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
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
/* GTP according to GSM TS 09.60 / 3GPP TS 29.060
 *
 * (C) 2012-2014 by sysmocom - s.f.m.c. GmbH
 * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org>
 *
 * Author: Harald Welte <hwelte@sysmocom.de>
 *	   Pablo Neira Ayuso <pablo@netfilter.org>
 *	   Andreas Schultz <aschultz@travelping.com>
 *
 * 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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/udp.h>
#include <linux/rculist.h>
#include <linux/jhash.h>
#include <linux/if_tunnel.h>
#include <linux/net.h>
#include <linux/file.h>
#include <linux/gtp.h>

#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/genetlink.h>
#include <net/netns/generic.h>
#include <net/gtp.h>

/* An active session for the subscriber. */
struct pdp_ctx {
	struct hlist_node	hlist_tid;
	struct hlist_node	hlist_addr;

	union {
		u64		tid;
		struct {
			u64	tid;
			u16	flow;
		} v0;
		struct {
			u32	i_tei;
			u32	o_tei;
		} v1;
	} u;
	u8			gtp_version;
	u16			af;

	struct in_addr		ms_addr_ip4;
	struct in_addr		peer_addr_ip4;

	struct sock		*sk;
	struct net_device       *dev;

	atomic_t		tx_seq;
	struct rcu_head		rcu_head;
};

/* One instance of the GTP device. */
struct gtp_dev {
	struct list_head	list;

	struct sock		*sk0;
	struct sock		*sk1u;

	struct net_device	*dev;

	unsigned int		role;
	unsigned int		hash_size;
	struct hlist_head	*tid_hash;
	struct hlist_head	*addr_hash;
};

static unsigned int gtp_net_id __read_mostly;

struct gtp_net {
	struct list_head gtp_dev_list;
};

static u32 gtp_h_initval;

static void pdp_context_delete(struct pdp_ctx *pctx);

static inline u32 gtp0_hashfn(u64 tid)
{
	u32 *tid32 = (u32 *) &tid;
	return jhash_2words(tid32[0], tid32[1], gtp_h_initval);
}

static inline u32 gtp1u_hashfn(u32 tid)
{
	return jhash_1word(tid, gtp_h_initval);
}

static inline u32 ipv4_hashfn(__be32 ip)
{
	return jhash_1word((__force u32)ip, gtp_h_initval);
}

/* Resolve a PDP context structure based on the 64bit TID. */
static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid)
{
	struct hlist_head *head;
	struct pdp_ctx *pdp;

	head = &gtp->tid_hash[gtp0_hashfn(tid) % gtp->hash_size];

	hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
		if (pdp->gtp_version == GTP_V0 &&
		    pdp->u.v0.tid == tid)
			return pdp;
	}
	return NULL;
}

/* Resolve a PDP context structure based on the 32bit TEI. */
static struct pdp_ctx *gtp1_pdp_find(struct gtp_dev *gtp, u32 tid)
{
	struct hlist_head *head;
	struct pdp_ctx *pdp;

	head = &gtp->tid_hash[gtp1u_hashfn(tid) % gtp->hash_size];

	hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
		if (pdp->gtp_version == GTP_V1 &&
		    pdp->u.v1.i_tei == tid)
			return pdp;
	}
	return NULL;
}

/* Resolve a PDP context based on IPv4 address of MS. */
static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
{
	struct hlist_head *head;
	struct pdp_ctx *pdp;

	head = &gtp->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size];

	hlist_for_each_entry_rcu(pdp, head, hlist_addr) {
		if (pdp->af == AF_INET &&
		    pdp->ms_addr_ip4.s_addr == ms_addr)
			return pdp;
	}

	return NULL;
}

static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
				  unsigned int hdrlen, unsigned int role)
{
	struct iphdr *iph;

	if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
		return false;

	iph = (struct iphdr *)(skb->data + hdrlen);

	if (role == GTP_ROLE_SGSN)
		return iph->daddr == pctx->ms_addr_ip4.s_addr;
	else
		return iph->saddr == pctx->ms_addr_ip4.s_addr;
}

/* Check if the inner IP address in this packet is assigned to any
 * existing mobile subscriber.
 */
static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
			     unsigned int hdrlen, unsigned int role)
{
	switch (ntohs(skb->protocol)) {
	case ETH_P_IP:
		return gtp_check_ms_ipv4(skb, pctx, hdrlen, role);
	}
	return false;
}

static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
			unsigned int hdrlen, unsigned int role)
{
	struct pcpu_sw_netstats *stats;

	if (!gtp_check_ms(skb, pctx, hdrlen, role)) {
		netdev_dbg(pctx->dev, "No PDP ctx for this MS\n");
		return 1;
	}

