net/ipv4/inet_timewait_sock.c



e48c414ee61f


172589ccdde4
9e337b0fb3ba
5a0e3ad6af86
3a9a231d9772
e48c414ee61f

696ab2d3bffc
e48c414ee61f
13475a30b66c
2a8875e73ffb


13475a30b66c


2a8875e73ffb


13475a30b66c


2a8875e73ffb


3cdaedae635b


2a8875e73ffb


3cdaedae635b


e48c414ee61f
acd159b6b582

e48c414ee61f

13475a30b66c
e48c414ee61f
9db66bdcc837
e48c414ee61f
9db66bdcc837
13475a30b66c
9db66bdcc837
e48c414ee61f

7f635ab71eef

3cdaedae635b
e48c414ee61f
3cdaedae635b
e48c414ee61f
3cdaedae635b
e48c414ee61f

91df42bedccb

e48c414ee61f

13475a30b66c


e48c414ee61f

4dbc8ef7e112
7054fb9376e1
4dbc8ef7e112

7054fb9376e1
4dbc8ef7e112
7054fb9376e1
4dbc8ef7e112


7054fb9376e1


e48c414ee61f


463c84b97f24
81c3d5470ecc
9db66bdcc837
e48c414ee61f


c720c7e8383a
7f635ab71eef
e48c414ee61f
463c84b97f24
547b792cac0a
e48c414ee61f


9db66bdcc837
e48c414ee61f
3ab5aee7fe84


3ab5aee7fe84


e48c414ee61f
47e1c323069b

2a8875e73ffb
47e1c323069b


9db66bdcc837
e48c414ee61f
696ab2d3bffc

c676270bcd25

6d6ee43e0b8b

54e6ecb23951
c676270bcd25


9e337b0fb3ba

c676270bcd25
c720c7e8383a

c676270bcd25
66b13d99d96a
c720c7e8383a
c676270bcd25

c720c7e8383a

c676270bcd25

81c3d5470ecc
c676270bcd25
f5715aea4564
c676270bcd25
cd5342d90555
47e1c323069b


c676270bcd25
eeb2b8560676
c676270bcd25


696ab2d3bffc


f2bf415cfed7


696ab2d3bffc


f2bf415cfed7


696ab2d3bffc


95c961747284
696ab2d3bffc


696ab2d3bffc


80a1096bac73
696ab2d3bffc
696ab2d3bffc


696ab2d3bffc

65f27f38446e
696ab2d3bffc
65f27f38446e

696ab2d3bffc

95c9382a3452

696ab2d3bffc


696ab2d3bffc


696ab2d3bffc


172589ccdde4
696ab2d3bffc


696ab2d3bffc


f2bf415cfed7


696ab2d3bffc


f2bf415cfed7


696ab2d3bffc

696ab2d3bffc
d315492b1a6b
b099ce2602d8
d315492b1a6b


3ab5aee7fe84
575f4cd5a5b6
d315492b1a6b
575f4cd5a5b6


d315492b1a6b
575f4cd5a5b6
d315492b1a6b
b099ce2602d8

d315492b1a6b

575f4cd5a5b6


b099ce2602d8

575f4cd5a5b6


91035f0b7d89
d315492b1a6b
91035f0b7d89
d315492b1a6b
575f4cd5a5b6
d315492b1a6b
575f4cd5a5b6


d315492b1a6b
d315492b1a6b


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


/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Generic TIME_WAIT sockets functions
 *
 *		From code orinally in TCP
 */

#include <linux/kernel.h>
#include <linux/kmemcheck.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>


/**
 *	inet_twsk_unhash - unhash a timewait socket from established hash
 *	@tw: timewait socket
 *
 *	unhash a timewait socket from established hash, if hashed.
 *	ehash lock must be held by caller.
 *	Returns 1 if caller should call inet_twsk_put() after lock release.
 */
int inet_twsk_unhash(struct inet_timewait_sock *tw)
{
	if (hlist_nulls_unhashed(&tw->tw_node))
		return 0;

	hlist_nulls_del_rcu(&tw->tw_node);
	sk_nulls_node_init(&tw->tw_node);
	/*
	 * We cannot call inet_twsk_put() ourself under lock,
	 * caller must call it for us.
	 */
	return 1;
}

