summaryrefslogtreecommitdiffstats
path: root/net/ipv4/ip_sockglue.c
blob: 43c05854d752f94c88dbb3dbd4ab43a111a93d0d (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
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
/*
 * 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 to API glue.
 *
 * Authors:	see ip.c
 *
 * Fixes:
 *		Many		:	Split from ip.c , see ip.c for history.
 *		Martin Mares	:	TOS setting fixed.
 *		Alan Cox	:	Fixed a couple of oopses in Martin's
 *					TOS tweaks.
 *		Mike McLagan	:	Routing by source
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/tcp_states.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/netfilter.h>
#include <linux/route.h>
#include <linux/mroute.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <net/compat.h>
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include <net/transp_v6.h>
#endif

#include <linux/errqueue.h>
#include <asm/uaccess.h>

#define IP_CMSG_PKTINFO		1
#define IP_CMSG_TTL		2
#define IP_CMSG_TOS		4
#define IP_CMSG_RECVOPTS	8
#define IP_CMSG_RETOPTS		16
#define IP_CMSG_PASSSEC		32
#define IP_CMSG_ORIGDSTADDR     64

/*
 *	SOL_IP control messages.
 */

static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
	struct in_pktinfo info;
	struct rtable *rt = skb->rtable;

	info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
	if (rt) {
		info.ipi_ifindex = rt->rt_iif;
		info.ipi_spec_dst.s_addr = rt->rt_spec_dst;
	} else {
		info.ipi_ifindex = 0;
		info.ipi_spec_dst.s_addr = 0;
	}

	put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}

static void ip_cmsg_recv_ttl(struct msghdr *msg, struct sk_buff *skb)
{
	int ttl = ip_hdr(skb)->ttl;
	put_cmsg(msg, SOL_IP, IP_TTL, sizeof(int), &ttl);
}

static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb)
{
	put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos);
}

static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb)
{
	if (IPCB(skb)->opt.optlen == 0)
		return;

	put_cmsg(msg, SOL_IP, IP_RECVOPTS, IPCB(skb)->opt.optlen,
		 ip_hdr(skb) + 1);
}


static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
{
	unsigned char optbuf[sizeof(struct ip_options) + 40];
	struct ip_options * opt = (struct ip_options *)optbuf;

	if (IPCB(skb)->opt.optlen == 0)
		return;

	if (ip_options_echo(opt, skb)) {
		msg->msg_flags |= MSG_CTRUNC;
		return;
	}
	ip_options_undo(opt);

	put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
}

static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
{
	char *secdata;
	u32 seclen, secid;
	int err;

	err = security_socket_getpeersec_dgram(NULL, skb, &secid);
	if (err)
		return;

	err = security_secid_to_secctx(secid, &secdata, &seclen);
	if (err)
		return;

	put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata);
	security_release_secctx(secdata, seclen);
}

static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
	struct sockaddr_in sin;
	struct iphdr *iph = ip_hdr(skb);
	__be16 *ports = (__be16 *)skb_transport_header(skb);

	if (skb_transport_offset(skb) + 4 > skb->len)
		return;

	/* All current transport protocols have the port numbers in the
	 * first four bytes of the transport header and this function is
	 * written with this assumption in mind.
	 */

	sin.sin_family = AF_INET;
	sin.sin_addr.s_addr = iph->daddr;
	sin.sin_port = ports[1];
	memset(sin.sin_zero, 0, sizeof(sin.sin_zero));

	put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
}

void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
	struct inet_sock *inet = inet_sk(skb->sk);
	unsigned flags = inet->cmsg_flags;

	/* Ordered by supposed usage frequency */
	if (flags & 1)
		ip_cmsg_recv_pktinfo(msg, skb);
	if ((flags>>=1) == 0)
		return;

	if (flags & 1)
		ip_cmsg_recv_ttl(msg, skb);
	if ((flags>>=1) == 0)
		return;

	if (flags & 1)
		ip_cmsg_recv_tos(msg, skb);
	if ((flags>>=1) == 0)
		return;

	if (flags & 1)
		ip_cmsg_recv_opts(msg, skb);
	if ((flags>>=1) == 0)
		return;

	if (flags & 1)
		ip_cmsg_recv_retopts(msg, skb);
	if ((flags>>=1) == 0)
		return;

	if (flags & 1)
		ip_cmsg_recv_security(msg, skb);

	if ((flags>>=1) == 0)
		return;
	if (flags & 1)
		ip_cmsg_recv_dstaddr(msg, skb);

