Free Electrons

Embedded Linux Experts

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
/*
 * This is a module which is used for queueing packets and communicating with
 * userspace via nfnetlink.
 *
 * (C) 2005 by Harald Welte <laforge@netfilter.org>
 * (C) 2007 by Patrick McHardy <kaber@trash.net>
 *
 * Based on the old ipv4-only ip_queue.c:
 * (C) 2000-2002 James Morris <jmorris@intercode.com.au>
 * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 */
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/proc_fs.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_queue.h>
#include <linux/list.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/netfilter/nf_queue.h>
#include <net/netns/generic.h>
#include <net/netfilter/nfnetlink_queue.h>

#include <linux/atomic.h>

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
#include "../bridge/br_private.h"
#endif

#define NFQNL_QMAX_DEFAULT 1024

/* We're using struct nlattr which has 16bit nla_len. Note that nla_len
 * includes the header length. Thus, the maximum packet length that we
 * support is 65531 bytes. We send truncated packets if the specified length
 * is larger than that.  Userspace can check for presence of NFQA_CAP_LEN
 * attribute to detect truncation.
 */
#define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN)

struct nfqnl_instance {
	struct hlist_node hlist;		/* global list of queues */
	struct rcu_head rcu;

	u32 peer_portid;
	unsigned int queue_maxlen;
	unsigned int copy_range;
	unsigned int queue_dropped;
	unsigned int queue_user_dropped;


	u_int16_t queue_num;			/* number of this queue */
	u_int8_t copy_mode;
	u_int32_t flags;			/* Set using NFQA_CFG_FLAGS */
/*
 * Following fields are dirtied for each queued packet,
 * keep them in same cache line if possible.
 */
	spinlock_t	lock;
	unsigned int	queue_total;
	unsigned int	id_sequence;		/* 'sequence' of pkt ids */
	struct list_head queue_list;		/* packets in queue */
};

typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long);

static int nfnl_queue_net_id __read_mostly;

#define INSTANCE_BUCKETS	16
struct nfnl_queue_net {
	spinlock_t instances_lock;
	struct hlist_head instance_table[INSTANCE_BUCKETS];
};

static struct nfnl_queue_net *nfnl_queue_pernet(struct net *net)
{
	return net_generic(net, nfnl_queue_net_id);
}

static inline u_int8_t instance_hashfn(u_int16_t queue_num)
{
	return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS;
}

static struct nfqnl_instance *
instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num)
{
	struct hlist_head *head;
	struct nfqnl_instance *inst;

	head = &q->instance_table[instance_hashfn(queue_num)];
	hlist_for_each_entry_rcu(inst, head, hlist) {
		if (inst->queue_num == queue_num)
			return inst;
	}
	return NULL;
}

static struct nfqnl_instance *
instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid)
{
	struct nfqnl_instance *inst;
	unsigned int h;
	int err;

	spin_lock(&q->instances_lock);
	if (instance_lookup(q, queue_num)) {
		err = -EEXIST;
		goto out_unlock;
	}

	inst = kzalloc(sizeof(*inst), GFP_ATOMIC);
	if (!inst) {
		err = -ENOMEM;
		goto out_unlock;
	}

	inst->queue_num = queue_num;
	inst->peer_portid = portid;
	inst->queue_maxlen = NFQNL_QMAX_DEFAULT;
	inst->copy_range = NFQNL_MAX_COPY_RANGE;
	inst->copy_mode = NFQNL_COPY_NONE;
	spin_lock_init(&inst->lock);
	INIT_LIST_HEAD(&inst->queue_list);

	if (!try_module_get(THIS_MODULE)) {
		err = -EAGAIN;
		goto out_free;
	}

	h = instance_hashfn(queue_num);
	hlist_add_head_rcu(&inst->hlist, &q->instance_table[h]);

	spin_unlock(&q->instances_lock);

	return inst;

out_free:
	kfree(inst);
out_unlock:
	spin_unlock(&q->instances_lock);
	return ERR_PTR(err);
}

static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
			unsigned long data);

static void
instance_destroy_rcu(struct rcu_head *head)
{
	struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance,
						   rcu);

	nfqnl_flush(inst, NULL, 0);
	kfree(inst);
	module_put(THIS_MODULE);
}

static void
__instance_destroy(struct nfqnl_instance *inst)
{
	hlist_del_rcu(&inst->hlist);
	call_rcu(&inst->rcu, instance_destroy_rcu);
}

static void
instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst)
{
	spin_lock(&q->instances_lock);
	__instance_destroy(inst);
	spin_unlock(&q->instances_lock);
}

static inline void
__enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
{
       list_add_tail(&entry->list, &queue->queue_list);
       queue->queue_total++;
}

