Free Electrons

Embedded Linux Experts

  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
/* netfilter.c: look after the filters for various protocols.
 * Heavily influenced by the old firewall.c by David Bonn and Alan Cox.
 *
 * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any
 * way.
 *
 * Rusty Russell (C)2000 -- This code is GPL.
 * Patrick McHardy (c) 2006-2012
 */
#include <linux/kernel.h>
#include <linux/netfilter.h>
#include <net/protocol.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/wait.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/if.h>
#include <linux/netdevice.h>
#include <linux/netfilter_ipv6.h>
#include <linux/inetdevice.h>
#include <linux/proc_fs.h>
#include <linux/mutex.h>
#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include <net/sock.h>

#include "nf_internals.h"

static DEFINE_MUTEX(afinfo_mutex);

const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
EXPORT_SYMBOL(nf_afinfo);
const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
EXPORT_SYMBOL_GPL(nf_ipv6_ops);

DEFINE_PER_CPU(bool, nf_skb_duplicated);
EXPORT_SYMBOL_GPL(nf_skb_duplicated);

int nf_register_afinfo(const struct nf_afinfo *afinfo)
{
	mutex_lock(&afinfo_mutex);
	RCU_INIT_POINTER(nf_afinfo[afinfo->family], afinfo);
	mutex_unlock(&afinfo_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(nf_register_afinfo);

void nf_unregister_afinfo(const struct nf_afinfo *afinfo)
{
	mutex_lock(&afinfo_mutex);
	RCU_INIT_POINTER(nf_afinfo[afinfo->family], NULL);
	mutex_unlock(&afinfo_mutex);
	synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_unregister_afinfo);

#ifdef HAVE_JUMP_LABEL
struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
EXPORT_SYMBOL(nf_hooks_needed);
#endif

static DEFINE_MUTEX(nf_hook_mutex);

/* max hooks per family/hooknum */
#define MAX_HOOK_COUNT		1024

#define nf_entry_dereference(e) \
	rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex))

static struct nf_hook_entries *allocate_hook_entries_size(u16 num)
{
	struct nf_hook_entries *e;
	size_t alloc = sizeof(*e) +
		       sizeof(struct nf_hook_entry) * num +
		       sizeof(struct nf_hook_ops *) * num;

	if (num == 0)
		return NULL;

	e = kvzalloc(alloc, GFP_KERNEL);
	if (e)
		e->num_hook_entries = num;
	return e;
}

static unsigned int accept_all(void *priv,
			       struct sk_buff *skb,
			       const struct nf_hook_state *state)
{
	return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */
}

static const struct nf_hook_ops dummy_ops = {
	.hook = accept_all,
	.priority = INT_MIN,
};

static struct nf_hook_entries *
nf_hook_entries_grow(const struct nf_hook_entries *old,
		     const struct nf_hook_ops *reg)
{
	unsigned int i, alloc_entries, nhooks, old_entries;
	struct nf_hook_ops **orig_ops = NULL;
	struct nf_hook_ops **new_ops;
	struct nf_hook_entries *new;
	bool inserted = false;

	alloc_entries = 1;
	old_entries = old ? old->num_hook_entries : 0;

	if (old) {
		orig_ops = nf_hook_entries_get_hook_ops(old);

		for (i = 0; i < old_entries; i++) {
			if (orig_ops[i] != &dummy_ops)
				alloc_entries++;
		}
	}

	if (alloc_entries > MAX_HOOK_COUNT)
		return ERR_PTR(-E2BIG);

	new = allocate_hook_entries_size(alloc_entries);
	if (!new)
		return ERR_PTR(-ENOMEM);

	new_ops = nf_hook_entries_get_hook_ops(new);

	i = 0;
	nhooks = 0;
	while (i < old_entries) {
		if (orig_ops[i] == &dummy_ops) {
			++i;
			continue;
		}
		if (inserted || reg->priority > orig_ops[i]->priority) {
			new_ops[nhooks] = (void *)orig_ops[i];
			new->hooks[nhooks] = old->hooks[i];
			i++;
		} else {
			new_ops[nhooks] = (void *)reg;
			new->hooks[nhooks].hook = reg->hook;
			new->hooks[nhooks].priv = reg->priv;
			inserted = true;
		}
		nhooks++;
	}

	if (!inserted) {
		new_ops[nhooks] = (void *)reg;
		new->hooks[nhooks].hook = reg->hook;
		new->hooks[nhooks].priv = reg->priv;
	}

	return new;
}

static void hooks_validate(const struct nf_hook_entries *hooks)
{
#ifdef CONFIG_DEBUG_KERNEL
	struct nf_hook_ops **orig_ops;
	int prio = INT_MIN;
	size_t i = 0;

	orig_ops = nf_hook_entries_get_hook_ops(hooks);

	for (i = 0; i < hooks->num_hook_entries; i++) {
		if (orig_ops[i] == &dummy_ops)
			continue;

