Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	Internet Control Message Protocol (ICMPv6)
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on net/ipv4/icmp.c
 *
 *	RFC 1885
 */

/*
 *	Changes:
 *
 *	Andi Kleen		:	exception handling
 *	Andi Kleen			add rate limits. never reply to a icmp.
 *					add more length checks and other fixes.
 *	yoshfuji		:	ensure to sent parameter problem for
 *					fragments.
 *	YOSHIFUJI Hideaki @USAGI:	added sysctl for icmp rate limit.
 *	Randy Dunlap and
 *	YOSHIFUJI Hideaki @USAGI:	Per-interface statistics support
 *	Kazunori MIYAZAWA @USAGI:       change output process to use ip6_append_data
 */

#define pr_fmt(fmt) "IPv6: " fmt

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/netfilter.h>
#include <linux/slab.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>

#include <net/ip.h>
#include <net/sock.h>

#include <net/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/ping.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/inet_common.h>
#include <net/dsfield.h>
#include <net/l3mdev.h>

#include <linux/uaccess.h>

/*
 *	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 *icmpv6_sk(struct net *net)
{
	return this_cpu_read(*net->ipv6.icmp_sk);
}

static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		       u8 type, u8 code, int offset, __be32 info)
{
	/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
	struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
	struct net *net = dev_net(skb->dev);

	if (type == ICMPV6_PKT_TOOBIG)
		ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
	else if (type == NDISC_REDIRECT)
		ip6_redirect(skb, net, skb->dev->ifindex, 0,
			     sock_net_uid(net, NULL));

	if (!(type & ICMPV6_INFOMSG_MASK))
		if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
			ping_err(skb, offset, ntohl(info));

	return 0;
}

static int icmpv6_rcv(struct sk_buff *skb);

static const struct inet6_protocol icmpv6_protocol = {
	.handler	=	icmpv6_rcv,
	.err_handler	=	icmpv6_err,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

/* Called with BH disabled */
static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
{
	struct sock *sk;

	sk = icmpv6_sk(net);
	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
		/* This can happen if the output path (f.e. SIT or
		 * ip6ip6 tunnel) signals dst_link_failure() for an
		 * outgoing ICMP6 packet.
		 */
		return NULL;
	}
	return sk;
}

static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
{
	spin_unlock(&sk->sk_lock.slock);
}

/*
 * Figure out, may we reply to this packet with icmp error.
 *
 * We do not reply, if:
 *	- it was icmp error message.
 *	- it is truncated, so that it is known, that protocol is ICMPV6
 *	  (i.e. in the middle of some exthdr)
 *
 *	--ANK (980726)
 */

static bool is_ineligible(const struct sk_buff *skb)
{
	int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
	int len = skb->len - ptr;
	__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
	__be16 frag_off;

	if (len < 0)
		return true;

	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
	if (ptr < 0)
		return false;
	if (nexthdr == IPPROTO_ICMPV6) {
		u8 _type, *tp;
		tp = skb_header_pointer(skb,
			ptr+offsetof(struct icmp6hdr, icmp6_type),
			sizeof(_type), &_type);
		if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
			return true;
	}
	return false;
}

static bool icmpv6_mask_allow(struct net *net, int type)
{
	if (type > ICMPV6_MSG_MAX)
		return true;

	/* Limit if icmp type is set in ratemask. */
	if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask))
		return true;

	return false;
}

static bool icmpv6_global_allow(struct net *net, int type)
{
	if (icmpv6_mask_allow(net, type))
		return true;

	if (icmp_global_allow())
		return true;

	return false;
}

/*
 * Check the ICMP output rate limit
 */
static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
			       struct flowi6 *fl6)
{
	struct net *net = sock_net(sk);
	struct dst_entry *dst;
	bool res = false;

	if (icmpv6_mask_allow(net, type))
		return true;