static void
__dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
{
	list_del(&entry->list);
	queue->queue_total--;
}

static struct nf_queue_entry *
find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id)
{
	struct nf_queue_entry *entry = NULL, *i;

	spin_lock_bh(&queue->lock);

	list_for_each_entry(i, &queue->queue_list, list) {
		if (i->id == id) {
			entry = i;
			break;
		}
	}

	if (entry)
		__dequeue_entry(queue, entry);

	spin_unlock_bh(&queue->lock);

	return entry;
}

static void
nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
{
	struct nf_queue_entry *entry, *next;

	spin_lock_bh(&queue->lock);
	list_for_each_entry_safe(entry, next, &queue->queue_list, list) {
		if (!cmpfn || cmpfn(entry, data)) {
			list_del(&entry->list);
			queue->queue_total--;
			nf_reinject(entry, NF_DROP);
		}
	}
	spin_unlock_bh(&queue->lock);
}

static int
nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
		      bool csum_verify)
{
	__u32 flags = 0;

	if (packet->ip_summed == CHECKSUM_PARTIAL)
		flags = NFQA_SKB_CSUMNOTREADY;
	else if (csum_verify)
		flags = NFQA_SKB_CSUM_NOTVERIFIED;

	if (skb_is_gso(packet))
		flags |= NFQA_SKB_GSO;

	return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0;
}

static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
{
	const struct cred *cred;

	if (!sk_fullsock(sk))
		return 0;

	read_lock_bh(&sk->sk_callback_lock);
	if (sk->sk_socket && sk->sk_socket->file) {
		cred = sk->sk_socket->file->f_cred;
		if (nla_put_be32(skb, NFQA_UID,
		    htonl(from_kuid_munged(&init_user_ns, cred->fsuid))))
			goto nla_put_failure;
		if (nla_put_be32(skb, NFQA_GID,
		    htonl(from_kgid_munged(&init_user_ns, cred->fsgid))))
			goto nla_put_failure;
	}
	read_unlock_bh(&sk->sk_callback_lock);
	return 0;

nla_put_failure:
	read_unlock_bh(&sk->sk_callback_lock);
	return -1;
}

static struct sk_buff *
nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
			   struct nf_queue_entry *entry,
			   __be32 **packet_id_ptr)
{
	size_t size;
	size_t data_len = 0, cap_len = 0;
	unsigned int hlen = 0;
	struct sk_buff *skb;
	struct nlattr *nla;
	struct nfqnl_msg_packet_hdr *pmsg;
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	struct sk_buff *entskb = entry->skb;
	struct net_device *indev;
	struct net_device *outdev;
	struct nf_conn *ct = NULL;
	enum ip_conntrack_info uninitialized_var(ctinfo);
	bool csum_verify;

	size =    nlmsg_total_size(sizeof(struct nfgenmsg))
		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
#endif
		+ nla_total_size(sizeof(u_int32_t))	/* mark */
		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
		+ nla_total_size(sizeof(u_int32_t))	/* skbinfo */
		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */

	if (entskb->tstamp.tv64)
		size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));

	if (entry->state.hook <= NF_INET_FORWARD ||
	   (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL))
		csum_verify = !skb_csum_unnecessary(entskb);
	else
		csum_verify = false;

	outdev = entry->state.out;

	switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) {
	case NFQNL_COPY_META:
	case NFQNL_COPY_NONE:
		break;

	case NFQNL_COPY_PACKET:
		if (!(queue->flags & NFQA_CFG_F_GSO) &&
		    entskb->ip_summed == CHECKSUM_PARTIAL &&
		    skb_checksum_help(entskb))
			return NULL;

		data_len = ACCESS_ONCE(queue->copy_range);
		if (data_len > entskb->len)
			data_len = entskb->len;

		hlen = skb_zerocopy_headlen(entskb);
		hlen = min_t(unsigned int, hlen, data_len);
		size += sizeof(struct nlattr) + hlen;
		cap_len = entskb->len;
		break;
	}

	if (queue->flags & NFQA_CFG_F_CONNTRACK)
		ct = nfqnl_ct_get(entskb, &size, &ctinfo);

	if (queue->flags & NFQA_CFG_F_UID_GID) {
		size +=  (nla_total_size(sizeof(u_int32_t))	/* uid */
			+ nla_total_size(sizeof(u_int32_t)));	/* gid */
	}

	skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
				  GFP_ATOMIC);
	if (!skb) {
		skb_tx_error(entskb);
		return NULL;
	}

