TIME-WAIT
 * or goes from LAST-ACK to CLOSE.
 */
void tcp_update_metrics(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_metrics_block *tm;
	unsigned long rtt;
	u32 val;
	int m;

	if (sysctl_tcp_nometrics_save || !dst)
		return;

	if (dst->flags & DST_HOST)
		dst_confirm(dst);

	rcu_read_lock();
	if (icsk->icsk_backoff || !tp->srtt) {
		/* This session failed to estimate rtt. Why?
		 * Probably, no packets returned in time.  Reset our
		 * results.
		 */
		tm = tcp_get_metrics(sk, dst, false);
		if (tm && !tcp_metric_locked(tm, TCP_METRIC_RTT))
			tcp_metric_set(tm, TCP_METRIC_RTT, 0);
		goto out_unlock;
	} else
		tm = tcp_get_metrics(sk, dst, true);

	if (!tm)
		goto out_unlock;

	rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
	m = rtt - tp->srtt;

	/* If newly calculated rtt larger than stored one, store new
	 * one. Otherwise, use EWMA. Remember, rtt overestimation is
	 * always better than underestimation.
	 */
	if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) {
		if (m <= 0)
			rtt = tp->srtt;
		else
			rtt -= (m >> 3);
		tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt);
	}

	if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) {
		unsigned long var;

		if (m < 0)
			m = -m;

		/* Scale deviation to rttvar fixed point */
		m >>= 1;
		if (m < tp->mdev)
			m = tp->mdev;

		var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR);
		if (m >= var)
			var = m;
		else
			var -= (var - m) >> 2;

		tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var);
	}

	if (tcp_in_initial_slowstart(tp)) {
		/* Slow start still did not finish. */
		if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
			if (val && (tp->snd_cwnd >> 1) > val)
				tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
					       tp->snd_cwnd >> 1);
		}
		if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) {
			val = tcp_metric_get(tm, TCP_METRIC_CWND);
			if (tp->snd_cwnd > val)
				tcp_metric_set(tm, TCP_METRIC_CWND,
					       tp->snd_cwnd);
		}
	} else if (tp->snd_cwnd > tp->snd_ssthresh &&
		   icsk->icsk_ca_state == TCP_CA_Open) {
		/* Cong. avoidance phase, cwnd is reliable. */
		if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
			tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
				       max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
		if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) {
			val = tcp_metric_get(tm, TCP_METRIC_CWND);
			tcp_metric_set(tm, TCP_METRIC_CWND, (val + tp->snd_cwnd) >> 1);
		}
	} else {
		/* Else slow start did not finish, cwnd is non-sense,
		 * ssthresh may be also invalid.
		 */
		if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) {
			val = tcp_metric_get(tm, TCP_METRIC_CWND);
			tcp_metric_set(tm, TCP_METRIC_CWND,
				       (val + tp->snd_ssthresh) >> 1);
		}
		if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
			if (val && tp->snd_ssthresh > val)
				tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
					       tp->snd_ssthresh);
		}
		if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
			val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
			if (val < tp->reordering &&
			    tp->reordering != sysctl_tcp_reordering)
				tcp_metric_set(tm, TCP_METRIC_REORDERING,
					       tp->reordering);
		}
	}
	tm->tcpm_stamp = jiffies;
out_unlock:
	rcu_read_unlock();
}

/* Initialize metrics on socket. */

void tcp_init_metrics(struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_get(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_metrics_block *tm;
	u32 val;

	if (dst == NULL)
		goto reset;

	dst_confirm(dst);

	rcu_read_lock();
	tm = tcp_get_metrics(sk, dst, true);
	if (!tm) {
		rcu_read_unlock();
		goto reset;
	}

	if (tcp_metric_locked(tm, TCP_METRIC_CWND))
		tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);

	val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
	if (val) {
		tp->snd_ssthresh = val;
		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
			tp->snd_ssthresh = tp->snd_cwnd_clamp;
	} else {
		/* ssthresh may have been reduced unnecessarily during.
		 * 3WHS. Restore it back to its initial default.
		 */
		tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
	}
	val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
	if (val && tp->reordering != val) {
		tcp_disable_fack(tp);
		tcp_disable_early_retrans(tp);
		tp->reordering = val;
	}

