aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter/nf_conntrack_expect.c
blob: 4b2e1fb28bb438d695715fc492f52bf7809ade5d (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
/* Expectation handling for nf_conntrack. */

/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
 * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
 * (c) 2005-2012 Patrick McHardy <kaber@trash.net>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/types.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/netns/hash.h>

#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>

unsigned int nf_ct_expect_hsize __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);

struct hlist_head *nf_ct_expect_hash __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hash);

unsigned int nf_ct_expect_max __read_mostly;

static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
static unsigned int nf_ct_expect_hashrnd __read_mostly;

/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
				u32 portid, int report)
{
	struct nf_conn_help *master_help = nfct_help(exp->master);
	struct net *net = nf_ct_exp_net(exp);

	NF_CT_ASSERT(master_help);
	NF_CT_ASSERT(!timer_pending(&exp->timeout));

	hlist_del_rcu(&exp->hnode);
	net->ct.expect_count--;

	hlist_del(&exp->lnode);
	master_help->expecting[exp->class]--;

	nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
	nf_ct_expect_put(exp);

	NF_CT_STAT_INC(net, expect_delete);
}
EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report);

static void nf_ct_expectation_timed_out(unsigned long ul_expect)
{
	struct nf_conntrack_expect *exp = (void *)ul_expect;

	spin_lock_bh(&nf_conntrack_expect_lock);
	nf_ct_unlink_expect(exp);
	spin_unlock_bh(&nf_conntrack_expect_lock);
	nf_ct_expect_put(exp);
}

static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
	unsigned int hash, seed;

	get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd));

	seed = nf_ct_expect_hashrnd ^ net_hash_mix(n);

	hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
		      (((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
		       (__force __u16)tuple->dst.u.all) ^ seed);

	return reciprocal_scale(hash, nf_ct_expect_hsize);
}

static bool
nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
		const struct nf_conntrack_expect *i,
		const struct nf_conntrack_zone *zone,
		const struct net *net)
{
	return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
	       net_eq(net, nf_ct_net(i->master)) &&
	       nf_ct_zone_equal_any(i->master, zone);
}

struct nf_conntrack_expect *
__nf_ct_expect_find(struct net *net,
		    const struct nf_conntrack_zone *zone,
		    const struct nf_conntrack_tuple *tuple)
{
	struct nf_conntrack_expect *i;
	unsigned int h;

	if (!net->ct.expect_count)
		return NULL;

	h = nf_ct_expect_dst_hash(net, tuple);
	hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) {
		if (nf_ct_exp_equal(tuple, i, zone, net))
			return i;
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(__nf_ct_expect_find);

/* Just find a expectation corresponding to a tuple. */
struct nf_conntrack_expect *
nf_ct_expect_find_get(struct net *net,
		      const struct nf_conntrack_zone *zone,
		      const struct nf_conntrack_tuple *tuple)
{
	struct nf_conntrack_expect *i;

	rcu_read_lock();
	i = __nf_ct_expect_find(net, zone, tuple);
	if (i && !atomic_inc_not_zero(&i->use))
		i = NULL;
	rcu_read_unlock();

	return i;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_find_get);

/* If an expectation for this connection is found, it gets delete from
 * global list then returned. */
struct nf_conntrack_expect *
nf_ct_find_expectation(struct net *net,
		       const struct nf_conntrack_zone *zone,
		       const struct nf_conntrack_tuple *tuple)
{
	struct nf_conntrack_expect *i, *exp = NULL;
	unsigned int h;

	if (!net->ct.expect_count)
		return NULL;

	h = nf_ct_expect_dst_hash(net, tuple);
	hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) {
		if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
		    nf_ct_exp_equal(tuple, i, zone, net)) {
			exp = i;
			break;
		}
	}
	if (!exp)
		return NULL;

	/* If master is not in hash table yet (ie. packet hasn't left
	   this machine yet), how can other end know about expected?
	   Hence these are not the droids you are looking for (if
	   master ct never got confirmed, we'd hold a reference to it
	   and weird things would happen to future packets). */
	if (!nf_ct_is_confirmed(exp->master))
		return NULL;

	/* Avoid race with other CPUs, that for exp->master ct, is
	 * about to invoke ->destroy(), or nf_ct_delete() via timeout
	 * or early_drop().
	 *
	 * The atomic_inc_not_zero() check tells:  If that fails, we
	 * know that the ct is being destroyed.  If it succeeds, we
	 * can be sure the ct cannot disappear underneath.
	 */
	if (unlikely(nf_ct_is_dying(exp->master) ||
		     !atomic_inc_not_zero(&exp->master->ct_general.use)))
		return NULL;

