summaryrefslogtreecommitdiff
path: root/net/ipv4/icmp.c
blob: 695979b7ef6d08c2056384d90c9671efd7ae90dd (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
/*
 *	NET3:	Implementation of the ICMP protocol layer.
 *
 *		Alan Cox, <alan@lxorguk.ukuu.org.uk>
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 *
 *	Some of the function names and the icmp unreach table for this
 *	module were derived from [icmp.c 1.0.11 06/02/93] by
 *	Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting.
 *	Other than that this module is a complete rewrite.
 *
 *	Fixes:
 *	Clemens Fruhwirth	:	introduce global icmp rate limiting
 *					with icmp type masking ability instead
 *					of broken per type icmp timeouts.
 *		Mike Shaver	:	RFC1122 checks.
 *		Alan Cox	:	Multicast ping reply as self.
 *		Alan Cox	:	Fix atomicity lockup in ip_build_xmit
 *					call.
 *		Alan Cox	:	Added 216,128 byte paths to the MTU
 *					code.
 *		Martin Mares	:	RFC1812 checks.
 *		Martin Mares	:	Can be configured to follow redirects
 *					if acting as a router _without_ a
 *					routing protocol (RFC 1812).
 *		Martin Mares	:	Echo requests may be configured to
 *					be ignored (RFC 1812).
 *		Martin Mares	:	Limitation of ICMP error message
 *					transmit rate (RFC 1812).
 *		Martin Mares	:	TOS and Precedence set correctly
 *					(RFC 1812).
 *		Martin Mares	:	Now copying as much data from the
 *					original packet as we can without
 *					exceeding 576 bytes (RFC 1812).
 *	Willy Konynenberg	:	Transparent proxying support.
 *		Keith Owens	:	RFC1191 correction for 4.2BSD based
 *					path MTU bug.
 *		Thomas Quinot	:	ICMP Dest Unreach codes up to 15 are
 *					valid (RFC 1812).
 *		Andi Kleen	:	Check all packet lengths properly
 *					and moved all kfree_skb() up to
 *					icmp_rcv.
 *		Andi Kleen	:	Move the rate limit bookkeeping
 *					into the dest entry and use a token
 *					bucket filter (thanks to ANK). Make
 *					the rates sysctl configurable.
 *		Yu Tianli	:	Fixed two ugly bugs in icmp_send
 *					- IP option length was accounted wrongly
 *					- ICMP header length was not accounted
 *					  at all.
 *              Tristan Greaves :       Added sysctl option to ignore bogus
 *              			broadcast responses from broken routers.
 *
 * To Fix:
 *
 *	- Should use skb_pull() instead of all the manual checking.
 *	  This would also greatly simply some upper layer error handlers. --AK
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/types.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/string.h>
#include <linux/netfilter_ipv4.h>
#include <linux/slab.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/protocol.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/ping.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/init.h>
#include <linux/uaccess.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <net/inet_common.h>
#include <net/ip_fib.h>
#include <net/l3mdev.h>

/*
 *	Build xmit assembly blocks
 */

struct icmp_bxm {
	struct sk_buff *skb;
	int offset;
	int data_len;

	struct {
		struct icmphdr icmph;
		__be32	       times[3];
	} data;
	int head_len;
	struct ip_options_data replyopts;
};

/* An array of errno for error messages from dest unreach. */
/* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */

const struct icmp_err icmp_err_convert[] = {
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNREACH */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_UNREACH */
		.fatal = 0,
	},
	{
		.errno = ENOPROTOOPT	/* ICMP_PROT_UNREACH */,
		.fatal = 1,
	},
	{
		.errno = ECONNREFUSED,	/* ICMP_PORT_UNREACH */
		.fatal = 1,
	},
	{
		.errno = EMSGSIZE,	/* ICMP_FRAG_NEEDED */
		.fatal = 0,
	},
	{
		.errno = EOPNOTSUPP,	/* ICMP_SR_FAILED */
		.fatal = 0,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNKNOWN */
		.fatal = 1,
	},
	{
		.errno = EHOSTDOWN,	/* ICMP_HOST_UNKNOWN */
		.fatal = 1,
	},
	{
		.errno = ENONET,	/* ICMP_HOST_ISOLATED */
		.fatal = 1,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_ANO	*/
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_ANO */
		.fatal = 1,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNR_TOS */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_UNR_TOS */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PKT_FILTERED */
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PREC_VIOLATION */
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PREC_CUTOFF */
		.fatal = 1,
	},
};
EXPORT_SYMBOL(icmp_err_convert);

