summaryrefslogtreecommitdiff
path: root/net/ipv4/raw.c
blob: 0b8e06ca75d6a5d836cdbd442f8a2e38995b19f9 (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
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * 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.
 *
 *		RAW - implementation of IP "raw" sockets.
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() fixed up
 *		Alan Cox	:	ICMP error handling
 *		Alan Cox	:	EMSGSIZE if you send too big a packet
 *		Alan Cox	: 	Now uses generic datagrams and shared
 *					skbuff library. No more peek crashes,
 *					no more backlogs
 *		Alan Cox	:	Checks sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram/skb_copy_datagram
 *		Alan Cox	:	Raw passes ip options too
 *		Alan Cox	:	Setsocketopt added
 *		Alan Cox	:	Fixed error return for broadcasts
 *		Alan Cox	:	Removed wake_up calls
 *		Alan Cox	:	Use ttl/tos
 *		Alan Cox	:	Cleaned up old debugging
 *		Alan Cox	:	Use new kernel side addresses
 *	Arnt Gulbrandsen	:	Fixed MSG_DONTROUTE in raw sockets.
 *		Alan Cox	:	BSD style RAW socket demultiplexing.
 *		Alan Cox	:	Beginnings of mrouted support.
 *		Alan Cox	:	Added IP_HDRINCL option.
 *		Alan Cox	:	Skip broadcast check if BSDism set.
 *		David S. Miller	:	New socket lookup architecture.
 */

#include <linux/types.h>
#include <linux/atomic.h>
#include <asm/byteorder.h>
#include <asm/current.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/mroute.h>
#include <linux/netdevice.h>
#include <linux/in_route.h>
#include <linux/route.h>
#include <linux/skbuff.h>
#include <linux/igmp.h>
#include <net/net_namespace.h>
#include <net/dst.h>
#include <net/sock.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/uio.h>

struct raw_frag_vec {
	struct msghdr *msg;
	union {
		struct icmphdr icmph;
		char c[1];
	} hdr;
	int hlen;
};

struct raw_hashinfo raw_v4_hashinfo = {
	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
EXPORT_SYMBOL_GPL(raw_v4_hashinfo);

int raw_hash_sk(struct sock *sk)
{
	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
	struct hlist_head *head;

	head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];

	write_lock_bh(&h->lock);
	sk_add_node(sk, head);
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
	write_unlock_bh(&h->lock);

	return 0;
}
EXPORT_SYMBOL_GPL(raw_hash_sk);

void raw_unhash_sk(struct sock *sk)
{
	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;

	write_lock_bh(&h->lock);
	if (sk_del_node_init(sk))
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
	write_unlock_bh(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);

struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
			     unsigned short num, __be32 raddr, __be32 laddr,
			     int dif, int sdif)
{
	sk_for_each_from(sk) {
		struct inet_sock *inet = inet_sk(sk);

		if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
		    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
		    raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
			goto found; /* gotcha */
	}
	sk = NULL;
found:
	return sk;
}
EXPORT_SYMBOL_GPL(__raw_v4_lookup);

/*
 *	0 - deliver
 *	1 - block
 */
static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
{
	struct icmphdr _hdr;
	const struct icmphdr *hdr;

	hdr = skb_header_pointer(skb, skb_transport_offset(skb),
				 sizeof(_hdr), &_hdr);
	if (!hdr)
		return 1;

	if (hdr->type < 32) {
		__u32 data = raw_sk(sk)->filter.data;

		return ((1U << hdr->type) & data) != 0;
	}

	/* Do not block unknown ICMP types */
	return 0;
}

/* IP input processing comes here for RAW socket delivery.
 * Caller owns SKB, so we must make clones.
 *
 * RFC 1122: SHOULD pass TOS value up to the transport layer.
 * -> It does. And not only TOS, but all IP header.
 */
static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
{
	int sdif = inet_sdif(skb);
	int dif = inet_iif(skb);
	struct sock *sk;
	struct hlist_head *head;
	int delivered = 0;
	struct net *net;

	read_lock(&raw_v4_hashinfo.lock);
	head = &raw_v4_hashinfo.ht[hash];
	if (hlist_empty(head))
		goto out;

	net = dev_net(skb->dev);
	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
			     iph->saddr, iph->daddr, dif, sdif);

	while (sk) {
		delivered = 1;
		if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
		    ip_mc_sf_allow(sk, iph->daddr, iph->saddr,
				   skb->dev->ifindex, sdif)) {
			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);