	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
		atomic_inc(&exp->use);
		return exp;
	} else if (del_timer(&exp->timeout)) {
		nf_ct_unlink_expect(exp);
		return exp;
	}
	/* Undo exp->master refcnt increase, if del_timer() failed */
	nf_ct_put(exp->master);

	return NULL;
}

/* delete all expectations for this conntrack */
void nf_ct_remove_expectations(struct nf_conn *ct)
{
	struct nf_conn_help *help = nfct_help(ct);
	struct nf_conntrack_expect *exp;
	struct hlist_node *next;

	/* Optimization: most connection never expect any others. */
	if (!help)
		return;

	spin_lock_bh(&nf_conntrack_expect_lock);
	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
		if (del_timer(&exp->timeout)) {
			nf_ct_unlink_expect(exp);
			nf_ct_expect_put(exp);
		}
	}
	spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);

/* Would two expected things clash? */
static inline int expect_clash(const struct nf_conntrack_expect *a,
			       const struct nf_conntrack_expect *b)
{
	/* Part covered by intersection of masks must be unequal,
	   otherwise they clash */
	struct nf_conntrack_tuple_mask intersect_mask;
	int count;

	intersect_mask.src.u.all = a->mask.src.u.all & b->mask.src.u.all;

	for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
		intersect_mask.src.u3.all[count] =
			a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
	}

	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
	       net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
	       nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}

static inline int expect_matches(const struct nf_conntrack_expect *a,
				 const struct nf_conntrack_expect *b)
{
	return a->master == b->master && a->class == b->class &&
	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
	       net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
	       nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}

/* Generally a bad idea to call this: could have matched already. */
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
{
	spin_lock_bh(&nf_conntrack_expect_lock);
	if (del_timer(&exp->timeout)) {
		nf_ct_unlink_expect(exp);
		nf_ct_expect_put(exp);
	}
	spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);

/* We don't increase the master conntrack refcount for non-fulfilled
 * conntracks. During the conntrack destruction, the expectations are
 * always killed before the conntrack itself */
struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
{
	struct nf_conntrack_expect *new;

	new = kmem_cache_alloc(nf_ct_expect_cachep, GFP_ATOMIC);
	if (!new)
		return NULL;

	new->master = me;
	atomic_set(&new->use, 1);
	return new;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);

void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
		       u_int8_t family,
		       const union nf_inet_addr *saddr,
		       const union nf_inet_addr *daddr,
		       u_int8_t proto, const __be16 *src, const __be16 *dst)
{
	int len;

	if (family == AF_INET)
		len = 4;
	else
		len = 16;

	exp->flags = 0;
	exp->class = class;
	exp->expectfn = NULL;
	exp->helper = NULL;
	exp->tuple.src.l3num = family;
	exp->tuple.dst.protonum = proto;

	if (saddr) {
		memcpy(&exp->tuple.src.u3, saddr, len);
		if (sizeof(exp->tuple.src.u3) > len)
			/* address needs to be cleared for nf_ct_tuple_equal */
			memset((void *)&exp->tuple.src.u3 + len, 0x00,
			       sizeof(exp->tuple.src.u3) - len);
		memset(&exp->mask.src.u3, 0xFF, len);
		if (sizeof(exp->mask.src.u3) > len)
			memset((void *)&exp->mask.src.u3 + len, 0x00,
			       sizeof(exp->mask.src.u3) - len);
	} else {
		memset(&exp->tuple.src.u3, 0x00, sizeof(exp->tuple.src.u3));
		memset(&exp->mask.src.u3, 0x00, sizeof(exp->mask.src.u3));
	}

	if (src) {
		exp->tuple.src.u.all = *src;
		exp->mask.src.u.all = htons(0xFFFF);
	} else {
		exp->tuple.src.u.all = 0;
		exp->mask.src.u.all = 0;
	}

	memcpy(&exp->tuple.dst.u3, daddr, len);
	if (sizeof(exp->tuple.dst.u3) > len)
		/* address needs to be cleared for nf_ct_tuple_equal */
		memset((void *)&exp->tuple.dst.u3 + len, 0x00,
		       sizeof(exp->tuple.dst.u3) - len);

	exp->tuple.dst.u.all = *dst;

