public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob 5db7b1698ce385bf22aa7221d1e7cbe088a865aa 33143 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
 
// SPDX-License-Identifier: GPL-2.0-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
 *
 * tap.c - Functions to communicate with guest- or namespace-facing interface
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 *
 */

#include <sched.h>
#include <unistd.h>
#include <signal.h>
#include <stdio.h>
#include <errno.h>
#include <limits.h>
#include <string.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <net/if_arp.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <stdint.h>
#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/uio.h>
#include <stdbool.h>
#include <stdlib.h>
#include <netinet/ip.h>
#include <netinet/tcp.h>
#include <netinet/udp.h>
#include <netinet/ip_icmp.h>
#include <netinet/if_ether.h>

#include <linux/if_tun.h>
#include <linux/icmpv6.h>

#include "checksum.h"
#include "util.h"
#include "ip.h"
#include "iov.h"
#include "passt.h"
#include "arp.h"
#include "dhcp.h"
#include "ndp.h"
#include "dhcpv6.h"
#include "pcap.h"
#include "netlink.h"
#include "pasta.h"
#include "packet.h"
#include "tap.h"
#include "log.h"

/* IPv4 (plus ARP) and IPv6 message batches from tap/guest to IP handlers */
static PACKET_POOL_NOINIT(pool_tap4, TAP_MSGS, pkt_buf);
static PACKET_POOL_NOINIT(pool_tap6, TAP_MSGS, pkt_buf);

#define TAP_SEQS		128 /* Different L4 tuples in one batch */
#define FRAGMENT_MSG_RATE	10  /* # seconds between fragment warnings */

/**
 * tap_send_single() - Send a single frame
 * @c:		Execution context
 * @data:	Packet buffer
 * @len:	Total L2 packet length
 */
void tap_send_single(const struct ctx *c, const void *data, size_t len)
{
	uint32_t vnet_len = htonl(len);
	struct iovec iov[2];
	size_t iovcnt = 0;

	if (c->mode == MODE_PASST) {
		iov[iovcnt] = IOV_OF_LVALUE(vnet_len);
		iovcnt++;
	}

	iov[iovcnt].iov_base = (void *)data;
	iov[iovcnt].iov_len = len;
	iovcnt++;

	tap_send_frames(c, iov, iovcnt, 1);
}

/**
 * tap_ip4_daddr() - Normal IPv4 destination address for inbound packets
 * @c:		Execution context
 *
 * Return: IPv4 address, network order
 */
struct in_addr tap_ip4_daddr(const struct ctx *c)
{
	return c->ip4.addr_seen;
}

/**
 * tap_ip6_daddr() - Normal IPv6 destination address for inbound packets
 * @c:		Execution context
 * @src:	Source address
 *
 * Return: pointer to IPv6 address
 */
const struct in6_addr *tap_ip6_daddr(const struct ctx *c,
				     const struct in6_addr *src)
{
	if (IN6_IS_ADDR_LINKLOCAL(src))
		return &c->ip6.addr_ll_seen;
	return &c->ip6.addr_seen;
}

/**
 * tap_push_l2h() - Build an L2 header for an inbound packet
 * @c:		Execution context
 * @buf:	Buffer address at which to generate header
 * @proto:	Ethernet protocol number for L3
 *
 * Return: pointer at which to write the packet's payload
 */
static void *tap_push_l2h(const struct ctx *c, void *buf, uint16_t proto)
{
	struct ethhdr *eh = (struct ethhdr *)buf;

	/* TODO: ARP table lookup */
	memcpy(eh->h_dest, c->mac_guest, ETH_ALEN);
	memcpy(eh->h_source, c->mac, ETH_ALEN);
	eh->h_proto = ntohs(proto);
	return eh + 1;
}

/**
 * tap_push_ip4h() - Build IPv4 header for inbound packet, with checksum
 * @c:		Execution context
 * @src:	IPv4 source address, network order
 * @dst:	IPv4 destination address, network order
 * @len:	L4 payload length
 * @proto:	L4 protocol number
 *
 * Return: pointer at which to write the packet's payload
 */
static void *tap_push_ip4h(struct iphdr *ip4h, struct in_addr src,
			   struct in_addr dst, size_t len, uint8_t proto)
{
	ip4h->version = 4;
	ip4h->ihl = sizeof(struct iphdr) / 4;
	ip4h->tos = 0;
	ip4h->tot_len = htons(len + sizeof(*ip4h));
	ip4h->id = 0;
	ip4h->frag_off = 0;
	ip4h->ttl = 255;
	ip4h->protocol = proto;
	ip4h->saddr = src.s_addr;
	ip4h->daddr = dst.s_addr;
	ip4h->check = csum_ip4_header(ip4h->tot_len, proto, src, dst);
	return ip4h + 1;
}