	/* Get rid of the GTP + UDP headers. */
	if (iptunnel_pull_header(skb, hdrlen, skb->protocol,
				 !net_eq(sock_net(pctx->sk), dev_net(pctx->dev))))
		return -1;

	netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n");

	/* Now that the UDP and the GTP header have been removed, set up the
	 * new network header. This is required by the upper layer to
	 * calculate the transport header.
	 */
	skb_reset_network_header(skb);

	skb->dev = pctx->dev;

	stats = this_cpu_ptr(pctx->dev->tstats);
	u64_stats_update_begin(&stats->syncp);
	stats->rx_packets++;
	stats->rx_bytes += skb->len;
	u64_stats_update_end(&stats->syncp);

	netif_rx(skb);
	return 0;
}

/* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
{
	unsigned int hdrlen = sizeof(struct udphdr) +
			      sizeof(struct gtp0_header);
	struct gtp0_header *gtp0;
	struct pdp_ctx *pctx;

	if (!pskb_may_pull(skb, hdrlen))
		return -1;

	gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr));

	if ((gtp0->flags >> 5) != GTP_V0)
		return 1;

	if (gtp0->type != GTP_TPDU)
		return 1;

	pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid));
	if (!pctx) {
		netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
		return 1;
	}

	return gtp_rx(pctx, skb, hdrlen, gtp->role);
}

static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
{
	unsigned int hdrlen = sizeof(struct udphdr) +
			      sizeof(struct gtp1_header);
	struct gtp1_header *gtp1;
	struct pdp_ctx *pctx;

	if (!pskb_may_pull(skb, hdrlen))
		return -1;

	gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));

	if ((gtp1->flags >> 5) != GTP_V1)
		return 1;

	if (gtp1->type != GTP_TPDU)
		return 1;

	/* From 29.060: "This field shall be present if and only if any one or
	 * more of the S, PN and E flags are set.".
	 *
	 * If any of the bit is set, then the remaining ones also have to be
	 * set.
	 */
	if (gtp1->flags & GTP1_F_MASK)
		hdrlen += 4;

	/* Make sure the header is larger enough, including extensions. */
	if (!pskb_may_pull(skb, hdrlen))
		return -1;

	gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));

	pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid));
	if (!pctx) {
		netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
		return 1;
	}

	return gtp_rx(pctx, skb, hdrlen, gtp->role);
}

static void gtp_encap_destroy(struct sock *sk)
{
	struct gtp_dev *gtp;

	gtp = rcu_dereference_sk_user_data(sk);
	if (gtp) {
		udp_sk(sk)->encap_type = 0;
		rcu_assign_sk_user_data(sk, NULL);
		sock_put(sk);
	}
}

static void gtp_encap_disable_sock(struct sock *sk)
{
	if (!sk)
		return;

	gtp_encap_destroy(sk);
}

static void gtp_encap_disable(struct gtp_dev *gtp)
{
	gtp_encap_disable_sock(gtp->sk0);
	gtp_encap_disable_sock(gtp->sk1u);
}

/* UDP encapsulation receive handler. See net/ipv4/udp.c.
 * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
 */
static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
	struct gtp_dev *gtp;
	int ret = 0;

	gtp = rcu_dereference_sk_user_data(sk);
	if (!gtp)
		return 1;

	netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);

	switch (udp_sk(sk)->encap_type) {
	case UDP_ENCAP_GTP0:
		netdev_dbg(gtp->dev, "received GTP0 packet\n");
		ret = gtp0_udp_encap_recv(gtp, skb);
		break;
	case UDP_ENCAP_GTP1U:
		netdev_dbg(gtp->dev, "received GTP1U packet\n");
		ret = gtp1u_udp_encap_recv(gtp, skb);
		break;
	default:
		ret = -1; /* Shouldn't happen. */
	}

	switch (ret) {
	case 1:
		netdev_dbg(gtp->dev, "pass up to the process\n");
		break;
	case 0:
		break;
	case -1:
		netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
		kfree_skb(skb);
		ret = 0;
		break;
	}

	return ret;
}

static int gtp_dev_init(struct net_device *dev)
{
	struct gtp_dev *gtp = netdev_priv(dev);

	gtp->dev = dev;