			/* Not releasing hash table! */
			if (clone)
				raw_rcv(sk, clone);
		}
		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
				     iph->saddr, iph->daddr,
				     skb->dev->ifindex, sdif);
	}
out:
	read_unlock(&raw_v4_hashinfo.lock);
	return delivered;
}

int raw_local_deliver(struct sk_buff *skb, int protocol)
{
	int hash;
	struct sock *raw_sk;

	hash = protocol & (RAW_HTABLE_SIZE - 1);
	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);

	/* If there maybe a raw socket we must check - if not we
	 * don't care less
	 */
	if (raw_sk && !raw_v4_input(skb, ip_hdr(skb), hash))
		raw_sk = NULL;

	return raw_sk != NULL;

}

static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
{
	struct inet_sock *inet = inet_sk(sk);
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	int err = 0;
	int harderr = 0;

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
		ipv4_sk_update_pmtu(skb, sk, info);
	else if (type == ICMP_REDIRECT) {
		ipv4_sk_redirect(skb, sk);
		return;
	}

	/* Report error on raw socket, if:
	   1. User requested ip_recverr.
	   2. Socket is connected (otherwise the error indication
	      is useless without ip_recverr and error is hard.
	 */
	if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED)
		return;

	switch (type) {
	default:
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	case ICMP_SOURCE_QUENCH:
		return;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		harderr = 1;
		break;
	case ICMP_DEST_UNREACH:
		err = EHOSTUNREACH;
		if (code > NR_ICMP_UNREACH)
			break;
		err = icmp_err_convert[code].errno;
		harderr = icmp_err_convert[code].fatal;
		if (code == ICMP_FRAG_NEEDED) {
			harderr = inet->pmtudisc != IP_PMTUDISC_DONT;
			err = EMSGSIZE;
		}
	}

	if (inet->recverr) {
		const struct iphdr *iph = (const struct iphdr *)skb->data;
		u8 *payload = skb->data + (iph->ihl << 2);

		if (inet->hdrincl)
			payload = skb->data;
		ip_icmp_error(sk, skb, err, 0, info, payload);
	}

	if (inet->recverr || harderr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	}
}

void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
{
	int hash;
	struct sock *raw_sk;
	const struct iphdr *iph;
	struct net *net;

	hash = protocol & (RAW_HTABLE_SIZE - 1);

	read_lock(&raw_v4_hashinfo.lock);
	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
	if (raw_sk) {
		int dif = skb->dev->ifindex;
		int sdif = inet_sdif(skb);

		iph = (const struct iphdr *)skb->data;
		net = dev_net(skb->dev);

		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
						iph->daddr, iph->saddr,
						dif, sdif)) != NULL) {
			raw_err(raw_sk, skb, info);
			raw_sk = sk_next(raw_sk);
			iph = (const struct iphdr *)skb->data;
		}
	}
	read_unlock(&raw_v4_hashinfo.lock);
}

static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	/* Charge it to the socket. */

	ipv4_pktinfo_prepare(sk, skb);
	if (sock_queue_rcv_skb(sk, skb) < 0) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	return NET_RX_SUCCESS;
}

int raw_rcv(struct sock *sk, struct sk_buff *skb)
{
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
		atomic_inc(&sk->sk_drops);
		kfree_skb(skb);
		return NET_RX_DROP;
	}
	nf_reset(skb);

	skb_push(skb, skb->data - skb_network_header(skb));

	raw_rcv_skb(sk, skb);
	return 0;
}

static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
			   struct msghdr *msg, size_t length,
			   struct rtable **rtp, unsigned int flags,
			   const struct sockcm_cookie *sockc)
{
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	struct iphdr *iph;
	struct sk_buff *skb;
	unsigned int iphlen;
	int err;
	struct rtable *rt = *rtp;
	int hlen, tlen;

	if (length > rt->dst.dev->mtu) {
		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
			       rt->dst.dev->mtu);
		return -EMSGSIZE;
	}
	if (length < sizeof(struct iphdr))
		return -EINVAL;

	if (flags&MSG_PROBE)
		goto out;

	hlen = LL_RESERVED_SPACE(rt->dst.dev);
	tlen = rt->dst.dev->needed_tailroom;
	skb = sock_alloc_send_skb(sk,
				  length + hlen + tlen + 15,
				  flags & MSG_DONTWAIT, &err);
	if (!skb)
		goto error;
	skb_reserve(skb, hlen);