/**
 *	inet_twsk_bind_unhash - unhash a timewait socket from bind hash
 *	@tw: timewait socket
 *	@hashinfo: hashinfo pointer
 *
 *	unhash a timewait socket from bind hash, if hashed.
 *	bind hash lock must be held by caller.
 *	Returns 1 if caller should call inet_twsk_put() after lock release.
 */
int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
			  struct inet_hashinfo *hashinfo)
{
	struct inet_bind_bucket *tb = tw->tw_tb;

	if (!tb)
		return 0;

	__hlist_del(&tw->tw_bind_node);
	tw->tw_tb = NULL;
	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
	/*
	 * We cannot call inet_twsk_put() ourself under lock,
	 * caller must call it for us.
	 */
	return 1;
}

/* Must be called with locally disabled BHs. */
static void __inet_twsk_kill(struct inet_timewait_sock *tw,
			     struct inet_hashinfo *hashinfo)
{
	struct inet_bind_hashbucket *bhead;
	int refcnt;
	/* Unlink from established hashes. */
	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);

	spin_lock(lock);
	refcnt = inet_twsk_unhash(tw);
	spin_unlock(lock);

	/* Disassociate with bind bucket. */
	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
			hashinfo->bhash_size)];

	spin_lock(&bhead->lock);
	refcnt += inet_twsk_bind_unhash(tw, hashinfo);
	spin_unlock(&bhead->lock);

#ifdef SOCK_REFCNT_DEBUG
	if (atomic_read(&tw->tw_refcnt) != 1) {
		pr_debug("%s timewait_sock %p refcnt=%d\n",
			 tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
	}
#endif
	while (refcnt) {
		inet_twsk_put(tw);
		refcnt--;
	}
}

static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
{
	struct module *owner = tw->tw_prot->owner;
	twsk_destructor((struct sock *)tw);
#ifdef SOCK_REFCNT_DEBUG
	pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
#endif
	release_net(twsk_net(tw));
	kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
	module_put(owner);
}

void inet_twsk_put(struct inet_timewait_sock *tw)
{
	if (atomic_dec_and_test(&tw->tw_refcnt))
		inet_twsk_free(tw);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);

/*
 * Enter the time wait state. This is called with locally disabled BH.
 * Essentially we whip up a timewait bucket, copy the relevant info into it
 * from the SK, and mess with hash chains and list linkage.
 */
void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
			   struct inet_hashinfo *hashinfo)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
	spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
	struct inet_bind_hashbucket *bhead;
	/* Step 1: Put TW into bind hash. Original socket stays there too.
	   Note, that any socket with inet->num != 0 MUST be bound in
	   binding cache, even if it is closed.
	 */
	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
			hashinfo->bhash_size)];
	spin_lock(&bhead->lock);
	tw->tw_tb = icsk->icsk_bind_hash;
	WARN_ON(!icsk->icsk_bind_hash);
	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
	spin_unlock(&bhead->lock);

	spin_lock(lock);

	/*
	 * Step 2: Hash TW into TIMEWAIT chain.
	 * Should be done before removing sk from established chain
	 * because readers are lockless and search established first.
	 */
	inet_twsk_add_node_rcu(tw, &ehead->twchain);

	/* Step 3: Remove SK from established hash. */
	if (__sk_nulls_del_node_init_rcu(sk))
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);

	/*
	 * Notes :
	 * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
	 * - We add one reference for the bhash link
	 * - We add one reference for the ehash link
	 * - We want this refcnt update done before allowing other
	 *   threads to find this tw in ehash chain.
	 */
	atomic_add(1 + 1 + 1, &tw->tw_refcnt);

	spin_unlock(lock);
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);

struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state)
{
	struct inet_timewait_sock *tw =
		kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
				 GFP_ATOMIC);
	if (tw != NULL) {
		const struct inet_sock *inet = inet_sk(sk);

		kmemcheck_annotate_bitfield(tw, flags);

