summaryrefslogtreecommitdiffstats
path: root/net/ipv4/ip_fragment.c
blob: bbe7f72db9c157ba2d6c5292637c2f58ad39a123 (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
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
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
/*
 * 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.
 *
 *		The IP fragmentation functionality.
 *
 * Authors:	Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
 *		Alan Cox <alan@lxorguk.ukuu.org.uk>
 *
 * Fixes:
 *		Alan Cox	:	Split from ip.c , see ip_input.c for history.
 *		David S. Miller :	Begin massive cleanup...
 *		Andi Kleen	:	Add sysctls.
 *		xxxx		:	Overlapfrag bug.
 *		Ultima          :       ip_expire() kernel panic.
 *		Bill Hawes	:	Frag accounting and evictor fixes.
 *		John McDonald	:	0 length frag bug.
 *		Alexey Kuznetsov:	SMP races, threading, cleanup.
 *		Patrick McHardy :	LRU queue of frag heads for evictor.
 */

#define pr_fmt(fmt) "IPv4: " fmt

#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/jiffies.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <net/route.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/inet_frag.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/inet.h>
#include <linux/netfilter_ipv4.h>
#include <net/inet_ecn.h>
#include <net/l3mdev.h>

/* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
 * as well. Or notify me, at least. --ANK
 */
static const char ip_frag_cache_name[] = "ip4-frags";

struct ipfrag_skb_cb
{
	struct inet_skb_parm	h;
	int			offset;
};

#define FRAG_CB(skb)	((struct ipfrag_skb_cb *)((skb)->cb))

/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
	struct inet_frag_queue q;

	u32		user;
	__be32		saddr;
	__be32		daddr;
	__be16		id;
	u8		protocol;
	u8		ecn; /* RFC3168 support */
	u16		max_df_size; /* largest frag with DF set seen */
	int             iif;
	int             vif;   /* L3 master device index */
	unsigned int    rid;
	struct inet_peer *peer;
};

static u8 ip4_frag_ecn(u8 tos)
{
	return 1 << (tos & INET_ECN_MASK);
}

static struct inet_frags ip4_frags;

int ip_frag_mem(struct net *net)
{
	return sum_frag_mem_limit(&net->ipv4.frags);
}

static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
			 struct net_device *dev);

struct ip4_create_arg {
	struct iphdr *iph;
	u32 user;
	int vif;
};

static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
{
	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
	return jhash_3words((__force u32)id << 16 | prot,
			    (__force u32)saddr, (__force u32)daddr,
			    ip4_frags.rnd);
}

static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
{
	const struct ipq *ipq;

	ipq = container_of(q, struct ipq, q);
	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
}

static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
{
	const struct ipq *qp;
	const struct ip4_create_arg *arg = a;

	qp = container_of(q, struct ipq, q);
	return	qp->id == arg->iph->id &&
		qp->saddr == arg->iph->saddr &&
		qp->daddr == arg->iph->daddr &&
		qp->protocol == arg->iph->protocol &&
		qp->user == arg->user &&
		qp->vif == arg->vif;
}

static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
	struct ipq *qp = container_of(q, struct ipq, q);
	struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
					       frags);
	struct net *net = container_of(ipv4, struct net, ipv4);

	const struct ip4_create_arg *arg = a;

	qp->protocol = arg->iph->protocol;
	qp->id = arg->iph->id;
	qp->ecn = ip4_frag_ecn(arg->iph->tos);
	qp->saddr = arg->iph->saddr;
	qp->daddr = arg->iph->daddr;
	qp->vif = arg->vif;
	qp->user = arg->user;
	qp->peer = q->net->max_dist ?
		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
		NULL;
}

static void ip4_frag_free(struct inet_frag_queue *q)
{
	struct ipq *qp;

	qp = container_of(q, struct ipq, q);
	if (qp->peer)
		inet_putpeer(qp->peer);
}


/* Destruction primitives. */

static void ipq_put(struct ipq *ipq)
{
	inet_frag_put(&ipq->q, &ip4_frags);
}

/* Kill ipq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static void ipq_kill(struct ipq *ipq)
{
	inet_frag_kill(&ipq->q, &ip4_frags);
}

static bool frag_expire_skip_icmp(u32 user)
{
	return user == IP_DEFRAG_AF_PACKET ||
	       ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN,
					 __IP_DEFRAG_CONNTRACK_IN_END) ||
	       ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN,
					 __IP_DEFRAG_CONNTRACK_BRIDGE_IN);
}