}

int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
{
	int err;
	struct cmsghdr *cmsg;

	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
		if (!CMSG_OK(msg, cmsg))
			return -EINVAL;
		if (cmsg->cmsg_level != SOL_IP)
			continue;
		switch (cmsg->cmsg_type) {
		case IP_RETOPTS:
			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40);
			if (err)
				return err;
			break;
		case IP_PKTINFO:
		{
			struct in_pktinfo *info;
			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
				return -EINVAL;
			info = (struct in_pktinfo *)CMSG_DATA(cmsg);
			ipc->oif = info->ipi_ifindex;
			ipc->addr = info->ipi_spec_dst.s_addr;
			break;
		}
		default:
			return -EINVAL;
		}
	}
	return 0;
}


/* Special input handler for packets caught by router alert option.
   They are selected only by protocol field, and then processed likely
   local ones; but only if someone wants them! Otherwise, router
   not running rsvpd will kill RSVP.

   It is user level problem, what it will make with them.
   I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
   but receiver should be enough clever f.e. to forward mtrace requests,
   sent to multicast group to reach destination designated router.
 */
struct ip_ra_chain *ip_ra_chain;
DEFINE_RWLOCK(ip_ra_lock);

int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *))
{
	struct ip_ra_chain *ra, *new_ra, **rap;

	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num == IPPROTO_RAW)
		return -EINVAL;

	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;

	write_lock_bh(&ip_ra_lock);
	for (rap = &ip_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
		if (ra->sk == sk) {
			if (on) {
				write_unlock_bh(&ip_ra_lock);
				kfree(new_ra);
				return -EADDRINUSE;
			}
			*rap = ra->next;
			write_unlock_bh(&ip_ra_lock);

			if (ra->destructor)
				ra->destructor(sk);
			sock_put(sk);
			kfree(ra);
			return 0;
		}
	}
	if (new_ra == NULL) {
		write_unlock_bh(&ip_ra_lock);
		return -ENOBUFS;
	}
	new_ra->sk = sk;
	new_ra->destructor = destructor;

	new_ra->next = ra;
	*rap = new_ra;
	sock_hold(sk);
	write_unlock_bh(&ip_ra_lock);

	return 0;
}

void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
		   __be16 port, u32 info, u8 *payload)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sock_exterr_skb *serr;

	if (!inet->recverr)
		return;

	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb)
		return;

	serr = SKB_EXT_ERR(skb);
	serr->ee.ee_errno = err;
	serr->ee.ee_origin = SO_EE_ORIGIN_ICMP;
	serr->ee.ee_type = icmp_hdr(skb)->type;
	serr->ee.ee_code = icmp_hdr(skb)->code;
	serr->ee.ee_pad = 0;
	serr->ee.ee_info = info;
	serr->ee.ee_data = 0;
	serr->addr_offset = (u8 *)&(((struct iphdr *)(icmp_hdr(skb) + 1))->daddr) -
				   skb_network_header(skb);
	serr->port = port;

	if (skb_pull(skb, payload - skb->data) != NULL) {
		skb_reset_transport_header(skb);
		if (sock_queue_err_skb(sk, skb) == 0)
			return;
	}
	kfree_skb(skb);
}

void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sock_exterr_skb *serr;
	struct iphdr *iph;
	struct sk_buff *skb;

	if (!inet->recverr)
		return;

	skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC);
	if (!skb)
		return;

	skb_put(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	iph->daddr = daddr;

	serr = SKB_EXT_ERR(skb);
	serr->ee.ee_errno = err;
	serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
	serr->ee.ee_type = 0;
	serr->ee.ee_code = 0;
	serr->ee.ee_pad = 0;
	serr->ee.ee_info = info;
	serr->ee.ee_data = 0;
	serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
	serr->port = port;

