public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob fb3f790b04efdc87dce177f53fb2f279e4825ccc 35743 bytes (raw)

   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
 
// SPDX-License-Identifier: AGPL-3.0-or-later

/* PASST - Plug A Simple Socket Transport
 *  for qemu/UNIX domain socket mode
 *
 * PASTA - Pack A Subtle Tap Abstraction
 *  for network namespace/tap device mode
 *
 * udp.c - UDP L2-L4 translation routines
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

/**
 * DOC: Theory of Operation
 *
 *
 * For UDP, a reduced version of port-based connection tracking is implemented
 * with two purposes:
 * - binding ephemeral ports when they're used as source port by the guest, so
 *   that replies on those ports can be forwarded back to the guest, with a
 *   fixed timeout for this binding
 * - packets received from the local host get their source changed to a local
 *   address (gateway address) so that they can be forwarded to the guest, and
 *   packets sent as replies by the guest need their destination address to
 *   be changed back to the address of the local host. This is dynamic to allow
 *   connections from the gateway as well, and uses the same fixed 180s timeout
 * 
 * Sockets for bound ports are created at initialisation time, one set for IPv4
 * and one for IPv6.
 *
 * Packets are forwarded back and forth, by prepending and stripping UDP headers
 * in the obvious way, with no port translation.
 *
 * In PASTA mode, the L2-L4 translation is skipped for connections to ports
 * bound between namespaces using the loopback interface, messages are directly
 * transferred between L4 sockets instead. These are called spliced connections
 * for consistency with the TCP implementation, but the splice() syscall isn't
 * actually used as it wouldn't make sense for datagram-based connections: a
 * pair of recvmmsg() and sendmmsg() deals with this case.
 *
 * The connection tracking for PASTA mode is slightly complicated by the absence
 * of actual connections, see struct udp_splice_port, and these examples:
 *
 * - from init to namespace:
 *
 *   - forward direction: 127.0.0.1:5000 -> 127.0.0.1:80 in init from socket s,
 *     with epoll reference: index = 80, splice = 1, orig = 1, ns = 0
 *     - if udp_splice_ns[V4][5000].sock:
 *       - send packet to udp_splice_ns[V4][5000].sock, with destination port
 *         80
 *     - otherwise:
 *       - create new socket udp_splice_ns[V4][5000].sock
 *       - bind in namespace to 127.0.0.1:5000
 *       - add to epoll with reference: index = 5000, splice = 1, orig = 0,
 *         ns = 1
 *     - update udp_splice_init[V4][80].ts and udp_splice_ns[V4][5000].ts with
 *       current time
 *
 *   - reverse direction: 127.0.0.1:80 -> 127.0.0.1:5000 in namespace socket s,
 *     having epoll reference: index = 5000, splice = 1, orig = 0, ns = 1
 *     - if udp_splice_init[V4][80].sock:
 *       - send to udp_splice_init[V4][80].sock, with destination port 5000
 *       - update udp_splice_init[V4][80].ts and udp_splice_ns[V4][5000].ts with
 *         current time
 *     - otherwise, discard
 *
 * - from namespace to init:
 *
 *   - forward direction: 127.0.0.1:2000 -> 127.0.0.1:22 in namespace from
 *     socket s, with epoll reference: index = 22, splice = 1, orig = 1, ns = 1
 *     - if udp4_splice_init[V4][2000].sock:
 *       - send packet to udp_splice_init[V4][2000].sock, with destination
 *         port 22
 *     - otherwise:
 *       - create new socket udp_splice_init[V4][2000].sock
 *       - bind in init to 127.0.0.1:2000
 *       - add to epoll with reference: index = 2000, splice = 1, orig = 0,
 *         ns = 0
 *     - update udp_splice_ns[V4][22].ts and udp_splice_init[V4][2000].ts with
 *       current time
 *
 *   - reverse direction: 127.0.0.1:22 -> 127.0.0.1:2000 in init from socket s,
 *     having epoll reference: index = 2000, splice = 1, orig = 0, ns = 0
 *   - if udp_splice_ns[V4][22].sock:
 *     - send to udp_splice_ns[V4][22].sock, with destination port 2000
 *     - update udp_splice_ns[V4][22].ts and udp_splice_init[V4][2000].ts with
 *       current time
 *   - otherwise, discard
 */

#include <sched.h>
#include <stdio.h>
#include <errno.h>
#include <limits.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/udp.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/uio.h>
#include <unistd.h>
#include <time.h>
#include <assert.h>

#include "checksum.h"
#include "util.h"
#include "passt.h"
#include "tap.h"
#include "pcap.h"
#include "log.h"

#define UDP_CONN_TIMEOUT	180 /* s, timeout for ephemeral or local bind */
#define UDP_MAX_FRAMES		32  /* max # of frames to receive at once */

/**
 * struct udp_tap_port - Port tracking based on tap-facing source port
 * @sock:	Socket bound to source port used as index
 * @flags:	Flags for local bind, loopback address/unicast address as source
 * @ts:		Activity timestamp from tap, used for socket aging
 */
struct udp_tap_port {
	int sock;
	uint8_t flags;
#define PORT_LOCAL	BIT(0)
#define PORT_LOOPBACK	BIT(1)
#define PORT_GUA	BIT(2)

	time_t ts;
};

/**
 * struct udp_splice_port - Bound socket for spliced communication
 * @sock:	Socket bound to index port
 * @ts:		Activity timestamp
 */
struct udp_splice_port {
	int sock;
	time_t ts;
};

/* Port tracking, arrays indexed by packet source port (host order) */
static struct udp_tap_port	udp_tap_map	[IP_VERSIONS][NUM_PORTS];

/* "Spliced" sockets indexed by bound port (host order) */
static struct udp_splice_port udp_splice_ns  [IP_VERSIONS][NUM_PORTS];
static struct udp_splice_port udp_splice_init[IP_VERSIONS][NUM_PORTS];

enum udp_act_type {
	UDP_ACT_TAP,
	UDP_ACT_SPLICE_NS,
	UDP_ACT_SPLICE_INIT,
	UDP_ACT_TYPE_MAX,
};