/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(unsigned long arg)
{
	struct ipq *qp;
	struct net *net;

	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	spin_lock(&qp->q.lock);

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);

	if (!inet_frag_evicting(&qp->q)) {
		struct sk_buff *head = qp->q.fragments;
		const struct iphdr *iph;
		int err;

		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);

		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
			goto out;

		rcu_read_lock();
		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out_rcu_unlock;

		/* skb has no dst, perform route lookup again */
		iph = ip_hdr(head);
		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
					   iph->tos, head->dev);
		if (err)
			goto out_rcu_unlock;

		/* Only an end host needs to send an ICMP
		 * "Fragment Reassembly Timeout" message, per RFC792.
		 */
		if (frag_expire_skip_icmp(qp->user) &&
		    (skb_rtable(head)->rt_type != RTN_LOCAL))
			goto out_rcu_unlock;

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
		rcu_read_unlock();
	}
out:
	spin_unlock(&qp->q.lock);
	ipq_put(qp);
}

/* Find the correct entry in the "incomplete datagrams" queue for
 * this IP datagram, and create new one, if nothing is found.
 */
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
			   u32 user, int vif)
{
	struct inet_frag_queue *q;
	struct ip4_create_arg arg;
	unsigned int hash;

	arg.iph = iph;
	arg.user = user;
	arg.vif = vif;

	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);

	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
	if (IS_ERR_OR_NULL(q)) {
		inet_frag_maybe_warn_overflow(q, pr_fmt());
		return NULL;
	}
	return container_of(q, struct ipq, q);
}

/* Is the fragment too far ahead to be part of ipq? */
static int ip_frag_too_far(struct ipq *qp)
{
	struct inet_peer *peer = qp->peer;
	unsigned int max = qp->q.net->max_dist;
	unsigned int start, end;

	int rc;

	if (!peer || !max)
		return 0;

	start = qp->rid;
	end = atomic_inc_return(&peer->rid);
	qp->rid = end;

	rc = qp->q.fragments && (end - start) > max;

	if (rc) {
		struct net *net;

		net = container_of(qp->q.net, struct net, ipv4.frags);
		__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	}

	return rc;
}

static int ip_frag_reinit(struct ipq *qp)
{
	struct sk_buff *fp;
	unsigned int sum_truesize = 0;

	if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
		atomic_inc(&qp->q.refcnt);
		return -ETIMEDOUT;
	}

	fp = qp->q.fragments;
	do {
		struct sk_buff *xp = fp->next;

		sum_truesize += fp->truesize;
		kfree_skb(fp);
		fp = xp;
	} while (fp);
	sub_frag_mem_limit(qp->q.net, sum_truesize);

	qp->q.flags = 0;
	qp->q.len = 0;
	qp->q.meat = 0;
	qp->q.fragments = NULL;
	qp->q.fragments_tail = NULL;
	qp->iif = 0;
	qp->ecn = 0;

	return 0;
}

/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	unsigned int fragsize;
	int flags, offset;
	int ihl, end;
	int err = -ENOENT;
	u8 ecn;

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto err;

	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
	    unlikely(ip_frag_too_far(qp)) &&
	    unlikely(err = ip_frag_reinit(qp))) {
		ipq_kill(qp);
		goto err;
	}

	ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
	offset = ntohs(ip_hdr(skb)->frag_off);
	flags = offset & ~IP_OFFSET;
	offset &= IP_OFFSET;
	offset <<= 3;		/* offset is in 8-byte chunks */
	ihl = ip_hdrlen(skb);

	/* Determine the position of this fragment. */
	end = offset + skb->len - skb_network_offset(skb) - ihl;
	err = -EINVAL;

