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
/*
 *	Handle firewalling
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek		<buytenh@gnu.org>
 *	Bart De Schuymer		<bdschuym@pandora.be>
 *
 *	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.
 *
 *	Lennert dedicates this file to Kerstin Wurdinger.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_arp.h>
#include <linux/in_route.h>
#include <linux/rculist.h>
#include <linux/inetdevice.h>

#include <net/ip.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/route.h>
#include <net/netfilter/br_netfilter.h>
#include <net/netns/generic.h>

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

static unsigned int brnf_net_id __read_mostly;

struct brnf_net {
	bool enabled;
};

#ifdef CONFIG_SYSCTL
static struct ctl_table_header *brnf_sysctl_header;
static int brnf_call_iptables __read_mostly = 1;
static int brnf_call_ip6tables __read_mostly = 1;
static int brnf_call_arptables __read_mostly = 1;
static int brnf_filter_vlan_tagged __read_mostly;
static int brnf_filter_pppoe_tagged __read_mostly;
static int brnf_pass_vlan_indev __read_mostly;
#else
#define brnf_call_iptables 1
#define brnf_call_ip6tables 1
#define brnf_call_arptables 1
#define brnf_filter_vlan_tagged 0
#define brnf_filter_pppoe_tagged 0
#define brnf_pass_vlan_indev 0
#endif

#define IS_IP(skb) \
	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP))

#define IS_IPV6(skb) \
	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))

#define IS_ARP(skb) \
	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))

static inline __be16 vlan_proto(const struct sk_buff *skb)
{
	if (skb_vlan_tag_present(skb))
		return skb->protocol;
	else if (skb->protocol == htons(ETH_P_8021Q))
		return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
	else
		return 0;
}

#define IS_VLAN_IP(skb) \
	(vlan_proto(skb) == htons(ETH_P_IP) && \
	 brnf_filter_vlan_tagged)

#define IS_VLAN_IPV6(skb) \
	(vlan_proto(skb) == htons(ETH_P_IPV6) && \
	 brnf_filter_vlan_tagged)

#define IS_VLAN_ARP(skb) \
	(vlan_proto(skb) == htons(ETH_P_ARP) &&	\
	 brnf_filter_vlan_tagged)

static inline __be16 pppoe_proto(const struct sk_buff *skb)
{
	return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
			    sizeof(struct pppoe_hdr)));
}

#define IS_PPPOE_IP(skb) \
	(skb->protocol == htons(ETH_P_PPP_SES) && \
	 pppoe_proto(skb) == htons(PPP_IP) && \
	 brnf_filter_pppoe_tagged)

#define IS_PPPOE_IPV6(skb) \
	(skb->protocol == htons(ETH_P_PPP_SES) && \
	 pppoe_proto(skb) == htons(PPP_IPV6) && \
	 brnf_filter_pppoe_tagged)

/* largest possible L2 header, see br_nf_dev_queue_xmit() */
#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)

struct brnf_frag_data {
	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
	u8 encap_size;
	u8 size;
	u16 vlan_tci;
	__be16 vlan_proto;
};

static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);

static void nf_bridge_info_free(struct sk_buff *skb)
{
	if (skb->nf_bridge) {
		nf_bridge_put(skb->nf_bridge);
		skb->nf_bridge = NULL;
	}
}

static inline struct net_device *bridge_parent(const struct net_device *dev)
{
	struct net_bridge_port *port;

	port = br_port_get_rcu(dev);
	return port ? port->br->dev : NULL;
}

static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = skb->nf_bridge;

	if (atomic_read(&nf_bridge->use) > 1) {
		struct nf_bridge_info *tmp = nf_bridge_alloc(skb);

		if (tmp) {
			memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
			atomic_set(&tmp->use, 1);
		}
		nf_bridge_put(nf_bridge);
		nf_bridge = tmp;
	}
	return nf_bridge;
}

unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
{
	switch (skb->protocol) {
	case __cpu_to_be16(ETH_P_8021Q):
		return VLAN_HLEN;
	case __cpu_to_be16(ETH_P_PPP_SES):
		return PPPOE_SES_HLEN;
	default:
		return 0;
	}
}

static inline void nf_bridge_pull_encap_header(struct sk_buff *skb)
{
	unsigned int len = nf_bridge_encap_header_len(skb);

	skb_pull(skb, len);
	skb->network_header += len;
}

static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
{
	unsigned int len = nf_bridge_encap_header_len(skb);

	skb_pull_rcsum(skb, len);
	skb->network_header += len;
}

/* When handing a packet over to the IP layer
 * check whether we have a skb that is in the
 * expected format
 */

static int br_validate_ipv4(struct net *net, struct sk_buff *skb)
{
	const struct iphdr *iph;
	u32 len;