	nlh = nlmsg_put(skb, 0, 0,
			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
			sizeof(struct nfgenmsg), 0);
	if (!nlh) {
		skb_tx_error(entskb);
		kfree_skb(skb);
		return NULL;
	}
	nfmsg = nlmsg_data(nlh);
	nfmsg->nfgen_family = entry->state.pf;
	nfmsg->version = NFNETLINK_V0;
	nfmsg->res_id = htons(queue->queue_num);

	nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg));
	pmsg = nla_data(nla);
	pmsg->hw_protocol	= entskb->protocol;
	pmsg->hook		= entry->state.hook;
	*packet_id_ptr		= &pmsg->packet_id;

	indev = entry->state.in;
	if (indev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)))
			goto nla_put_failure;
#else
		if (entry->state.pf == PF_BRIDGE) {
			/* Case 1: indev is physical input device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
					 htonl(indev->ifindex)) ||
			/* this is the bridge group "brX" */
			/* rcu_read_lock()ed by __nf_queue */
			    nla_put_be32(skb, NFQA_IFINDEX_INDEV,
					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
				goto nla_put_failure;
		} else {
			int physinif;

			/* Case 2: indev is bridge group, we need to look for
			 * physical device (when called from ipv4) */
			if (nla_put_be32(skb, NFQA_IFINDEX_INDEV,
					 htonl(indev->ifindex)))
				goto nla_put_failure;

			physinif = nf_bridge_get_physinif(entskb);
			if (physinif &&
			    nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
					 htonl(physinif)))
				goto nla_put_failure;
		}
#endif
	}

	if (outdev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)))
			goto nla_put_failure;
#else
		if (entry->state.pf == PF_BRIDGE) {
			/* Case 1: outdev is physical output device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV,
					 htonl(outdev->ifindex)) ||
			/* this is the bridge group "brX" */
			/* rcu_read_lock()ed by __nf_queue */
			    nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
				goto nla_put_failure;
		} else {
			int physoutif;

			/* Case 2: outdev is bridge group, we need to look for
			 * physical output device (when called from ipv4) */
			if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
					 htonl(outdev->ifindex)))
				goto nla_put_failure;

			physoutif = nf_bridge_get_physoutif(entskb);
			if (physoutif &&
			    nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV,
					 htonl(physoutif)))
				goto nla_put_failure;
		}
#endif
	}

	if (entskb->mark &&
	    nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark)))
		goto nla_put_failure;

	if (indev && entskb->dev &&
	    entskb->mac_header != entskb->network_header) {
		struct nfqnl_msg_packet_hw phw;
		int len;

		memset(&phw, 0, sizeof(phw));
		len = dev_parse_header(entskb, phw.hw_addr);
		if (len) {
			phw.hw_addrlen = htons(len);
			if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw))
				goto nla_put_failure;
		}
	}

	if (entskb->tstamp.tv64) {
		struct nfqnl_msg_packet_timestamp ts;
		struct timeval tv = ktime_to_timeval(entskb->tstamp);
		ts.sec = cpu_to_be64(tv.tv_sec);
		ts.usec = cpu_to_be64(tv.tv_usec);

		if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts))
			goto nla_put_failure;
	}

	if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk &&
	    nfqnl_put_sk_uidgid(skb, entskb->sk) < 0)
		goto nla_put_failure;

	if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
		goto nla_put_failure;

	if (cap_len > data_len &&
	    nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
		goto nla_put_failure;

	if (nfqnl_put_packet_info(skb, entskb, csum_verify))
		goto nla_put_failure;

	if (data_len) {
		struct nlattr *nla;

		if (skb_tailroom(skb) < sizeof(*nla) + hlen)
			goto nla_put_failure;

		nla = (struct nlattr *)skb_put(skb, sizeof(*nla));
		nla->nla_type = NFQA_PAYLOAD;
		nla->nla_len = nla_attr_size(data_len);

		if (skb_zerocopy(skb, entskb, data_len, hlen))
			goto nla_put_failure;
	}

	nlh->nlmsg_len = skb->len;
	return skb;

nla_put_failure:
	skb_tx_error(entskb);
	kfree_skb(skb);
	net_err_ratelimited("nf_queue: error creating packet message\n");
	return NULL;
}

static int
__nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue,
			struct nf_queue_entry *entry)
{
	struct sk_buff *nskb;
	int err = -ENOBUFS;
	__be32 *packet_id_ptr;
	int failopen = 0;

	nskb = nfqnl_build_packet_message(net, queue, entry, &packet_id_ptr);
	if (nskb == NULL) {
		err = -ENOMEM;
		goto err_out;
	}
	spin_lock_bh(&queue->lock);

	if (queue->queue_total >= queue->queue_maxlen) {
		if (queue->flags & NFQA_CFG_F_FAIL_OPEN) {
			failopen = 1;
			err = 0;
		} else {
			queue->queue_dropped++;
			net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n",
					     queue->queue_total);
		}
		goto err_out_free_nskb;
	}
	entry->id = ++queue->id_sequence;
	*packet_id_ptr = htonl(entry->id);