	/* Is this the final fragment? */
	if ((flags & IP_MF) == 0) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < qp->q.len ||
		    ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
			goto err;
		qp->q.flags |= INET_FRAG_LAST_IN;
		qp->q.len = end;
	} else {
		if (end&7) {
			end &= ~7;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
		if (end > qp->q.len) {
			/* Some bits beyond end -> corruption. */
			if (qp->q.flags & INET_FRAG_LAST_IN)
				goto err;
			qp->q.len = end;
		}
	}
	if (end == offset)
		goto err;

	err = -ENOMEM;
	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
		goto err;

	err = pskb_trim_rcsum(skb, end - offset);
	if (err)
		goto err;

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = qp->q.fragments_tail;
	if (!prev || FRAG_CB(prev)->offset < offset) {
		next = NULL;
		goto found;
	}
	prev = NULL;
	for (next = qp->q.fragments; next != NULL; next = next->next) {
		if (FRAG_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

found:
	/* We found where to put this one.  Check for overlap with
	 * preceding fragment, and, if needed, align things so that
	 * any overlaps are eliminated.
	 */
	if (prev) {
		int i = (FRAG_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			err = -EINVAL;
			if (end <= offset)
				goto err;
			err = -ENOMEM;
			if (!pskb_pull(skb, i))
				goto err;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
	}

	err = -ENOMEM;

	while (next && FRAG_CB(next)->offset < end) {
		int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			if (!pskb_pull(next, i))
				goto err;
			FRAG_CB(next)->offset += i;
			qp->q.meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragment is completely overridden with
			 * new one drop it.
			 */
			next = next->next;

			if (prev)
				prev->next = next;
			else
				qp->q.fragments = next;

			qp->q.meat -= free_it->len;
			sub_frag_mem_limit(qp->q.net, free_it->truesize);
			kfree_skb(free_it);
		}
	}

	FRAG_CB(skb)->offset = offset;

	/* Insert this fragment in the chain of fragments. */
	skb->next = next;
	if (!next)
		qp->q.fragments_tail = skb;
	if (prev)
		prev->next = skb;
	else
		qp->q.fragments = skb;

	dev = skb->dev;
	if (dev) {
		qp->iif = dev->ifindex;
		skb->dev = NULL;
	}
	qp->q.stamp = skb->tstamp;
	qp->q.meat += skb->len;
	qp->ecn |= ecn;
	add_frag_mem_limit(qp->q.net, skb->truesize);
	if (offset == 0)
		qp->q.flags |= INET_FRAG_FIRST_IN;

	fragsize = skb->len + ihl;

	if (fragsize > qp->q.max_size)
		qp->q.max_size = fragsize;

	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
	    fragsize > qp->max_df_size)
		qp->max_df_size = fragsize;

	if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
	    qp->q.meat == qp->q.len) {
		unsigned long orefdst = skb->_skb_refdst;

		skb->_skb_refdst = 0UL;
		err = ip_frag_reasm(qp, prev, dev);
		skb->_skb_refdst = orefdst;
		return err;
	}

	skb_dst_drop(skb);
	return -EINPROGRESS;

err:
	kfree_skb(skb);
	return err;
}


/* Build a new IP datagram from all its fragments. */

static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
			 struct net_device *dev)
{
	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
	struct iphdr *iph;
	struct sk_buff *fp, *head = qp->q.fragments;
	int len;
	int ihlen;
	int err;
	u8 ecn;

	ipq_kill(qp);

	ecn = ip_frag_ecn_table[qp->ecn];
	if (unlikely(ecn == 0xff)) {
		err = -EINVAL;
		goto out_fail;
	}
	/* Make the one we just received the head. */
	if (prev) {
		head = prev->next;
		fp = skb_clone(head, GFP_ATOMIC);
		if (!fp)
			goto out_nomem;

		fp->next = head->next;
		if (!fp->next)
			qp->q.fragments_tail = fp;
		prev->next = fp;

		skb_morph(head, qp->q.fragments);
		head->next = qp->q.fragments->next;

		consume_skb(qp->q.fragments);
		qp->q.fragments = head;
	}

	WARN_ON(!head);
	WARN_ON(FRAG_CB(head)->offset != 0);

	/* Allocate a new buffer for the datagram. */
	ihlen = ip_hdrlen(head);
	len = ihlen + qp->q.len;

	err = -E2BIG;
	if (len > 65535)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_unclone(head, GFP_ATOMIC))
		goto out_nomem;