		WARN_ON(orig_ops[i]->priority < prio);

		if (orig_ops[i]->priority > prio)
			prio = orig_ops[i]->priority;
	}
#endif
}

/*
 * __nf_hook_entries_try_shrink - try to shrink hook array
 *
 * @pp -- location of hook blob
 *
 * Hook unregistration must always succeed, so to-be-removed hooks
 * are replaced by a dummy one that will just move to next hook.
 *
 * This counts the current dummy hooks, attempts to allocate new blob,
 * copies the live hooks, then replaces and discards old one.
 *
 * return values:
 *
 * Returns address to free, or NULL.
 */
static void *__nf_hook_entries_try_shrink(struct nf_hook_entries __rcu **pp)
{
	struct nf_hook_entries *old, *new = NULL;
	unsigned int i, j, skip = 0, hook_entries;
	struct nf_hook_ops **orig_ops;
	struct nf_hook_ops **new_ops;

	old = nf_entry_dereference(*pp);
	if (WARN_ON_ONCE(!old))
		return NULL;

	orig_ops = nf_hook_entries_get_hook_ops(old);
	for (i = 0; i < old->num_hook_entries; i++) {
		if (orig_ops[i] == &dummy_ops)
			skip++;
	}

	/* if skip == hook_entries all hooks have been removed */
	hook_entries = old->num_hook_entries;
	if (skip == hook_entries)
		goto out_assign;

	if (skip == 0)
		return NULL;

	hook_entries -= skip;
	new = allocate_hook_entries_size(hook_entries);
	if (!new)
		return NULL;

	new_ops = nf_hook_entries_get_hook_ops(new);
	for (i = 0, j = 0; i < old->num_hook_entries; i++) {
		if (orig_ops[i] == &dummy_ops)
			continue;
		new->hooks[j] = old->hooks[i];
		new_ops[j] = (void *)orig_ops[i];
		j++;
	}
	hooks_validate(new);
out_assign:
	rcu_assign_pointer(*pp, new);
	return old;
}

static struct nf_hook_entries __rcu **nf_hook_entry_head(struct net *net, const struct nf_hook_ops *reg)
{
	if (reg->pf != NFPROTO_NETDEV)
		return net->nf.hooks[reg->pf]+reg->hooknum;

#ifdef CONFIG_NETFILTER_INGRESS
	if (reg->hooknum == NF_NETDEV_INGRESS) {
		if (reg->dev && dev_net(reg->dev) == net)
			return &reg->dev->nf_hooks_ingress;
	}
#endif
	WARN_ON_ONCE(1);
	return NULL;
}

int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
{
	struct nf_hook_entries *p, *new_hooks;
	struct nf_hook_entries __rcu **pp;

	if (reg->pf == NFPROTO_NETDEV) {
#ifndef CONFIG_NETFILTER_INGRESS
		if (reg->hooknum == NF_NETDEV_INGRESS)
			return -EOPNOTSUPP;
#endif
		if (reg->hooknum != NF_NETDEV_INGRESS ||
		    !reg->dev || dev_net(reg->dev) != net)
			return -EINVAL;
	}

	pp = nf_hook_entry_head(net, reg);
	if (!pp)
		return -EINVAL;

	mutex_lock(&nf_hook_mutex);

	p = nf_entry_dereference(*pp);
	new_hooks = nf_hook_entries_grow(p, reg);

	if (!IS_ERR(new_hooks))
		rcu_assign_pointer(*pp, new_hooks);

	mutex_unlock(&nf_hook_mutex);
	if (IS_ERR(new_hooks))
		return PTR_ERR(new_hooks);

	hooks_validate(new_hooks);
#ifdef CONFIG_NETFILTER_INGRESS
	if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
		net_inc_ingress_queue();
#endif
#ifdef HAVE_JUMP_LABEL
	static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
#endif
	synchronize_net();
	BUG_ON(p == new_hooks);
	kvfree(p);
	return 0;
}
EXPORT_SYMBOL(nf_register_net_hook);