/* Activity-based aging for bindings */
static uint8_t udp_act[IP_VERSIONS][UDP_ACT_TYPE_MAX][DIV_ROUND_UP(NUM_PORTS, 8)];

/* Static buffers */

/**
 * udp4_l2_buf_t - Pre-cooked IPv4 packet buffers for tap connections
 * @s_in:	Source socket address, filled in by recvmmsg()
 * @psum:	Partial IP header checksum (excluding tot_len and saddr)
 * @vnet_len:	4-byte qemu vnet buffer length descriptor, only for passt mode
 * @eh:		Pre-filled Ethernet header
 * @iph:	Pre-filled IP header (except for tot_len and saddr)
 * @uh:		Headroom for UDP header
 * @data:	Storage for UDP payload
 */
static struct udp4_l2_buf_t {
	struct sockaddr_in s_in;
	uint32_t psum;

	uint32_t vnet_len;
	struct ethhdr eh;
	struct iphdr iph;
	struct udphdr uh;
	uint8_t data[USHRT_MAX -
		     (sizeof(struct iphdr) + sizeof(struct udphdr))];
} __attribute__ ((packed, aligned(__alignof__(unsigned int))))
udp4_l2_buf[UDP_MAX_FRAMES];

/**
 * udp6_l2_buf_t - Pre-cooked IPv6 packet buffers for tap connections
 * @s_in6:	Source socket address, filled in by recvmmsg()
 * @vnet_len:	4-byte qemu vnet buffer length descriptor, only for passt mode
 * @eh:		Pre-filled Ethernet header
 * @ip6h:	Pre-filled IP header (except for payload_len and addresses)
 * @uh:		Headroom for UDP header
 * @data:	Storage for UDP payload
 */
struct udp6_l2_buf_t {
	struct sockaddr_in6 s_in6;
#ifdef __AVX2__
	/* Align ip6h to 32-byte boundary. */
	uint8_t pad[64 - (sizeof(struct sockaddr_in6) + sizeof(struct ethhdr) +
			  sizeof(uint32_t))];
#endif

	uint32_t vnet_len;
	struct ethhdr eh;
	struct ipv6hdr ip6h;
	struct udphdr uh;
	uint8_t data[USHRT_MAX -
		     (sizeof(struct ipv6hdr) + sizeof(struct udphdr))];
#ifdef __AVX2__
} __attribute__ ((packed, aligned(32)))
#else
} __attribute__ ((packed, aligned(__alignof__(unsigned int))))
#endif
udp6_l2_buf[UDP_MAX_FRAMES];

/* recvmmsg()/sendmmsg() data for tap */
static struct iovec	udp4_l2_iov_sock	[UDP_MAX_FRAMES];
static struct iovec	udp6_l2_iov_sock	[UDP_MAX_FRAMES];

static struct iovec	udp4_l2_iov_tap		[UDP_MAX_FRAMES];
static struct iovec	udp6_l2_iov_tap		[UDP_MAX_FRAMES];

static struct mmsghdr	udp4_l2_mh_sock		[UDP_MAX_FRAMES];
static struct mmsghdr	udp6_l2_mh_sock		[UDP_MAX_FRAMES];

static struct mmsghdr	udp4_l2_mh_tap		[UDP_MAX_FRAMES];
static struct mmsghdr	udp6_l2_mh_tap		[UDP_MAX_FRAMES];

/* recvmmsg()/sendmmsg() data for "spliced" connections */
static struct iovec	udp4_iov_splice		[UDP_MAX_FRAMES];
static struct iovec	udp6_iov_splice		[UDP_MAX_FRAMES];

static struct sockaddr_in udp4_localname = {
	.sin_family = AF_INET,
	.sin_addr = IN4ADDR_LOOPBACK_INIT,
};
static struct sockaddr_in6 udp6_localname = {
	.sin6_family = AF_INET6,
	.sin6_addr = IN6ADDR_LOOPBACK_INIT,
};

static struct mmsghdr	udp4_mh_splice		[UDP_MAX_FRAMES];
static struct mmsghdr	udp6_mh_splice		[UDP_MAX_FRAMES];

/**
 * udp_invert_portmap() - Compute reverse port translations for return packets
 * @fwd:	Port forwarding configuration to compute reverse map for
 */
static void udp_invert_portmap(struct udp_port_fwd *fwd)
{
	int i;

	assert(ARRAY_SIZE(fwd->f.delta) == ARRAY_SIZE(fwd->rdelta));
	for (i = 0; i < ARRAY_SIZE(fwd->f.delta); i++) {
		in_port_t delta = fwd->f.delta[i];

		if (delta)
			fwd->rdelta[(in_port_t)i + delta] = NUM_PORTS - delta;
	}
}

/**
 * udp_update_check4() - Update checksum with variable parts from stored one
 * @buf:	L2 packet buffer with final IPv4 header
 */
static void udp_update_check4(struct udp4_l2_buf_t *buf)
{
	uint32_t sum = buf->psum;

	sum += buf->iph.tot_len;
	sum += (buf->iph.saddr >> 16) & 0xffff;
	sum += buf->iph.saddr & 0xffff;

	buf->iph.check = (uint16_t)~csum_fold(sum);
}

/**
 * udp_update_l2_buf() - Update L2 buffers with Ethernet and IPv4 addresses
 * @eth_d:	Ethernet destination address, NULL if unchanged
 * @eth_s:	Ethernet source address, NULL if unchanged
 * @ip_da:	Pointer to IPv4 destination address, NULL if unchanged
 */
void udp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s,
		       const struct in_addr *ip_da)
{
	int i;

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		struct udp4_l2_buf_t *b4 = &udp4_l2_buf[i];
		struct udp6_l2_buf_t *b6 = &udp6_l2_buf[i];

		if (eth_d) {
			memcpy(b4->eh.h_dest, eth_d, ETH_ALEN);
			memcpy(b6->eh.h_dest, eth_d, ETH_ALEN);
		}

		if (eth_s) {
			memcpy(b4->eh.h_source, eth_s, ETH_ALEN);
			memcpy(b6->eh.h_source, eth_s, ETH_ALEN);
		}

		if (ip_da) {
			b4->iph.daddr = ip_da->s_addr;
			if (!i) {
				b4->iph.saddr = 0;
				b4->iph.tot_len = 0;
				b4->iph.check = 0;
				b4->psum = sum_16b(&b4->iph, 20);
			} else {
				b4->psum = udp4_l2_buf[0].psum;
			}
		}
	}
}