/*
 *	ICMP control array. This specifies what to do with each ICMP.
 */

struct icmp_control {
	bool (*handler)(struct sk_buff *skb);
	short   error;		/* This ICMP is classed as an error message */
};

static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];

/*
 *	The ICMP socket(s). This is the most convenient way to flow control
 *	our ICMP output as well as maintain a clean interface throughout
 *	all layers. All Socketless IP sends will soon be gone.
 *
 *	On SMP we have one ICMP socket per-cpu.
 */
static struct sock *icmp_sk(struct net *net)
{
	return *this_cpu_ptr(net->ipv4.icmp_sk);
}

/* Called with BH disabled */
static inline struct sock *icmp_xmit_lock(struct net *net)
{
	struct sock *sk;

	sk = icmp_sk(net);

	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
		/* This can happen if the output path signals a
		 * dst_link_failure() for an outgoing ICMP packet.
		 */
		return NULL;
	}
	return sk;
}

static inline void icmp_xmit_unlock(struct sock *sk)
{
	spin_unlock(&sk->sk_lock.slock);
}

int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
int sysctl_icmp_msgs_burst __read_mostly = 50;

static struct {
	spinlock_t	lock;
	u32		credit;
	u32		stamp;
} icmp_global = {
	.lock		= __SPIN_LOCK_UNLOCKED(icmp_global.lock),
};

/**
 * icmp_global_allow - Are we allowed to send one more ICMP message ?
 *
 * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
 * Returns false if we reached the limit and can not send another packet.
 * Note: called with BH disabled
 */
bool icmp_global_allow(void)
{
	u32 credit, delta, incr = 0, now = (u32)jiffies;
	bool rc = false;

	/* Check if token bucket is empty and cannot be refilled
	 * without taking the spinlock.
	 */
	if (!icmp_global.credit) {
		delta = min_t(u32, now - icmp_global.stamp, HZ);
		if (delta < HZ / 50)
			return false;
	}

	spin_lock(&icmp_global.lock);
	delta = min_t(u32, now - icmp_global.stamp, HZ);
	if (delta >= HZ / 50) {
		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
		if (incr)
			icmp_global.stamp = now;
	}
	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
	if (credit) {
		credit--;
		rc = true;
	}
	icmp_global.credit = credit;
	spin_unlock(&icmp_global.lock);
	return rc;
}
EXPORT_SYMBOL(icmp_global_allow);

static bool icmpv4_mask_allow(struct net *net, int type, int code)
{
	if (type > NR_ICMP_TYPES)
		return true;

	/* Don't limit PMTU discovery. */
	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
		return true;

	/* Limit if icmp type is enabled in ratemask. */
	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
		return true;

	return false;
}

static bool icmpv4_global_allow(struct net *net, int type, int code)
{
	if (icmpv4_mask_allow(net, type, code))
		return true;

	if (icmp_global_allow())
		return true;

	return false;
}

/*
 *	Send an ICMP frame.
 */

static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
			       struct flowi4 *fl4, int type, int code)
{
	struct dst_entry *dst = &rt->dst;
	struct inet_peer *peer;
	bool rc = true;
	int vif;

	if (icmpv4_mask_allow(net, type, code))
		goto out;

	/* No rate limit on loopback */
	if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
		goto out;

	vif = l3mdev_master_ifindex(dst->dev);
	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
	rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
	if (peer)
		inet_putpeer(peer);
out:
	return rc;
}