/*
 * __nf_unregister_net_hook - remove a hook from blob
 *
 * @oldp: current address of hook blob
 * @unreg: hook to unregister
 *
 * This cannot fail, hook unregistration must always succeed.
 * Therefore replace the to-be-removed hook with a dummy hook.
 */
static void __nf_unregister_net_hook(struct nf_hook_entries *old,
				     const struct nf_hook_ops *unreg)
{
	struct nf_hook_ops **orig_ops;
	bool found = false;
	unsigned int i;

	orig_ops = nf_hook_entries_get_hook_ops(old);
	for (i = 0; i < old->num_hook_entries; i++) {
		if (orig_ops[i] != unreg)
			continue;
		WRITE_ONCE(old->hooks[i].hook, accept_all);
		WRITE_ONCE(orig_ops[i], &dummy_ops);
		found = true;
		break;
	}

	if (found) {
#ifdef CONFIG_NETFILTER_INGRESS
		if (unreg->pf == NFPROTO_NETDEV && unreg->hooknum == NF_NETDEV_INGRESS)
			net_dec_ingress_queue();
#endif
#ifdef HAVE_JUMP_LABEL
		static_key_slow_dec(&nf_hooks_needed[unreg->pf][unreg->hooknum]);
#endif
	} else {
		WARN_ONCE(1, "hook not found, pf %d num %d", unreg->pf, unreg->hooknum);
	}
}

void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
{
	struct nf_hook_entries __rcu **pp;
	struct nf_hook_entries *p;
	unsigned int nfq;

	pp = nf_hook_entry_head(net, reg);
	if (!pp)
		return;

	mutex_lock(&nf_hook_mutex);

	p = nf_entry_dereference(*pp);
	if (WARN_ON_ONCE(!p)) {
		mutex_unlock(&nf_hook_mutex);
		return;
	}

	__nf_unregister_net_hook(p, reg);

	p = __nf_hook_entries_try_shrink(pp);
	mutex_unlock(&nf_hook_mutex);
	if (!p)
		return;

	synchronize_net();

	/* other cpu might still process nfqueue verdict that used reg */
	nfq = nf_queue_nf_hook_drop(net);
	if (nfq)
		synchronize_net();
	kvfree(p);
}
EXPORT_SYMBOL(nf_unregister_net_hook);

int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
			  unsigned int n)
{
	unsigned int i;
	int err = 0;

	for (i = 0; i < n; i++) {
		err = nf_register_net_hook(net, &reg[i]);
		if (err)
			goto err;
	}
	return err;

err:
	if (i > 0)
		nf_unregister_net_hooks(net, reg, i);
	return err;
}
EXPORT_SYMBOL(nf_register_net_hooks);

void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
			     unsigned int hookcount)
{
	struct nf_hook_entries *to_free[16], *p;
	struct nf_hook_entries __rcu **pp;
	unsigned int i, j, n;

	mutex_lock(&nf_hook_mutex);
	for (i = 0; i < hookcount; i++) {
		pp = nf_hook_entry_head(net, &reg[i]);
		if (!pp)
			continue;

		p = nf_entry_dereference(*pp);
		if (WARN_ON_ONCE(!p))
			continue;
		__nf_unregister_net_hook(p, &reg[i]);
	}
	mutex_unlock(&nf_hook_mutex);

	do {
		n = min_t(unsigned int, hookcount, ARRAY_SIZE(to_free));

		mutex_lock(&nf_hook_mutex);

		for (i = 0, j = 0; i < hookcount && j < n; i++) {
			pp = nf_hook_entry_head(net, &reg[i]);
			if (!pp)
				continue;

			p = nf_entry_dereference(*pp);
			if (!p)
				continue;

			to_free[j] = __nf_hook_entries_try_shrink(pp);
			if (to_free[j])
				++j;
		}

		mutex_unlock(&nf_hook_mutex);

		if (j) {
			unsigned int nfq;

			synchronize_net();

			/* need 2nd synchronize_net() if nfqueue is used, skb
			 * can get reinjected right before nf_queue_hook_drop()
			 */
			nfq = nf_queue_nf_hook_drop(net);
			if (nfq)
				synchronize_net();

			for (i = 0; i < j; i++)
				kvfree(to_free[i]);
		}

		reg += n;
		hookcount -= n;
	} while (hookcount > 0);
}
EXPORT_SYMBOL(nf_unregister_net_hooks);