		/* Give us an identity. */
		tw->tw_daddr	    = inet->inet_daddr;
		tw->tw_rcv_saddr    = inet->inet_rcv_saddr;
		tw->tw_bound_dev_if = sk->sk_bound_dev_if;
		tw->tw_tos	    = inet->tos;
		tw->tw_num	    = inet->inet_num;
		tw->tw_state	    = TCP_TIME_WAIT;
		tw->tw_substate	    = state;
		tw->tw_sport	    = inet->inet_sport;
		tw->tw_dport	    = inet->inet_dport;
		tw->tw_family	    = sk->sk_family;
		tw->tw_reuse	    = sk->sk_reuse;
		tw->tw_hash	    = sk->sk_hash;
		tw->tw_ipv6only	    = 0;
		tw->tw_transparent  = inet->transparent;
		tw->tw_prot	    = sk->sk_prot_creator;
		twsk_net_set(tw, hold_net(sock_net(sk)));
		/*
		 * Because we use RCU lookups, we should not set tw_refcnt
		 * to a non null value before everything is setup for this
		 * timewait socket.
		 */
		atomic_set(&tw->tw_refcnt, 0);
		inet_twsk_dead_node_init(tw);
		__module_get(tw->tw_prot->owner);
	}

	return tw;
}
EXPORT_SYMBOL_GPL(inet_twsk_alloc);

/* Returns non-zero if quota exceeded.  */
static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr,
				    const int slot)
{
	struct inet_timewait_sock *tw;
	struct hlist_node *node;
	unsigned int killed;
	int ret;

	/* NOTE: compare this to previous version where lock
	 * was released after detaching chain. It was racy,
	 * because tw buckets are scheduled in not serialized context
	 * in 2.3 (with netfilter), and with softnet it is common, because
	 * soft irqs are not sequenced.
	 */
	killed = 0;
	ret = 0;
rescan:
	inet_twsk_for_each_inmate(tw, node, &twdr->cells[slot]) {
		__inet_twsk_del_dead_node(tw);
		spin_unlock(&twdr->death_lock);
		__inet_twsk_kill(tw, twdr->hashinfo);
#ifdef CONFIG_NET_NS
		NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED);
#endif
		inet_twsk_put(tw);
		killed++;
		spin_lock(&twdr->death_lock);
		if (killed > INET_TWDR_TWKILL_QUOTA) {
			ret = 1;
			break;
		}

		/* While we dropped twdr->death_lock, another cpu may have
		 * killed off the next TW bucket in the list, therefore
		 * do a fresh re-read of the hlist head node with the
		 * lock reacquired.  We still use the hlist traversal
		 * macro in order to get the prefetches.
		 */
		goto rescan;
	}

	twdr->tw_count -= killed;
#ifndef CONFIG_NET_NS
	NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITED, killed);
#endif
	return ret;
}

void inet_twdr_hangman(unsigned long data)
{
	struct inet_timewait_death_row *twdr;
	unsigned int need_timer;

	twdr = (struct inet_timewait_death_row *)data;
	spin_lock(&twdr->death_lock);

	if (twdr->tw_count == 0)
		goto out;

	need_timer = 0;
	if (inet_twdr_do_twkill_work(twdr, twdr->slot)) {
		twdr->thread_slots |= (1 << twdr->slot);
		schedule_work(&twdr->twkill_work);
		need_timer = 1;
	} else {
		/* We purged the entire slot, anything left?  */
		if (twdr->tw_count)
			need_timer = 1;
		twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1));
	}
	if (need_timer)
		mod_timer(&twdr->tw_timer, jiffies + twdr->period);
out:
	spin_unlock(&twdr->death_lock);
}
EXPORT_SYMBOL_GPL(inet_twdr_hangman);

void inet_twdr_twkill_work(struct work_struct *work)
{
	struct inet_timewait_death_row *twdr =
		container_of(work, struct inet_timewait_death_row, twkill_work);
	int i;

	BUILD_BUG_ON((INET_TWDR_TWKILL_SLOTS - 1) >
			(sizeof(twdr->thread_slots) * 8));

	while (twdr->thread_slots) {
		spin_lock_bh(&twdr->death_lock);
		for (i = 0; i < INET_TWDR_TWKILL_SLOTS; i++) {
			if (!(twdr->thread_slots & (1 << i)))