	/* nfnetlink_unicast will either free the nskb or add it to a socket */
	err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT);
	if (err < 0) {
		queue->queue_user_dropped++;
		goto err_out_unlock;
	}

	__enqueue_entry(queue, entry);

	spin_unlock_bh(&queue->lock);
	return 0;

err_out_free_nskb:
	kfree_skb(nskb);
err_out_unlock:
	spin_unlock_bh(&queue->lock);
	if (failopen)
		nf_reinject(entry, NF_ACCEPT);
err_out:
	return err;
}

static struct nf_queue_entry *
nf_queue_entry_dup(struct nf_queue_entry *e)
{
	struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC);
	if (entry) {
		if (nf_queue_entry_get_refs(entry))
			return entry;
		kfree(entry);
	}
	return NULL;
}

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* When called from bridge netfilter, skb->data must point to MAC header
 * before calling skb_gso_segment(). Else, original MAC header is lost
 * and segmented skbs will be sent to wrong destination.
 */
static void nf_bridge_adjust_skb_data(struct sk_buff *skb)
{
	if (skb->nf_bridge)
		__skb_push(skb, skb->network_header - skb->mac_header);
}

static void nf_bridge_adjust_segmented_data(struct sk_buff *skb)
{
	if (skb->nf_bridge)
		__skb_pull(skb, skb->network_header - skb->mac_header);
}
#else
#define nf_bridge_adjust_skb_data(s) do {} while (0)
#define nf_bridge_adjust_segmented_data(s) do {} while (0)
#endif

static void free_entry(struct nf_queue_entry *entry)
{
	nf_queue_entry_release_refs(entry);
	kfree(entry);
}

static int
__nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue,
			   struct sk_buff *skb, struct nf_queue_entry *entry)
{
	int ret = -ENOMEM;
	struct nf_queue_entry *entry_seg;

	nf_bridge_adjust_segmented_data(skb);

	if (skb->next == NULL) { /* last packet, no need to copy entry */
		struct sk_buff *gso_skb = entry->skb;
		entry->skb = skb;
		ret = __nfqnl_enqueue_packet(net, queue, entry);
		if (ret)
			entry->skb = gso_skb;
		return ret;
	}

	skb->next = NULL;

	entry_seg = nf_queue_entry_dup(entry);
	if (entry_seg) {
		entry_seg->skb = skb;
		ret = __nfqnl_enqueue_packet(net, queue, entry_seg);
		if (ret)
			free_entry(entry_seg);
	}
	return ret;
}

static int
nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
{
	unsigned int queued;
	struct nfqnl_instance *queue;
	struct sk_buff *skb, *segs;
	int err = -ENOBUFS;
	struct net *net = dev_net(entry->state.in ?
				  entry->state.in : entry->state.out);
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);

	/* rcu_read_lock()ed by nf_hook_slow() */
	queue = instance_lookup(q, queuenum);
	if (!queue)
		return -ESRCH;

	if (queue->copy_mode == NFQNL_COPY_NONE)
		return -EINVAL;

	skb = entry->skb;

	switch (entry->state.pf) {
	case NFPROTO_IPV4:
		skb->protocol = htons(ETH_P_IP);
		break;
	case NFPROTO_IPV6:
		skb->protocol = htons(ETH_P_IPV6);
		break;
	}

	if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb))
		return __nfqnl_enqueue_packet(net, queue, entry);

	nf_bridge_adjust_skb_data(skb);
	segs = skb_gso_segment(skb, 0);
	/* Does not use PTR_ERR to limit the number of error codes that can be
	 * returned by nf_queue.  For instance, callers rely on -ECANCELED to
	 * mean 'ignore this hook'.
	 */
	if (IS_ERR_OR_NULL(segs))
		goto out_err;
	queued = 0;
	err = 0;
	do {
		struct sk_buff *nskb = segs->next;
		if (err == 0)
			err = __nfqnl_enqueue_packet_gso(net, queue,
							segs, entry);
		if (err == 0)
			queued++;
		else
			kfree_skb(segs);
		segs = nskb;
	} while (segs);

	if (queued) {
		if (err) /* some segments are already queued */
			free_entry(entry);
		kfree_skb(skb);
		return 0;
	}
 out_err:
	nf_bridge_adjust_segmented_data(skb);
	return err;
}

static int
nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
{
	struct sk_buff *nskb;