	/*
	 * Look up the output route.
	 * XXX: perhaps the expire for routing entries cloned by
	 * this lookup should be more aggressive (not longer than timeout).
	 */
	dst = ip6_route_output(net, sk, fl6);
	if (dst->error) {
		IP6_INC_STATS(net, ip6_dst_idev(dst),
			      IPSTATS_MIB_OUTNOROUTES);
	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
		res = true;
	} else {
		struct rt6_info *rt = (struct rt6_info *)dst;
		int tmo = net->ipv6.sysctl.icmpv6_time;
		struct inet_peer *peer;

		/* Give more bandwidth to wider prefixes. */
		if (rt->rt6i_dst.plen < 128)
			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);

		peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1);
		res = inet_peer_xrlim_allow(peer, tmo);
		if (peer)
			inet_putpeer(peer);
	}
	dst_release(dst);
	return res;
}

/*
 *	an inline helper for the "simple" if statement below
 *	checks if parameter problem report is caused by an
 *	unrecognized IPv6 option that has the Option Type
 *	highest-order two bits set to 10
 */

static bool opt_unrec(struct sk_buff *skb, __u32 offset)
{
	u8 _optval, *op;

	offset += skb_network_offset(skb);
	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
	if (!op)
		return true;
	return (*op & 0xC0) == 0x80;
}

void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
				struct icmp6hdr *thdr, int len)
{
	struct sk_buff *skb;
	struct icmp6hdr *icmp6h;

	skb = skb_peek(&sk->sk_write_queue);
	if (!skb)
		return;

	icmp6h = icmp6_hdr(skb);
	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
	icmp6h->icmp6_cksum = 0;

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		skb->csum = csum_partial(icmp6h,
					sizeof(struct icmp6hdr), skb->csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
						      &fl6->daddr,
						      len, fl6->flowi6_proto,
						      skb->csum);
	} else {
		__wsum tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);
		}

		tmp_csum = csum_partial(icmp6h,
					sizeof(struct icmp6hdr), tmp_csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
						      &fl6->daddr,
						      len, fl6->flowi6_proto,
						      tmp_csum);
	}
	ip6_push_pending_frames(sk);
}

struct icmpv6_msg {
	struct sk_buff	*skb;
	int		offset;
	uint8_t		type;
};

static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
	struct sk_buff *org_skb = msg->skb;
	__wsum csum = 0;

	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
				      to, len, csum);
	skb->csum = csum_block_add(skb->csum, csum, odd);
	if (!(msg->type & ICMPV6_INFOMSG_MASK))
		nf_ct_attach(skb, org_skb);
	return 0;
}

#if IS_ENABLED(CONFIG_IPV6_MIP6)
static void mip6_addr_swap(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct ipv6_destopt_hao *hao;
	struct in6_addr tmp;
	int off;

	if (opt->dsthao) {
		off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
		if (likely(off >= 0)) {
			hao = (struct ipv6_destopt_hao *)
					(skb_network_header(skb) + off);
			tmp = iph->saddr;
			iph->saddr = hao->addr;
			hao->addr = tmp;
		}
	}
}
#else
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif

static struct dst_entry *icmpv6_route_lookup(struct net *net,
					     struct sk_buff *skb,
					     struct sock *sk,
					     struct flowi6 *fl6)
{
	struct dst_entry *dst, *dst2;
	struct flowi6 fl2;
	int err;

	err = ip6_dst_lookup(net, sk, &dst, fl6);
	if (err)
		return ERR_PTR(err);

	/*
	 * We won't send icmp if the destination is known
	 * anycast.
	 */
	if (ipv6_anycast_destination(dst, &fl6->daddr)) {
		net_dbg_ratelimited("icmp6_send: acast source\n");
		dst_release(dst);
		return ERR_PTR(-EINVAL);
	}