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;
	skb->tstamp = sockc->transmit_time;
	skb_dst_set(skb, &rt->dst);
	*rtp = NULL;

	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	skb_put(skb, length);

	skb->ip_summed = CHECKSUM_NONE;

	skb_setup_tx_timestamp(skb, sockc->tsflags);

	if (flags & MSG_CONFIRM)
		skb_set_dst_pending_confirm(skb, 1);

	skb->transport_header = skb->network_header;
	err = -EFAULT;
	if (memcpy_from_msg(iph, msg, length))
		goto error_free;

	iphlen = iph->ihl * 4;

	/*
	 * We don't want to modify the ip header, but we do need to
	 * be sure that it won't cause problems later along the network
	 * stack.  Specifically we want to make sure that iph->ihl is a
	 * sane value.  If ihl points beyond the length of the buffer passed
	 * in, reject the frame as invalid
	 */
	err = -EINVAL;
	if (iphlen > length)
		goto error_free;

	if (iphlen >= sizeof(*iph)) {
		if (!iph->saddr)
			iph->saddr = fl4->saddr;
		iph->check   = 0;
		iph->tot_len = htons(length);
		if (!iph->id)
			ip_select_ident(net, skb, NULL);

		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
		skb->transport_header += iphlen;
		if (iph->protocol == IPPROTO_ICMP &&
		    length >= iphlen + sizeof(struct icmphdr))
			icmp_out_count(net, ((struct icmphdr *)
				skb_transport_header(skb))->type);
	}

	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
		      net, sk, skb, NULL, rt->dst.dev,
		      dst_output);
	if (err > 0)
		err = net_xmit_errno(err);
	if (err)
		goto error;
out:
	return 0;

error_free:
	kfree_skb(skb);
error:
	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
	if (err == -ENOBUFS && !inet->recverr)
		err = 0;
	return err;
}

static int raw_probe_proto_opt(struct raw_frag_vec *rfv, struct flowi4 *fl4)
{
	int err;

	if (fl4->flowi4_proto != IPPROTO_ICMP)
		return 0;

	/* We only need the first two bytes. */
	rfv->hlen = 2;

	err = memcpy_from_msg(rfv->hdr.c, rfv->msg, rfv->hlen);
	if (err)
		return err;

	fl4->fl4_icmp_type = rfv->hdr.icmph.type;
	fl4->fl4_icmp_code = rfv->hdr.icmph.code;

	return 0;
}

static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
		       struct sk_buff *skb)
{
	struct raw_frag_vec *rfv = from;

	if (offset < rfv->hlen) {
		int copy = min(rfv->hlen - offset, len);

		if (skb->ip_summed == CHECKSUM_PARTIAL)
			memcpy(to, rfv->hdr.c + offset, copy);
		else
			skb->csum = csum_block_add(
				skb->csum,
				csum_partial_copy_nocheck(rfv->hdr.c + offset,
							  to, copy, 0),
				odd);

		odd = 0;
		offset += copy;
		to += copy;
		len -= copy;

		if (!len)
			return 0;
	}

	offset -= rfv->hlen;

	return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
}

static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	struct ipcm_cookie ipc;
	struct rtable *rt = NULL;
	struct flowi4 fl4;
	int free = 0;
	__be32 daddr;
	__be32 saddr;
	u8  tos;
	int err;
	struct ip_options_data opt_copy;
	struct raw_frag_vec rfv;
	int hdrincl;

	err = -EMSGSIZE;
	if (len > 0xFFFF)
		goto out;

	/* hdrincl should be READ_ONCE(inet->hdrincl)
	 * but READ_ONCE() doesn't work with bit fields.
	 * Doing this indirectly yields the same result.
	 */
	hdrincl = inet->hdrincl;
	hdrincl = READ_ONCE(hdrincl);
	/*
	 *	Check the flags.
	 */

	err = -EOPNOTSUPP;
	if (msg->msg_flags & MSG_OOB)	/* Mirror BSD error message */
		goto out;               /* compatibility */