/*
 *	Maintain the counters used in the SNMP statistics for outgoing ICMP
 */
void icmp_out_count(struct net *net, unsigned char type)
{
	ICMPMSGOUT_INC_STATS(net, type);
	ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS);
}

/*
 *	Checksum each fragment, and on the first include the headers and final
 *	checksum.
 */
static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
			  struct sk_buff *skb)
{
	struct icmp_bxm *icmp_param = (struct icmp_bxm *)from;
	__wsum csum;

	csum = skb_copy_and_csum_bits(icmp_param->skb,
				      icmp_param->offset + offset,
				      to, len, 0);

	skb->csum = csum_block_add(skb->csum, csum, odd);
	if (icmp_pointers[icmp_param->data.icmph.type].error)
		nf_ct_attach(skb, icmp_param->skb);
	return 0;
}

static void icmp_push_reply(struct icmp_bxm *icmp_param,
			    struct flowi4 *fl4,
			    struct ipcm_cookie *ipc, struct rtable **rt)
{
	struct sock *sk;
	struct sk_buff *skb;

	sk = icmp_sk(dev_net((*rt)->dst.dev));
	if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param,
			   icmp_param->data_len+icmp_param->head_len,
			   icmp_param->head_len,
			   ipc, rt, MSG_DONTWAIT) < 0) {
		__ICMP_INC_STATS(sock_net(sk), ICMP_MIB_OUTERRORS);
		ip_flush_pending_frames(sk);
	} else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
		struct icmphdr *icmph = icmp_hdr(skb);
		__wsum csum = 0;
		struct sk_buff *skb1;

		skb_queue_walk(&sk->sk_write_queue, skb1) {
			csum = csum_add(csum, skb1->csum);
		}
		csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
						 (char *)icmph,
						 icmp_param->head_len, csum);
		icmph->checksum = csum_fold(csum);
		skb->ip_summed = CHECKSUM_NONE;
		ip_push_pending_frames(sk, fl4);
	}
}

/*
 *	Driving logic for building and sending ICMP messages.
 */

static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
	struct ipcm_cookie ipc;
	struct rtable *rt = skb_rtable(skb);
	struct net *net = dev_net(rt->dst.dev);
	struct flowi4 fl4;
	struct sock *sk;
	struct inet_sock *inet;
	__be32 daddr, saddr;
	u32 mark = IP4_REPLY_MARK(net, skb->mark);
	int type = icmp_param->data.icmph.type;
	int code = icmp_param->data.icmph.code;

	if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
		return;

	/* Needed by both icmp_global_allow and icmp_xmit_lock */
	local_bh_disable();

	/* global icmp_msgs_per_sec */
	if (!icmpv4_global_allow(net, type, code))
		goto out_bh_enable;

	sk = icmp_xmit_lock(net);
	if (!sk)
		goto out_bh_enable;
	inet = inet_sk(sk);

	icmp_param->data.icmph.checksum = 0;

	ipcm_init(&ipc);
	inet->tos = ip_hdr(skb)->tos;
	sk->sk_mark = mark;
	daddr = ipc.addr = ip_hdr(skb)->saddr;
	saddr = fib_compute_spec_dst(skb);

	if (icmp_param->replyopts.opt.opt.optlen) {
		ipc.opt = &icmp_param->replyopts.opt;
		if (ipc.opt->opt.srr)
			daddr = icmp_param->replyopts.opt.opt.faddr;
	}
	memset(&fl4, 0, sizeof(fl4));
	fl4.daddr = daddr;
	fl4.saddr = saddr;
	fl4.flowi4_mark = mark;
	fl4.flowi4_uid = sock_net_uid(net, NULL);
	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
	fl4.flowi4_proto = IPPROTO_ICMP;
	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt))
		goto out_unlock;
	if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
		icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
	ip_rt_put(rt);
out_unlock:
	icmp_xmit_unlock(sk);
out_bh_enable:
	local_bh_enable();
}