	if (diff < 0) {
		if (pskb_trim(e->skb, data_len))
			return -ENOMEM;
	} else if (diff > 0) {
		if (data_len > 0xFFFF)
			return -EINVAL;
		if (diff > skb_tailroom(e->skb)) {
			nskb = skb_copy_expand(e->skb, skb_headroom(e->skb),
					       diff, GFP_ATOMIC);
			if (!nskb) {
				printk(KERN_WARNING "nf_queue: OOM "
				      "in mangle, dropping packet\n");
				return -ENOMEM;
			}
			kfree_skb(e->skb);
			e->skb = nskb;
		}
		skb_put(e->skb, diff);
	}
	if (!skb_make_writable(e->skb, data_len))
		return -ENOMEM;
	skb_copy_to_linear_data(e->skb, data, data_len);
	e->skb->ip_summed = CHECKSUM_NONE;
	return 0;
}

static int
nfqnl_set_mode(struct nfqnl_instance *queue,
	       unsigned char mode, unsigned int range)
{
	int status = 0;

	spin_lock_bh(&queue->lock);
	switch (mode) {
	case NFQNL_COPY_NONE:
	case NFQNL_COPY_META:
		queue->copy_mode = mode;
		queue->copy_range = 0;
		break;

	case NFQNL_COPY_PACKET:
		queue->copy_mode = mode;
		if (range == 0 || range > NFQNL_MAX_COPY_RANGE)
			queue->copy_range = NFQNL_MAX_COPY_RANGE;
		else
			queue->copy_range = range;
		break;

	default:
		status = -EINVAL;

	}
	spin_unlock_bh(&queue->lock);

	return status;
}

static int
dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
{
	if (entry->state.in)
		if (entry->state.in->ifindex == ifindex)
			return 1;
	if (entry->state.out)
		if (entry->state.out->ifindex == ifindex)
			return 1;
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	if (entry->skb->nf_bridge) {
		int physinif, physoutif;

		physinif = nf_bridge_get_physinif(entry->skb);
		physoutif = nf_bridge_get_physoutif(entry->skb);

		if (physinif == ifindex || physoutif == ifindex)
			return 1;
	}
#endif
	return 0;
}

/* drop all packets with either indev or outdev == ifindex from all queue
 * instances */
static void
nfqnl_dev_drop(struct net *net, int ifindex)
{
	int i;
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);

	rcu_read_lock();

	for (i = 0; i < INSTANCE_BUCKETS; i++) {
		struct nfqnl_instance *inst;
		struct hlist_head *head = &q->instance_table[i];

		hlist_for_each_entry_rcu(inst, head, hlist)
			nfqnl_flush(inst, dev_cmp, ifindex);
	}

	rcu_read_unlock();
}

#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)

static int
nfqnl_rcv_dev_event(struct notifier_block *this,
		    unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);

	/* Drop any packets associated with the downed device */
	if (event == NETDEV_DOWN)
		nfqnl_dev_drop(dev_net(dev), dev->ifindex);
	return NOTIFY_DONE;
}

static struct notifier_block nfqnl_dev_notifier = {
	.notifier_call	= nfqnl_rcv_dev_event,
};

static int
nfqnl_rcv_nl_event(struct notifier_block *this,
		   unsigned long event, void *ptr)
{
	struct netlink_notify *n = ptr;
	struct nfnl_queue_net *q = nfnl_queue_pernet(n->net);

	if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) {
		int i;

		/* destroy all instances for this portid */
		spin_lock(&q->instances_lock);
		for (i = 0; i < INSTANCE_BUCKETS; i++) {
			struct hlist_node *t2;
			struct nfqnl_instance *inst;
			struct hlist_head *head = &q->instance_table[i];

			hlist_for_each_entry_safe(inst, t2, head, hlist) {
				if (n->portid == inst->peer_portid)
					__instance_destroy(inst);
			}
		}
		spin_unlock(&q->instances_lock);
	}
	return NOTIFY_DONE;
}

static struct notifier_block nfqnl_rtnl_notifier = {
	.notifier_call	= nfqnl_rcv_nl_event,
};

static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = {
	[NFQA_VERDICT_HDR]	= { .len = sizeof(struct nfqnl_msg_verdict_hdr) },
	[NFQA_MARK]		= { .type = NLA_U32 },
	[NFQA_PAYLOAD]		= { .type = NLA_UNSPEC },
	[NFQA_CT]		= { .type = NLA_UNSPEC },
	[NFQA_EXP]		= { .type = NLA_UNSPEC },
};

static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = {
	[NFQA_VERDICT_HDR]	= { .len = sizeof(struct nfqnl_msg_verdict_hdr) },
	[NFQA_MARK]		= { .type = NLA_U32 },
};