	/*
	 *	Get and verify the address.
	 */

	if (msg->msg_namelen) {
		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
		err = -EINVAL;
		if (msg->msg_namelen < sizeof(*usin))
			goto out;
		if (usin->sin_family != AF_INET) {
			pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
				     __func__, current->comm);
			err = -EAFNOSUPPORT;
			if (usin->sin_family)
				goto out;
		}
		daddr = usin->sin_addr.s_addr;
		/* ANK: I did not forget to get protocol from port field.
		 * I just do not know, who uses this weirdness.
		 * IP_HDRINCL is much more convenient.
		 */
	} else {
		err = -EDESTADDRREQ;
		if (sk->sk_state != TCP_ESTABLISHED)
			goto out;
		daddr = inet->inet_daddr;
	}

	ipcm_init_sk(&ipc, inet);

	if (msg->msg_controllen) {
		err = ip_cmsg_send(sk, msg, &ipc, false);
		if (unlikely(err)) {
			kfree(ipc.opt);
			goto out;
		}
		if (ipc.opt)
			free = 1;
	}

	saddr = ipc.addr;
	ipc.addr = daddr;

	if (!ipc.opt) {
		struct ip_options_rcu *inet_opt;

		rcu_read_lock();
		inet_opt = rcu_dereference(inet->inet_opt);
		if (inet_opt) {
			memcpy(&opt_copy, inet_opt,
			       sizeof(*inet_opt) + inet_opt->opt.optlen);
			ipc.opt = &opt_copy.opt;
		}
		rcu_read_unlock();
	}

	if (ipc.opt) {
		err = -EINVAL;
		/* Linux does not mangle headers on raw sockets,
		 * so that IP options + IP_HDRINCL is non-sense.
		 */
		if (hdrincl)
			goto done;
		if (ipc.opt->opt.srr) {
			if (!daddr)
				goto done;
			daddr = ipc.opt->opt.faddr;
		}
	}
	tos = get_rtconn_flags(&ipc, sk);
	if (msg->msg_flags & MSG_DONTROUTE)
		tos |= RTO_ONLINK;

	if (ipv4_is_multicast(daddr)) {
		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
			ipc.oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
	} else if (!ipc.oif) {
		ipc.oif = inet->uc_index;
	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
		/* oif is set, packet is to local broadcast and
		 * and uc_index is set. oif is most likely set
		 * by sk_bound_dev_if. If uc_index != oif check if the
		 * oif is an L3 master and uc_index is an L3 slave.
		 * If so, we want to allow the send using the uc_index.
		 */
		if (ipc.oif != inet->uc_index &&
		    ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),
							      inet->uc_index)) {
			ipc.oif = inet->uc_index;
		}
	}

	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
			   RT_SCOPE_UNIVERSE,
			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
			   inet_sk_flowi_flags(sk) |
			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
			   daddr, saddr, 0, 0, sk->sk_uid);

	if (!hdrincl) {
		rfv.msg = msg;
		rfv.hlen = 0;

		err = raw_probe_proto_opt(&rfv, &fl4);
		if (err)
			goto done;
	}

	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
	rt = ip_route_output_flow(net, &fl4, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		rt = NULL;
		goto done;
	}

	err = -EACCES;
	if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
		goto done;

	if (msg->msg_flags & MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	if (hdrincl)
		err = raw_send_hdrinc(sk, &fl4, msg, len,
				      &rt, msg->msg_flags, &ipc.sockc);

	 else {
		if (!ipc.addr)
			ipc.addr = fl4.daddr;
		lock_sock(sk);
		err = ip_append_data(sk, &fl4, raw_getfrag,
				     &rfv, len, 0,
				     &ipc, &rt, msg->msg_flags);
		if (err)
			ip_flush_pending_frames(sk);
		else if (!(msg->msg_flags & MSG_MORE)) {
			err = ip_push_pending_frames(sk, &fl4);
			if (err == -ENOBUFS && !inet->recverr)
				err = 0;
		}
		release_sock(sk);
	}
done:
	if (free)
		kfree(ipc.opt);
	ip_rt_put(rt);

out:
	if (err < 0)
		return err;
	return len;

do_confirm:
	if (msg->msg_flags & MSG_PROBE)
		dst_confirm_neigh(&rt->dst, &fl4.daddr);
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

static void raw_close(struct sock *sk, long timeout)
{
	/*
	 * Raw sockets may have direct kernel references. Kill them.
	 */
	ip_ra_control(sk, 0, NULL);

	sk_common_release(sk);
}

static void raw_destroy(struct sock *sk)
{
	lock_sock(sk);
	ip_flush_pending_frames(sk);
	release_sock(sk);
}