	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
	skb_reset_transport_header(skb);

	if (sock_queue_err_skb(sk, skb))
		kfree_skb(skb);
}

/*
 *	Handle MSG_ERRQUEUE
 */
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
{
	struct sock_exterr_skb *serr;
	struct sk_buff *skb, *skb2;
	struct sockaddr_in *sin;
	struct {
		struct sock_extended_err ee;
		struct sockaddr_in	 offender;
	} errhdr;
	int err;
	int copied;

	err = -EAGAIN;
	skb = skb_dequeue(&sk->sk_error_queue);
	if (skb == NULL)
		goto out;

	copied = skb->len;
	if (copied > len) {
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}
	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	if (err)
		goto out_free_skb;

	sock_recv_timestamp(msg, sk, skb);

	serr = SKB_EXT_ERR(skb);

	sin = (struct sockaddr_in *)msg->msg_name;
	if (sin) {
		sin->sin_family = AF_INET;
		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
						   serr->addr_offset);
		sin->sin_port = serr->port;
		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
	}

	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
	sin = &errhdr.offender;
	sin->sin_family = AF_UNSPEC;
	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
		struct inet_sock *inet = inet_sk(sk);

		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));
		if (inet->cmsg_flags)
			ip_cmsg_recv(msg, skb);
	}

	put_cmsg(msg, SOL_IP, IP_RECVERR, sizeof(errhdr), &errhdr);

	/* Now we could try to dump offended packet options */

	msg->msg_flags |= MSG_ERRQUEUE;
	err = copied;

	/* Reset and regenerate socket error */
	spin_lock_bh(&sk->sk_error_queue.lock);
	sk->sk_err = 0;
	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
		spin_unlock_bh(&sk->sk_error_queue.lock);
		sk->sk_error_report(sk);
	} else
		spin_unlock_bh(&sk->sk_error_queue.lock);

out_free_skb:
	kfree_skb(skb);
out:
	return err;
}


/*
 *	Socket option code for IP. This is the end of the line after any TCP,UDP etc options on
 *	an IP socket.
 */

static int do_ip_setsockopt(struct sock *sk, int level,
			    int optname, char __user *optval, int optlen)
{
	struct inet_sock *inet = inet_sk(sk);
	int val = 0, err;

	if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) |
			     (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) |
			     (1<<IP_RETOPTS) | (1<<IP_TOS) |
			     (1<<IP_TTL) | (1<<IP_HDRINCL) |
			     (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) |
			     (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
			     (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) ||
	    optname == IP_MULTICAST_TTL ||
	    optname == IP_MULTICAST_LOOP ||
	    optname == IP_RECVORIGDSTADDR) {
		if (optlen >= sizeof(int)) {
			if (get_user(val, (int __user *) optval))
				return -EFAULT;
		} else if (optlen >= sizeof(char)) {
			unsigned char ucval;

			if (get_user(ucval, (unsigned char __user *) optval))
				return -EFAULT;
			val = (int) ucval;
		}
	}

	/* If optlen==0, it is equivalent to val == 0 */

	if (ip_mroute_opt(optname))
		return ip_mroute_setsockopt(sk, optname, optval, optlen);

	err = 0;
	lock_sock(sk);