	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
	if (!dev->tstats)
		return -ENOMEM;

	return 0;
}

static void gtp_dev_uninit(struct net_device *dev)
{
	struct gtp_dev *gtp = netdev_priv(dev);

	gtp_encap_disable(gtp);
	free_percpu(dev->tstats);
}

static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
					   const struct sock *sk,
					   __be32 daddr)
{
	memset(fl4, 0, sizeof(*fl4));
	fl4->flowi4_oif		= sk->sk_bound_dev_if;
	fl4->daddr		= daddr;
	fl4->saddr		= inet_sk(sk)->inet_saddr;
	fl4->flowi4_tos		= RT_CONN_FLAGS(sk);
	fl4->flowi4_proto	= sk->sk_protocol;

	return ip_route_output_key(sock_net(sk), fl4);
}

static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
{
	int payload_len = skb->len;
	struct gtp0_header *gtp0;

	gtp0 = skb_push(skb, sizeof(*gtp0));

	gtp0->flags	= 0x1e; /* v0, GTP-non-prime. */
	gtp0->type	= GTP_TPDU;
	gtp0->length	= htons(payload_len);
	gtp0->seq	= htons((atomic_inc_return(&pctx->tx_seq) - 1) % 0xffff);
	gtp0->flow	= htons(pctx->u.v0.flow);
	gtp0->number	= 0xff;
	gtp0->spare[0]	= gtp0->spare[1] = gtp0->spare[2] = 0xff;
	gtp0->tid	= cpu_to_be64(pctx->u.v0.tid);
}

static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
{
	int payload_len = skb->len;
	struct gtp1_header *gtp1;

	gtp1 = skb_push(skb, sizeof(*gtp1));

	/* Bits    8  7  6  5  4  3  2	1
	 *	  +--+--+--+--+--+--+--+--+
	 *	  |version |PT| 0| E| S|PN|
	 *	  +--+--+--+--+--+--+--+--+
	 *	    0  0  1  1	1  0  0  0
	 */
	gtp1->flags	= 0x30; /* v1, GTP-non-prime. */
	gtp1->type	= GTP_TPDU;
	gtp1->length	= htons(payload_len);
	gtp1->tid	= htonl(pctx->u.v1.o_tei);

	/* TODO: Suppport for extension header, sequence number and N-PDU.
	 *	 Update the length field if any of them is available.
	 */
}

struct gtp_pktinfo {
	struct sock		*sk;
	struct iphdr		*iph;
	struct flowi4		fl4;
	struct rtable		*rt;
	struct pdp_ctx		*pctx;
	struct net_device	*dev;
	__be16			gtph_port;
};

static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo)
{
	switch (pktinfo->pctx->gtp_version) {
	case GTP_V0:
		pktinfo->gtph_port = htons(GTP0_PORT);
		gtp0_push_header(skb, pktinfo->pctx);
		break;
	case GTP_V1:
		pktinfo->gtph_port = htons(GTP1U_PORT);
		gtp1_push_header(skb, pktinfo->pctx);
		break;
	}
}

static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo,
					struct sock *sk, struct iphdr *iph,
					struct pdp_ctx *pctx, struct rtable *rt,
					struct flowi4 *fl4,
					struct net_device *dev)
{
	pktinfo->sk	= sk;
	pktinfo->iph	= iph;
	pktinfo->pctx	= pctx;
	pktinfo->rt	= rt;
	pktinfo->fl4	= *fl4;
	pktinfo->dev	= dev;
}

static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
			     struct gtp_pktinfo *pktinfo)
{
	struct gtp_dev *gtp = netdev_priv(dev);
	struct pdp_ctx *pctx;
	struct rtable *rt;
	struct flowi4 fl4;
	struct iphdr *iph;
	__be16 df;
	int mtu;

	/* Read the IP destination address and resolve the PDP context.
	 * Prepend PDP header with TEI/TID from PDP ctx.
	 */
	iph = ip_hdr(skb);
	if (gtp->role == GTP_ROLE_SGSN)
		pctx = ipv4_pdp_find(gtp, iph->saddr);
	else
		pctx = ipv4_pdp_find(gtp, iph->daddr);

	if (!pctx) {
		netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
			   &iph->daddr);
		return -ENOENT;
	}
	netdev_dbg(dev, "found PDP context %p\n", pctx);

	rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr);
	if (IS_ERR(rt)) {
		netdev_dbg(dev, "no route to SSGN %pI4\n",
			   &pctx->peer_addr_ip4.s_addr);
		dev->stats.tx_carrier_errors++;
		goto err;
	}

	if (rt->dst.dev == dev) {
		netdev_dbg(dev, "circular route to SSGN %pI4\n",
			   &pctx->peer_addr_ip4.s_addr);
		dev->stats.collisions++;
		goto err_rt;
	}

	skb_dst_drop(skb);