/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
	u32 tb_id = RT_TABLE_LOCAL;
	int ret = -EINVAL;
	int chk_addr_ret;

	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
		goto out;

	if (sk->sk_bound_dev_if)
		tb_id = l3mdev_fib_table_by_index(sock_net(sk),
						 sk->sk_bound_dev_if) ? : tb_id;

	chk_addr_ret = inet_addr_type_table(sock_net(sk), addr->sin_addr.s_addr,
					    tb_id);

	ret = -EADDRNOTAVAIL;
	if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
		goto out;
	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->inet_saddr = 0;  /* Use device */
	sk_dst_reset(sk);
	ret = 0;
out:	return ret;
}

/*
 *	This should be easy, if there is something there
 *	we return it, otherwise we block.
 */

static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
		       int noblock, int flags, int *addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	size_t copied = 0;
	int err = -EOPNOTSUPP;
	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
	struct sk_buff *skb;

	if (flags & MSG_OOB)
		goto out;

	if (flags & MSG_ERRQUEUE) {
		err = ip_recv_error(sk, msg, len, addr_len);
		goto out;
	}

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

	copied = skb->len;
	if (len < copied) {
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}

	err = skb_copy_datagram_msg(skb, 0, msg, copied);
	if (err)
		goto done;

	sock_recv_ts_and_drops(msg, sk, skb);

	/* Copy the address. */
	if (sin) {
		sin->sin_family = AF_INET;
		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
		sin->sin_port = 0;
		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
		*addr_len = sizeof(*sin);
	}
	if (inet->cmsg_flags)
		ip_cmsg_recv(msg, skb);
	if (flags & MSG_TRUNC)
		copied = skb->len;
done:
	skb_free_datagram(sk, skb);
out:
	if (err)
		return err;
	return copied;
}

static int raw_sk_init(struct sock *sk)
{
	struct raw_sock *rp = raw_sk(sk);

	if (inet_sk(sk)->inet_num == IPPROTO_ICMP)
		memset(&rp->filter, 0, sizeof(rp->filter));
	return 0;
}

static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
{
	if (optlen > sizeof(struct icmp_filter))
		optlen = sizeof(struct icmp_filter);
	if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
		return -EFAULT;
	return 0;
}

static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen)
{
	int len, ret = -EFAULT;

	if (get_user(len, optlen))
		goto out;
	ret = -EINVAL;
	if (len < 0)
		goto out;
	if (len > sizeof(struct icmp_filter))
		len = sizeof(struct icmp_filter);
	ret = -EFAULT;
	if (put_user(len, optlen) ||
	    copy_to_user(optval, &raw_sk(sk)->filter, len))
		goto out;
	ret = 0;
out:	return ret;
}

static int do_raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_seticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	if (level != SOL_RAW)
		return ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, unsigned int optlen)
{
	if (level != SOL_RAW)
		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_geticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return compat_ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ: {
		int amount = sk_wmem_alloc_get(sk);

		return put_user(amount, (int __user *)arg);
	}
	case SIOCINQ: {
		struct sk_buff *skb;
		int amount = 0;

		spin_lock_bh(&sk->sk_receive_queue.lock);
		skb = skb_peek(&sk->sk_receive_queue);
		if (skb)
			amount = skb->len;
		spin_unlock_bh(&sk->sk_receive_queue.lock);
		return put_user(amount, (int __user *)arg);
	}

	default:
#ifdef CONFIG_IP_MROUTE
		return ipmr_ioctl(sk, cmd, (void __user *)arg);
#else
		return -ENOIOCTLCMD;
#endif
	}
}

#ifdef CONFIG_COMPAT
static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ:
	case SIOCINQ:
		return -ENOIOCTLCMD;
	default:
#ifdef CONFIG_IP_MROUTE
		return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg));
#else
		return -ENOIOCTLCMD;
#endif
	}
}
#endif

int raw_abort(struct sock *sk, int err)
{
	lock_sock(sk);

	sk->sk_err = err;
	sk->sk_error_report(sk);
	__udp_disconnect(sk, 0);

	release_sock(sk);

	return 0;
}
EXPORT_SYMBOL_GPL(raw_abort);