	switch (optname) {
	case IP_OPTIONS:
	{
		struct ip_options * opt = NULL;
		if (optlen > 40 || optlen < 0)
			goto e_inval;
		err = ip_options_get_from_user(sock_net(sk), &opt,
					       optval, optlen);
		if (err)
			break;
		if (inet->is_icsk) {
			struct inet_connection_sock *icsk = inet_csk(sk);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
			if (sk->sk_family == PF_INET ||
			    (!((1 << sk->sk_state) &
			       (TCPF_LISTEN | TCPF_CLOSE)) &&
			     inet->daddr != LOOPBACK4_IPV6)) {
#endif
				if (inet->opt)
					icsk->icsk_ext_hdr_len -= inet->opt->optlen;
				if (opt)
					icsk->icsk_ext_hdr_len += opt->optlen;
				icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
			}
#endif
		}
		opt = xchg(&inet->opt, opt);
		kfree(opt);
		break;
	}
	case IP_PKTINFO:
		if (val)
			inet->cmsg_flags |= IP_CMSG_PKTINFO;
		else
			inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
		break;
	case IP_RECVTTL:
		if (val)
			inet->cmsg_flags |=  IP_CMSG_TTL;
		else
			inet->cmsg_flags &= ~IP_CMSG_TTL;
		break;
	case IP_RECVTOS:
		if (val)
			inet->cmsg_flags |=  IP_CMSG_TOS;
		else
			inet->cmsg_flags &= ~IP_CMSG_TOS;
		break;
	case IP_RECVOPTS:
		if (val)
			inet->cmsg_flags |=  IP_CMSG_RECVOPTS;
		else
			inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
		break;
	case IP_RETOPTS:
		if (val)
			inet->cmsg_flags |= IP_CMSG_RETOPTS;
		else
			inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
		break;
	case IP_PASSSEC:
		if (val)
			inet->cmsg_flags |= IP_CMSG_PASSSEC;
		else
			inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
		break;
	case IP_RECVORIGDSTADDR:
		if (val)
			inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
		else
			inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
		break;
	case IP_TOS:	/* This sets both TOS and Precedence */
		if (sk->sk_type == SOCK_STREAM) {
			val &= ~3;
			val |= inet->tos & 3;
		}
		if (inet->tos != val) {
			inet->tos = val;
			sk->sk_priority = rt_tos2priority(val);
			sk_dst_reset(sk);
		}
		break;
	case IP_TTL:
		if (optlen<1)
			goto e_inval;
		if (val != -1 && (val < 1 || val>255))
			goto e_inval;
		inet->uc_ttl = val;
		break;
	case IP_HDRINCL:
		if (sk->sk_type != SOCK_RAW) {
			err = -ENOPROTOOPT;
			break;
		}
		inet->hdrincl = val ? 1 : 0;
		break;
	case IP_MTU_DISCOVER:
		if (val<0 || val>3)
			goto e_inval;
		inet->pmtudisc = val;
		break;
	case IP_RECVERR:
		inet->recverr = !!val;
		if (!val)
			skb_queue_purge(&sk->sk_error_queue);
		break;
	case IP_MULTICAST_TTL:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (optlen<1)
			goto e_inval;
		if (val == -1)
			val = 1;
		if (val < 0 || val > 255)
			goto e_inval;
		inet->mc_ttl = val;
		break;
	case IP_MULTICAST_LOOP:
		if (optlen<1)
			goto e_inval;
		inet->mc_loop = !!val;
		break;
	case IP_MULTICAST_IF:
	{
		struct ip_mreqn mreq;
		struct net_device *dev = NULL;

		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		/*
		 *	Check the arguments are allowable
		 */

		err = -EFAULT;
		if (optlen >= sizeof(struct ip_mreqn)) {
			if (copy_from_user(&mreq, optval, sizeof(mreq)))
				break;
		} else {
			memset(&mreq, 0, sizeof(mreq));
			if (optlen >= sizeof(struct in_addr) &&
			    copy_from_user(&mreq.imr_address, optval, sizeof(struct in_addr)))
				break;
		}

		if (!mreq.imr_ifindex) {
			if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
				inet->mc_index = 0;
				inet->mc_addr  = 0;
				err = 0;
				break;
			}
			dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
			if (dev) {
				mreq.imr_ifindex = dev->ifindex;
				dev_put(dev);
			}
		} else
			dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex);


		err = -EADDRNOTAVAIL;
		if (!dev)
			break;

		err = -EINVAL;
		if (sk->sk_bound_dev_if &&
		    mreq.imr_ifindex != sk->sk_bound_dev_if)
			break;

		inet->mc_index = mreq.imr_ifindex;
		inet->mc_addr  = mreq.imr_address.s_addr;
		err = 0;
		break;
	}