/**
 * udp_sock4_iov_init() - Initialise scatter-gather L2 buffers for IPv4 sockets
 * @c:		Execution context
 */
static void udp_sock4_iov_init(const struct ctx *c)
{
	struct mmsghdr *h;
	int i;

	for (i = 0; i < ARRAY_SIZE(udp4_l2_buf); i++) {
		udp4_l2_buf[i] = (struct udp4_l2_buf_t) {
			.eh = L2_BUF_ETH_IP4_INIT,
			.iph = L2_BUF_IP4_INIT(IPPROTO_UDP)
		};
	}

	for (i = 0, h = udp4_l2_mh_sock; i < UDP_MAX_FRAMES; i++, h++) {
		struct msghdr *mh = &h->msg_hdr;

		mh->msg_name			= &udp4_l2_buf[i].s_in;
		mh->msg_namelen			= sizeof(udp4_l2_buf[i].s_in);

		udp4_l2_iov_sock[i].iov_base	= udp4_l2_buf[i].data;
		udp4_l2_iov_sock[i].iov_len	= sizeof(udp4_l2_buf[i].data);
		mh->msg_iov			= &udp4_l2_iov_sock[i];
		mh->msg_iovlen			= 1;
	}

	for (i = 0, h = udp4_l2_mh_tap; i < UDP_MAX_FRAMES; i++, h++) {
		struct msghdr *mh = &h->msg_hdr;

		if (c->mode == MODE_PASTA)
			udp4_l2_iov_tap[i].iov_base	= &udp4_l2_buf[i].eh;
		else
			udp4_l2_iov_tap[i].iov_base	= &udp4_l2_buf[i].vnet_len;

		mh->msg_iov			= &udp4_l2_iov_tap[i];
		mh->msg_iovlen			= 1;
	}
}

/**
 * udp_sock6_iov_init() - Initialise scatter-gather L2 buffers for IPv6 sockets
 * @c:		Execution context
 */
static void udp_sock6_iov_init(const struct ctx *c)
{
	struct mmsghdr *h;
	int i;

	for (i = 0; i < ARRAY_SIZE(udp6_l2_buf); i++) {
		udp6_l2_buf[i] = (struct udp6_l2_buf_t) {
			.eh = L2_BUF_ETH_IP6_INIT,
			.ip6h = L2_BUF_IP6_INIT(IPPROTO_UDP)
		};
	}

	for (i = 0, h = udp6_l2_mh_sock; i < UDP_MAX_FRAMES; i++, h++) {
		struct msghdr *mh = &h->msg_hdr;

		mh->msg_name			= &udp6_l2_buf[i].s_in6;
		mh->msg_namelen			= sizeof(struct sockaddr_in6);

		udp6_l2_iov_sock[i].iov_base	= udp6_l2_buf[i].data;
		udp6_l2_iov_sock[i].iov_len	= sizeof(udp6_l2_buf[i].data);
		mh->msg_iov			= &udp6_l2_iov_sock[i];
		mh->msg_iovlen			= 1;
	}

	for (i = 0, h = udp6_l2_mh_tap; i < UDP_MAX_FRAMES; i++, h++) {
		struct msghdr *mh = &h->msg_hdr;

		if (c->mode == MODE_PASTA)
			udp6_l2_iov_tap[i].iov_base	= &udp6_l2_buf[i].eh;
		else
			udp6_l2_iov_tap[i].iov_base	= &udp6_l2_buf[i].vnet_len;

		mh->msg_iov			= &udp6_l2_iov_tap[i];
		mh->msg_iovlen			= 1;
	}
}

/**
 * udp_splice_new() - Create and prepare socket for "spliced" binding
 * @c:		Execution context
 * @v6:		Set for IPv6 sockets
 * @src:	Source port of original connection, host order
 * @splice:	UDP_BACK_TO_INIT from init, UDP_BACK_TO_NS from namespace
 *
 * Return: prepared socket, negative error code on failure
 *
 * #syscalls:pasta getsockname
 */
int udp_splice_new(const struct ctx *c, int v6, in_port_t src, bool ns)
{
	struct epoll_event ev = { .events = EPOLLIN | EPOLLRDHUP | EPOLLHUP };
	union epoll_ref ref = { .r.proto = IPPROTO_UDP,
				.r.p.udp.udp = { .splice = true, .ns = ns,
						 .v6 = v6, .port = src }
			      };
	struct udp_splice_port *sp;
	int act, s;

	if (ns) {
		sp = &udp_splice_ns[v6 ? V6 : V4][src];
		act = UDP_ACT_SPLICE_NS;
	} else {
		sp = &udp_splice_init[v6 ? V6 : V4][src];
		act = UDP_ACT_SPLICE_INIT;
	}

	s = socket(v6 ? AF_INET6 : AF_INET, SOCK_DGRAM | SOCK_NONBLOCK,
		   IPPROTO_UDP);

	if (s > SOCKET_MAX) {
		close(s);
		return -EIO;
	}

	if (s < 0)
		return s;

	ref.r.s = s;

	if (v6) {
		struct sockaddr_in6 addr6 = {
			.sin6_family = AF_INET6,
			.sin6_port = htons(src),
			.sin6_addr = IN6ADDR_LOOPBACK_INIT,
		};
		if (bind(s, (struct sockaddr *)&addr6, sizeof(addr6)))
			goto fail;
	} else {
		struct sockaddr_in addr4 = {
			.sin_family = AF_INET,
			.sin_port = htons(src),
			.sin_addr = { .s_addr = htonl(INADDR_LOOPBACK) },
		};
		if (bind(s, (struct sockaddr *)&addr4, sizeof(addr4)))
			goto fail;
	}

	sp->sock = s;
	bitmap_set(udp_act[v6 ? V6 : V4][act], src);

	ev.data.u64 = ref.u64;
	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, s, &ev);
	return s;

fail:
	close(s);
	return -1;
}

/**
 * struct udp_splice_new_ns_arg - Arguments for udp_splice_new_ns()
 * @c:		Execution context
 * @v6:		Set for IPv6
 * @src:	Source port of originating datagram, host order
 * @dst:	Destination port of originating datagram, host order
 * @s:		Newly created socket or negative error code
 */
struct udp_splice_new_ns_arg {
	const struct ctx *c;
	int v6;
	in_port_t src;
	int s;
};