static struct nfqnl_instance *
verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid)
{
	struct nfqnl_instance *queue;

	queue = instance_lookup(q, queue_num);
	if (!queue)
		return ERR_PTR(-ENODEV);

	if (queue->peer_portid != nlportid)
		return ERR_PTR(-EPERM);

	return queue;
}

static struct nfqnl_msg_verdict_hdr*
verdicthdr_get(const struct nlattr * const nfqa[])
{
	struct nfqnl_msg_verdict_hdr *vhdr;
	unsigned int verdict;

	if (!nfqa[NFQA_VERDICT_HDR])
		return NULL;

	vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]);
	verdict = ntohl(vhdr->verdict) & NF_VERDICT_MASK;
	if (verdict > NF_MAX_VERDICT || verdict == NF_STOLEN)
		return NULL;
	return vhdr;
}

static int nfq_id_after(unsigned int id, unsigned int max)
{
	return (int)(id - max) > 0;
}

static int
nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb,
		   const struct nlmsghdr *nlh,
		   const struct nlattr * const nfqa[])
{
	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
	struct nf_queue_entry *entry, *tmp;
	unsigned int verdict, maxid;
	struct nfqnl_msg_verdict_hdr *vhdr;
	struct nfqnl_instance *queue;
	LIST_HEAD(batch_list);
	u16 queue_num = ntohs(nfmsg->res_id);

	struct net *net = sock_net(ctnl);
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);

	queue = verdict_instance_lookup(q, queue_num,
					NETLINK_CB(skb).portid);
	if (IS_ERR(queue))
		return PTR_ERR(queue);

	vhdr = verdicthdr_get(nfqa);
	if (!vhdr)
		return -EINVAL;

	verdict = ntohl(vhdr->verdict);
	maxid = ntohl(vhdr->id);

	spin_lock_bh(&queue->lock);

	list_for_each_entry_safe(entry, tmp, &queue->queue_list, list) {
		if (nfq_id_after(entry->id, maxid))
			break;
		__dequeue_entry(queue, entry);
		list_add_tail(&entry->list, &batch_list);
	}

	spin_unlock_bh(&queue->lock);

	if (list_empty(&batch_list))
		return -ENOENT;

	list_for_each_entry_safe(entry, tmp, &batch_list, list) {
		if (nfqa[NFQA_MARK])
			entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));
		nf_reinject(entry, verdict);
	}
	return 0;
}

static int
nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
		   const struct nlmsghdr *nlh,
		   const struct nlattr * const nfqa[])
{
	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
	u_int16_t queue_num = ntohs(nfmsg->res_id);

	struct nfqnl_msg_verdict_hdr *vhdr;
	struct nfqnl_instance *queue;
	unsigned int verdict;
	struct nf_queue_entry *entry;
	enum ip_conntrack_info uninitialized_var(ctinfo);
	struct nf_conn *ct = NULL;

	struct net *net = sock_net(ctnl);
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);

	queue = instance_lookup(q, queue_num);
	if (!queue)
		queue = verdict_instance_lookup(q, queue_num,
						NETLINK_CB(skb).portid);
	if (IS_ERR(queue))
		return PTR_ERR(queue);

	vhdr = verdicthdr_get(nfqa);
	if (!vhdr)
		return -EINVAL;

	verdict = ntohl(vhdr->verdict);

	entry = find_dequeue_entry(queue, ntohl(vhdr->id));
	if (entry == NULL)
		return -ENOENT;

	if (nfqa[NFQA_CT]) {
		ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo);
		if (ct && nfqa[NFQA_EXP]) {
			nfqnl_attach_expect(ct, nfqa[NFQA_EXP],
					    NETLINK_CB(skb).portid,
					    nlmsg_report(nlh));
		}
	}

	if (nfqa[NFQA_PAYLOAD]) {
		u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]);
		int diff = payload_len - entry->skb->len;

		if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]),
				 payload_len, entry, diff) < 0)
			verdict = NF_DROP;

		if (ct)
			nfqnl_ct_seq_adjust(entry->skb, ct, ctinfo, diff);
	}

	if (nfqa[NFQA_MARK])
		entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));

	nf_reinject(entry, verdict);
	return 0;
}

static int
nfqnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb,
		  const struct nlmsghdr *nlh,
		  const struct nlattr * const nfqa[])
{
	return -ENOTSUPP;
}

static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
	[NFQA_CFG_CMD]		= { .len = sizeof(struct nfqnl_msg_config_cmd) },
	[NFQA_CFG_PARAMS]	= { .len = sizeof(struct nfqnl_msg_config_params) },
};

static const struct nf_queue_handler nfqh = {
	.outfn	= &nfqnl_enqueue_packet,
};

static int
nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
		  const struct nlmsghdr *nlh,
		  const struct nlattr * const nfqa[])
{
	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
	u_int16_t queue_num = ntohs(nfmsg->res_id);
	struct nfqnl_instance *queue;
	struct nfqnl_msg_config_cmd *cmd = NULL;
	struct net *net = sock_net(ctnl);
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);
	int ret = 0;

	if (nfqa[NFQA_CFG_CMD]) {
		cmd = nla_data(nfqa[NFQA_CFG_CMD]);