	case IP_ADD_MEMBERSHIP:
	case IP_DROP_MEMBERSHIP:
	{
		struct ip_mreqn mreq;

		err = -EPROTO;
		if (inet_sk(sk)->is_icsk)
			break;

		if (optlen < sizeof(struct ip_mreq))
			goto e_inval;
		err = -EFAULT;
		if (optlen >= sizeof(struct ip_mreqn)) {
			if (copy_from_user(&mreq, optval, sizeof(mreq)))
				break;
		} else {
			memset(&mreq, 0, sizeof(mreq));
			if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
				break;
		}

		if (optname == IP_ADD_MEMBERSHIP)
			err = ip_mc_join_group(sk, &mreq);
		else
			err = ip_mc_leave_group(sk, &mreq);
		break;
	}
	case IP_MSFILTER:
	{
		extern int sysctl_igmp_max_msf;
		struct ip_msfilter *msf;

		if (optlen < IP_MSFILTER_SIZE(0))
			goto e_inval;
		if (optlen > sysctl_optmem_max) {
			err = -ENOBUFS;
			break;
		}
		msf = kmalloc(optlen, GFP_KERNEL);
		if (!msf) {
			err = -ENOBUFS;
			break;
		}
		err = -EFAULT;
		if (copy_from_user(msf, optval, optlen)) {
			kfree(msf);
			break;
		}
		/* numsrc >= (1G-4) overflow in 32 bits */
		if (msf->imsf_numsrc >= 0x3ffffffcU ||
		    msf->imsf_numsrc > sysctl_igmp_max_msf) {
			kfree(msf);
			err = -ENOBUFS;
			break;
		}
		if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
			kfree(msf);
			err = -EINVAL;
			break;
		}
		err = ip_mc_msfilter(sk, msf, 0);
		kfree(msf);
		break;
	}
	case IP_BLOCK_SOURCE:
	case IP_UNBLOCK_SOURCE:
	case IP_ADD_SOURCE_MEMBERSHIP:
	case IP_DROP_SOURCE_MEMBERSHIP:
	{
		struct ip_mreq_source mreqs;
		int omode, add;

		if (optlen != sizeof(struct ip_mreq_source))
			goto e_inval;
		if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
			err = -EFAULT;
			break;
		}
		if (optname == IP_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == IP_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
			struct ip_mreqn mreq;

			mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
			mreq.imr_address.s_addr = mreqs.imr_interface;
			mreq.imr_ifindex = 0;
			err = ip_mc_join_group(sk, &mreq);
			if (err && err != -EADDRINUSE)
				break;
			omode = MCAST_INCLUDE;
			add = 1;
		} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
			omode = MCAST_INCLUDE;
			add = 0;
		}
		err = ip_mc_source(add, omode, sk, &mreqs, 0);
		break;
	}
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct group_req greq;
		struct sockaddr_in *psin;
		struct ip_mreqn mreq;

		if (optlen < sizeof(struct group_req))
			goto e_inval;
		err = -EFAULT;
		if (copy_from_user(&greq, optval, sizeof(greq)))
			break;
		psin = (struct sockaddr_in *)&greq.gr_group;
		if (psin->sin_family != AF_INET)
			goto e_inval;
		memset(&mreq, 0, sizeof(mreq));
		mreq.imr_multiaddr = psin->sin_addr;
		mreq.imr_ifindex = greq.gr_interface;

		if (optname == MCAST_JOIN_GROUP)
			err = ip_mc_join_group(sk, &mreq);
		else
			err = ip_mc_leave_group(sk, &mreq);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct group_source_req greqs;
		struct ip_mreq_source mreqs;
		struct sockaddr_in *psin;
		int omode, add;

		if (optlen != sizeof(struct group_source_req))
			goto e_inval;
		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
			err = -EFAULT;
			break;
		}
		if (greqs.gsr_group.ss_family != AF_INET ||
		    greqs.gsr_source.ss_family != AF_INET) {
			err = -EADDRNOTAVAIL;
			break;
		}
		psin = (struct sockaddr_in *)&greqs.gsr_group;
		mreqs.imr_multiaddr = psin->sin_addr.s_addr;
		psin = (struct sockaddr_in *)&greqs.gsr_source;
		mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
		mreqs.imr_interface = 0; /* use index for mc_source */