	/* This is similar to tnl_update_pmtu(). */
	df = iph->frag_off;
	if (df) {
		mtu = dst_mtu(&rt->dst) - dev->hard_header_len -
			sizeof(struct iphdr) - sizeof(struct udphdr);
		switch (pctx->gtp_version) {
		case GTP_V0:
			mtu -= sizeof(struct gtp0_header);
			break;
		case GTP_V1:
			mtu -= sizeof(struct gtp1_header);
			break;
		}
	} else {
		mtu = dst_mtu(&rt->dst);
	}

	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);

	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
	    mtu < ntohs(iph->tot_len)) {
		netdev_dbg(dev, "packet too big, fragmentation needed\n");
		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			  htonl(mtu));
		goto err_rt;
	}

	gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev);
	gtp_push_header(skb, pktinfo);

	return 0;
err_rt:
	ip_rt_put(rt);
err:
	return -EBADMSG;
}

static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
	unsigned int proto = ntohs(skb->protocol);
	struct gtp_pktinfo pktinfo;
	int err;

	/* Ensure there is sufficient headroom. */
	if (skb_cow_head(skb, dev->needed_headroom))
		goto tx_err;

	skb_reset_inner_headers(skb);

	/* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
	rcu_read_lock();
	switch (proto) {
	case ETH_P_IP:
		err = gtp_build_skb_ip4(skb, dev, &pktinfo);
		break;
	default:
		err = -EOPNOTSUPP;
		break;
	}
	rcu_read_unlock();

	if (err < 0)
		goto tx_err;

	switch (proto) {
	case ETH_P_IP:
		netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n",
			   &pktinfo.iph->saddr, &pktinfo.iph->daddr);
		udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb,
				    pktinfo.fl4.saddr, pktinfo.fl4.daddr,
				    pktinfo.iph->tos,
				    ip4_dst_hoplimit(&pktinfo.rt->dst),
				    0,
				    pktinfo.gtph_port, pktinfo.gtph_port,
				    true, false);
		break;
	}

	return NETDEV_TX_OK;
tx_err:
	dev->stats.tx_errors++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static const struct net_device_ops gtp_netdev_ops = {
	.ndo_init		= gtp_dev_init,
	.ndo_uninit		= gtp_dev_uninit,
	.ndo_start_xmit		= gtp_dev_xmit,
	.ndo_get_stats64	= ip_tunnel_get_stats64,
};

static void gtp_link_setup(struct net_device *dev)
{
	dev->netdev_ops		= &gtp_netdev_ops;
	dev->needs_free_netdev	= true;

	dev->hard_header_len = 0;
	dev->addr_len = 0;

	/* Zero header length. */
	dev->type = ARPHRD_NONE;
	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;

	dev->priv_flags	|= IFF_NO_QUEUE;
	dev->features	|= NETIF_F_LLTX;
	netif_keep_dst(dev);

	/* Assume largest header, ie. GTPv0. */
	dev->needed_headroom	= LL_MAX_HEADER +
				  sizeof(struct iphdr) +
				  sizeof(struct udphdr) +
				  sizeof(struct gtp0_header);
}

static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
static void gtp_hashtable_free(struct gtp_dev *gtp);
static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);

static int gtp_newlink(struct net *src_net, struct net_device *dev,
		       struct nlattr *tb[], struct nlattr *data[],
		       struct netlink_ext_ack *extack)
{
	struct gtp_dev *gtp;
	struct gtp_net *gn;
	int hashsize, err;

	if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1])
		return -EINVAL;

	gtp = netdev_priv(dev);

	err = gtp_encap_enable(gtp, data);
	if (err < 0)
		return err;

	if (!data[IFLA_GTP_PDP_HASHSIZE])
		hashsize = 1024;
	else
		hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);

	err = gtp_hashtable_new(gtp, hashsize);
	if (err < 0)
		goto out_encap;

	err = register_netdevice(dev);
	if (err < 0) {
		netdev_dbg(dev, "failed to register new netdev %d\n", err);
		goto out_hashtable;
	}

	gn = net_generic(dev_net(dev), gtp_net_id);
	list_add_rcu(&gtp->list, &gn->gtp_dev_list);

	netdev_dbg(dev, "registered new GTP interface\n");

	return 0;

out_hashtable:
	gtp_hashtable_free(gtp);
out_encap:
	gtp_encap_disable(gtp);
	return err;
}

static void gtp_dellink(struct net_device *dev, struct list_head *head)
{
	struct gtp_dev *gtp = netdev_priv(dev);

	gtp_encap_disable(gtp);
	gtp_hashtable_free(gtp);
	list_del_rcu(&gtp->list);
	unregister_netdevice_queue(dev, head);
}