	/* No need to clone since we're just using its address. */
	dst2 = dst;

	dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0);
	if (!IS_ERR(dst)) {
		if (dst != dst2)
			return dst;
	} else {
		if (PTR_ERR(dst) == -EPERM)
			dst = NULL;
		else
			return dst;
	}

	err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
	if (err)
		goto relookup_failed;

	err = ip6_dst_lookup(net, sk, &dst2, &fl2);
	if (err)
		goto relookup_failed;

	dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP);
	if (!IS_ERR(dst2)) {
		dst_release(dst);
		dst = dst2;
	} else {
		err = PTR_ERR(dst2);
		if (err == -EPERM) {
			dst_release(dst);
			return dst2;
		} else
			goto relookup_failed;
	}

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

static struct net_device *icmp6_dev(const struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;

	/* for local traffic to local address, skb dev is the loopback
	 * device. Check if there is a dst attached to the skb and if so
	 * get the real device index. Same is needed for replies to a link
	 * local address on a device enslaved to an L3 master device
	 */
	if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
		const struct rt6_info *rt6 = skb_rt6_info(skb);

		if (rt6)
			dev = rt6->rt6i_idev->dev;
	}

	return dev;
}

static int icmp6_iif(const struct sk_buff *skb)
{
	return icmp6_dev(skb)->ifindex;
}

/*
 *	Send an ICMP message in response to a packet in error
 */
static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
		       const struct in6_addr *force_saddr)
{
	struct inet6_dev *idev = NULL;
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct sock *sk;
	struct net *net;
	struct ipv6_pinfo *np;
	const struct in6_addr *saddr = NULL;
	struct dst_entry *dst;
	struct icmp6hdr tmp_hdr;
	struct flowi6 fl6;
	struct icmpv6_msg msg;
	struct ipcm6_cookie ipc6;
	int iif = 0;
	int addr_type = 0;
	int len;
	u32 mark;

	if ((u8 *)hdr < skb->head ||
	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
		return;

	if (!skb->dev)
		return;
	net = dev_net(skb->dev);
	mark = IP6_REPLY_MARK(net, skb->mark);
	/*
	 *	Make sure we respect the rules
	 *	i.e. RFC 1885 2.4(e)
	 *	Rule (e.1) is enforced by not using icmp6_send
	 *	in any code that processes icmp errors.
	 */
	addr_type = ipv6_addr_type(&hdr->daddr);

	if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
	    ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
		saddr = &hdr->daddr;

	/*
	 *	Dest addr check
	 */

	if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
		if (type != ICMPV6_PKT_TOOBIG &&
		    !(type == ICMPV6_PARAMPROB &&
		      code == ICMPV6_UNK_OPTION &&
		      (opt_unrec(skb, info))))
			return;

		saddr = NULL;
	}

	addr_type = ipv6_addr_type(&hdr->saddr);

	/*
	 *	Source addr check
	 */

	if (__ipv6_addr_needs_scope_id(addr_type)) {
		iif = icmp6_iif(skb);
	} else {
		dst = skb_dst(skb);
		iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev);
	}

	/*
	 *	Must not send error if the source does not uniquely
	 *	identify a single node (RFC2463 Section 2.4).
	 *	We check unspecified / multicast addresses here,
	 *	and anycast addresses will be checked later.
	 */
	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
		net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
				    &hdr->saddr, &hdr->daddr);
		return;
	}

	/*
	 *	Never answer to a ICMP packet.
	 */
	if (is_ineligible(skb)) {
		net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
				    &hdr->saddr, &hdr->daddr);
		return;
	}

	/* Needed by both icmp_global_allow and icmpv6_xmit_lock */
	local_bh_disable();