static struct rtable *icmp_route_lookup(struct net *net,
					struct flowi4 *fl4,
					struct sk_buff *skb_in,
					const struct iphdr *iph,
					__be32 saddr, u8 tos, u32 mark,
					int type, int code,
					struct icmp_bxm *param)
{
	struct rtable *rt, *rt2;
	struct flowi4 fl4_dec;
	int err;

	memset(fl4, 0, sizeof(*fl4));
	fl4->daddr = (param->replyopts.opt.opt.srr ?
		      param->replyopts.opt.opt.faddr : iph->saddr);
	fl4->saddr = saddr;
	fl4->flowi4_mark = mark;
	fl4->flowi4_uid = sock_net_uid(net, NULL);
	fl4->flowi4_tos = RT_TOS(tos);
	fl4->flowi4_proto = IPPROTO_ICMP;
	fl4->fl4_icmp_type = type;
	fl4->fl4_icmp_code = code;
	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);

	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
	rt = ip_route_output_key_hash(net, fl4, skb_in);
	if (IS_ERR(rt))
		return rt;

	/* No need to clone since we're just using its address. */
	rt2 = rt;

	rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
					   flowi4_to_flowi(fl4), NULL, 0);
	if (!IS_ERR(rt)) {
		if (rt != rt2)
			return rt;
	} else if (PTR_ERR(rt) == -EPERM) {
		rt = NULL;
	} else
		return rt;

	err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4_dec), AF_INET);
	if (err)
		goto relookup_failed;

	if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
				     fl4_dec.saddr) == RTN_LOCAL) {
		rt2 = __ip_route_output_key(net, &fl4_dec);
		if (IS_ERR(rt2))
			err = PTR_ERR(rt2);
	} else {
		struct flowi4 fl4_2 = {};
		unsigned long orefdst;

		fl4_2.daddr = fl4_dec.saddr;
		rt2 = ip_route_output_key(net, &fl4_2);
		if (IS_ERR(rt2)) {
			err = PTR_ERR(rt2);
			goto relookup_failed;
		}
		/* Ugh! */
		orefdst = skb_in->_skb_refdst; /* save old refdst */
		skb_dst_set(skb_in, NULL);
		err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
				     RT_TOS(tos), rt2->dst.dev);

		dst_release(&rt2->dst);
		rt2 = skb_rtable(skb_in);
		skb_in->_skb_refdst = orefdst; /* restore old refdst */
	}

	if (err)
		goto relookup_failed;

	rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,
					    flowi4_to_flowi(&fl4_dec), NULL,
					    XFRM_LOOKUP_ICMP);
	if (!IS_ERR(rt2)) {
		dst_release(&rt->dst);
		memcpy(fl4, &fl4_dec, sizeof(*fl4));
		rt = rt2;
	} else if (PTR_ERR(rt2) == -EPERM) {
		if (rt)
			dst_release(&rt->dst);
		return rt2;
	} else {
		err = PTR_ERR(rt2);
		goto relookup_failed;
	}
	return rt;

relookup_failed:
	if (rt)
		return rt;
	return ERR_PTR(err);
}

/*
 *	Send an ICMP message in response to a situation
 *
 *	RFC 1122: 3.2.2	MUST send at least the IP header and 8 bytes of header.
 *		  MAY send more (we do).
 *			MUST NOT change this header information.
 *			MUST NOT reply to a multicast/broadcast IP address.
 *			MUST NOT reply to a multicast/broadcast MAC address.
 *			MUST reply to only the first fragment.
 */

void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
	struct iphdr *iph;
	int room;
	struct icmp_bxm icmp_param;
	struct rtable *rt = skb_rtable(skb_in);
	struct ipcm_cookie ipc;
	struct flowi4 fl4;
	__be32 saddr;
	u8  tos;
	u32 mark;
	struct net *net;
	struct sock *sk;

	if (!rt)
		goto out;
	net = dev_net(rt->dst.dev);