		/* Obsolete commands without queue context */
		switch (cmd->command) {
		case NFQNL_CFG_CMD_PF_BIND: return 0;
		case NFQNL_CFG_CMD_PF_UNBIND: return 0;
		}
	}

	rcu_read_lock();
	queue = instance_lookup(q, queue_num);
	if (queue && queue->peer_portid != NETLINK_CB(skb).portid) {
		ret = -EPERM;
		goto err_out_unlock;
	}

	if (cmd != NULL) {
		switch (cmd->command) {
		case NFQNL_CFG_CMD_BIND:
			if (queue) {
				ret = -EBUSY;
				goto err_out_unlock;
			}
			queue = instance_create(q, queue_num,
						NETLINK_CB(skb).portid);
			if (IS_ERR(queue)) {
				ret = PTR_ERR(queue);
				goto err_out_unlock;
			}
			break;
		case NFQNL_CFG_CMD_UNBIND:
			if (!queue) {
				ret = -ENODEV;
				goto err_out_unlock;
			}
			instance_destroy(q, queue);
			break;
		case NFQNL_CFG_CMD_PF_BIND:
		case NFQNL_CFG_CMD_PF_UNBIND:
			break;
		default:
			ret = -ENOTSUPP;
			break;
		}
	}

	if (nfqa[NFQA_CFG_PARAMS]) {
		struct nfqnl_msg_config_params *params;

		if (!queue) {
			ret = -ENODEV;
			goto err_out_unlock;
		}
		params = nla_data(nfqa[NFQA_CFG_PARAMS]);
		nfqnl_set_mode(queue, params->copy_mode,
				ntohl(params->copy_range));
	}

	if (nfqa[NFQA_CFG_QUEUE_MAXLEN]) {
		__be32 *queue_maxlen;

		if (!queue) {
			ret = -ENODEV;
			goto err_out_unlock;
		}
		queue_maxlen = nla_data(nfqa[NFQA_CFG_QUEUE_MAXLEN]);
		spin_lock_bh(&queue->lock);
		queue->queue_maxlen = ntohl(*queue_maxlen);
		spin_unlock_bh(&queue->lock);
	}

	if (nfqa[NFQA_CFG_FLAGS]) {
		__u32 flags, mask;

		if (!queue) {
			ret = -ENODEV;
			goto err_out_unlock;
		}

		if (!nfqa[NFQA_CFG_MASK]) {
			/* A mask is needed to specify which flags are being
			 * changed.
			 */
			ret = -EINVAL;
			goto err_out_unlock;
		}

		flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS]));
		mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK]));

		if (flags >= NFQA_CFG_F_MAX) {
			ret = -EOPNOTSUPP;
			goto err_out_unlock;
		}

		spin_lock_bh(&queue->lock);
		queue->flags &= ~mask;
		queue->flags |= flags & mask;
		spin_unlock_bh(&queue->lock);
	}

err_out_unlock:
	rcu_read_unlock();
	return ret;
}

static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = {
	[NFQNL_MSG_PACKET]	= { .call_rcu = nfqnl_recv_unsupp,
				    .attr_count = NFQA_MAX, },
	[NFQNL_MSG_VERDICT]	= { .call_rcu = nfqnl_recv_verdict,
				    .attr_count = NFQA_MAX,
				    .policy = nfqa_verdict_policy },
	[NFQNL_MSG_CONFIG]	= { .call = nfqnl_recv_config,
				    .attr_count = NFQA_CFG_MAX,
				    .policy = nfqa_cfg_policy },
	[NFQNL_MSG_VERDICT_BATCH]={ .call_rcu = nfqnl_recv_verdict_batch,
				    .attr_count = NFQA_MAX,
				    .policy = nfqa_verdict_batch_policy },
};

static const struct nfnetlink_subsystem nfqnl_subsys = {
	.name		= "nf_queue",
	.subsys_id	= NFNL_SUBSYS_QUEUE,
	.cb_count	= NFQNL_MSG_MAX,
	.cb		= nfqnl_cb,
};