	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
	if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
		goto out_bh_enable;

	mip6_addr_swap(skb);

	memset(&fl6, 0, sizeof(fl6));
	fl6.flowi6_proto = IPPROTO_ICMPV6;
	fl6.daddr = hdr->saddr;
	if (force_saddr)
		saddr = force_saddr;
	if (saddr)
		fl6.saddr = *saddr;
	fl6.flowi6_mark = mark;
	fl6.flowi6_oif = iif;
	fl6.fl6_icmp_type = type;
	fl6.fl6_icmp_code = code;
	fl6.flowi6_uid = sock_net_uid(net, NULL);
	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));

	sk = icmpv6_xmit_lock(net);
	if (!sk)
		goto out_bh_enable;

	sk->sk_mark = mark;
	np = inet6_sk(sk);

	if (!icmpv6_xrlim_allow(sk, type, &fl6))
		goto out;

	tmp_hdr.icmp6_type = type;
	tmp_hdr.icmp6_code = code;
	tmp_hdr.icmp6_cksum = 0;
	tmp_hdr.icmp6_pointer = htonl(info);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;

	ipcm6_init_sk(&ipc6, np);
	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);

	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
	if (IS_ERR(dst))
		goto out;

	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);

	msg.skb = skb;
	msg.offset = skb_network_offset(skb);
	msg.type = type;

	len = skb->len - msg.offset;
	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
	if (len < 0) {
		net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n",
				    &hdr->saddr, &hdr->daddr);
		goto out_dst_release;
	}

	rcu_read_lock();
	idev = __in6_dev_get(skb->dev);

	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
			    len + sizeof(struct icmp6hdr),
			    sizeof(struct icmp6hdr),
			    &ipc6, &fl6, (struct rt6_info *)dst,
			    MSG_DONTWAIT)) {
		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
		ip6_flush_pending_frames(sk);
	} else {
		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
					   len + sizeof(struct icmp6hdr));
	}
	rcu_read_unlock();
out_dst_release:
	dst_release(dst);
out:
	icmpv6_xmit_unlock(sk);
out_bh_enable:
	local_bh_enable();
}

/* Slightly more convenient version of icmp6_send.
 */
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
	kfree_skb(skb);
}

/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
 * if sufficient data bytes are available
 * @nhs is the size of the tunnel header(s) :
 *  Either an IPv4 header for SIT encap
 *         an IPv4 header + GRE header for GRE encap
 */
int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
			       unsigned int data_len)
{
	struct in6_addr temp_saddr;
	struct rt6_info *rt;
	struct sk_buff *skb2;
	u32 info = 0;

	if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
		return 1;

	/* RFC 4884 (partial) support for ICMP extensions */
	if (data_len < 128 || (data_len & 7) || skb->len < data_len)
		data_len = 0;

	skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);

	if (!skb2)
		return 1;

	skb_dst_drop(skb2);
	skb_pull(skb2, nhs);
	skb_reset_network_header(skb2);

	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
			skb, 0);

	if (rt && rt->dst.dev)
		skb2->dev = rt->dst.dev;

	ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);

	if (data_len) {
		/* RFC 4884 (partial) support :
		 * insert 0 padding at the end, before the extensions
		 */
		__skb_push(skb2, nhs);
		skb_reset_network_header(skb2);
		memmove(skb2->data, skb2->data + nhs, data_len - nhs);
		memset(skb2->data + data_len - nhs, 0, nhs);
		/* RFC 4884 4.5 : Length is measured in 64-bit words,
		 * and stored in reserved[0]
		 */
		info = (data_len/8) << 24;
	}
	if (type == ICMP_TIME_EXCEEDED)
		icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
			   info, &temp_saddr);
	else
		icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
			   info, &temp_saddr);
	if (rt)
		ip6_rt_put(rt);

	kfree_skb(skb2);

	return 0;
}
EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);

static void icmpv6_echo_reply(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct sock *sk;
	struct inet6_dev *idev;
	struct ipv6_pinfo *np;
	const struct in6_addr *saddr = NULL;
	struct icmp6hdr *icmph = icmp6_hdr(skb);
	struct icmp6hdr tmp_hdr;
	struct flowi6 fl6;
	struct icmpv6_msg msg;
	struct dst_entry *dst;
	struct ipcm6_cookie ipc6;
	u32 mark = IP6_REPLY_MARK(net, skb->mark);
	bool acast;