/**
 * udp_splice_new_ns() - Enter namespace and call udp_splice_new()
 * @arg:	See struct udp_splice_new_ns_arg
 *
 * Return: 0
 */
static int udp_splice_new_ns(void *arg)
{
	struct udp_splice_new_ns_arg *a;

	a = (struct udp_splice_new_ns_arg *)arg;

	if (ns_enter(a->c))
		return 0;

	a->s = udp_splice_new(a->c, a->v6, a->src, true);

	return 0;
}

/**
 * udp_mmh_splice_port() - Is source address of message suitable for splicing?
 * @v6:		Is @sa a sockaddr_in6 (otherwise sockaddr_in)?
 * @mmh:	mmsghdr of incoming message
 *
 * Return: if @sa refers to localhost (127.0.0.1 or ::1) the port from
 *         @sa in host order, otherwise -1.
 */
static int udp_mmh_splice_port(bool v6, const struct mmsghdr *mmh)
{
	const struct sockaddr_in6 *sa6 = mmh->msg_hdr.msg_name;
	const struct sockaddr_in *sa4 = mmh->msg_hdr.msg_name;

	if (v6 && IN6_IS_ADDR_LOOPBACK(&sa6->sin6_addr))
		return ntohs(sa6->sin6_port);

	if (!v6 && IN4_IS_ADDR_LOOPBACK(&sa4->sin_addr))
		return ntohs(sa4->sin_port);

	return -1;
}

/**
 * udp_splice_sendfrom() - Send datagrams from given port to given port
 * @c:		Execution context
 * @start:	Index of first datagram in udp[46]_l2_buf
 * @n:		Number of datagrams to send
 * @src:	Datagrams will be sent from this port (on origin side)
 * @dst:	Datagrams will be send to this port (on destination side)
 * @v6:		Send as IPv6?
 * @from_ns:	If true send from pasta ns to init, otherwise reverse
 * @allow_new:	If true create sending socket if needed, if false discard
 *              if no sending socket is available
 * @now:	Timestamp
 */
static void udp_splice_sendfrom(const struct ctx *c, unsigned start, unsigned n,
				in_port_t src, in_port_t dst,
				bool v6, bool from_ns, bool allow_new,
				const struct timespec *now)
{
	struct mmsghdr *mmh_recv, *mmh_send;
	unsigned int i;
	int s;

	if (v6) {
		mmh_recv = udp6_l2_mh_sock;
		mmh_send = udp6_mh_splice;
	} else {
		mmh_recv = udp4_l2_mh_sock;
		mmh_send = udp4_mh_splice;
	}

	if (from_ns) {
		src += c->udp.fwd_in.rdelta[src];
		s = udp_splice_init[v6][src].sock;
		if (!s && allow_new)
			s = udp_splice_new(c, v6, src, false);

		if (s < 0)
			return;

		udp_splice_ns[v6][dst].ts = now->tv_sec;
		udp_splice_init[v6][src].ts = now->tv_sec;
	} else {
		src += c->udp.fwd_out.rdelta[src];
		s = udp_splice_ns[v6][src].sock;
		if (!s && allow_new) {
			struct udp_splice_new_ns_arg arg = {
				c, v6, src, -1,
			};

			NS_CALL(udp_splice_new_ns, &arg);
			s = arg.s;
		}
		if (s < 0)
			return;

		udp_splice_init[v6][dst].ts = now->tv_sec;
		udp_splice_ns[v6][src].ts = now->tv_sec;
	}

	for (i = start; i < start + n; i++)
		mmh_send[i].msg_hdr.msg_iov->iov_len = mmh_recv[i].msg_len;

	sendmmsg(s, mmh_send + start, n, MSG_NOSIGNAL);
}

/**
 * udp_update_hdr4() - Update headers for one IPv4 datagram
 * @c:		Execution context
 * @n:		Index of buffer in udp4_l2_buf pool
 * @dstport:	Destination port number
 * @now:	Current timestamp
 *
 * Return: size of tap frame with headers
 */
static size_t udp_update_hdr4(const struct ctx *c, int n, in_port_t dstport,
			      const struct timespec *now)
{
	struct udp4_l2_buf_t *b = &udp4_l2_buf[n];
	size_t ip_len, buf_len;
	in_port_t src_port;

	ip_len = udp4_l2_mh_sock[n].msg_len + sizeof(b->iph) + sizeof(b->uh);

	b->iph.tot_len = htons(ip_len);

	src_port = ntohs(b->s_in.sin_port);

	if (!IN4_IS_ADDR_UNSPECIFIED(&c->ip4.dns_match) &&
	    IN4_ARE_ADDR_EQUAL(&b->s_in.sin_addr, &c->ip4.dns_host) &&
	    src_port == 53) {
		b->iph.saddr = c->ip4.dns_match.s_addr;
	} else if (IN4_IS_ADDR_LOOPBACK(&b->s_in.sin_addr) ||
		   IN4_IS_ADDR_UNSPECIFIED(&b->s_in.sin_addr)||
		   IN4_ARE_ADDR_EQUAL(&b->s_in.sin_addr, &c->ip4.addr_seen)) {
		b->iph.saddr = c->ip4.gw.s_addr;
		udp_tap_map[V4][src_port].ts = now->tv_sec;
		udp_tap_map[V4][src_port].flags |= PORT_LOCAL;

		if (IN4_ARE_ADDR_EQUAL(&b->s_in.sin_addr.s_addr, &c->ip4.addr_seen))
			udp_tap_map[V4][src_port].flags &= ~PORT_LOOPBACK;
		else
			udp_tap_map[V4][src_port].flags |= PORT_LOOPBACK;