	/*
	 *	Find the original header. It is expected to be valid, of course.
	 *	Check this, icmp_send is called from the most obscure devices
	 *	sometimes.
	 */
	iph = ip_hdr(skb_in);

	if ((u8 *)iph < skb_in->head ||
	    (skb_network_header(skb_in) + sizeof(*iph)) >
	    skb_tail_pointer(skb_in))
		goto out;

	/*
	 *	No replies to physical multicast/broadcast
	 */
	if (skb_in->pkt_type != PACKET_HOST)
		goto out;

	/*
	 *	Now check at the protocol level
	 */
	if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto out;

	/*
	 *	Only reply to fragment 0. We byte re-order the constant
	 *	mask for efficiency.
	 */
	if (iph->frag_off & htons(IP_OFFSET))
		goto out;

	/*
	 *	If we send an ICMP error to an ICMP error a mess would result..
	 */
	if (icmp_pointers[type].error) {
		/*
		 *	We are an error, check if we are replying to an
		 *	ICMP error
		 */
		if (iph->protocol == IPPROTO_ICMP) {
			u8 _inner_type, *itp;

			itp = skb_header_pointer(skb_in,
						 skb_network_header(skb_in) +
						 (iph->ihl << 2) +
						 offsetof(struct icmphdr,
							  type) -
						 skb_in->data,
						 sizeof(_inner_type),
						 &_inner_type);
			if (!itp)
				goto out;

			/*
			 *	Assume any unknown ICMP type is an error. This
			 *	isn't specified by the RFC, but think about it..
			 */
			if (*itp > NR_ICMP_TYPES ||
			    icmp_pointers[*itp].error)
				goto out;
		}
	}

	/* Needed by both icmp_global_allow and icmp_xmit_lock */
	local_bh_disable();

	/* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
	 * incoming dev is loopback.  If outgoing dev change to not be
	 * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
	 */
	if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
	      !icmpv4_global_allow(net, type, code))
		goto out_bh_enable;

	sk = icmp_xmit_lock(net);
	if (!sk)
		goto out_bh_enable;

	/*
	 *	Construct source address and options.
	 */

	saddr = iph->daddr;
	if (!(rt->rt_flags & RTCF_LOCAL)) {
		struct net_device *dev = NULL;

		rcu_read_lock();
		if (rt_is_input_route(rt) &&
		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));

		if (dev)
			saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
		else
			saddr = 0;
		rcu_read_unlock();
	}

	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
					   IPTOS_PREC_INTERNETCONTROL) :
					  iph->tos;
	mark = IP4_REPLY_MARK(net, skb_in->mark);

	if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
		goto out_unlock;


	/*
	 *	Prepare data for ICMP header.
	 */

	icmp_param.data.icmph.type	 = type;
	icmp_param.data.icmph.code	 = code;
	icmp_param.data.icmph.un.gateway = info;
	icmp_param.data.icmph.checksum	 = 0;
	icmp_param.skb	  = skb_in;
	icmp_param.offset = skb_network_offset(skb_in);
	inet_sk(sk)->tos = tos;
	sk->sk_mark = mark;
	ipcm_init(&ipc);
	ipc.addr = iph->saddr;
	ipc.opt = &icmp_param.replyopts.opt;

	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
			       type, code, &icmp_param);
	if (IS_ERR(rt))
		goto out_unlock;

	/* peer icmp_ratelimit */
	if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
		goto ende;

	/* RFC says return as much as we can without exceeding 576 bytes. */

	room = dst_mtu(&rt->dst);
	if (room > 576)
		room = 576;
	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
	room -= sizeof(struct icmphdr);

	icmp_param.data_len = skb_in->len - icmp_param.offset;
	if (icmp_param.data_len > room)
		icmp_param.data_len = room;
	icmp_param.head_len = sizeof(struct icmphdr);

	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
ende:
	ip_rt_put(rt);
out_unlock:
	icmp_xmit_unlock(sk);
out_bh_enable:
	local_bh_enable();
out:;
}
EXPORT_SYMBOL(icmp_send);


static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
{
	const struct iphdr *iph = (const struct iphdr *) skb->data;
	const struct net_protocol *ipprot;
	int protocol = iph->protocol;