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

	iph = ip_hdr(skb);

	/* Basic sanity checks */
	if (iph->ihl < 5 || iph->version != 4)
		goto inhdr_error;

	if (!pskb_may_pull(skb, iph->ihl*4))
		goto inhdr_error;

	iph = ip_hdr(skb);
	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto inhdr_error;

	len = ntohs(iph->tot_len);
	if (skb->len < len) {
		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
		goto drop;
	} else if (len < (iph->ihl*4))
		goto inhdr_error;

	if (pskb_trim_rcsum(skb, len)) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
	/* We should really parse IP options here but until
	 * somebody who actually uses IP options complains to
	 * us we'll just silently ignore the options because
	 * we're lazy!
	 */
	return 0;

inhdr_error:
	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
	return -1;
}

void nf_bridge_update_protocol(struct sk_buff *skb)
{
	switch (skb->nf_bridge->orig_proto) {
	case BRNF_PROTO_8021Q:
		skb->protocol = htons(ETH_P_8021Q);
		break;
	case BRNF_PROTO_PPPOE:
		skb->protocol = htons(ETH_P_PPP_SES);
		break;
	case BRNF_PROTO_UNCHANGED:
		break;
	}
}

/* Obtain the correct destination MAC address, while preserving the original
 * source MAC address. If we already know this address, we just copy it. If we
 * don't, we use the neighbour framework to find out. In both cases, we make
 * sure that br_handle_frame_finish() is called afterwards.
 */
int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct neighbour *neigh;
	struct dst_entry *dst;

	skb->dev = bridge_parent(skb->dev);
	if (!skb->dev)
		goto free_skb;
	dst = skb_dst(skb);
	neigh = dst_neigh_lookup_skb(dst, skb);
	if (neigh) {
		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
		int ret;

		if (neigh->hh.hh_len) {
			neigh_hh_bridge(&neigh->hh, skb);
			skb->dev = nf_bridge->physindev;
			ret = br_handle_frame_finish(net, sk, skb);
		} else {
			/* the neighbour function below overwrites the complete
			 * MAC header, so we save the Ethernet source address and
			 * protocol number.
			 */
			skb_copy_from_linear_data_offset(skb,
							 -(ETH_HLEN-ETH_ALEN),
							 nf_bridge->neigh_header,
							 ETH_HLEN-ETH_ALEN);
			/* tell br_dev_xmit to continue with forwarding */
			nf_bridge->bridged_dnat = 1;
			/* FIXME Need to refragment */
			ret = neigh->output(neigh, skb);
		}
		neigh_release(neigh);
		return ret;
	}
free_skb:
	kfree_skb(skb);
	return 0;
}

static inline bool
br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
			     const struct nf_bridge_info *nf_bridge)
{
	return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr;
}

/* This requires some explaining. If DNAT has taken place,
 * we will need to fix up the destination Ethernet address.
 * This is also true when SNAT takes place (for the reply direction).
 *
 * There are two cases to consider:
 * 1. The packet was DNAT'ed to a device in the same bridge
 *    port group as it was received on. We can still bridge
 *    the packet.
 * 2. The packet was DNAT'ed to a different device, either
 *    a non-bridged device or another bridge port group.
 *    The packet will need to be routed.
 *
 * The correct way of distinguishing between these two cases is to
 * call ip_route_input() and to look at skb->dst->dev, which is
 * changed to the destination device if ip_route_input() succeeds.
 *
 * Let's first consider the case that ip_route_input() succeeds:
 *
 * If the output device equals the logical bridge device the packet
 * came in on, we can consider this bridging. The corresponding MAC
 * address will be obtained in br_nf_pre_routing_finish_bridge.
 * Otherwise, the packet is considered to be routed and we just
 * change the destination MAC address so that the packet will
 * later be passed up to the IP stack to be routed. For a redirected
 * packet, ip_route_input() will give back the localhost as output device,
 * which differs from the bridge device.
 *
 * Let's now consider the case that ip_route_input() fails:
 *
 * This can be because the destination address is martian, in which case
 * the packet will be dropped.
 * If IP forwarding is disabled, ip_route_input() will fail, while
 * ip_route_output_key() can return success. The source
 * address for ip_route_output_key() is set to zero, so ip_route_output_key()
 * thinks we're handling a locally generated packet and won't care
 * if IP forwarding is enabled. If the output device equals the logical bridge
 * device, we proceed as if ip_route_input() succeeded. If it differs from the
 * logical bridge port or if ip_route_output_key() fails we drop the packet.
 */
static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct iphdr *iph = ip_hdr(skb);
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
	struct rtable *rt;
	int err;