		if (optname == MCAST_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == MCAST_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
			struct ip_mreqn mreq;

			psin = (struct sockaddr_in *)&greqs.gsr_group;
			mreq.imr_multiaddr = psin->sin_addr;
			mreq.imr_address.s_addr = 0;
			mreq.imr_ifindex = greqs.gsr_interface;
			err = ip_mc_join_group(sk, &mreq);
			if (err && err != -EADDRINUSE)
				break;
			greqs.gsr_interface = mreq.imr_ifindex;
			omode = MCAST_INCLUDE;
			add = 1;
		} else /* MCAST_LEAVE_SOURCE_GROUP */ {
			omode = MCAST_INCLUDE;
			add = 0;
		}
		err = ip_mc_source(add, omode, sk, &mreqs,
				   greqs.gsr_interface);
		break;
	}
	case MCAST_MSFILTER:
	{
		extern int sysctl_igmp_max_msf;
		struct sockaddr_in *psin;
		struct ip_msfilter *msf = NULL;
		struct group_filter *gsf = NULL;
		int msize, i, ifindex;

		if (optlen < GROUP_FILTER_SIZE(0))
			goto e_inval;
		if (optlen > sysctl_optmem_max) {
			err = -ENOBUFS;
			break;
		}
		gsf = kmalloc(optlen, GFP_KERNEL);
		if (!gsf) {
			err = -ENOBUFS;
			break;
		}
		err = -EFAULT;
		if (copy_from_user(gsf, optval, optlen)) {
			goto mc_msf_out;
		}
		/* numsrc >= (4G-140)/128 overflow in 32 bits */
		if (gsf->gf_numsrc >= 0x1ffffff ||
		    gsf->gf_numsrc > sysctl_igmp_max_msf) {
			err = -ENOBUFS;
			goto mc_msf_out;
		}
		if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
			err = -EINVAL;
			goto mc_msf_out;
		}
		msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
		msf = kmalloc(msize, GFP_KERNEL);
		if (!msf) {
			err = -ENOBUFS;
			goto mc_msf_out;
		}
		ifindex = gsf->gf_interface;
		psin = (struct sockaddr_in *)&gsf->gf_group;
		if (psin->sin_family != AF_INET) {
			err = -EADDRNOTAVAIL;
			goto mc_msf_out;
		}
		msf->imsf_multiaddr = psin->sin_addr.s_addr;
		msf->imsf_interface = 0;
		msf->imsf_fmode = gsf->gf_fmode;
		msf->imsf_numsrc = gsf->gf_numsrc;
		err = -EADDRNOTAVAIL;
		for (i=0; i<gsf->gf_numsrc; ++i) {
			psin = (struct sockaddr_in *)&gsf->gf_slist[i];

			if (psin->sin_family != AF_INET)
				goto mc_msf_out;
			msf->imsf_slist[i] = psin->sin_addr.s_addr;
		}
		kfree(gsf);
		gsf = NULL;

		err = ip_mc_msfilter(sk, msf, ifindex);
	mc_msf_out:
		kfree(msf);
		kfree(gsf);
		break;
	}
	case IP_ROUTER_ALERT:
		err = ip_ra_control(sk, val ? 1 : 0, NULL);
		break;

	case IP_FREEBIND:
		if (optlen<1)
			goto e_inval;
		inet->freebind = !!val;
		break;

	case IP_IPSEC_POLICY:
	case IP_XFRM_POLICY:
		err = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			break;
		err = xfrm_user_policy(sk, optname, optval, optlen);
		break;

	case IP_TRANSPARENT:
		if (!capable(CAP_NET_ADMIN)) {
			err = -EPERM;
			break;
		}
		if (optlen < 1)
			goto e_inval;
		inet->transparent = !!val;
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	}
	release_sock(sk);
	return err;

e_inval:
	release_sock(sk);
	return -EINVAL;
}

int ip_setsockopt(struct sock *sk, int level,
		int optname, char __user *optval, int optlen)
{
	int err;

	if (level != SOL_IP)
		return -ENOPROTOOPT;