	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) &&
	    net->ipv6.sysctl.icmpv6_echo_ignore_multicast)
		return;

	saddr = &ipv6_hdr(skb)->daddr;

	acast = ipv6_anycast_destination(skb_dst(skb), saddr);
	if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast)
		return;

	if (!ipv6_unicast_destination(skb) &&
	    !(net->ipv6.sysctl.anycast_src_echo_reply && acast))
		saddr = NULL;

	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;

	memset(&fl6, 0, sizeof(fl6));
	if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
		fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb));

	fl6.flowi6_proto = IPPROTO_ICMPV6;
	fl6.daddr = ipv6_hdr(skb)->saddr;
	if (saddr)
		fl6.saddr = *saddr;
	fl6.flowi6_oif = icmp6_iif(skb);
	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
	fl6.flowi6_mark = mark;
	fl6.flowi6_uid = sock_net_uid(net, NULL);
	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));

	local_bh_disable();
	sk = icmpv6_xmit_lock(net);
	if (!sk)
		goto out_bh_enable;
	sk->sk_mark = mark;
	np = inet6_sk(sk);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;

	if (ip6_dst_lookup(net, sk, &dst, &fl6))
		goto out;
	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
	if (IS_ERR(dst))
		goto out;

	/* Check the ratelimit */
	if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
	    !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
		goto out_dst_release;

	idev = __in6_dev_get(skb->dev);

	msg.skb = skb;
	msg.offset = 0;
	msg.type = ICMPV6_ECHO_REPLY;

	ipcm6_init_sk(&ipc6, np);
	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
	ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));

	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
			    skb->len + sizeof(struct icmp6hdr),
			    sizeof(struct icmp6hdr), &ipc6, &fl6,
			    (struct rt6_info *)dst, MSG_DONTWAIT)) {
		__ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
		ip6_flush_pending_frames(sk);
	} else {
		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
					   skb->len + sizeof(struct icmp6hdr));
	}
out_dst_release:
	dst_release(dst);
out:
	icmpv6_xmit_unlock(sk);
out_bh_enable:
	local_bh_enable();
}

void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
{
	const struct inet6_protocol *ipprot;
	int inner_offset;
	__be16 frag_off;
	u8 nexthdr;
	struct net *net = dev_net(skb->dev);

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		goto out;

	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
	if (ipv6_ext_hdr(nexthdr)) {
		/* now skip over extension headers */
		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
						&nexthdr, &frag_off);
		if (inner_offset < 0)
			goto out;
	} else {
		inner_offset = sizeof(struct ipv6hdr);
	}

	/* Checkin header including 8 bytes of inner protocol header. */
	if (!pskb_may_pull(skb, inner_offset+8))
		goto out;

	/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
	   Without this we will not able f.e. to make source routed
	   pmtu discovery.
	   Corresponding argument (opt) to notifiers is already added.
	   --ANK (980726)
	 */

	ipprot = rcu_dereference(inet6_protos[nexthdr]);
	if (ipprot && ipprot->err_handler)
		ipprot->err_handler(skb, NULL, type, code, inner_offset, info);

	raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info);
	return;

out:
	__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
}

/*
 *	Handle icmp messages
 */

static int icmpv6_rcv(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct net_device *dev = icmp6_dev(skb);
	struct inet6_dev *idev = __in6_dev_get(dev);
	const struct in6_addr *saddr, *daddr;
	struct icmp6hdr *hdr;
	u8 type;
	bool success = false;

	if (!xfrm6_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_no_count;

		if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
			goto drop_no_count;