	/* Checkin full IP header plus 8 bytes of protocol to
	 * avoid additional coding at protocol handlers.
	 */
	if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) {
		__ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
		return;
	}

	raw_icmp_error(skb, protocol, info);

	ipprot = rcu_dereference(inet_protos[protocol]);
	if (ipprot && ipprot->err_handler)
		ipprot->err_handler(skb, info);
}

static bool icmp_tag_validation(int proto)
{
	bool ok;

	rcu_read_lock();
	ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
	rcu_read_unlock();
	return ok;
}

/*
 *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and
 *	ICMP_PARAMETERPROB.
 */

static bool icmp_unreach(struct sk_buff *skb)
{
	const struct iphdr *iph;
	struct icmphdr *icmph;
	struct net *net;
	u32 info = 0;

	net = dev_net(skb_dst(skb)->dev);

	/*
	 *	Incomplete header ?
	 * 	Only checks for the IP header, there should be an
	 *	additional check for longer headers in upper levels.
	 */

	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto out_err;

	icmph = icmp_hdr(skb);
	iph   = (const struct iphdr *)skb->data;

	if (iph->ihl < 5) /* Mangled header, drop. */
		goto out_err;

	switch (icmph->type) {
	case ICMP_DEST_UNREACH:
		switch (icmph->code & 15) {
		case ICMP_NET_UNREACH:
		case ICMP_HOST_UNREACH:
		case ICMP_PROT_UNREACH:
		case ICMP_PORT_UNREACH:
			break;
		case ICMP_FRAG_NEEDED:
			/* for documentation of the ip_no_pmtu_disc
			 * values please see
			 * Documentation/networking/ip-sysctl.txt
			 */
			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
			default:
				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
						    &iph->daddr);
				break;
			case 2:
				goto out;
			case 3:
				if (!icmp_tag_validation(iph->protocol))
					goto out;
				/* fall through */
			case 0:
				info = ntohs(icmph->un.frag.mtu);
			}
			break;
		case ICMP_SR_FAILED:
			net_dbg_ratelimited("%pI4: Source Route Failed\n",
					    &iph->daddr);
			break;
		default:
			break;
		}
		if (icmph->code > NR_ICMP_UNREACH)
			goto out;
		break;
	case ICMP_PARAMETERPROB:
		info = ntohl(icmph->un.gateway) >> 24;
		break;
	case ICMP_TIME_EXCEEDED:
		__ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS);
		if (icmph->code == ICMP_EXC_FRAGTIME)
			goto out;
		break;
	}

	/*
	 *	Throw it at our lower layers
	 *
	 *	RFC 1122: 3.2.2 MUST extract the protocol ID from the passed
	 *		  header.
	 *	RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the
	 *		  transport layer.
	 *	RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to
	 *		  transport layer.
	 */

	/*
	 *	Check the other end isn't violating RFC 1122. Some routers send
	 *	bogus responses to broadcast frames. If you see this message
	 *	first check your netmask matches at both ends, if it does then
	 *	get the other vendor to fix their kit.
	 */

	if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
	    inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
		net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
				     &ip_hdr(skb)->saddr,
				     icmph->type, icmph->code,
				     &iph->daddr, skb->dev->name);
		goto out;
	}

	icmp_socket_deliver(skb, info);

out:
	return true;
out_err:
	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
	return false;
}


/*
 *	Handle ICMP_REDIRECT.
 */

static bool icmp_redirect(struct sk_buff *skb)
{
	if (skb->len < sizeof(struct iphdr)) {
		__ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
		return false;
	}