/**
 * tap_udp4_send() - Send UDP over IPv4 packet
 * @c:		Execution context
 * @src:	IPv4 source address
 * @sport:	UDP source port
 * @dst:	IPv4 destination address
 * @dport:	UDP destination port
 * @in:		UDP payload contents (not including UDP header)
 * @len:	UDP payload length (not including UDP header)
 */
void tap_udp4_send(const struct ctx *c, struct in_addr src, in_port_t sport,
		   struct in_addr dst, in_port_t dport,
		   const void *in, size_t len)
{
	size_t l4len = len + sizeof(struct udphdr);
	char buf[USHRT_MAX];
	struct iphdr *ip4h = tap_push_l2h(c, buf, ETH_P_IP);
	struct udphdr *uh = tap_push_ip4h(ip4h, src, dst, l4len, IPPROTO_UDP);
	char *data = (char *)(uh + 1);

	uh->source = htons(sport);
	uh->dest = htons(dport);
	uh->len = htons(l4len);
	csum_udp4(uh, src, dst, in, len);
	memcpy(data, in, len);

	tap_send_single(c, buf, len + (data - buf));
}

/**
 * tap_icmp4_send() - Send ICMPv4 packet
 * @c:		Execution context
 * @src:	IPv4 source address
 * @dst:	IPv4 destination address
 * @in:		ICMP packet, including ICMP header
 * @len:	ICMP packet length, including ICMP header
 */
void tap_icmp4_send(const struct ctx *c, struct in_addr src, struct in_addr dst,
		    const void *in, size_t len)
{
	char buf[USHRT_MAX];
	struct iphdr *ip4h = tap_push_l2h(c, buf, ETH_P_IP);
	struct icmphdr *icmp4h = tap_push_ip4h(ip4h, src, dst,
					       len, IPPROTO_ICMP);

	memcpy(icmp4h, in, len);
	csum_icmp4(icmp4h, icmp4h + 1, len - sizeof(*icmp4h));

	tap_send_single(c, buf, len + ((char *)icmp4h - buf));
}

/**
 * tap_push_ip6h() - Build IPv6 header for inbound packet
 * @c:		Execution context
 * @src:	IPv6 source address
 * @dst:	IPv6 destination address
 * @len:	L4 payload length
 * @proto:	L4 protocol number
 * @flow:	IPv6 flow identifier
 *
 * Return: pointer at which to write the packet's payload
 */
static void *tap_push_ip6h(struct ipv6hdr *ip6h,
			   const struct in6_addr *src,
			   const struct in6_addr *dst,
			   size_t len, uint8_t proto, uint32_t flow)
{
	ip6h->payload_len = htons(len);
	ip6h->priority = 0;
	ip6h->version = 6;
	ip6h->nexthdr = proto;
	ip6h->hop_limit = 255;
	ip6h->saddr = *src;
	ip6h->daddr = *dst;
	ip6h->flow_lbl[0] = (flow >> 16) & 0xf;
	ip6h->flow_lbl[1] = (flow >> 8) & 0xff;
	ip6h->flow_lbl[2] = (flow >> 0) & 0xff;
	return ip6h + 1;
}

/**
 * tap_udp6_send() - Send UDP over IPv6 packet
 * @c:		Execution context
 * @src:	IPv6 source address
 * @sport:	UDP source port
 * @dst:	IPv6 destination address
 * @dport:	UDP destination port
 * @flow:	Flow label
 * @in:		UDP payload contents (not including UDP header)
 * @len:	UDP payload length (not including UDP header)
 */
void tap_udp6_send(const struct ctx *c,
		   const struct in6_addr *src, in_port_t sport,
		   const struct in6_addr *dst, in_port_t dport,
		   uint32_t flow, const void *in, size_t len)
{
	size_t l4len = len + sizeof(struct udphdr);
	char buf[USHRT_MAX];
	struct ipv6hdr *ip6h = tap_push_l2h(c, buf, ETH_P_IPV6);
	struct udphdr *uh = tap_push_ip6h(ip6h, src, dst,
					  l4len, IPPROTO_UDP, flow);
	char *data = (char *)(uh + 1);