struct proto raw_prot = {
	.name		   = "RAW",
	.owner		   = THIS_MODULE,
	.close		   = raw_close,
	.destroy	   = raw_destroy,
	.connect	   = ip4_datagram_connect,
	.disconnect	   = __udp_disconnect,
	.ioctl		   = raw_ioctl,
	.init		   = raw_sk_init,
	.setsockopt	   = raw_setsockopt,
	.getsockopt	   = raw_getsockopt,
	.sendmsg	   = raw_sendmsg,
	.recvmsg	   = raw_recvmsg,
	.bind		   = raw_bind,
	.backlog_rcv	   = raw_rcv_skb,
	.release_cb	   = ip4_datagram_release_cb,
	.hash		   = raw_hash_sk,
	.unhash		   = raw_unhash_sk,
	.obj_size	   = sizeof(struct raw_sock),
	.useroffset	   = offsetof(struct raw_sock, filter),
	.usersize	   = sizeof_field(struct raw_sock, filter),
	.h.raw_hash	   = &raw_v4_hashinfo,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_raw_setsockopt,
	.compat_getsockopt = compat_raw_getsockopt,
	.compat_ioctl	   = compat_raw_ioctl,
#endif
	.diag_destroy	   = raw_abort,
};

#ifdef CONFIG_PROC_FS
static struct sock *raw_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
	struct raw_iter_state *state = raw_seq_private(seq);

	for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
			++state->bucket) {
		sk_for_each(sk, &h->ht[state->bucket])
			if (sock_net(sk) == seq_file_net(seq))
				goto found;
	}
	sk = NULL;
found:
	return sk;
}

static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
{
	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
	struct raw_iter_state *state = raw_seq_private(seq);

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sock_net(sk) != seq_file_net(seq));

	if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
		sk = sk_head(&h->ht[state->bucket]);
		goto try_again;
	}
	return sk;
}

static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = raw_get_first(seq);

	if (sk)
		while (pos && (sk = raw_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

void *raw_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));

	read_lock(&h->lock);
	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL_GPL(raw_seq_start);

void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == SEQ_START_TOKEN)
		sk = raw_get_first(seq);
	else
		sk = raw_get_next(seq, v);
	++*pos;
	return sk;
}
EXPORT_SYMBOL_GPL(raw_seq_next);

void raw_seq_stop(struct seq_file *seq, void *v)
{
	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));

	read_unlock(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_seq_stop);

static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
{
	struct inet_sock *inet = inet_sk(sp);
	__be32 dest = inet->inet_daddr,
	       src = inet->inet_rcv_saddr;
	__u16 destp = 0,
	      srcp  = inet->inet_num;

	seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n",
		i, src, srcp, dest, destp, sp->sk_state,
		sk_wmem_alloc_get(sp),
		sk_rmem_alloc_get(sp),
		0, 0L, 0,
		from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
		0, sock_i_ino(sp),
		refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
}

static int raw_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "  sl  local_address rem_address   st tx_queue "
				"rx_queue tr tm->when retrnsmt   uid  timeout "
				"inode ref pointer drops\n");
	else
		raw_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
	return 0;
}

static const struct seq_operations raw_seq_ops = {
	.start = raw_seq_start,
	.next  = raw_seq_next,
	.stop  = raw_seq_stop,
	.show  = raw_seq_show,
};

static __net_init int raw_init_net(struct net *net)
{
	if (!proc_create_net_data("raw", 0444, net->proc_net, &raw_seq_ops,
			sizeof(struct raw_iter_state), &raw_v4_hashinfo))
		return -ENOMEM;

	return 0;
}

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

static __net_initdata struct pernet_operations raw_net_ops = {
	.init = raw_init_net,
	.exit = raw_exit_net,
};

int __init raw_proc_init(void)
{
	return register_pernet_subsys(&raw_net_ops);
}

void __init raw_proc_exit(void)
{
	unregister_pernet_subsys(&raw_net_ops);
}
#endif /* CONFIG_PROC_FS */

static void raw_sysctl_init_net(struct net *net)
{
#ifdef CONFIG_NET_L3_MASTER_DEV
	net->ipv4.sysctl_raw_l3mdev_accept = 1;
#endif
}

static int __net_init raw_sysctl_init(struct net *net)
{
	raw_sysctl_init_net(net);
	return 0;
}

static struct pernet_operations __net_initdata raw_sysctl_ops = {
	.init	= raw_sysctl_init,
};

void __init raw_init(void)
{
	raw_sysctl_init_net(&init_net);
	if (register_pernet_subsys(&raw_sysctl_ops))
		panic("RAW: failed to init sysctl parameters.\n");
}