#ifdef CONFIG_NF_NAT_NEEDED
	memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
	memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
#endif
}
EXPORT_SYMBOL_GPL(nf_ct_expect_init);

static void nf_ct_expect_free_rcu(struct rcu_head *head)
{
	struct nf_conntrack_expect *exp;

	exp = container_of(head, struct nf_conntrack_expect, rcu);
	kmem_cache_free(nf_ct_expect_cachep, exp);
}

void nf_ct_expect_put(struct nf_conntrack_expect *exp)
{
	if (atomic_dec_and_test(&exp->use))
		call_rcu(&exp->rcu, nf_ct_expect_free_rcu);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_put);

static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
{
	struct nf_conn_help *master_help = nfct_help(exp->master);
	struct nf_conntrack_helper *helper;
	struct net *net = nf_ct_exp_net(exp);
	unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);

	/* two references : one for hash insert, one for the timer */
	atomic_add(2, &exp->use);

	hlist_add_head(&exp->lnode, &master_help->expectations);
	master_help->expecting[exp->class]++;

	hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
	net->ct.expect_count++;

	setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
		    (unsigned long)exp);
	helper = rcu_dereference_protected(master_help->helper,
					   lockdep_is_held(&nf_conntrack_expect_lock));
	if (helper) {
		exp->timeout.expires = jiffies +
			helper->expect_policy[exp->class].timeout * HZ;
	}
	add_timer(&exp->timeout);

	NF_CT_STAT_INC(net, expect_create);
}

/* Race with expectations being used means we could have none to find; OK. */
static void evict_oldest_expect(struct nf_conn *master,
				struct nf_conntrack_expect *new)
{
	struct nf_conn_help *master_help = nfct_help(master);
	struct nf_conntrack_expect *exp, *last = NULL;

	hlist_for_each_entry(exp, &master_help->expectations, lnode) {
		if (exp->class == new->class)
			last = exp;
	}

	if (last && del_timer(&last->timeout)) {
		nf_ct_unlink_expect(last);
		nf_ct_expect_put(last);
	}
}

static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
{
	const struct nf_conntrack_expect_policy *p;
	struct nf_conntrack_expect *i;
	struct nf_conn *master = expect->master;
	struct nf_conn_help *master_help = nfct_help(master);
	struct nf_conntrack_helper *helper;
	struct net *net = nf_ct_exp_net(expect);
	struct hlist_node *next;
	unsigned int h;
	int ret = 0;

	if (!master_help) {
		ret = -ESHUTDOWN;
		goto out;
	}
	h = nf_ct_expect_dst_hash(net, &expect->tuple);
	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
		if (expect_matches(i, expect)) {
			if (del_timer(&i->timeout)) {
				nf_ct_unlink_expect(i);
				nf_ct_expect_put(i);
				break;
			}
		} else if (expect_clash(i, expect)) {
			ret = -EBUSY;
			goto out;
		}
	}
	/* Will be over limit? */
	helper = rcu_dereference_protected(master_help->helper,
					   lockdep_is_held(&nf_conntrack_expect_lock));
	if (helper) {
		p = &helper->expect_policy[expect->class];
		if (p->max_expected &&
		    master_help->expecting[expect->class] >= p->max_expected) {
			evict_oldest_expect(master, expect);
			if (master_help->expecting[expect->class]
						>= p->max_expected) {
				ret = -EMFILE;
				goto out;
			}
		}
	}

	if (net->ct.expect_count >= nf_ct_expect_max) {
		net_warn_ratelimited("nf_conntrack: expectation table full\n");
		ret = -EMFILE;
	}
out:
	return ret;
}

int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
				u32 portid, int report)
{
	int ret;

	spin_lock_bh(&nf_conntrack_expect_lock);
	ret = __nf_ct_expect_check(expect);
	if (ret < 0)
		goto out;

	nf_ct_expect_insert(expect);

	spin_unlock_bh(&nf_conntrack_expect_lock);
	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
	return 0;
out:
	spin_unlock_bh(&nf_conntrack_expect_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);