	uh->source = htons(sport);
	uh->dest = htons(dport);
	uh->len = htons(l4len);
	csum_udp6(uh, src, dst, in, len);
	memcpy(data, in, len);

	tap_send_single(c, buf, len + (data - buf));
}

/**
 * tap_icmp6_send() - Send ICMPv6 packet
 * @c:		Execution context
 * @src:	IPv6 source address
 * @dst:	IPv6 destination address
 * @in:		ICMP packet, including ICMP header
 * @len:	ICMP packet length, including ICMP header
 */
void tap_icmp6_send(const struct ctx *c,
		    const struct in6_addr *src, const struct in6_addr *dst,
		    const void *in, size_t len)
{
	char buf[USHRT_MAX];
	struct ipv6hdr *ip6h = tap_push_l2h(c, buf, ETH_P_IPV6);
	struct icmp6hdr *icmp6h = tap_push_ip6h(ip6h, src, dst, len,
						IPPROTO_ICMPV6, 0);

	memcpy(icmp6h, in, len);
	csum_icmp6(icmp6h, src, dst, icmp6h + 1, len - sizeof(*icmp6h));

	tap_send_single(c, buf, len + ((char *)icmp6h - buf));
}

/**
 * tap_send_frames_pasta() - Send multiple frames to the pasta tap
 * @c:			Execution context
 * @iov:		Array of buffers
 * @bufs_per_frame:	Number of buffers (iovec entries) per frame
 * @nframes:		Number of frames to send
 *
 * @iov must have total length @bufs_per_frame * @nframes, with each set of
 * @bufs_per_frame contiguous buffers representing a single frame.
 *
 * Return: number of frames successfully sent
 *
 * #syscalls:pasta write
 */
static size_t tap_send_frames_pasta(const struct ctx *c,
				    const struct iovec *iov,
				    size_t bufs_per_frame, size_t nframes)
{
	size_t nbufs = bufs_per_frame * nframes;
	size_t i;

	for (i = 0; i < nbufs; i += bufs_per_frame) {
		ssize_t rc = writev(c->fd_tap, iov + i, bufs_per_frame);
		size_t framelen = iov_size(iov + i, bufs_per_frame);

		if (rc < 0) {
			debug("tap write: %s", strerror(errno));

			switch (errno) {
			case EAGAIN:
#if EAGAIN != EWOULDBLOCK
			case EWOULDBLOCK:
#endif
			case EINTR:
			case ENOBUFS:
			case ENOSPC:
				break;
			default:
				die("Write error on tap device, exiting");
			}
		} else if ((size_t)rc < framelen) {
			debug("short write on tuntap: %zd/%zu", rc, framelen);
			break;
		}
	}

	return i / bufs_per_frame;
}

/**
 * tap_send_frames_passt() - Send multiple frames to the passt tap
 * @c:			Execution context
 * @iov:		Array of buffers, each containing one frame
 * @bufs_per_frame:	Number of buffers (iovec entries) per frame
 * @nframes:		Number of frames to send
 *
 * @iov must have total length @bufs_per_frame * @nframes, with each set of
 * @bufs_per_frame contiguous buffers representing a single frame.
 *
 * Return: number of frames successfully sent
 *
 * #syscalls:passt sendmsg
 */
static size_t tap_send_frames_passt(const struct ctx *c,
				    const struct iovec *iov,
				    size_t bufs_per_frame, size_t nframes)
{
	size_t nbufs = bufs_per_frame * nframes;
	struct msghdr mh = {
		.msg_iov = (void *)iov,
		.msg_iovlen = nbufs,
	};
	size_t buf_offset;
	unsigned int i;
	ssize_t sent;

	sent = sendmsg(c->fd_tap, &mh, MSG_NOSIGNAL | MSG_DONTWAIT);
	if (sent < 0)
		return 0;