/* Returns 1 if okfn() needs to be executed by the caller,
 * -EPERM for NF_DROP, 0 otherwise.  Caller must hold rcu_read_lock. */
int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
		 const struct nf_hook_entries *e, unsigned int s)
{
	unsigned int verdict;
	int ret;

	for (; s < e->num_hook_entries; s++) {
		verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state);
		switch (verdict & NF_VERDICT_MASK) {
		case NF_ACCEPT:
			break;
		case NF_DROP:
			kfree_skb(skb);
			ret = NF_DROP_GETERR(verdict);
			if (ret == 0)
				ret = -EPERM;
			return ret;
		case NF_QUEUE:
			ret = nf_queue(skb, state, e, s, verdict);
			if (ret == 1)
				continue;
			return ret;
		default:
			/* Implicit handling for NF_STOLEN, as well as any other
			 * non conventional verdicts.
			 */
			return 0;
		}
	}

	return 1;
}
EXPORT_SYMBOL(nf_hook_slow);


int skb_make_writable(struct sk_buff *skb, unsigned int writable_len)
{
	if (writable_len > skb->len)
		return 0;

	/* Not exclusive use of packet?  Must copy. */
	if (!skb_cloned(skb)) {
		if (writable_len <= skb_headlen(skb))
			return 1;
	} else if (skb_clone_writable(skb, writable_len))
		return 1;

	if (writable_len <= skb_headlen(skb))
		writable_len = 0;
	else
		writable_len -= skb_headlen(skb);

	return !!__pskb_pull_tail(skb, writable_len);
}
EXPORT_SYMBOL(skb_make_writable);

/* This needs to be compiled in any case to avoid dependencies between the
 * nfnetlink_queue code and nf_conntrack.
 */
struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly;
EXPORT_SYMBOL_GPL(nfnl_ct_hook);

#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* This does not belong here, but locally generated errors need it if connection
   tracking in use: without this, connection may not be in hash table, and hence
   manufactured ICMP or RST packets will not be associated with it. */
void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *)
		__rcu __read_mostly;
EXPORT_SYMBOL(ip_ct_attach);

void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb)
{
	void (*attach)(struct sk_buff *, const struct sk_buff *);

	if (skb->_nfct) {
		rcu_read_lock();
		attach = rcu_dereference(ip_ct_attach);
		if (attach)
			attach(new, skb);
		rcu_read_unlock();
	}
}
EXPORT_SYMBOL(nf_ct_attach);

void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly;
EXPORT_SYMBOL(nf_ct_destroy);

void nf_conntrack_destroy(struct nf_conntrack *nfct)
{
	void (*destroy)(struct nf_conntrack *);

	rcu_read_lock();
	destroy = rcu_dereference(nf_ct_destroy);
	BUG_ON(destroy == NULL);
	destroy(nfct);
	rcu_read_unlock();
}
EXPORT_SYMBOL(nf_conntrack_destroy);

/* Built-in default zone used e.g. by modules. */
const struct nf_conntrack_zone nf_ct_zone_dflt = {
	.id	= NF_CT_DEFAULT_ZONE_ID,
	.dir	= NF_CT_DEFAULT_ZONE_DIR,
};
EXPORT_SYMBOL_GPL(nf_ct_zone_dflt);
#endif /* CONFIG_NF_CONNTRACK */

#ifdef CONFIG_NF_NAT_NEEDED
void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
EXPORT_SYMBOL(nf_nat_decode_session_hook);
#endif

static int __net_init netfilter_net_init(struct net *net)
{
	int i, h;

	for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) {
		for (h = 0; h < NF_MAX_HOOKS; h++)
			RCU_INIT_POINTER(net->nf.hooks[i][h], NULL);
	}

#ifdef CONFIG_PROC_FS
	net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter",
						net->proc_net);
	if (!net->nf.proc_netfilter) {
		if (!net_eq(net, &init_net))
			pr_err("cannot create netfilter proc entry");

		return -ENOMEM;
	}
#endif

	return 0;
}

static void __net_exit netfilter_net_exit(struct net *net)
{
	remove_proc_entry("netfilter", net->proc_net);
}

static struct pernet_operations netfilter_net_ops = {
	.init = netfilter_net_init,
	.exit = netfilter_net_exit,
};

int __init netfilter_init(void)
{
	int ret;

	ret = register_pernet_subsys(&netfilter_net_ops);
	if (ret < 0)
		goto err;

	ret = netfilter_log_init();
	if (ret < 0)
		goto err_pernet;

	return 0;
err_pernet:
	unregister_pernet_subsys(&netfilter_net_ops);
err:
	return ret;
}