#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct ct_expect_iter_state {
	struct seq_net_private p;
	unsigned int bucket;
};

static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
{
	struct ct_expect_iter_state *st = seq->private;
	struct hlist_node *n;

	for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
		n = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
		if (n)
			return n;
	}
	return NULL;
}

static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
					     struct hlist_node *head)
{
	struct ct_expect_iter_state *st = seq->private;

	head = rcu_dereference(hlist_next_rcu(head));
	while (head == NULL) {
		if (++st->bucket >= nf_ct_expect_hsize)
			return NULL;
		head = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
	}
	return head;
}

static struct hlist_node *ct_expect_get_idx(struct seq_file *seq, loff_t pos)
{
	struct hlist_node *head = ct_expect_get_first(seq);

	if (head)
		while (pos && (head = ct_expect_get_next(seq, head)))
			pos--;
	return pos ? NULL : head;
}

static void *exp_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(RCU)
{
	rcu_read_lock();
	return ct_expect_get_idx(seq, *pos);
}

static void *exp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	(*pos)++;
	return ct_expect_get_next(seq, v);
}

static void exp_seq_stop(struct seq_file *seq, void *v)
	__releases(RCU)
{
	rcu_read_unlock();
}

static int exp_seq_show(struct seq_file *s, void *v)
{
	struct nf_conntrack_expect *expect;
	struct nf_conntrack_helper *helper;
	struct hlist_node *n = v;
	char *delim = "";

	expect = hlist_entry(n, struct nf_conntrack_expect, hnode);

	if (expect->timeout.function)
		seq_printf(s, "%ld ", timer_pending(&expect->timeout)
			   ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
	else
		seq_printf(s, "- ");
	seq_printf(s, "l3proto = %u proto=%u ",
		   expect->tuple.src.l3num,
		   expect->tuple.dst.protonum);
	print_tuple(s, &expect->tuple,
		    __nf_ct_l3proto_find(expect->tuple.src.l3num),
		    __nf_ct_l4proto_find(expect->tuple.src.l3num,
				       expect->tuple.dst.protonum));

	if (expect->flags & NF_CT_EXPECT_PERMANENT) {
		seq_printf(s, "PERMANENT");
		delim = ",";
	}
	if (expect->flags & NF_CT_EXPECT_INACTIVE) {
		seq_printf(s, "%sINACTIVE", delim);
		delim = ",";
	}
	if (expect->flags & NF_CT_EXPECT_USERSPACE)
		seq_printf(s, "%sUSERSPACE", delim);

	helper = rcu_dereference(nfct_help(expect->master)->helper);
	if (helper) {
		seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name);
		if (helper->expect_policy[expect->class].name[0])
			seq_printf(s, "/%s",
				   helper->expect_policy[expect->class].name);
	}

	seq_putc(s, '\n');

	return 0;
}

static const struct seq_operations exp_seq_ops = {
	.start = exp_seq_start,
	.next = exp_seq_next,
	.stop = exp_seq_stop,
	.show = exp_seq_show
};

static int exp_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &exp_seq_ops,
			sizeof(struct ct_expect_iter_state));
}

static const struct file_operations exp_file_ops = {
	.owner   = THIS_MODULE,
	.open    = exp_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_net,
};
#endif /* CONFIG_NF_CONNTRACK_PROCFS */

static int exp_proc_init(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
	struct proc_dir_entry *proc;
	kuid_t root_uid;
	kgid_t root_gid;

	proc = proc_create("nf_conntrack_expect", 0440, net->proc_net,
			   &exp_file_ops);
	if (!proc)
		return -ENOMEM;

	root_uid = make_kuid(net->user_ns, 0);
	root_gid = make_kgid(net->user_ns, 0);
	if (uid_valid(root_uid) && gid_valid(root_gid))
		proc_set_user(proc, root_uid, root_gid);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
	return 0;
}

static void exp_proc_remove(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
	remove_proc_entry("nf_conntrack_expect", net->proc_net);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
}

module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);

int nf_conntrack_expect_pernet_init(struct net *net)
{
	net->ct.expect_count = 0;
	return exp_proc_init(net);
}

void nf_conntrack_expect_pernet_fini(struct net *net)
{
	exp_proc_remove(net);
}

int nf_conntrack_expect_init(void)
{
	if (!nf_ct_expect_hsize) {
		nf_ct_expect_hsize = nf_conntrack_htable_size / 256;
		if (!nf_ct_expect_hsize)
			nf_ct_expect_hsize = 1;
	}
	nf_ct_expect_max = nf_ct_expect_hsize * 4;
	nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect",
				sizeof(struct nf_conntrack_expect),
				0, 0, NULL);
	if (!nf_ct_expect_cachep)
		return -ENOMEM;

	nf_ct_expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
	if (!nf_ct_expect_hash) {
		kmem_cache_destroy(nf_ct_expect_cachep);
		return -ENOMEM;
	}

	return 0;
}

void nf_conntrack_expect_fini(void)
{
	rcu_barrier(); /* Wait for call_rcu() before destroy */
	kmem_cache_destroy(nf_ct_expect_cachep);
	nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_hsize);
}