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

		if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
			goto drop_no_count;

		skb_set_network_header(skb, nh);
	}

	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INMSGS);

	saddr = &ipv6_hdr(skb)->saddr;
	daddr = &ipv6_hdr(skb)->daddr;

	if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
		net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
				    saddr, daddr);
		goto csum_error;
	}

	if (!pskb_pull(skb, sizeof(*hdr)))
		goto discard_it;

	hdr = icmp6_hdr(skb);

	type = hdr->icmp6_type;

	ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type);

	switch (type) {
	case ICMPV6_ECHO_REQUEST:
		if (!net->ipv6.sysctl.icmpv6_echo_ignore_all)
			icmpv6_echo_reply(skb);
		break;

	case ICMPV6_ECHO_REPLY:
		success = ping_rcv(skb);
		break;

	case ICMPV6_PKT_TOOBIG:
		/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
		   standard destination cache. Seems, only "advanced"
		   destination cache will allow to solve this problem
		   --ANK (980726)
		 */
		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
			goto discard_it;
		hdr = icmp6_hdr(skb);

		/* to notify */
		/* fall through */
	case ICMPV6_DEST_UNREACH:
	case ICMPV6_TIME_EXCEED:
	case ICMPV6_PARAMPROB:
		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
		break;

	case NDISC_ROUTER_SOLICITATION:
	case NDISC_ROUTER_ADVERTISEMENT:
	case NDISC_NEIGHBOUR_SOLICITATION:
	case NDISC_NEIGHBOUR_ADVERTISEMENT:
	case NDISC_REDIRECT:
		ndisc_rcv(skb);
		break;

	case ICMPV6_MGM_QUERY:
		igmp6_event_query(skb);
		break;

	case ICMPV6_MGM_REPORT:
		igmp6_event_report(skb);
		break;

	case ICMPV6_MGM_REDUCTION:
	case ICMPV6_NI_QUERY:
	case ICMPV6_NI_REPLY:
	case ICMPV6_MLD2_REPORT:
	case ICMPV6_DHAAD_REQUEST:
	case ICMPV6_DHAAD_REPLY:
	case ICMPV6_MOBILE_PREFIX_SOL:
	case ICMPV6_MOBILE_PREFIX_ADV:
		break;

	default:
		/* informational */
		if (type & ICMPV6_INFOMSG_MASK)
			break;

		net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n",
				    saddr, daddr);

		/*
		 * error of unknown type.
		 * must pass to upper level
		 */

		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
	}

	/* until the v6 path can be better sorted assume failure and
	 * preserve the status quo behaviour for the rest of the paths to here
	 */
	if (success)
		consume_skb(skb);
	else
		kfree_skb(skb);

	return 0;

csum_error:
	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
discard_it:
	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
	kfree_skb(skb);
	return 0;
}

void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
		      u8 type,
		      const struct in6_addr *saddr,
		      const struct in6_addr *daddr,
		      int oif)
{
	memset(fl6, 0, sizeof(*fl6));
	fl6->saddr = *saddr;
	fl6->daddr = *daddr;
	fl6->flowi6_proto	= IPPROTO_ICMPV6;
	fl6->fl6_icmp_type	= type;
	fl6->fl6_icmp_code	= 0;
	fl6->flowi6_oif		= oif;
	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}

static void __net_exit icmpv6_sk_exit(struct net *net)
{
	int i;

	for_each_possible_cpu(i)
		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv6.icmp_sk, i));
	free_percpu(net->ipv6.icmp_sk);
}

static int __net_init icmpv6_sk_init(struct net *net)
{
	struct sock *sk;
	int err, i;

	net->ipv6.icmp_sk = alloc_percpu(struct sock *);
	if (!net->ipv6.icmp_sk)
		return -ENOMEM;

	for_each_possible_cpu(i) {
		err = inet_ctl_sock_create(&sk, PF_INET6,
					   SOCK_RAW, IPPROTO_ICMPV6, net);
		if (err < 0) {
			pr_err("Failed to initialize the ICMP6 control socket (err %d)\n",
			       err);
			goto fail;
		}