	/* If the first fragment is fragmented itself, we split
	 * it to two chunks: the first with data and paged part
	 * and the second, holding only fragments. */
	if (skb_has_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		clone = alloc_skb(0, GFP_ATOMIC);
		if (!clone)
			goto out_nomem;
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_frag_list_init(head);
		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
		clone->len = clone->data_len = head->data_len - plen;
		head->data_len -= clone->len;
		head->len -= clone->len;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;
		add_frag_mem_limit(qp->q.net, clone->truesize);
	}

	skb_shinfo(head)->frag_list = head->next;
	skb_push(head, head->data - skb_network_header(head));

	for (fp=head->next; fp; fp = fp->next) {
		head->data_len += fp->len;
		head->len += fp->len;
		if (head->ip_summed != fp->ip_summed)
			head->ip_summed = CHECKSUM_NONE;
		else if (head->ip_summed == CHECKSUM_COMPLETE)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
	}
	sub_frag_mem_limit(qp->q.net, head->truesize);

	head->next = NULL;
	head->dev = dev;
	head->tstamp = qp->q.stamp;
	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

	iph = ip_hdr(head);
	iph->tot_len = htons(len);
	iph->tos |= ecn;

	/* When we set IP_DF on a refragmented skb we must also force a
	 * call to ip_fragment to avoid forwarding a DF-skb of size s while
	 * original sender only sent fragments of size f (where f < s).
	 *
	 * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
	 * frag seen to avoid sending tiny DF-fragments in case skb was built
	 * from one very small df-fragment and one large non-df frag.
	 */
	if (qp->max_df_size == qp->q.max_size) {
		IPCB(head)->flags |= IPSKB_FRAG_PMTU;
		iph->frag_off = htons(IP_DF);
	} else {
		iph->frag_off = 0;
	}

	ip_send_check(iph);

	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
	qp->q.fragments = NULL;
	qp->q.fragments_tail = NULL;
	return 0;

out_nomem:
	net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
	err = -ENOMEM;
	goto out_fail;
out_oversize:
	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	return err;
}

/* Process an incoming IP datagram fragment. */
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
	int vif = l3mdev_master_ifindex_rcu(dev);
	struct ipq *qp;

	__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
	skb_orphan(skb);

	/* Lookup (or create) queue header */
	qp = ip_find(net, ip_hdr(skb), user, vif);
	if (qp) {
		int ret;

		spin_lock(&qp->q.lock);

		ret = ip_frag_queue(qp, skb);

		spin_unlock(&qp->q.lock);
		ipq_put(qp);
		return ret;
	}

	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -ENOMEM;
}
EXPORT_SYMBOL(ip_defrag);

struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
	struct iphdr iph;
	int netoff;
	u32 len;

	if (skb->protocol != htons(ETH_P_IP))
		return skb;

	netoff = skb_network_offset(skb);

	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
		return skb;

	if (iph.ihl < 5 || iph.version != 4)
		return skb;

	len = ntohs(iph.tot_len);
	if (skb->len < netoff + len || len < (iph.ihl * 4))
		return skb;

	if (ip_is_fragment(&iph)) {
		skb = skb_share_check(skb, GFP_ATOMIC);
		if (skb) {
			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
				return skb;
			if (pskb_trim_rcsum(skb, netoff + len))
				return skb;
			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
			if (ip_defrag(net, skb, user))
				return NULL;
			skb_clear_hash(skb);
		}
	}
	return skb;
}
EXPORT_SYMBOL(ip_check_defrag);

#ifdef CONFIG_SYSCTL
static int zero;

static struct ctl_table ip4_frags_ns_ctl_table[] = {
	{
		.procname	= "ipfrag_high_thresh",
		.data		= &init_net.ipv4.frags.high_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &init_net.ipv4.frags.low_thresh
	},
	{
		.procname	= "ipfrag_low_thresh",
		.data		= &init_net.ipv4.frags.low_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &init_net.ipv4.frags.high_thresh
	},
	{
		.procname	= "ipfrag_time",
		.data		= &init_net.ipv4.frags.timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "ipfrag_max_dist",
		.data		= &init_net.ipv4.frags.max_dist,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero
	},
	{ }
};