static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
	[IFLA_GTP_FD0]			= { .type = NLA_U32 },
	[IFLA_GTP_FD1]			= { .type = NLA_U32 },
	[IFLA_GTP_PDP_HASHSIZE]		= { .type = NLA_U32 },
	[IFLA_GTP_ROLE]			= { .type = NLA_U32 },
};

static int gtp_validate(struct nlattr *tb[], struct nlattr *data[],
			struct netlink_ext_ack *extack)
{
	if (!data)
		return -EINVAL;

	return 0;
}

static size_t gtp_get_size(const struct net_device *dev)
{
	return nla_total_size(sizeof(__u32));	/* IFLA_GTP_PDP_HASHSIZE */
}

static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct gtp_dev *gtp = netdev_priv(dev);

	if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size))
		goto nla_put_failure;

	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static struct rtnl_link_ops gtp_link_ops __read_mostly = {
	.kind		= "gtp",
	.maxtype	= IFLA_GTP_MAX,
	.policy		= gtp_policy,
	.priv_size	= sizeof(struct gtp_dev),
	.setup		= gtp_link_setup,
	.validate	= gtp_validate,
	.newlink	= gtp_newlink,
	.dellink	= gtp_dellink,
	.get_size	= gtp_get_size,
	.fill_info	= gtp_fill_info,
};

static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
{
	int i;

	gtp->addr_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
	if (gtp->addr_hash == NULL)
		return -ENOMEM;

	gtp->tid_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
	if (gtp->tid_hash == NULL)
		goto err1;

	gtp->hash_size = hsize;

	for (i = 0; i < hsize; i++) {
		INIT_HLIST_HEAD(&gtp->addr_hash[i]);
		INIT_HLIST_HEAD(&gtp->tid_hash[i]);
	}
	return 0;
err1:
	kfree(gtp->addr_hash);
	return -ENOMEM;
}

static void gtp_hashtable_free(struct gtp_dev *gtp)
{
	struct pdp_ctx *pctx;
	int i;

	for (i = 0; i < gtp->hash_size; i++)
		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
			pdp_context_delete(pctx);

	synchronize_rcu();
	kfree(gtp->addr_hash);
	kfree(gtp->tid_hash);
}

static struct sock *gtp_encap_enable_socket(int fd, int type,
					    struct gtp_dev *gtp)
{
	struct udp_tunnel_sock_cfg tuncfg = {NULL};
	struct socket *sock;
	struct sock *sk;
	int err;

	pr_debug("enable gtp on %d, %d\n", fd, type);

	sock = sockfd_lookup(fd, &err);
	if (!sock) {
		pr_debug("gtp socket fd=%d not found\n", fd);
		return NULL;
	}

	if (sock->sk->sk_protocol != IPPROTO_UDP) {
		pr_debug("socket fd=%d not UDP\n", fd);
		sk = ERR_PTR(-EINVAL);
		goto out_sock;
	}

	if (rcu_dereference_sk_user_data(sock->sk)) {
		sk = ERR_PTR(-EBUSY);
		goto out_sock;
	}

	sk = sock->sk;
	sock_hold(sk);

	tuncfg.sk_user_data = gtp;
	tuncfg.encap_type = type;
	tuncfg.encap_rcv = gtp_encap_recv;
	tuncfg.encap_destroy = gtp_encap_destroy;

	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);

out_sock:
	sockfd_put(sock);
	return sk;
}

static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
{
	struct sock *sk1u = NULL;
	struct sock *sk0 = NULL;
	unsigned int role = GTP_ROLE_GGSN;

	if (data[IFLA_GTP_FD0]) {
		u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]);

		sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
		if (IS_ERR(sk0))
			return PTR_ERR(sk0);
	}

	if (data[IFLA_GTP_FD1]) {
		u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]);

		sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
		if (IS_ERR(sk1u)) {
			if (sk0)
				gtp_encap_disable_sock(sk0);
			return PTR_ERR(sk1u);
		}
	}

	if (data[IFLA_GTP_ROLE]) {
		role = nla_get_u32(data[IFLA_GTP_ROLE]);
		if (role > GTP_ROLE_SGSN)
			return -EINVAL;
	}

	gtp->sk0 = sk0;
	gtp->sk1u = sk1u;
	gtp->role = role;

	return 0;
}

static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
{
	struct gtp_dev *gtp = NULL;
	struct net_device *dev;
	struct net *net;

	/* Examine the link attributes and figure out which network namespace
	 * we are talking about.
	 */
	if (nla[GTPA_NET_NS_FD])
		net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD]));
	else
		net = get_net(src_net);

	if (IS_ERR(net))
		return NULL;