	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
	/* we need to exclude all possible ENOPROTOOPTs except default case */
	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
			optname != IP_IPSEC_POLICY &&
			optname != IP_XFRM_POLICY &&
			!ip_mroute_opt(optname)) {
		lock_sock(sk);
		err = nf_setsockopt(sk, PF_INET, optname, optval, optlen);
		release_sock(sk);
	}
#endif
	return err;
}

#ifdef CONFIG_COMPAT
int compat_ip_setsockopt(struct sock *sk, int level, int optname,
			 char __user *optval, int optlen)
{
	int err;

	if (level != SOL_IP)
		return -ENOPROTOOPT;

	if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER)
		return compat_mc_setsockopt(sk, level, optname, optval, optlen,
			ip_setsockopt);

	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
	/* we need to exclude all possible ENOPROTOOPTs except default case */
	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
			optname != IP_IPSEC_POLICY &&
			optname != IP_XFRM_POLICY &&
			!ip_mroute_opt(optname)) {
		lock_sock(sk);
		err = compat_nf_setsockopt(sk, PF_INET, optname,
					   optval, optlen);
		release_sock(sk);
	}
#endif
	return err;
}

EXPORT_SYMBOL(compat_ip_setsockopt);
#endif

/*
 *	Get the options. Note for future reference. The GET of IP options gets the
 *	_received_ ones. The set sets the _sent_ ones.
 */

static int do_ip_getsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int __user *optlen)
{
	struct inet_sock *inet = inet_sk(sk);
	int val;
	int len;

	if (level != SOL_IP)
		return -EOPNOTSUPP;

	if (ip_mroute_opt(optname))
		return ip_mroute_getsockopt(sk, optname, optval, optlen);

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

	lock_sock(sk);

	switch (optname) {
	case IP_OPTIONS:
	{
		unsigned char optbuf[sizeof(struct ip_options)+40];
		struct ip_options * opt = (struct ip_options *)optbuf;
		opt->optlen = 0;
		if (inet->opt)
			memcpy(optbuf, inet->opt,
			       sizeof(struct ip_options)+
			       inet->opt->optlen);
		release_sock(sk);

		if (opt->optlen == 0)
			return put_user(0, optlen);

		ip_options_undo(opt);

		len = min_t(unsigned int, len, opt->optlen);
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, opt->__data, len))
			return -EFAULT;
		return 0;
	}
	case IP_PKTINFO:
		val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
		break;
	case IP_RECVTTL:
		val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
		break;
	case IP_RECVTOS:
		val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
		break;
	case IP_RECVOPTS:
		val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
		break;
	case IP_RETOPTS:
		val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
		break;
	case IP_PASSSEC:
		val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
		break;
	case IP_RECVORIGDSTADDR:
		val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
		break;
	case IP_TOS:
		val = inet->tos;
		break;
	case IP_TTL:
		val = (inet->uc_ttl == -1 ?
		       sysctl_ip_default_ttl :
		       inet->uc_ttl);
		break;
	case IP_HDRINCL:
		val = inet->hdrincl;
		break;
	case IP_MTU_DISCOVER:
		val = inet->pmtudisc;
		break;
	case IP_MTU:
	{
		struct dst_entry *dst;
		val = 0;
		dst = sk_dst_get(sk);
		if (dst) {
			val = dst_mtu(dst);
			dst_release(dst);
		}
		if (!val) {
			release_sock(sk);
			return -ENOTCONN;
		}
		break;
	}
	case IP_RECVERR:
		val = inet->recverr;
		break;
	case IP_MULTICAST_TTL:
		val = inet->mc_ttl;
		break;
	case IP_MULTICAST_LOOP:
		val = inet->mc_loop;
		break;
	case IP_MULTICAST_IF:
	{
		struct in_addr addr;
		len = min_t(unsigned int, len, sizeof(struct in_addr));
		addr.s_addr = inet->mc_addr;
		release_sock(sk);