#ifdef CONFIG_PROC_FS
struct iter_state {
	struct seq_net_private p;
	unsigned int bucket;
};

static struct hlist_node *get_first(struct seq_file *seq)
{
	struct iter_state *st = seq->private;
	struct net *net;
	struct nfnl_queue_net *q;

	if (!st)
		return NULL;

	net = seq_file_net(seq);
	q = nfnl_queue_pernet(net);
	for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) {
		if (!hlist_empty(&q->instance_table[st->bucket]))
			return q->instance_table[st->bucket].first;
	}
	return NULL;
}

static struct hlist_node *get_next(struct seq_file *seq, struct hlist_node *h)
{
	struct iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);

	h = h->next;
	while (!h) {
		struct nfnl_queue_net *q;

		if (++st->bucket >= INSTANCE_BUCKETS)
			return NULL;

		q = nfnl_queue_pernet(net);
		h = q->instance_table[st->bucket].first;
	}
	return h;
}

static struct hlist_node *get_idx(struct seq_file *seq, loff_t pos)
{
	struct hlist_node *head;
	head = get_first(seq);

	if (head)
		while (pos && (head = get_next(seq, head)))
			pos--;
	return pos ? NULL : head;
}

static void *seq_start(struct seq_file *s, loff_t *pos)
	__acquires(nfnl_queue_pernet(seq_file_net(s))->instances_lock)
{
	spin_lock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock);
	return get_idx(s, *pos);
}

static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
{
	(*pos)++;
	return get_next(s, v);
}

static void seq_stop(struct seq_file *s, void *v)
	__releases(nfnl_queue_pernet(seq_file_net(s))->instances_lock)
{
	spin_unlock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock);
}

static int seq_show(struct seq_file *s, void *v)
{
	const struct nfqnl_instance *inst = v;

	seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n",
		   inst->queue_num,
		   inst->peer_portid, inst->queue_total,
		   inst->copy_mode, inst->copy_range,
		   inst->queue_dropped, inst->queue_user_dropped,
		   inst->id_sequence, 1);
	return seq_has_overflowed(s);
}

static const struct seq_operations nfqnl_seq_ops = {
	.start	= seq_start,
	.next	= seq_next,
	.stop	= seq_stop,
	.show	= seq_show,
};

static int nfqnl_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &nfqnl_seq_ops,
			sizeof(struct iter_state));
}

static const struct file_operations nfqnl_file_ops = {
	.owner	 = THIS_MODULE,
	.open	 = nfqnl_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_net,
};

#endif /* PROC_FS */

static int __net_init nfnl_queue_net_init(struct net *net)
{
	unsigned int i;
	struct nfnl_queue_net *q = nfnl_queue_pernet(net);

	for (i = 0; i < INSTANCE_BUCKETS; i++)
		INIT_HLIST_HEAD(&q->instance_table[i]);

	spin_lock_init(&q->instances_lock);

#ifdef CONFIG_PROC_FS
	if (!proc_create("nfnetlink_queue", 0440,
			 net->nf.proc_netfilter, &nfqnl_file_ops))
		return -ENOMEM;
#endif
	return 0;
}

static void __net_exit nfnl_queue_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
	remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter);
#endif
}

static struct pernet_operations nfnl_queue_net_ops = {
	.init	= nfnl_queue_net_init,
	.exit	= nfnl_queue_net_exit,
	.id	= &nfnl_queue_net_id,
	.size	= sizeof(struct nfnl_queue_net),
};

static int __init nfnetlink_queue_init(void)
{
	int status;

	status = register_pernet_subsys(&nfnl_queue_net_ops);
	if (status < 0) {
		pr_err("nf_queue: failed to register pernet ops\n");
		goto out;
	}

	netlink_register_notifier(&nfqnl_rtnl_notifier);
	status = nfnetlink_subsys_register(&nfqnl_subsys);
	if (status < 0) {
		pr_err("nf_queue: failed to create netlink socket\n");
		goto cleanup_netlink_notifier;
	}

	register_netdevice_notifier(&nfqnl_dev_notifier);
	nf_register_queue_handler(&nfqh);
	return status;

cleanup_netlink_notifier:
	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
out:
	return status;
}

static void __exit nfnetlink_queue_fini(void)
{
	nf_unregister_queue_handler();
	unregister_netdevice_notifier(&nfqnl_dev_notifier);
	nfnetlink_subsys_unregister(&nfqnl_subsys);
	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
	unregister_pernet_subsys(&nfnl_queue_net_ops);

	rcu_barrier(); /* Wait for completion of call_rcu()'s */
}

MODULE_DESCRIPTION("netfilter packet queue handler");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_QUEUE);

module_init(nfnetlink_queue_init);
module_exit(nfnetlink_queue_fini);