	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
		/* there aught to be a stat */
		return false;
	}

	icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway);
	return true;
}

/*
 *	Handle ICMP_ECHO ("ping") requests.
 *
 *	RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
 *		  requests.
 *	RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be
 *		  included in the reply.
 *	RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring
 *		  echo requests, MUST have default=NOT.
 *	See also WRT handling of options once they are done and working.
 */

static bool icmp_echo(struct sk_buff *skb)
{
	struct net *net;

	net = dev_net(skb_dst(skb)->dev);
	if (!net->ipv4.sysctl_icmp_echo_ignore_all) {
		struct icmp_bxm icmp_param;

		icmp_param.data.icmph	   = *icmp_hdr(skb);
		icmp_param.data.icmph.type = ICMP_ECHOREPLY;
		icmp_param.skb		   = skb;
		icmp_param.offset	   = 0;
		icmp_param.data_len	   = skb->len;
		icmp_param.head_len	   = sizeof(struct icmphdr);
		icmp_reply(&icmp_param, skb);
	}
	/* should there be an ICMP stat for ignored echos? */
	return true;
}

/*
 *	Handle ICMP Timestamp requests.
 *	RFC 1122: 3.2.2.8 MAY implement ICMP timestamp requests.
 *		  SHOULD be in the kernel for minimum random latency.
 *		  MUST be accurate to a few minutes.
 *		  MUST be updated at least at 15Hz.
 */
static bool icmp_timestamp(struct sk_buff *skb)
{
	struct icmp_bxm icmp_param;
	/*
	 *	Too short.
	 */
	if (skb->len < 4)
		goto out_err;

	/*
	 *	Fill in the current time as ms since midnight UT:
	 */
	icmp_param.data.times[1] = inet_current_timestamp();
	icmp_param.data.times[2] = icmp_param.data.times[1];

	BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4));

	icmp_param.data.icmph	   = *icmp_hdr(skb);
	icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
	icmp_param.data.icmph.code = 0;
	icmp_param.skb		   = skb;
	icmp_param.offset	   = 0;
	icmp_param.data_len	   = 0;
	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
	icmp_reply(&icmp_param, skb);
	return true;

out_err:
	__ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
	return false;
}

static bool icmp_discard(struct sk_buff *skb)
{
	/* pretend it was a success */
	return true;
}

/*
 *	Deal with incoming ICMP packets.
 */
int icmp_rcv(struct sk_buff *skb)
{
	struct icmphdr *icmph;
	struct rtable *rt = skb_rtable(skb);
	struct net *net = dev_net(rt->dst.dev);
	bool success;

	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		struct sec_path *sp = skb_sec_path(skb);
		int nh;

		if (!(sp && sp->xvec[sp->len - 1]->props.flags &
				 XFRM_STATE_ICMP))
			goto drop;

		if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr)))
			goto drop;

		nh = skb_network_offset(skb);
		skb_set_network_header(skb, sizeof(*icmph));

		if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
			goto drop;

		skb_set_network_header(skb, nh);
	}

	__ICMP_INC_STATS(net, ICMP_MIB_INMSGS);

	if (skb_checksum_simple_validate(skb))
		goto csum_error;

	if (!pskb_pull(skb, sizeof(*icmph)))
		goto error;

	icmph = icmp_hdr(skb);

	ICMPMSGIN_INC_STATS(net, icmph->type);
	/*
	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
	 *
	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
	 *		  discarded.
	 */
	if (icmph->type > NR_ICMP_TYPES)
		goto error;


	/*
	 *	Parse the ICMP message
	 */

	if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
		/*
		 *	RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be
		 *	  silently ignored (we let user decide with a sysctl).
		 *	RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently
		 *	  discarded if to broadcast/multicast.
		 */
		if ((icmph->type == ICMP_ECHO ||
		     icmph->type == ICMP_TIMESTAMP) &&
		    net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
			goto error;
		}
		if (icmph->type != ICMP_ECHO &&
		    icmph->type != ICMP_TIMESTAMP &&
		    icmph->type != ICMP_ADDRESS &&
		    icmph->type != ICMP_ADDRESSREPLY) {
			goto error;
		}
	}

	success = icmp_pointers[icmph->type].handler(skb);

	if (success)  {
		consume_skb(skb);
		return NET_RX_SUCCESS;
	}

drop:
	kfree_skb(skb);
	return NET_RX_DROP;
csum_error:
	__ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS);
error:
	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
	goto drop;
}

void icmp_err(struct sk_buff *skb, u32 info)
{
	struct iphdr *iph = (struct iphdr *)skb->data;
	int offset = iph->ihl<<2;
	struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
	int type = icmp_hdr(skb)->type;
	int code = icmp_hdr(skb)->code;
	struct net *net = dev_net(skb->dev);