	/* Check for any partial frames due to short send */
	i = iov_skip_bytes(iov, nbufs, sent, &buf_offset);

	if (i < nbufs && (buf_offset || (i % bufs_per_frame))) {
		/* Number of unsent or partially sent buffers for the frame */
		size_t rembufs = bufs_per_frame - (i % bufs_per_frame);

		if (write_remainder(c->fd_tap, &iov[i], rembufs, buf_offset) < 0) {
			err("tap: partial frame send: %s", strerror(errno));
			return i;
		}
		i += rembufs;
	}

	return i / bufs_per_frame;
}

/**
 * tap_send_frames() - Send out multiple prepared frames
 * @c:			Execution context
 * @iov:		Array of buffers, each containing one frame (with L2 headers)
 * @bufs_per_frame:	Number of buffers (iovec entries) per frame
 * @nframes:		Number of frames to send
 *
 * @iov must have total length @bufs_per_frame * @nframes, with each set of
 * @bufs_per_frame contiguous buffers representing a single frame.
 *
 * Return: number of frames actually sent
 */
size_t tap_send_frames(const struct ctx *c, const struct iovec *iov,
		       size_t bufs_per_frame, size_t nframes)
{
	size_t m;

	if (!nframes)
		return 0;

	if (c->mode == MODE_PASST)
		m = tap_send_frames_passt(c, iov, bufs_per_frame, nframes);
	else
		m = tap_send_frames_pasta(c, iov, bufs_per_frame, nframes);

	if (m < nframes)
		debug("tap: failed to send %zu frames of %zu",
		      nframes - m, nframes);

	pcap_multiple(iov, bufs_per_frame, m,
		      c->mode == MODE_PASST ? sizeof(uint32_t) : 0);

	return m;
}

/**
 * eth_update_mac() - Update tap L2 header with new Ethernet addresses
 * @eh:		Ethernet headers to update
 * @eth_d:	Ethernet destination address, NULL if unchanged
 * @eth_s:	Ethernet source address, NULL if unchanged
 */
void eth_update_mac(struct ethhdr *eh,
		    const unsigned char *eth_d, const unsigned char *eth_s)
{
	if (eth_d)
		memcpy(eh->h_dest, eth_d, sizeof(eh->h_dest));
	if (eth_s)
		memcpy(eh->h_source, eth_s, sizeof(eh->h_source));
}

PACKET_POOL_DECL(pool_l4, UIO_MAXIOV, pkt_buf);

/**
 * struct l4_seq4_t - Message sequence for one protocol handler call, IPv4
 * @msgs:	Count of messages in sequence
 * @protocol:	Protocol number
 * @source:	Source port
 * @dest:	Destination port
 * @saddr:	Source address
 * @daddr:	Destination address
 * @msg:	Array of messages that can be handled in a single call
 */
static struct tap4_l4_t {
	uint8_t protocol;

	uint16_t source;
	uint16_t dest;

	struct in_addr saddr;
	struct in_addr daddr;

	struct pool_l4_t p;
} tap4_l4[TAP_SEQS /* Arbitrary: TAP_MSGS in theory, so limit in users */];

/**
 * struct l4_seq6_t - Message sequence for one protocol handler call, IPv6
 * @msgs:	Count of messages in sequence
 * @protocol:	Protocol number
 * @source:	Source port
 * @dest:	Destination port
 * @saddr:	Source address
 * @daddr:	Destination address
 * @msg:	Array of messages that can be handled in a single call
 */
static struct tap6_l4_t {
	uint8_t protocol;

	uint16_t source;
	uint16_t dest;

	struct in6_addr saddr;
	struct in6_addr daddr;

	struct pool_l4_t p;
} tap6_l4[TAP_SEQS /* Arbitrary: TAP_MSGS in theory, so limit in users */];

/**
 * tap_packet_debug() - Print debug message for packet(s) from guest/tap
 * @iph:	IPv4 header, can be NULL
 * @ip6h:	IPv6 header, can be NULL
 * @seq4:	Pointer to @struct tap_l4_seq4, can be NULL
 * @proto6:	IPv6 protocol, for IPv6
 * @seq6:	Pointer to @struct tap_l4_seq6, can be NULL
 * @count:	Count of packets in this sequence
 */
static void tap_packet_debug(const struct iphdr *iph,
			     const struct ipv6hdr *ip6h,
			     const struct tap4_l4_t *seq4, uint8_t proto6,
			     const struct tap6_l4_t *seq6, int count)
{
	char buf6s[INET6_ADDRSTRLEN], buf6d[INET6_ADDRSTRLEN];
	char buf4s[INET_ADDRSTRLEN], buf4d[INET_ADDRSTRLEN];
	uint8_t proto = 0;