	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;

	if (nf_bridge->pkt_otherhost) {
		skb->pkt_type = PACKET_OTHERHOST;
		nf_bridge->pkt_otherhost = false;
	}
	nf_bridge->in_prerouting = 0;
	if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
			struct in_device *in_dev = __in_dev_get_rcu(dev);

			/* If err equals -EHOSTUNREACH the error is due to a
			 * martian destination or due to the fact that
			 * forwarding is disabled. For most martian packets,
			 * ip_route_output_key() will fail. It won't fail for 2 types of
			 * martian destinations: loopback destinations and destination
			 * 0.0.0.0. In both cases the packet will be dropped because the
			 * destination is the loopback device and not the bridge. */
			if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
				goto free_skb;

			rt = ip_route_output(net, iph->daddr, 0,
					     RT_TOS(iph->tos), 0);
			if (!IS_ERR(rt)) {
				/* - Bridged-and-DNAT'ed traffic doesn't
				 *   require ip_forwarding. */
				if (rt->dst.dev == dev) {
					skb_dst_set(skb, &rt->dst);
					goto bridged_dnat;
				}
				ip_rt_put(rt);
			}
free_skb:
			kfree_skb(skb);
			return 0;
		} else {
			if (skb_dst(skb)->dev == dev) {
bridged_dnat:
				skb->dev = nf_bridge->physindev;
				nf_bridge_update_protocol(skb);
				nf_bridge_push_encap_header(skb);
				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
						  net, sk, skb, skb->dev,
						  NULL,
						  br_nf_pre_routing_finish_bridge);
				return 0;
			}
			ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
			skb->pkt_type = PACKET_HOST;
		}
	} else {
		rt = bridge_parent_rtable(nf_bridge->physindev);
		if (!rt) {
			kfree_skb(skb);
			return 0;
		}
		skb_dst_set_noref(skb, &rt->dst);
	}

	skb->dev = nf_bridge->physindev;
	nf_bridge_update_protocol(skb);
	nf_bridge_push_encap_header(skb);
	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
			  br_handle_frame_finish);
	return 0;
}

static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev)
{
	struct net_device *vlan, *br;

	br = bridge_parent(dev);
	if (brnf_pass_vlan_indev == 0 || !skb_vlan_tag_present(skb))
		return br;

	vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
				    skb_vlan_tag_get(skb) & VLAN_VID_MASK);

	return vlan ? vlan : br;
}

/* Some common code for IPv4/IPv6 */
struct net_device *setup_pre_routing(struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);

	if (skb->pkt_type == PACKET_OTHERHOST) {
		skb->pkt_type = PACKET_HOST;
		nf_bridge->pkt_otherhost = true;
	}

	nf_bridge->in_prerouting = 1;
	nf_bridge->physindev = skb->dev;
	skb->dev = brnf_get_logical_dev(skb, skb->dev);

	if (skb->protocol == htons(ETH_P_8021Q))
		nf_bridge->orig_proto = BRNF_PROTO_8021Q;
	else if (skb->protocol == htons(ETH_P_PPP_SES))
		nf_bridge->orig_proto = BRNF_PROTO_PPPOE;

	/* Must drop socket now because of tproxy. */
	skb_orphan(skb);
	return skb->dev;
}