		bitmap_set(udp_act[V4][UDP_ACT_TAP], src_port);
	} else {
		b->iph.saddr = b->s_in.sin_addr.s_addr;
	}

	udp_update_check4(b);
	b->uh.source = b->s_in.sin_port;
	b->uh.dest = htons(dstport);
	b->uh.len = htons(udp4_l2_mh_sock[n].msg_len + sizeof(b->uh));

	buf_len = ip_len + sizeof(b->eh);

	if (c->mode == MODE_PASST) {
		b->vnet_len = htonl(buf_len);
		buf_len += sizeof(b->vnet_len);
	}

	return buf_len;
}

/**
 * udp_update_hdr6() - Update headers for one IPv6 datagram
 * @c:		Execution context
 * @n:		Index of buffer in udp6_l2_buf pool
 * @dstport:	Destination port number
 * @now:	Current timestamp
 *
 * Return: size of tap frame with headers
 */
static size_t udp_update_hdr6(const struct ctx *c, int n, in_port_t dstport,
			      const struct timespec *now)
{
	struct udp6_l2_buf_t *b = &udp6_l2_buf[n];
	size_t ip_len, buf_len;
	struct in6_addr *src;
	in_port_t src_port;

	src = &b->s_in6.sin6_addr;
	src_port = ntohs(b->s_in6.sin6_port);

	ip_len = udp6_l2_mh_sock[n].msg_len + sizeof(b->ip6h) + sizeof(b->uh);

	b->ip6h.payload_len = htons(udp6_l2_mh_sock[n].msg_len + sizeof(b->uh));

	if (IN6_IS_ADDR_LINKLOCAL(src)) {
		b->ip6h.daddr = c->ip6.addr_ll_seen;
		b->ip6h.saddr = b->s_in6.sin6_addr;
	} else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.dns_match) &&
		   IN6_ARE_ADDR_EQUAL(src, &c->ip6.dns_host) &&
		   src_port == 53) {
		b->ip6h.daddr = c->ip6.addr_seen;
		b->ip6h.saddr = c->ip6.dns_match;
	} else if (IN6_IS_ADDR_LOOPBACK(src)			||
		   IN6_ARE_ADDR_EQUAL(src, &c->ip6.addr_seen)	||
		   IN6_ARE_ADDR_EQUAL(src, &c->ip6.addr)) {
		b->ip6h.daddr = c->ip6.addr_ll_seen;

		if (IN6_IS_ADDR_LINKLOCAL(&c->ip6.gw))
			b->ip6h.saddr = c->ip6.gw;
		else
			b->ip6h.saddr = c->ip6.addr_ll;

		udp_tap_map[V6][src_port].ts = now->tv_sec;
		udp_tap_map[V6][src_port].flags |= PORT_LOCAL;

		if (IN6_IS_ADDR_LOOPBACK(src))
			udp_tap_map[V6][src_port].flags |= PORT_LOOPBACK;
		else
			udp_tap_map[V6][src_port].flags &= ~PORT_LOOPBACK;

		if (IN6_ARE_ADDR_EQUAL(src, &c->ip6.addr))
			udp_tap_map[V6][src_port].flags |= PORT_GUA;
		else
			udp_tap_map[V6][src_port].flags &= ~PORT_GUA;

		bitmap_set(udp_act[V6][UDP_ACT_TAP], src_port);
	} else {
		b->ip6h.daddr = c->ip6.addr_seen;
		b->ip6h.saddr = b->s_in6.sin6_addr;
	}

	b->uh.source = b->s_in6.sin6_port;
	b->uh.dest = htons(dstport);
	b->uh.len = b->ip6h.payload_len;

	b->ip6h.hop_limit = IPPROTO_UDP;
	b->ip6h.version = b->ip6h.nexthdr = b->uh.check = 0;
	b->uh.check = csum(&b->ip6h, ip_len, 0);
	b->ip6h.version = 6;
	b->ip6h.nexthdr = IPPROTO_UDP;
	b->ip6h.hop_limit = 255;

	buf_len = ip_len + sizeof(b->eh);

	if (c->mode == MODE_PASST) {
		b->vnet_len = htonl(buf_len);
		buf_len += sizeof(b->vnet_len);
	}

	return buf_len;
}

/**
 * udp_tap_send_pasta() - Send datagrams to the pasta tap interface
 * @c:		Execution context
 * @mmh:	Array of message headers to send
 * @n:		Number of message headers to send
 *
 * #syscalls:pasta write
 */
static void udp_tap_send_pasta(const struct ctx *c, struct mmsghdr *mmh,
			       unsigned int n)
{
	unsigned int i, j;

	for (i = 0; i < n; i++) {
		for (j = 0; j < mmh[i].msg_hdr.msg_iovlen; j++) {
			struct iovec *iov = &mmh[i].msg_hdr.msg_iov[j];

			/* We can't use writev() because the tap
			 * character device relies on the write()
			 * boundaries to discern frame boundaries
			 */
			if (write(c->fd_tap, iov->iov_base, iov->iov_len) < 0)
				debug("tap write: %s", strerror(errno));
			else
				pcap(iov->iov_base, iov->iov_len);
		}
	}
}

/**
 * udp_tap_send_passt() - Send datagrams to the passt tap interface
 * @c:		Execution context
 * @mmh:	Array of message headers to send
 * @n:		Number of message headers to send
 *
 * #syscalls:passt sendmmsg sendmsg
 */
static void udp_tap_send_passt(const struct ctx *c, struct mmsghdr *mmh, int n)
{
	struct msghdr *last_mh;
	ssize_t missing = 0;
	size_t msg_len = 0;
	unsigned int i;
	int ret;

	ret = sendmmsg(c->fd_tap, mmh, n, MSG_NOSIGNAL | MSG_DONTWAIT);
	if (ret <= 0)
		return;