		*per_cpu_ptr(net->ipv6.icmp_sk, i) = sk;

		/* Enough space for 2 64K ICMP packets, including
		 * sk_buff struct overhead.
		 */
		sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
	}
	return 0;

 fail:
	icmpv6_sk_exit(net);
	return err;
}

static struct pernet_operations icmpv6_sk_ops = {
	.init = icmpv6_sk_init,
	.exit = icmpv6_sk_exit,
};

int __init icmpv6_init(void)
{
	int err;

	err = register_pernet_subsys(&icmpv6_sk_ops);
	if (err < 0)
		return err;

	err = -EAGAIN;
	if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
		goto fail;

	err = inet6_register_icmp_sender(icmp6_send);
	if (err)
		goto sender_reg_err;
	return 0;

sender_reg_err:
	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
fail:
	pr_err("Failed to register ICMP6 protocol\n");
	unregister_pernet_subsys(&icmpv6_sk_ops);
	return err;
}

void icmpv6_cleanup(void)
{
	inet6_unregister_icmp_sender(icmp6_send);
	unregister_pernet_subsys(&icmpv6_sk_ops);
	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}


static const struct icmp6_err {
	int err;
	int fatal;
} tab_unreach[] = {
	{	/* NOROUTE */
		.err	= ENETUNREACH,
		.fatal	= 0,
	},
	{	/* ADM_PROHIBITED */
		.err	= EACCES,
		.fatal	= 1,
	},
	{	/* Was NOT_NEIGHBOUR, now reserved */
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* ADDR_UNREACH	*/
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* PORT_UNREACH	*/
		.err	= ECONNREFUSED,
		.fatal	= 1,
	},
	{	/* POLICY_FAIL */
		.err	= EACCES,
		.fatal	= 1,
	},
	{	/* REJECT_ROUTE	*/
		.err	= EACCES,
		.fatal	= 1,
	},
};

int icmpv6_err_convert(u8 type, u8 code, int *err)
{
	int fatal = 0;

	*err = EPROTO;

	switch (type) {
	case ICMPV6_DEST_UNREACH:
		fatal = 1;
		if (code < ARRAY_SIZE(tab_unreach)) {
			*err  = tab_unreach[code].err;
			fatal = tab_unreach[code].fatal;
		}
		break;

	case ICMPV6_PKT_TOOBIG:
		*err = EMSGSIZE;
		break;

	case ICMPV6_PARAMPROB:
		*err = EPROTO;
		fatal = 1;
		break;

	case ICMPV6_TIME_EXCEED:
		*err = EHOSTUNREACH;
		break;
	}

	return fatal;
}
EXPORT_SYMBOL(icmpv6_err_convert);

#ifdef CONFIG_SYSCTL
static struct ctl_table ipv6_icmp_table_template[] = {
	{
		.procname	= "ratelimit",
		.data		= &init_net.ipv6.sysctl.icmpv6_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_ms_jiffies,
	},
	{
		.procname	= "echo_ignore_all",
		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_all,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler = proc_dointvec,
	},
	{
		.procname	= "echo_ignore_multicast",
		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler = proc_dointvec,
	},
	{
		.procname	= "echo_ignore_anycast",
		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler = proc_dointvec,
	},
	{
		.procname	= "ratemask",
		.data		= &init_net.ipv6.sysctl.icmpv6_ratemask_ptr,
		.maxlen		= ICMPV6_MSG_MAX + 1,
		.mode		= 0644,
		.proc_handler = proc_do_large_bitmap,
	},
	{ },
};

struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
{
	struct ctl_table *table;

	table = kmemdup(ipv6_icmp_table_template,
			sizeof(ipv6_icmp_table_template),
			GFP_KERNEL);

	if (table) {
		table[0].data = &net->ipv6.sysctl.icmpv6_time;
		table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
		table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
		table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
		table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr;
	}
	return table;
}
#endif