/* Direct IPv6 traffic to br_nf_pre_routing_ipv6.
 * Replicate the checks that IPv4 does on packet reception.
 * Set skb->dev to the bridge device (i.e. parent of the
 * receiving device) to make netfilter happy, the REDIRECT
 * target in particular.  Save the original destination IP
 * address to be able to detect DNAT afterwards. */
static unsigned int br_nf_pre_routing(void *priv,
				      struct sk_buff *skb,
				      const struct nf_hook_state *state)
{
	struct nf_bridge_info *nf_bridge;
	struct net_bridge_port *p;
	struct net_bridge *br;
	__u32 len = nf_bridge_encap_header_len(skb);

	if (unlikely(!pskb_may_pull(skb, len)))
		return NF_DROP;

	p = br_port_get_rcu(state->in);
	if (p == NULL)
		return NF_DROP;
	br = p->br;

	if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) {
		if (!brnf_call_ip6tables && !br->nf_call_ip6tables)
			return NF_ACCEPT;

		nf_bridge_pull_encap_header_rcsum(skb);
		return br_nf_pre_routing_ipv6(priv, skb, state);
	}

	if (!brnf_call_iptables && !br->nf_call_iptables)
		return NF_ACCEPT;

	if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb))
		return NF_ACCEPT;

	nf_bridge_pull_encap_header_rcsum(skb);

	if (br_validate_ipv4(state->net, skb))
		return NF_DROP;

	nf_bridge_put(skb->nf_bridge);
	if (!nf_bridge_alloc(skb))
		return NF_DROP;
	if (!setup_pre_routing(skb))
		return NF_DROP;

	nf_bridge = nf_bridge_info_get(skb);
	nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;

	skb->protocol = htons(ETH_P_IP);

	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb,
		skb->dev, NULL,
		br_nf_pre_routing_finish);

	return NF_STOLEN;
}


/* PF_BRIDGE/LOCAL_IN ************************************************/
/* The packet is locally destined, which requires a real
 * dst_entry, so detach the fake one.  On the way up, the
 * packet would pass through PRE_ROUTING again (which already
 * took place when the packet entered the bridge), but we
 * register an IPv4 PRE_ROUTING 'sabotage' hook that will
 * prevent this from happening. */
static unsigned int br_nf_local_in(void *priv,
				   struct sk_buff *skb,
				   const struct nf_hook_state *state)
{
	br_drop_fake_rtable(skb);
	return NF_ACCEPT;
}

/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
	struct net_device *in;

	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {

		if (skb->protocol == htons(ETH_P_IP))
			nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;

		if (skb->protocol == htons(ETH_P_IPV6))
			nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;

		in = nf_bridge->physindev;
		if (nf_bridge->pkt_otherhost) {
			skb->pkt_type = PACKET_OTHERHOST;
			nf_bridge->pkt_otherhost = false;
		}
		nf_bridge_update_protocol(skb);
	} else {
		in = *((struct net_device **)(skb->cb));
	}
	nf_bridge_push_encap_header(skb);

	br_nf_hook_thresh(NF_BR_FORWARD, net, sk, skb, in, skb->dev,
			  br_forward_finish);
	return 0;
}


/* This is the 'purely bridged' case.  For IP, we pass the packet to
 * netfilter with indev and outdev set to the bridge device,
 * but we are still able to filter on the 'real' indev/outdev
 * because of the physdev module. For ARP, indev and outdev are the
 * bridge ports. */
static unsigned int br_nf_forward_ip(void *priv,
				     struct sk_buff *skb,
				     const struct nf_hook_state *state)
{
	struct nf_bridge_info *nf_bridge;
	struct net_device *parent;
	u_int8_t pf;

	if (!skb->nf_bridge)
		return NF_ACCEPT;

	/* Need exclusive nf_bridge_info since we might have multiple
	 * different physoutdevs. */
	if (!nf_bridge_unshare(skb))
		return NF_DROP;

	nf_bridge = nf_bridge_info_get(skb);
	if (!nf_bridge)
		return NF_DROP;

	parent = bridge_parent(state->out);
	if (!parent)
		return NF_DROP;

	if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
		pf = NFPROTO_IPV4;
	else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
		pf = NFPROTO_IPV6;
	else
		return NF_ACCEPT;

	nf_bridge_pull_encap_header(skb);

	if (skb->pkt_type == PACKET_OTHERHOST) {
		skb->pkt_type = PACKET_HOST;
		nf_bridge->pkt_otherhost = true;
	}

	if (pf == NFPROTO_IPV4) {
		if (br_validate_ipv4(state->net, skb))
			return NF_DROP;
		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
	}

	if (pf == NFPROTO_IPV6) {
		if (br_validate_ipv6(state->net, skb))
			return NF_DROP;
		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
	}

	nf_bridge->physoutdev = skb->dev;
	if (pf == NFPROTO_IPV4)
		skb->protocol = htons(ETH_P_IP);
	else
		skb->protocol = htons(ETH_P_IPV6);

	NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb,
		brnf_get_logical_dev(skb, state->in),
		parent,	br_nf_forward_finish);

	return NF_STOLEN;
}

static unsigned int br_nf_forward_arp(void *priv,
				      struct sk_buff *skb,
				      const struct nf_hook_state *state)
{
	struct net_bridge_port *p;
	struct net_bridge *br;
	struct net_device **d = (struct net_device **)(skb->cb);

	p = br_port_get_rcu(state->out);
	if (p == NULL)
		return NF_ACCEPT;
	br = p->br;

	if (!brnf_call_arptables && !br->nf_call_arptables)
		return NF_ACCEPT;

	if (!IS_ARP(skb)) {
		if (!IS_VLAN_ARP(skb))
			return NF_ACCEPT;
		nf_bridge_pull_encap_header(skb);
	}

	if (arp_hdr(skb)->ar_pln != 4) {
		if (IS_VLAN_ARP(skb))
			nf_bridge_push_encap_header(skb);
		return NF_ACCEPT;
	}
	*d = state->in;
	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->net, state->sk, skb,
		state->in, state->out, br_nf_forward_finish);

	return NF_STOLEN;
}

static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct brnf_frag_data *data;
	int err;

	data = this_cpu_ptr(&brnf_frag_data_storage);
	err = skb_cow_head(skb, data->size);

	if (err) {
		kfree_skb(skb);
		return 0;
	}

	if (data->vlan_tci) {
		skb->vlan_tci = data->vlan_tci;
		skb->vlan_proto = data->vlan_proto;
	}

	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
	__skb_push(skb, data->encap_size);

	nf_bridge_info_free(skb);
	return br_dev_queue_push_xmit(net, sk, skb);
}

static int
br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
		  int (*output)(struct net *, struct sock *, struct sk_buff *))
{
	unsigned int mtu = ip_skb_dst_mtu(sk, skb);
	struct iphdr *iph = ip_hdr(skb);

	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
		     (IPCB(skb)->frag_max_size &&
		      IPCB(skb)->frag_max_size > mtu))) {
		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	return ip_do_fragment(net, sk, skb, output);
}

static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
{
	if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE)
		return PPPOE_SES_HLEN;
	return 0;
}

static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge;
	unsigned int mtu_reserved;

	mtu_reserved = nf_bridge_mtu_reduction(skb);

	if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) {
		nf_bridge_info_free(skb);
		return br_dev_queue_push_xmit(net, sk, skb);
	}

	nf_bridge = nf_bridge_info_get(skb);

	/* This is wrong! We should preserve the original fragment
	 * boundaries by preserving frag_list rather than refragmenting.
	 */
	if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) &&
	    skb->protocol == htons(ETH_P_IP)) {
		struct brnf_frag_data *data;

		if (br_validate_ipv4(net, skb))
			goto drop;

		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;

		nf_bridge_update_protocol(skb);

		data = this_cpu_ptr(&brnf_frag_data_storage);

		data->vlan_tci = skb->vlan_tci;
		data->vlan_proto = skb->vlan_proto;
		data->encap_size = nf_bridge_encap_header_len(skb);
		data->size = ETH_HLEN + data->encap_size;

		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
						 data->size);

		return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
	}
	if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) &&
	    skb->protocol == htons(ETH_P_IPV6)) {
		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
		struct brnf_frag_data *data;

		if (br_validate_ipv6(net, skb))
			goto drop;

		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;

		nf_bridge_update_protocol(skb);

		data = this_cpu_ptr(&brnf_frag_data_storage);
		data->encap_size = nf_bridge_encap_header_len(skb);
		data->size = ETH_HLEN + data->encap_size;

		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
						 data->size);

		if (v6ops)
			return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);

		kfree_skb(skb);
		return -EMSGSIZE;
	}
	nf_bridge_info_free(skb);
	return br_dev_queue_push_xmit(net, sk, skb);
 drop:
	kfree_skb(skb);
	return 0;
}

/* PF_BRIDGE/POST_ROUTING ********************************************/
static unsigned int br_nf_post_routing(void *priv,
				       struct sk_buff *skb,
				       const struct nf_hook_state *state)
{
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
	struct net_device *realoutdev = bridge_parent(skb->dev);
	u_int8_t pf;