	/* If we lose some messages to sendmmsg() here, fine, it's UDP. However,
	 * the last message needs to be delivered completely, otherwise qemu
	 * will fail to reassemble the next message and close the connection. Go
	 * through headers from the last sent message, counting bytes, and, if
	 * and as soon as we see more bytes than sendmmsg() sent, re-send the
	 * rest with a blocking call.
	 *
	 * In pictures, given this example:
	 *
	 *				 	iov #0  iov #1  iov #2  iov #3
	 * tap_mmh[ret - 1].msg_hdr:		....    ......  .....   ......
	 * tap_mmh[ret - 1].msg_len:	7	....    ...
	 *
	 * when 'msglen' reaches:	10		      ^
	 * and 'missing' below is:	3	           ---
	 *
	 * re-send everything from here:		   ^--  -----   ------
	 */
	last_mh = &mmh[ret - 1].msg_hdr;
	for (i = 0; i < last_mh->msg_iovlen; i++) {
		if (missing <= 0) {
			msg_len += last_mh->msg_iov[i].iov_len;
			missing = msg_len - mmh[ret - 1].msg_len;
		}

		if (missing > 0) {
			uint8_t **iov_base;
			int first_offset;

			iov_base = (uint8_t **)&last_mh->msg_iov[i].iov_base;
			first_offset = last_mh->msg_iov[i].iov_len - missing;
			*iov_base += first_offset;
			last_mh->msg_iov[i].iov_len = missing;

			last_mh->msg_iov = &last_mh->msg_iov[i];

			if (sendmsg(c->fd_tap, last_mh, MSG_NOSIGNAL) < 0)
				debug("UDP: %li bytes to tap missing", missing);

			*iov_base -= first_offset;
			break;
		}
	}

	pcapmm(mmh, ret);
}

/**
 * udp_tap_send() - Prepare UDP datagrams and send to tap interface
 * @c:		Execution context
 * @start:	Index of first datagram in udp[46]_l2_buf pool
 * @n:		Number of datagrams to send
 * @dstport:	Destination port number
 * @v6:		True if using IPv6
 * @now:	Current timestamp
 *
 * Return: size of tap frame with headers
 */
static void udp_tap_send(const struct ctx *c,
			 unsigned int start, unsigned int n,
			 in_port_t dstport, bool v6, const struct timespec *now)
{
	int msg_bufs = 0, msg_i = 0;
	struct mmsghdr *tap_mmh;
	struct iovec *tap_iov;
	ssize_t msg_len = 0;
	unsigned int i;

	if (v6) {
		tap_mmh = udp6_l2_mh_tap;
		tap_iov = udp6_l2_iov_tap;
	} else {
		tap_mmh = udp4_l2_mh_tap;
		tap_iov = udp4_l2_iov_tap;
	}

	tap_mmh[0].msg_hdr.msg_iov = &tap_iov[start];
	for (i = start; i < start + n; i++) {
		size_t buf_len;

		if (v6)
			buf_len = udp_update_hdr6(c, i, dstport, now);
		else
			buf_len = udp_update_hdr4(c, i, dstport, now);

		tap_iov[i].iov_len = buf_len;

		/* With bigger messages, qemu closes the connection. */
		if (c->mode == MODE_PASST && msg_bufs &&
		    msg_len + buf_len > SHRT_MAX) {
			tap_mmh[msg_i].msg_hdr.msg_iovlen = msg_bufs;
			msg_i++;
			tap_mmh[msg_i].msg_hdr.msg_iov = &tap_iov[i];
			msg_len = msg_bufs = 0;
		}
		msg_len += buf_len;
		msg_bufs++;
	}
	tap_mmh[msg_i].msg_hdr.msg_iovlen = msg_bufs;

	if (c->mode == MODE_PASTA)
		udp_tap_send_pasta(c, tap_mmh, msg_i + 1);
	else
		udp_tap_send_passt(c, tap_mmh, msg_i + 1);
}

/**
 * udp_sock_handler() - Handle new data from socket
 * @c:		Execution context
 * @ref:	epoll reference
 * @events:	epoll events bitmap
 * @now:	Current timestamp
 *
 * #syscalls recvmmsg
 */
void udp_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events,
		      const struct timespec *now)
{
	/* For not entirely clear reasons (data locality?) pasta gets
	 * better throughput if we receive tap datagrams one at a
	 * atime.  For small splice datagrams throughput is slightly
	 * better if we do batch, but it's slightly worse for large
	 * splice datagrams.  Since we don't know before we receive
	 * whether we'll use tap or splice, always go one at a time
	 * for pasta mode.
	 */
	ssize_t n = (c->mode == MODE_PASST ? UDP_MAX_FRAMES : 1);
	in_port_t dstport = ref.r.p.udp.udp.port;
	bool v6 = ref.r.p.udp.udp.v6;
	struct mmsghdr *mmh_recv;
	unsigned int i, m;

	if (!(events & EPOLLIN))
		return;

	if (v6) {
		mmh_recv = udp6_l2_mh_sock;
		udp6_localname.sin6_port = htons(dstport);
	} else {
		mmh_recv = udp4_l2_mh_sock;
		udp4_localname.sin_port = htons(dstport);
	}

	n = recvmmsg(ref.r.s, mmh_recv, n, 0, NULL);
	if (n <= 0)
		return;

	for (i = 0; i < n; i += m) {
		int splicefrom = -1;
		m = n;

		if (ref.r.p.udp.udp.splice) {
			splicefrom = udp_mmh_splice_port(v6, mmh_recv + i);

			for (m = 1; i + m < n; m++) {
				int p;

				p = udp_mmh_splice_port(v6, mmh_recv + i + m);
				if (p != splicefrom)
					break;
			}
		}

		if (splicefrom >= 0)
			udp_splice_sendfrom(c, i, m, splicefrom, dstport,
					    v6, ref.r.p.udp.udp.ns,
					    ref.r.p.udp.udp.orig, now);
		else
			udp_tap_send(c, i, m, dstport, v6, now);
	}
}