	if (iph || seq4) {
		if (iph) {
			inet_ntop(AF_INET, &iph->saddr, buf4s, sizeof(buf4s));
			inet_ntop(AF_INET, &iph->daddr, buf4d, sizeof(buf4d));
			proto = iph->protocol;
		} else {
			inet_ntop(AF_INET, &seq4->saddr, buf4s, sizeof(buf4s));
			inet_ntop(AF_INET, &seq4->daddr, buf4d, sizeof(buf4d));
			proto = seq4->protocol;
		}
	} else {
		inet_ntop(AF_INET6, ip6h ? &ip6h->saddr : &seq6->saddr,
			  buf6s, sizeof(buf6s));
		inet_ntop(AF_INET6, ip6h ? &ip6h->daddr : &seq6->daddr,
			  buf6d, sizeof(buf6d));
		proto = proto6;
	}

	if (proto == IPPROTO_TCP || proto == IPPROTO_UDP) {
		trace("tap: protocol %i, %s%s%s:%i -> %s%s%s:%i (%i packet%s)",
		      proto,
		      seq4 ? "" : "[", seq4 ? buf4s : buf6s, seq4 ? "" : "]",
		      ntohs(seq4 ? seq4->source : seq6->source),
		      seq4 ? "" : "[", seq4 ? buf4d : buf6d, seq4 ? "" : "]",
		      ntohs(seq4 ? seq4->dest : seq6->dest),
		      count, count == 1 ? "" : "s");
	} else {
		trace("tap: protocol %i, %s -> %s (%i packet%s)",
		      proto, iph ? buf4s : buf6s, iph ? buf4d : buf6d,
		      count, count == 1 ? "" : "s");
	}
}

/**
 * tap4_is_fragment() - Determine if a packet is an IP fragment
 * @iph:	IPv4 header (length already validated)
 * @now:	Current timestamp
 *
 * Return: true if iph is an IP fragment, false otherwise
 */
static bool tap4_is_fragment(const struct iphdr *iph,
			     const struct timespec *now)
{
	if (ntohs(iph->frag_off) & ~IP_DF) {
		/* Ratelimit messages */
		static time_t last_message;
		static unsigned num_dropped;

		num_dropped++;
		if (now->tv_sec - last_message > FRAGMENT_MSG_RATE) {
			warn("Can't process IPv4 fragments (%u dropped)",
			     num_dropped);
			last_message = now->tv_sec;
			num_dropped = 0;
		}
		return true;
	}
	return false;
}

/**
 * tap4_handler() - IPv4 and ARP packet handler for tap file descriptor
 * @c:		Execution context
 * @in:		Ingress packet pool, packets with Ethernet headers
 * @now:	Current timestamp
 *
 * Return: count of packets consumed by handlers
 */
static int tap4_handler(struct ctx *c, const struct pool *in,
			const struct timespec *now)
{
	unsigned int i, j, seq_count;
	struct tap4_l4_t *seq;

	if (!c->ifi4 || !in->count)
		return in->count;

	i = 0;
resume:
	for (seq_count = 0, seq = NULL; i < in->count; i++) {
		size_t l2len, l3len, hlen, l4len;
		const struct ethhdr *eh;
		const struct udphdr *uh;
		struct iphdr *iph;
		const char *l4h;

		packet_get(in, i, 0, 0, &l2len);

		eh = packet_get(in, i, 0, sizeof(*eh), &l3len);
		if (!eh)
			continue;
		if (ntohs(eh->h_proto) == ETH_P_ARP) {
			PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));

			packet_add(pkt, l2len, (char *)eh);
			arp(c, pkt);
			continue;
		}

		iph = packet_get(in, i, sizeof(*eh), sizeof(*iph), NULL);
		if (!iph)
			continue;

		hlen = iph->ihl * 4UL;
		if (hlen < sizeof(*iph) || htons(iph->tot_len) > l3len ||
		    hlen > l3len)
			continue;