	/* if nf_bridge is set, but ->physoutdev is NULL, this packet came in
	 * on a bridge, but was delivered locally and is now being routed:
	 *
	 * POST_ROUTING was already invoked from the ip stack.
	 */
	if (!nf_bridge || !nf_bridge->physoutdev)
		return NF_ACCEPT;

	if (!realoutdev)
		return NF_DROP;

	if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
		pf = NFPROTO_IPV4;
	else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
		pf = NFPROTO_IPV6;
	else
		return NF_ACCEPT;

	/* We assume any code from br_dev_queue_push_xmit onwards doesn't care
	 * about the value of skb->pkt_type. */
	if (skb->pkt_type == PACKET_OTHERHOST) {
		skb->pkt_type = PACKET_HOST;
		nf_bridge->pkt_otherhost = true;
	}

	nf_bridge_pull_encap_header(skb);
	if (pf == NFPROTO_IPV4)
		skb->protocol = htons(ETH_P_IP);
	else
		skb->protocol = htons(ETH_P_IPV6);

	NF_HOOK(pf, NF_INET_POST_ROUTING, state->net, state->sk, skb,
		NULL, realoutdev,
		br_nf_dev_queue_xmit);

	return NF_STOLEN;
}

/* IP/SABOTAGE *****************************************************/
/* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING
 * for the second time. */
static unsigned int ip_sabotage_in(void *priv,
				   struct sk_buff *skb,
				   const struct nf_hook_state *state)
{
	if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) {
		state->okfn(state->net, state->sk, skb);
		return NF_STOLEN;
	}

	return NF_ACCEPT;
}

/* This is called when br_netfilter has called into iptables/netfilter,
 * and DNAT has taken place on a bridge-forwarded packet.
 *
 * neigh->output has created a new MAC header, with local br0 MAC
 * as saddr.
 *
 * This restores the original MAC saddr of the bridged packet
 * before invoking bridge forward logic to transmit the packet.
 */
static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);

	skb_pull(skb, ETH_HLEN);
	nf_bridge->bridged_dnat = 0;

	BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));

	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
				       nf_bridge->neigh_header,
				       ETH_HLEN - ETH_ALEN);
	skb->dev = nf_bridge->physindev;

	nf_bridge->physoutdev = NULL;
	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
}

static int br_nf_dev_xmit(struct sk_buff *skb)
{
	if (skb->nf_bridge && skb->nf_bridge->bridged_dnat) {
		br_nf_pre_routing_finish_bridge_slow(skb);
		return 1;
	}
	return 0;
}

static const struct nf_br_ops br_ops = {
	.br_dev_xmit_hook =	br_nf_dev_xmit,
};

void br_netfilter_enable(void)
{
}
EXPORT_SYMBOL_GPL(br_netfilter_enable);

/* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
 * br_dev_queue_push_xmit is called afterwards */
static struct nf_hook_ops br_nf_ops[] __read_mostly = {
	{
		.hook = br_nf_pre_routing,
		.pf = NFPROTO_BRIDGE,
		.hooknum = NF_BR_PRE_ROUTING,
		.priority = NF_BR_PRI_BRNF,
	},
	{
		.hook = br_nf_local_in,
		.pf = NFPROTO_BRIDGE,
		.hooknum = NF_BR_LOCAL_IN,
		.priority = NF_BR_PRI_BRNF,
	},
	{
		.hook = br_nf_forward_ip,
		.pf = NFPROTO_BRIDGE,
		.hooknum = NF_BR_FORWARD,
		.priority = NF_BR_PRI_BRNF - 1,
	},
	{
		.hook = br_nf_forward_arp,
		.pf = NFPROTO_BRIDGE,
		.hooknum = NF_BR_FORWARD,
		.priority = NF_BR_PRI_BRNF,
	},
	{
		.hook = br_nf_post_routing,
		.pf = NFPROTO_BRIDGE,
		.hooknum = NF_BR_POST_ROUTING,
		.priority = NF_BR_PRI_LAST,
	},
	{
		.hook = ip_sabotage_in,
		.pf = NFPROTO_IPV4,
		.hooknum = NF_INET_PRE_ROUTING,
		.priority = NF_IP_PRI_FIRST,
	},
	{
		.hook = ip_sabotage_in,
		.pf = NFPROTO_IPV6,
		.hooknum = NF_INET_PRE_ROUTING,
		.priority = NF_IP6_PRI_FIRST,
	},
};

static int brnf_device_event(struct notifier_block *unused, unsigned long event,
			     void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct brnf_net *brnet;
	struct net *net;
	int ret;

	if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE))
		return NOTIFY_DONE;