		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &addr, len))
			return -EFAULT;
		return 0;
	}
	case IP_MSFILTER:
	{
		struct ip_msfilter msf;
		int err;

		if (len < IP_MSFILTER_SIZE(0)) {
			release_sock(sk);
			return -EINVAL;
		}
		if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
			release_sock(sk);
			return -EFAULT;
		}
		err = ip_mc_msfget(sk, &msf,
				   (struct ip_msfilter __user *)optval, optlen);
		release_sock(sk);
		return err;
	}
	case MCAST_MSFILTER:
	{
		struct group_filter gsf;
		int err;

		if (len < GROUP_FILTER_SIZE(0)) {
			release_sock(sk);
			return -EINVAL;
		}
		if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
			release_sock(sk);
			return -EFAULT;
		}
		err = ip_mc_gsfget(sk, &gsf,
				   (struct group_filter __user *)optval, optlen);
		release_sock(sk);
		return err;
	}
	case IP_PKTOPTIONS:
	{
		struct msghdr msg;

		release_sock(sk);

		if (sk->sk_type != SOCK_STREAM)
			return -ENOPROTOOPT;

		msg.msg_control = optval;
		msg.msg_controllen = len;
		msg.msg_flags = 0;

		if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
			struct in_pktinfo info;

			info.ipi_addr.s_addr = inet->rcv_saddr;
			info.ipi_spec_dst.s_addr = inet->rcv_saddr;
			info.ipi_ifindex = inet->mc_index;
			put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
		}
		if (inet->cmsg_flags & IP_CMSG_TTL) {
			int hlim = inet->mc_ttl;
			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
		}
		len -= msg.msg_controllen;
		return put_user(len, optlen);
	}
	case IP_FREEBIND:
		val = inet->freebind;
		break;
	case IP_TRANSPARENT:
		val = inet->transparent;
		break;
	default:
		release_sock(sk);
		return -ENOPROTOOPT;
	}
	release_sock(sk);

	if (len < sizeof(int) && len > 0 && val>=0 && val<=255) {
		unsigned char ucval = (unsigned char)val;
		len = 1;
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &ucval, 1))
			return -EFAULT;
	} else {
		len = min_t(unsigned int, sizeof(int), len);
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &val, len))
			return -EFAULT;
	}
	return 0;
}

int ip_getsockopt(struct sock *sk, int level,
		  int optname, char __user *optval, int __user *optlen)
{
	int err;

	err = do_ip_getsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
	/* we need to exclude all possible ENOPROTOOPTs except default case */
	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
			!ip_mroute_opt(optname)) {
		int len;

		if (get_user(len, optlen))
			return -EFAULT;

		lock_sock(sk);
		err = nf_getsockopt(sk, PF_INET, optname, optval,
				&len);
		release_sock(sk);
		if (err >= 0)
			err = put_user(len, optlen);
		return err;
	}
#endif
	return err;
}

#ifdef CONFIG_COMPAT
int compat_ip_getsockopt(struct sock *sk, int level, int optname,
			 char __user *optval, int __user *optlen)
{
	int err;

	if (optname == MCAST_MSFILTER)
		return compat_mc_getsockopt(sk, level, optname, optval, optlen,
			ip_getsockopt);

	err = do_ip_getsockopt(sk, level, optname, optval, optlen);

#ifdef CONFIG_NETFILTER
	/* we need to exclude all possible ENOPROTOOPTs except default case */
	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
			!ip_mroute_opt(optname)) {
		int len;

		if (get_user(len, optlen))
			return -EFAULT;

		lock_sock(sk);
		err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
		release_sock(sk);
		if (err >= 0)
			err = put_user(len, optlen);
		return err;
	}
#endif
	return err;
}

EXPORT_SYMBOL(compat_ip_getsockopt);
#endif

EXPORT_SYMBOL(ip_cmsg_recv);

EXPORT_SYMBOL(ip_getsockopt);
EXPORT_SYMBOL(ip_setsockopt);