	val = tcp_metric_get(tm, TCP_METRIC_RTT);
	if (val == 0 || tp->srtt == 0) {
		rcu_read_unlock();
		goto reset;
	}
	/* Initial rtt is determined from SYN,SYN-ACK.
	 * The segment is small and rtt may appear much
	 * less than real one. Use per-dst memory
	 * to make it more realistic.
	 *
	 * A bit of theory. RTT is time passed after "normal" sized packet
	 * is sent until it is ACKed. In normal circumstances sending small
	 * packets force peer to delay ACKs and calculation is correct too.
	 * The algorithm is adaptive and, provided we follow specs, it
	 * NEVER underestimate RTT. BUT! If peer tries to make some clever
	 * tricks sort of "quick acks" for time long enough to decrease RTT
	 * to low value, and then abruptly stops to do it and starts to delay
	 * ACKs, wait for troubles.
	 */
	val = msecs_to_jiffies(val);
	if (val > tp->srtt) {
		tp->srtt = val;
		tp->rtt_seq = tp->snd_nxt;
	}
	val = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR);
	if (val > tp->mdev) {
		tp->mdev = val;
		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
	}
	rcu_read_unlock();

	tcp_set_rto(sk);
reset:
	if (tp->srtt == 0) {
		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
		 * 3WHS. This is most likely due to retransmission,
		 * including spurious one. Reset the RTO back to 3secs
		 * from the more aggressive 1sec to avoid more spurious
		 * retransmission.
		 */
		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
	}
	/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
	 * retransmitted. In light of RFC6298 more aggressive 1sec
	 * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
	 * retransmission has occurred.
	 */
	if (tp->total_retrans > 1)
		tp->snd_cwnd = 1;
	else
		tp->snd_cwnd = tcp_init_cwnd(tp, dst);
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check)
{
	struct tcp_metrics_block *tm;
	bool ret;

	if (!dst)
		return false;

	rcu_read_lock();
	tm = __tcp_get_metrics_req(req, dst);
	if (paws_check) {
		if (tm &&
		    (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
		    (s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW)
			ret = false;
		else
			ret = true;
	} else {
		if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)
			ret = true;
		else
			ret = false;
	}
	rcu_read_unlock();

	return ret;
}
EXPORT_SYMBOL_GPL(tcp_peer_is_proven);

void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)
{
	struct tcp_metrics_block *tm;

	rcu_read_lock();
	tm = tcp_get_metrics(sk, dst, true);
	if (tm) {
		struct tcp_sock *tp = tcp_sk(sk);

		if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {
			tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;
			tp->rx_opt.ts_recent = tm->tcpm_ts;
		}
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);

/* VJ's idea. Save last timestamp seen from this destination and hold
 * it at least for normal timewait interval to use for duplicate
 * segment detection in subsequent connections, before they enter
 * synchronized state.
 */
bool tcp_remember_stamp(struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_get(sk);
	bool ret = false;

	if (dst) {
		struct tcp_metrics_block *tm;

		rcu_read_lock();
		tm = tcp_get_metrics(sk, dst, true);
		if (tm) {
			struct tcp_sock *tp = tcp_sk(sk);

			if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||
			    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
			     tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
				tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
				tm->tcpm_ts = tp->rx_opt.ts_recent;
			}
			ret = true;
		}
		rcu_read_unlock();
	}
	return ret;
}

bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
{
	struct tcp_metrics_block *tm;
	bool ret = false;

	rcu_read_lock();
	tm = __tcp_get_metrics_tw(tw);
	if (tw) {
		const struct tcp_timewait_sock *tcptw;
		struct sock *sk = (struct sock *) tw;

		tcptw = tcp_twsk(sk);
		if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||
		    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
		     tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
			tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
			tm->tcpm_ts	   = tcptw->tw_ts_recent;
		}
		ret = true;
	}
	rcu_read_unlock();

	return ret;
}

static unsigned long tcpmhash_entries;
static int __init set_tcpmhash_entries(char *str)
{
	ssize_t ret;

	if (!str)
		return 0;

	ret = kstrtoul(str, 0, &tcpmhash_entries);
	if (ret)
		return 0;

	return 1;
}
__setup("tcpmhash_entries=", set_tcpmhash_entries);

static int __net_init tcp_net_metrics_init(struct net *net)
{
	int slots, size;

	slots = tcpmhash_entries;
	if (!slots) {
		if (totalram_pages >= 128 * 1024)
			slots = 16 * 1024;
		else
			slots = 8 * 1024;
	}

	size = slots * sizeof(struct tcpm_hash_bucket);

	net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL);
	if (!net->ipv4.tcp_metrics_hash)
		return -ENOMEM;

	net->ipv4.tcp_metrics_hash_mask = (slots - 1);

	return 0;
}

static void __net_exit tcp_net_metrics_exit(struct net *net)
{
	kfree(net->ipv4.tcp_metrics_hash);
}

static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
	.init	=	tcp_net_metrics_init,
	.exit	=	tcp_net_metrics_exit,
};

void __init tcp_metrics_init(void)
{
	register_pernet_subsys(&tcp_net_metrics_ops);
}