	ASSERT_RTNL();

	net = dev_net(dev);
	brnet = net_generic(net, brnf_net_id);
	if (brnet->enabled)
		return NOTIFY_OK;

	ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
	if (ret)
		return NOTIFY_BAD;

	brnet->enabled = true;
	return NOTIFY_OK;
}

static void __net_exit brnf_exit_net(struct net *net)
{
	struct brnf_net *brnet = net_generic(net, brnf_net_id);

	if (!brnet->enabled)
		return;

	nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
	brnet->enabled = false;
}

static struct pernet_operations brnf_net_ops __read_mostly = {
	.exit = brnf_exit_net,
	.id   = &brnf_net_id,
	.size = sizeof(struct brnf_net),
};

static struct notifier_block brnf_notifier __read_mostly = {
	.notifier_call = brnf_device_event,
};

/* recursively invokes nf_hook_slow (again), skipping already-called
 * hooks (< NF_BR_PRI_BRNF).
 *
 * Called with rcu read lock held.
 */
int br_nf_hook_thresh(unsigned int hook, struct net *net,
		      struct sock *sk, struct sk_buff *skb,
		      struct net_device *indev,
		      struct net_device *outdev,
		      int (*okfn)(struct net *, struct sock *,
				  struct sk_buff *))
{
	struct nf_hook_entry *elem;
	struct nf_hook_state state;
	int ret;

	for (elem = rcu_dereference(net->nf.hooks[NFPROTO_BRIDGE][hook]);
	     elem && nf_hook_entry_priority(elem) <= NF_BR_PRI_BRNF;
	     elem = rcu_dereference(elem->next))
		;

	if (!elem)
		return okfn(net, sk, skb);

	/* We may already have this, but read-locks nest anyway */
	rcu_read_lock();
	nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
			   sk, net, okfn);

	ret = nf_hook_slow(skb, &state, elem);
	rcu_read_unlock();
	if (ret == 1)
		ret = okfn(net, sk, skb);

	return ret;
}

#ifdef CONFIG_SYSCTL
static
int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
			    void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int ret;

	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);

	if (write && *(int *)(ctl->data))
		*(int *)(ctl->data) = 1;
	return ret;
}

static struct ctl_table brnf_table[] = {
	{
		.procname	= "bridge-nf-call-arptables",
		.data		= &brnf_call_arptables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-call-iptables",
		.data		= &brnf_call_iptables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-call-ip6tables",
		.data		= &brnf_call_ip6tables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-filter-vlan-tagged",
		.data		= &brnf_filter_vlan_tagged,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-filter-pppoe-tagged",
		.data		= &brnf_filter_pppoe_tagged,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-pass-vlan-input-dev",
		.data		= &brnf_pass_vlan_indev,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= brnf_sysctl_call_tables,
	},
	{ }
};
#endif

static int __init br_netfilter_init(void)
{
	int ret;

	ret = register_pernet_subsys(&brnf_net_ops);
	if (ret < 0)
		return ret;

	ret = register_netdevice_notifier(&brnf_notifier);
	if (ret < 0) {
		unregister_pernet_subsys(&brnf_net_ops);
		return ret;
	}

#ifdef CONFIG_SYSCTL
	brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table);
	if (brnf_sysctl_header == NULL) {
		printk(KERN_WARNING
		       "br_netfilter: can't register to sysctl.\n");
		unregister_netdevice_notifier(&brnf_notifier);
		unregister_pernet_subsys(&brnf_net_ops);
		return -ENOMEM;
	}
#endif
	RCU_INIT_POINTER(nf_br_ops, &br_ops);
	printk(KERN_NOTICE "Bridge firewalling registered\n");
	return 0;
}

static void __exit br_netfilter_fini(void)
{
	RCU_INIT_POINTER(nf_br_ops, NULL);
	unregister_netdevice_notifier(&brnf_notifier);
	unregister_pernet_subsys(&brnf_net_ops);
#ifdef CONFIG_SYSCTL
	unregister_net_sysctl_table(brnf_sysctl_header);
#endif
}

module_init(br_netfilter_init);
module_exit(br_netfilter_fini);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Lennert Buytenhek <buytenh@gnu.org>");
MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
MODULE_DESCRIPTION("Linux ethernet netfilter firewall bridge");