	/* Check if there's an existing gtpX device to configure */
	dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
	if (dev && dev->netdev_ops == &gtp_netdev_ops)
		gtp = netdev_priv(dev);

	put_net(net);
	return gtp;
}

static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
{
	pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
	pctx->af = AF_INET;
	pctx->peer_addr_ip4.s_addr =
		nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]);
	pctx->ms_addr_ip4.s_addr =
		nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);

	switch (pctx->gtp_version) {
	case GTP_V0:
		/* According to TS 09.60, sections 7.5.1 and 7.5.2, the flow
		 * label needs to be the same for uplink and downlink packets,
		 * so let's annotate this.
		 */
		pctx->u.v0.tid = nla_get_u64(info->attrs[GTPA_TID]);
		pctx->u.v0.flow = nla_get_u16(info->attrs[GTPA_FLOW]);
		break;
	case GTP_V1:
		pctx->u.v1.i_tei = nla_get_u32(info->attrs[GTPA_I_TEI]);
		pctx->u.v1.o_tei = nla_get_u32(info->attrs[GTPA_O_TEI]);
		break;
	default:
		break;
	}
}

static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
			struct genl_info *info)
{
	struct net_device *dev = gtp->dev;
	u32 hash_ms, hash_tid = 0;
	struct pdp_ctx *pctx;
	bool found = false;
	__be32 ms_addr;

	ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
	hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;

	hlist_for_each_entry_rcu(pctx, &gtp->addr_hash[hash_ms], hlist_addr) {
		if (pctx->ms_addr_ip4.s_addr == ms_addr) {
			found = true;
			break;
		}
	}

	if (found) {
		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
			return -EEXIST;
		if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
			return -EOPNOTSUPP;

		ipv4_pdp_fill(pctx, info);

		if (pctx->gtp_version == GTP_V0)
			netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n",
				   pctx->u.v0.tid, pctx);
		else if (pctx->gtp_version == GTP_V1)
			netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n",
				   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);

		return 0;

	}

	pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL);
	if (pctx == NULL)
		return -ENOMEM;

	sock_hold(sk);
	pctx->sk = sk;
	pctx->dev = gtp->dev;
	ipv4_pdp_fill(pctx, info);
	atomic_set(&pctx->tx_seq, 0);

	switch (pctx->gtp_version) {
	case GTP_V0:
		/* TS 09.60: "The flow label identifies unambiguously a GTP
		 * flow.". We use the tid for this instead, I cannot find a
		 * situation in which this doesn't unambiguosly identify the
		 * PDP context.
		 */
		hash_tid = gtp0_hashfn(pctx->u.v0.tid) % gtp->hash_size;
		break;
	case GTP_V1:
		hash_tid = gtp1u_hashfn(pctx->u.v1.i_tei) % gtp->hash_size;
		break;
	}

	hlist_add_head_rcu(&pctx->hlist_addr, &gtp->addr_hash[hash_ms]);
	hlist_add_head_rcu(&pctx->hlist_tid, &gtp->tid_hash[hash_tid]);

	switch (pctx->gtp_version) {
	case GTP_V0:
		netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
			   pctx->u.v0.tid, &pctx->peer_addr_ip4,
			   &pctx->ms_addr_ip4, pctx);
		break;
	case GTP_V1:
		netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
			   pctx->u.v1.i_tei, pctx->u.v1.o_tei,
			   &pctx->peer_addr_ip4, &pctx->ms_addr_ip4, pctx);
		break;
	}

	return 0;
}

static void pdp_context_free(struct rcu_head *head)
{
	struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head);

	sock_put(pctx->sk);
	kfree(pctx);
}

static void pdp_context_delete(struct pdp_ctx *pctx)
{
	hlist_del_rcu(&pctx->hlist_tid);
	hlist_del_rcu(&pctx->hlist_addr);
	call_rcu(&pctx->rcu_head, pdp_context_free);
}

static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
{
	unsigned int version;
	struct gtp_dev *gtp;
	struct sock *sk;
	int err;

	if (!info->attrs[GTPA_VERSION] ||
	    !info->attrs[GTPA_LINK] ||
	    !info->attrs[GTPA_PEER_ADDRESS] ||
	    !info->attrs[GTPA_MS_ADDRESS])
		return -EINVAL;

	version = nla_get_u32(info->attrs[GTPA_VERSION]);