/* secret interval has been deprecated */
static int ip4_frags_secret_interval_unused;
static struct ctl_table ip4_frags_ctl_table[] = {
	{
		.procname	= "ipfrag_secret_interval",
		.data		= &ip4_frags_secret_interval_unused,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{ }
};

static int __net_init ip4_frags_ns_ctl_register(struct net *net)
{
	struct ctl_table *table;
	struct ctl_table_header *hdr;

	table = ip4_frags_ns_ctl_table;
	if (!net_eq(net, &init_net)) {
		table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
		if (!table)
			goto err_alloc;

		table[0].data = &net->ipv4.frags.high_thresh;
		table[0].extra1 = &net->ipv4.frags.low_thresh;
		table[0].extra2 = &init_net.ipv4.frags.high_thresh;
		table[1].data = &net->ipv4.frags.low_thresh;
		table[1].extra2 = &net->ipv4.frags.high_thresh;
		table[2].data = &net->ipv4.frags.timeout;
		table[3].data = &net->ipv4.frags.max_dist;
	}

	hdr = register_net_sysctl(net, "net/ipv4", table);
	if (!hdr)
		goto err_reg;

	net->ipv4.frags_hdr = hdr;
	return 0;

err_reg:
	if (!net_eq(net, &init_net))
		kfree(table);
err_alloc:
	return -ENOMEM;
}

static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
{
	struct ctl_table *table;

	table = net->ipv4.frags_hdr->ctl_table_arg;
	unregister_net_sysctl_table(net->ipv4.frags_hdr);
	kfree(table);
}

static void __init ip4_frags_ctl_register(void)
{
	register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
}
#else
static int ip4_frags_ns_ctl_register(struct net *net)
{
	return 0;
}

static void ip4_frags_ns_ctl_unregister(struct net *net)
{
}

static void __init ip4_frags_ctl_register(void)
{
}
#endif

static int __net_init ipv4_frags_init_net(struct net *net)
{
	int res;

	/* Fragment cache limits.
	 *
	 * The fragment memory accounting code, (tries to) account for
	 * the real memory usage, by measuring both the size of frag
	 * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
	 * and the SKB's truesize.
	 *
	 * A 64K fragment consumes 129736 bytes (44*2944)+200
	 * (1500 truesize == 2944, sizeof(struct ipq) == 200)
	 *
	 * We will commit 4MB at one time. Should we cross that limit
	 * we will prune down to 3MB, making room for approx 8 big 64K
	 * fragments 8x128k.
	 */
	net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
	net->ipv4.frags.low_thresh  = 3 * 1024 * 1024;
	/*
	 * Important NOTE! Fragment queue must be destroyed before MSL expires.
	 * RFC791 is wrong proposing to prolongate timer each fragment arrival
	 * by TTL.
	 */
	net->ipv4.frags.timeout = IP_FRAG_TIME;

	net->ipv4.frags.max_dist = 64;

	res = inet_frags_init_net(&net->ipv4.frags);
	if (res)
		return res;
	res = ip4_frags_ns_ctl_register(net);
	if (res)
		inet_frags_uninit_net(&net->ipv4.frags);
	return res;
}

static void __net_exit ipv4_frags_exit_net(struct net *net)
{
	ip4_frags_ns_ctl_unregister(net);
	inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
}

static struct pernet_operations ip4_frags_ops = {
	.init = ipv4_frags_init_net,
	.exit = ipv4_frags_exit_net,
};

void __init ipfrag_init(void)
{
	ip4_frags_ctl_register();
	register_pernet_subsys(&ip4_frags_ops);
	ip4_frags.hashfn = ip4_hashfn;
	ip4_frags.constructor = ip4_frag_init;
	ip4_frags.destructor = ip4_frag_free;
	ip4_frags.qsize = sizeof(struct ipq);
	ip4_frags.match = ip4_frag_match;
	ip4_frags.frag_expire = ip_expire;
	ip4_frags.frags_cache_name = ip_frag_cache_name;
	if (inet_frags_init(&ip4_frags))
		panic("IP: failed to allocate ip4_frags cache\n");
}