/**
 * udp_tap_handler() - Handle packets from tap
 * @c:		Execution context
 * @af:		Address family, AF_INET or AF_INET6
 * @addr:	Destination address
 * @p:		Pool of UDP packets, with UDP headers
 * @now:	Current timestamp
 *
 * Return: count of consumed packets
 *
 * #syscalls sendmmsg
 */
int udp_tap_handler(struct ctx *c, int af, const void *addr,
		    const struct pool *p, const struct timespec *now)
{
	struct mmsghdr mm[UIO_MAXIOV];
	struct iovec m[UIO_MAXIOV];
	struct sockaddr_in6 s_in6;
	struct sockaddr_in s_in;
	struct sockaddr *sa;
	int i, s, count = 0;
	in_port_t src, dst;
	struct udphdr *uh;
	socklen_t sl;

	(void)c;

	uh = packet_get(p, 0, 0, sizeof(*uh), NULL);
	if (!uh)
		return 1;

	/* The caller already checks that all the messages have the same source
	 * and destination, so we can just take those from the first message.
	 */
	src = ntohs(uh->source);
	dst = ntohs(uh->dest);

	if (af == AF_INET) {
		s_in = (struct sockaddr_in) {
			.sin_family = AF_INET,
			.sin_port = uh->dest,
			.sin_addr = *(struct in_addr *)addr,
		};

		sa = (struct sockaddr *)&s_in;
		sl = sizeof(s_in);

		if (!(s = udp_tap_map[V4][src].sock)) {
			union udp_epoll_ref uref = { .udp.port = src };

			s = sock_l4(c, AF_INET, IPPROTO_UDP, NULL, NULL, src,
				    uref.u32);
			if (s < 0)
				return p->count;

			udp_tap_map[V4][src].sock = s;
			bitmap_set(udp_act[V4][UDP_ACT_TAP], src);
		}

		udp_tap_map[V4][src].ts = now->tv_sec;

		if (IN4_ARE_ADDR_EQUAL(&s_in.sin_addr, &c->ip4.gw) &&
		    !c->no_map_gw) {
			if (!(udp_tap_map[V4][dst].flags & PORT_LOCAL) ||
			    (udp_tap_map[V4][dst].flags & PORT_LOOPBACK))
				s_in.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
			else
				s_in.sin_addr = c->ip4.addr_seen;
		} else if (IN4_ARE_ADDR_EQUAL(&s_in.sin_addr,
					      &c->ip4.dns_match) &&
			   ntohs(s_in.sin_port) == 53) {
			s_in.sin_addr = c->ip4.dns[0];
		}
	} else {
		s_in6 = (struct sockaddr_in6) {
			.sin6_family = AF_INET6,
			.sin6_port = uh->dest,
			.sin6_addr = *(struct in6_addr *)addr,
		};
		const void *bind_addr = &in6addr_any;

		sa = (struct sockaddr *)&s_in6;
		sl = sizeof(s_in6);

		if (IN6_ARE_ADDR_EQUAL(addr, &c->ip6.gw) && !c->no_map_gw) {
			if (!(udp_tap_map[V6][dst].flags & PORT_LOCAL) ||
			    (udp_tap_map[V6][dst].flags & PORT_LOOPBACK))
				s_in6.sin6_addr = in6addr_loopback;
			else if (udp_tap_map[V6][dst].flags & PORT_GUA)
				s_in6.sin6_addr = c->ip6.addr;
			else
				s_in6.sin6_addr = c->ip6.addr_seen;
		} else if (IN6_ARE_ADDR_EQUAL(addr, &c->ip6.dns_match) &&
			   ntohs(s_in6.sin6_port) == 53) {
			s_in6.sin6_addr = c->ip6.dns[0];
		} else if (IN6_IS_ADDR_LINKLOCAL(&s_in6.sin6_addr)) {
			bind_addr = &c->ip6.addr_ll;
		}

		if (!(s = udp_tap_map[V6][src].sock)) {
			union udp_epoll_ref uref = { .udp.v6 = 1,
						     .udp.port = src };

			s = sock_l4(c, AF_INET6, IPPROTO_UDP, bind_addr, NULL,
				    src, uref.u32);
			if (s < 0)
				return p->count;

			udp_tap_map[V6][src].sock = s;
			bitmap_set(udp_act[V6][UDP_ACT_TAP], src);
		}

		udp_tap_map[V6][src].ts = now->tv_sec;
	}

	for (i = 0; i < (int)p->count; i++) {
		struct udphdr *uh_send;
		size_t len;

		uh_send = packet_get(p, i, 0, sizeof(*uh), &len);
		if (!uh_send)
			return p->count;

		mm[i].msg_hdr.msg_name = sa;
		mm[i].msg_hdr.msg_namelen = sl;

		if (len) {
			m[i].iov_base = (char *)(uh_send + 1);
			m[i].iov_len = len;

			mm[i].msg_hdr.msg_iov = m + i;
			mm[i].msg_hdr.msg_iovlen = 1;
		} else {
			mm[i].msg_hdr.msg_iov = NULL;
			mm[i].msg_hdr.msg_iovlen = 0;
		}

		mm[i].msg_hdr.msg_control = NULL;
		mm[i].msg_hdr.msg_controllen = 0;
		mm[i].msg_hdr.msg_flags = 0;

		count++;
	}

	count = sendmmsg(s, mm, count, MSG_NOSIGNAL);
	if (count < 0)
		return 1;

	return count;
}

/**
 * udp_sock_init() - Initialise listening sockets for a given port
 * @c:		Execution context
 * @ns:		In pasta mode, if set, bind with loopback address in namespace
 * @af:		Address family to select a specific IP version, or AF_UNSPEC
 * @addr:	Pointer to address for binding, NULL if not configured
 * @ifname:	Name of interface to bind to, NULL if not configured
 * @port:	Port, host order
 */
void udp_sock_init(const struct ctx *c, int ns, sa_family_t af,
		   const void *addr, const char *ifname, in_port_t port)
{
	union udp_epoll_ref uref = { .u32 = 0 };
	int s;

	if (ns) {
		uref.udp.port = (in_port_t)(port +
					    c->udp.fwd_out.f.delta[port]);
	} else {
		uref.udp.port = (in_port_t)(port +
					    c->udp.fwd_in.f.delta[port]);
	}