	switch (version) {
	case GTP_V0:
		if (!info->attrs[GTPA_TID] ||
		    !info->attrs[GTPA_FLOW])
			return -EINVAL;
		break;
	case GTP_V1:
		if (!info->attrs[GTPA_I_TEI] ||
		    !info->attrs[GTPA_O_TEI])
			return -EINVAL;
		break;

	default:
		return -EINVAL;
	}

	rcu_read_lock();

	gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
	if (!gtp) {
		err = -ENODEV;
		goto out_unlock;
	}

	if (version == GTP_V0)
		sk = gtp->sk0;
	else if (version == GTP_V1)
		sk = gtp->sk1u;
	else
		sk = NULL;

	if (!sk) {
		err = -ENODEV;
		goto out_unlock;
	}

	err = ipv4_pdp_add(gtp, sk, info);

out_unlock:
	rcu_read_unlock();
	return err;
}

static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net,
					    struct nlattr *nla[])
{
	struct gtp_dev *gtp;

	gtp = gtp_find_dev(net, nla);
	if (!gtp)
		return ERR_PTR(-ENODEV);

	if (nla[GTPA_MS_ADDRESS]) {
		__be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]);

		return ipv4_pdp_find(gtp, ip);
	} else if (nla[GTPA_VERSION]) {
		u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]);

		if (gtp_version == GTP_V0 && nla[GTPA_TID])
			return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID]));
		else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI])
			return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI]));
	}

	return ERR_PTR(-EINVAL);
}

static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[])
{
	struct pdp_ctx *pctx;

	if (nla[GTPA_LINK])
		pctx = gtp_find_pdp_by_link(net, nla);
	else
		pctx = ERR_PTR(-EINVAL);

	if (!pctx)
		pctx = ERR_PTR(-ENOENT);

	return pctx;
}

static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
{
	struct pdp_ctx *pctx;
	int err = 0;

	if (!info->attrs[GTPA_VERSION])
		return -EINVAL;

	rcu_read_lock();

	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
	if (IS_ERR(pctx)) {
		err = PTR_ERR(pctx);
		goto out_unlock;
	}

	if (pctx->gtp_version == GTP_V0)
		netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
			   pctx->u.v0.tid, pctx);
	else if (pctx->gtp_version == GTP_V1)
		netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
			   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);

	pdp_context_delete(pctx);

out_unlock:
	rcu_read_unlock();
	return err;
}

static struct genl_family gtp_genl_family;

static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
			      u32 type, struct pdp_ctx *pctx)
{
	void *genlh;

	genlh = genlmsg_put(skb, snd_portid, snd_seq, &gtp_genl_family, 0,
			    type);
	if (genlh == NULL)
		goto nlmsg_failure;

	if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
	    nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
	    nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
		goto nla_put_failure;

	switch (pctx->gtp_version) {
	case GTP_V0:
		if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) ||
		    nla_put_u16(skb, GTPA_FLOW, pctx->u.v0.flow))
			goto nla_put_failure;
		break;
	case GTP_V1:
		if (nla_put_u32(skb, GTPA_I_TEI, pctx->u.v1.i_tei) ||
		    nla_put_u32(skb, GTPA_O_TEI, pctx->u.v1.o_tei))
			goto nla_put_failure;
		break;
	}
	genlmsg_end(skb, genlh);
	return 0;

nlmsg_failure:
nla_put_failure:
	genlmsg_cancel(skb, genlh);
	return -EMSGSIZE;
}

static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
{
	struct pdp_ctx *pctx = NULL;
	struct sk_buff *skb2;
	int err;

	if (!info->attrs[GTPA_VERSION])
		return -EINVAL;

	rcu_read_lock();

	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
	if (IS_ERR(pctx)) {
		err = PTR_ERR(pctx);
		goto err_unlock;
	}

	skb2 = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
	if (skb2 == NULL) {
		err = -ENOMEM;
		goto err_unlock;
	}

	err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid,
				 info->snd_seq, info->nlhdr->nlmsg_type, pctx);
	if (err < 0)
		goto err_unlock_free;

	rcu_read_unlock();
	return genlmsg_unicast(genl_info_net(info), skb2, info->snd_portid);

err_unlock_free:
	kfree_skb(skb2);
err_unlock:
	rcu_read_unlock();
	return err;
}

static int gtp_genl_dump_pdp(struct sk_buff *skb,
				struct netlink_callback *cb)
{
	struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
	struct net *net = sock_net(skb->sk);
	struct gtp_net *gn = net_generic(net, gtp_net_id);
	unsigned long tid = cb->args[1];
	int i, k = cb->args[0], ret;
	struct pdp_ctx *pctx;

	if (cb->args[4])
		return 0;