	/*
	 * Use ping_err to handle all icmp errors except those
	 * triggered by ICMP_ECHOREPLY which sent from kernel.
	 */
	if (icmph->type != ICMP_ECHOREPLY) {
		ping_err(skb, offset, info);
		return;
	}

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
	else if (type == ICMP_REDIRECT)
		ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
}

/*
 *	This table is the definition of how we handle ICMP.
 */
static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
	[ICMP_ECHOREPLY] = {
		.handler = ping_rcv,
	},
	[1] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[2] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_DEST_UNREACH] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_SOURCE_QUENCH] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_REDIRECT] = {
		.handler = icmp_redirect,
		.error = 1,
	},
	[6] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[7] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_ECHO] = {
		.handler = icmp_echo,
	},
	[9] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[10] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_TIME_EXCEEDED] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_PARAMETERPROB] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_TIMESTAMP] = {
		.handler = icmp_timestamp,
	},
	[ICMP_TIMESTAMPREPLY] = {
		.handler = icmp_discard,
	},
	[ICMP_INFO_REQUEST] = {
		.handler = icmp_discard,
	},
	[ICMP_INFO_REPLY] = {
		.handler = icmp_discard,
	},
	[ICMP_ADDRESS] = {
		.handler = icmp_discard,
	},
	[ICMP_ADDRESSREPLY] = {
		.handler = icmp_discard,
	},
};

static void __net_exit icmp_sk_exit(struct net *net)
{
	int i;

	for_each_possible_cpu(i)
		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
	free_percpu(net->ipv4.icmp_sk);
	net->ipv4.icmp_sk = NULL;
}

static int __net_init icmp_sk_init(struct net *net)
{
	int i, err;

	net->ipv4.icmp_sk = alloc_percpu(struct sock *);
	if (!net->ipv4.icmp_sk)
		return -ENOMEM;

	for_each_possible_cpu(i) {
		struct sock *sk;

		err = inet_ctl_sock_create(&sk, PF_INET,
					   SOCK_RAW, IPPROTO_ICMP, net);
		if (err < 0)
			goto fail;

		*per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;

		/* Enough space for 2 64K ICMP packets, including
		 * sk_buff/skb_shared_info struct overhead.
		 */
		sk->sk_sndbuf =	2 * SKB_TRUESIZE(64 * 1024);

		/*
		 * Speedup sock_wfree()
		 */
		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
	}

	/* Control parameters for ECHO replies. */
	net->ipv4.sysctl_icmp_echo_ignore_all = 0;
	net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1;

	/* Control parameter - ignore bogus broadcast responses? */
	net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1;

	/*
	 * 	Configurable global rate limit.
	 *
	 *	ratelimit defines tokens/packet consumed for dst->rate_token
	 *	bucket ratemask defines which icmp types are ratelimited by
	 *	setting	it's bit position.
	 *
	 *	default:
	 *	dest unreachable (3), source quench (4),
	 *	time exceeded (11), parameter problem (12)
	 */

	net->ipv4.sysctl_icmp_ratelimit = 1 * HZ;
	net->ipv4.sysctl_icmp_ratemask = 0x1818;
	net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;

	return 0;

fail:
	for_each_possible_cpu(i)
		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
	free_percpu(net->ipv4.icmp_sk);
	return err;
}

static struct pernet_operations __net_initdata icmp_sk_ops = {
       .init = icmp_sk_init,
       .exit = icmp_sk_exit,
};

int __init icmp_init(void)
{
	return register_pernet_subsys(&icmp_sk_ops);
}