	if ((af == AF_INET || af == AF_UNSPEC) && c->ifi4) {
		uref.udp.v6 = 0;
		uref.udp.splice = (c->mode == MODE_PASTA);
		uref.udp.orig = true;

		if (!ns) {
			s = sock_l4(c, AF_INET, IPPROTO_UDP, addr, ifname,
				    port, uref.u32);

			udp_tap_map[V4][uref.udp.port].sock = s;
			udp_splice_init[V4][port].sock = s;
		} else {
			struct in_addr loopback = { htonl(INADDR_LOOPBACK) };
			uref.udp.ns = true;

			s = sock_l4(c, AF_INET, IPPROTO_UDP, &loopback,
				    ifname, port, uref.u32);
			udp_splice_ns[V4][port].sock = s;
		}
	}

	if ((af == AF_INET6 || af == AF_UNSPEC) && c->ifi6) {
		uref.udp.v6 = 1;
		uref.udp.splice = (c->mode == MODE_PASTA);
		uref.udp.orig = true;

		if (!ns) {
			s = sock_l4(c, AF_INET6, IPPROTO_UDP, addr, ifname,
				    port, uref.u32);

			udp_tap_map[V6][uref.udp.port].sock = s;
			udp_splice_init[V6][port].sock = s;
		} else {
			uref.udp.ns = true;

			s = sock_l4(c, AF_INET6, IPPROTO_UDP, &in6addr_loopback,
				    ifname, port, uref.u32);
			udp_splice_ns[V6][port].sock = s;
		}
	}
}

/**
 * udp_sock_init_ns() - Bind sockets in namespace for inbound connections
 * @arg:	Execution context
 *
 * Return: 0
 */
int udp_sock_init_ns(void *arg)
{
	struct ctx *c = (struct ctx *)arg;
	unsigned dst;

	if (ns_enter(c))
		return 0;

	for (dst = 0; dst < NUM_PORTS; dst++) {
		if (!bitmap_isset(c->udp.fwd_out.f.map, dst))
			continue;

		udp_sock_init(c, 1, AF_UNSPEC, NULL, NULL, dst);
	}

	return 0;
}

/**
 * udp_splice_iov_init() - Set up buffers and descriptors for recvmmsg/sendmmsg
 */
static void udp_splice_iov_init(void)
{
	int i;

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		struct msghdr *mh4 = &udp4_mh_splice[i].msg_hdr;
		struct msghdr *mh6 = &udp6_mh_splice[i].msg_hdr;

		mh4->msg_name = &udp4_localname;
		mh4->msg_namelen = sizeof(udp4_localname);

		mh6->msg_name = &udp6_localname;
		mh6->msg_namelen = sizeof(udp6_localname);

		udp4_iov_splice[i].iov_base = udp4_l2_buf[i].data;
		udp6_iov_splice[i].iov_base = udp6_l2_buf[i].data;

		mh4->msg_iov = &udp4_iov_splice[i];
		mh6->msg_iov = &udp6_iov_splice[i];
		mh4->msg_iovlen = mh6->msg_iovlen = 1;
	}
}

/**
 * udp_init() - Initialise per-socket data, and sockets in namespace
 * @c:		Execution context
 *
 * Return: 0
 */
int udp_init(struct ctx *c)
{
	if (c->ifi4)
		udp_sock4_iov_init(c);

	if (c->ifi6)
		udp_sock6_iov_init(c);

	udp_invert_portmap(&c->udp.fwd_in);
	udp_invert_portmap(&c->udp.fwd_out);

	if (c->mode == MODE_PASTA) {
		udp_splice_iov_init();
		NS_CALL(udp_sock_init_ns, c);
	}

	return 0;
}

/**
 * udp_timer_one() - Handler for timed events on one port
 * @c:		Execution context
 * @v6:		Set for IPv6 connections
 * @type:	Socket type
 * @port:	Port number, host order
 * @ts:		Timestamp from caller
 */
static void udp_timer_one(struct ctx *c, int v6, enum udp_act_type type,
			  in_port_t port, const struct timespec *ts)
{
	struct udp_splice_port *sp;
	struct udp_tap_port *tp;
	int s = -1;

	switch (type) {
	case UDP_ACT_TAP:
		tp = &udp_tap_map[v6 ? V6 : V4][port];

		if (ts->tv_sec - tp->ts > UDP_CONN_TIMEOUT) {
			s = tp->sock;
			tp->flags = 0;
		}

		break;
	case UDP_ACT_SPLICE_INIT:
		sp = &udp_splice_init[v6 ? V6 : V4][port];

		if (ts->tv_sec - sp->ts > UDP_CONN_TIMEOUT)
			s = sp->sock;

		break;
	case UDP_ACT_SPLICE_NS:
		sp = &udp_splice_ns[v6 ? V6 : V4][port];

		if (ts->tv_sec - sp->ts > UDP_CONN_TIMEOUT)
			s = sp->sock;

		break;
	default:
		return;
	}

	if (s > 0) {
		epoll_ctl(c->epollfd, EPOLL_CTL_DEL, s, NULL);
		close(s);
		bitmap_clear(udp_act[v6 ? V6 : V4][type], port);
	}
}

/**
 * udp_timer() - Scan activity bitmaps for ports with associated timed events
 * @c:		Execution context
 * @ts:		Timestamp from caller
 */
void udp_timer(struct ctx *c, const struct timespec *ts)
{
	int n, t, v6 = 0;
	unsigned int i;
	long *word, tmp;

	if (!c->ifi4)
		v6 = 1;
v6:
	for (t = 0; t < UDP_ACT_TYPE_MAX; t++) {
		word = (long *)udp_act[v6 ? V6 : V4][t];
		for (i = 0; i < ARRAY_SIZE(udp_act[0][0]);
		     i += sizeof(long), word++) {
			tmp = *word;
			while ((n = ffsl(tmp))) {
				tmp &= ~(1UL << (n - 1));
				udp_timer_one(c, v6, t, i * 8 + n - 1, ts);
			}
		}
	}

	if (!v6 && c->ifi6) {
		v6 = 1;
		goto v6;
	}
}

debug log:

solving fb3f790 ...
found fb3f790 in https://passt.top/passt

Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).