	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
		if (last_gtp && last_gtp != gtp)
			continue;
		else
			last_gtp = NULL;

		for (i = k; i < gtp->hash_size; i++) {
			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
				if (tid && tid != pctx->u.tid)
					continue;
				else
					tid = 0;

				ret = gtp_genl_fill_info(skb,
							 NETLINK_CB(cb->skb).portid,
							 cb->nlh->nlmsg_seq,
							 cb->nlh->nlmsg_type, pctx);
				if (ret < 0) {
					cb->args[0] = i;
					cb->args[1] = pctx->u.tid;
					cb->args[2] = (unsigned long)gtp;
					goto out;
				}
			}
		}
	}
	cb->args[4] = 1;
out:
	return skb->len;
}

static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
	[GTPA_LINK]		= { .type = NLA_U32, },
	[GTPA_VERSION]		= { .type = NLA_U32, },
	[GTPA_TID]		= { .type = NLA_U64, },
	[GTPA_PEER_ADDRESS]	= { .type = NLA_U32, },
	[GTPA_MS_ADDRESS]	= { .type = NLA_U32, },
	[GTPA_FLOW]		= { .type = NLA_U16, },
	[GTPA_NET_NS_FD]	= { .type = NLA_U32, },
	[GTPA_I_TEI]		= { .type = NLA_U32, },
	[GTPA_O_TEI]		= { .type = NLA_U32, },
};

static const struct genl_ops gtp_genl_ops[] = {
	{
		.cmd = GTP_CMD_NEWPDP,
		.doit = gtp_genl_new_pdp,
		.policy = gtp_genl_policy,
		.flags = GENL_ADMIN_PERM,
	},
	{
		.cmd = GTP_CMD_DELPDP,
		.doit = gtp_genl_del_pdp,
		.policy = gtp_genl_policy,
		.flags = GENL_ADMIN_PERM,
	},
	{
		.cmd = GTP_CMD_GETPDP,
		.doit = gtp_genl_get_pdp,
		.dumpit = gtp_genl_dump_pdp,
		.policy = gtp_genl_policy,
		.flags = GENL_ADMIN_PERM,
	},
};

static struct genl_family gtp_genl_family __ro_after_init = {
	.name		= "gtp",
	.version	= 0,
	.hdrsize	= 0,
	.maxattr	= GTPA_MAX,
	.netnsok	= true,
	.module		= THIS_MODULE,
	.ops		= gtp_genl_ops,
	.n_ops		= ARRAY_SIZE(gtp_genl_ops),
};

static int __net_init gtp_net_init(struct net *net)
{
	struct gtp_net *gn = net_generic(net, gtp_net_id);

	INIT_LIST_HEAD(&gn->gtp_dev_list);
	return 0;
}

static void __net_exit gtp_net_exit(struct net *net)
{
	struct gtp_net *gn = net_generic(net, gtp_net_id);
	struct gtp_dev *gtp;
	LIST_HEAD(list);

	rtnl_lock();
	list_for_each_entry(gtp, &gn->gtp_dev_list, list)
		gtp_dellink(gtp->dev, &list);

	unregister_netdevice_many(&list);
	rtnl_unlock();
}

static struct pernet_operations gtp_net_ops = {
	.init	= gtp_net_init,
	.exit	= gtp_net_exit,
	.id	= &gtp_net_id,
	.size	= sizeof(struct gtp_net),
};

static int __init gtp_init(void)
{
	int err;

	get_random_bytes(&gtp_h_initval, sizeof(gtp_h_initval));

	err = rtnl_link_register(&gtp_link_ops);
	if (err < 0)
		goto error_out;

	err = genl_register_family(&gtp_genl_family);
	if (err < 0)
		goto unreg_rtnl_link;

	err = register_pernet_subsys(&gtp_net_ops);
	if (err < 0)
		goto unreg_genl_family;

	pr_info("GTP module loaded (pdp ctx size %zd bytes)\n",
		sizeof(struct pdp_ctx));
	return 0;

unreg_genl_family:
	genl_unregister_family(&gtp_genl_family);
unreg_rtnl_link:
	rtnl_link_unregister(&gtp_link_ops);
error_out:
	pr_err("error loading GTP module loaded\n");
	return err;
}
late_initcall(gtp_init);

static void __exit gtp_fini(void)
{
	unregister_pernet_subsys(&gtp_net_ops);
	genl_unregister_family(&gtp_genl_family);
	rtnl_link_unregister(&gtp_link_ops);

	pr_info("GTP module unloaded\n");
}
module_exit(gtp_fini);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>");
MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("gtp");
MODULE_ALIAS_GENL_FAMILY("gtp");