		/* We don't handle IP fragments, drop them */
		if (tap4_is_fragment(iph, now))
			continue;

		l4len = htons(iph->tot_len) - hlen;

		if (IN4_IS_ADDR_LOOPBACK(&iph->saddr) ||
		    IN4_IS_ADDR_LOOPBACK(&iph->daddr)) {
			char sstr[INET_ADDRSTRLEN], dstr[INET_ADDRSTRLEN];

			debug("Loopback address on tap interface: %s -> %s",
			      inet_ntop(AF_INET, &iph->saddr, sstr, sizeof(sstr)),
			      inet_ntop(AF_INET, &iph->daddr, dstr, sizeof(dstr)));
			continue;
		}

		if (iph->saddr && c->ip4.addr_seen.s_addr != iph->saddr)
			c->ip4.addr_seen.s_addr = iph->saddr;

		l4h = packet_get(in, i, sizeof(*eh) + hlen, l4len, NULL);
		if (!l4h)
			continue;

		if (iph->protocol == IPPROTO_ICMP) {
			PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));

			if (c->no_icmp)
				continue;

			tap_packet_debug(iph, NULL, NULL, 0, NULL, 1);

			packet_add(pkt, l4len, l4h);
			icmp_tap_handler(c, PIF_TAP, AF_INET,
					 &iph->saddr, &iph->daddr,
					 pkt, now);
			continue;
		}

		uh = packet_get(in, i, sizeof(*eh) + hlen, sizeof(*uh), NULL);
		if (!uh)
			continue;

		if (iph->protocol == IPPROTO_UDP) {
			PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));

			packet_add(pkt, l2len, (char *)eh);
			if (dhcp(c, pkt))
				continue;
		}

		if (iph->protocol != IPPROTO_TCP &&
		    iph->protocol != IPPROTO_UDP) {
			tap_packet_debug(iph, NULL, NULL, 0, NULL, 1);
			continue;
		}

#define L4_MATCH(iph, uh, seq)						\
	(seq->protocol == iph->protocol &&				\
	 seq->source   == uh->source    && seq->dest  == uh->dest &&	\
	 seq->saddr.s_addr == iph->saddr && seq->daddr.s_addr == iph->daddr)

#define L4_SET(iph, uh, seq)						\
	do {								\
		seq->protocol		= iph->protocol;		\
		seq->source		= uh->source;			\
		seq->dest		= uh->dest;			\
		seq->saddr.s_addr	= iph->saddr;			\
		seq->daddr.s_addr	= iph->daddr;			\
	} while (0)

		if (seq && L4_MATCH(iph, uh, seq) && seq->p.count < UIO_MAXIOV)
			goto append;

		if (seq_count == TAP_SEQS)
			break;	/* Resume after flushing if i < in->count */

		for (seq = tap4_l4 + seq_count - 1; seq >= tap4_l4; seq--) {
			if (L4_MATCH(iph, uh, seq)) {
				if (seq->p.count >= UIO_MAXIOV)
					seq = NULL;
				break;
			}
		}

		if (!seq || seq < tap4_l4) {
			seq = tap4_l4 + seq_count++;
			L4_SET(iph, uh, seq);
			pool_flush((struct pool *)&seq->p);
		}

#undef L4_MATCH
#undef L4_SET

append:
		packet_add((struct pool *)&seq->p, l4len, l4h);
	}

	for (j = 0, seq = tap4_l4; j < seq_count; j++, seq++) {
		const struct pool *p = (const struct pool *)&seq->p;
		size_t k;

		tap_packet_debug(NULL, NULL, seq, 0, NULL, p->count);

		if (seq->protocol == IPPROTO_TCP) {
			if (c->no_tcp)
				continue;
			for (k = 0; k < p->count; )
				k += tcp_tap_handler(c, PIF_TAP, AF_INET,
						     &seq->saddr, &seq->daddr,
						     p, k, now);
		} else if (seq->protocol == IPPROTO_UDP) {
			if (c->no_udp)
				continue;
			for (k = 0; k < p->count; )
				k += udp_tap_handler(c, PIF_TAP, AF_INET,
						     &seq->saddr, &seq->daddr,
						     p, k, now);
		}
	}

	if (i < in->count)
		goto resume;

	return in->count;
}

/**
 * tap6_handler() - IPv6 packet handler for tap file descriptor
 * @c:		Execution context
 * @in:		Ingress packet pool, packets with Ethernet headers
 * @now:	Current timestamp
 *
 * Return: count of packets consumed by handlers
 */
static int tap6_handler(struct ctx *c, const struct pool *in,
			const struct timespec *now)
{
	unsigned int i, j, seq_count = 0;
	struct tap6_l4_t *seq;

	if (!c->ifi6 || !in->count)
		return in->count;

	i = 0;
resume:
	for (seq_count = 0, seq = NULL; i < in->count; i++) {
		size_t l4len, plen, check;
		struct in6_addr *saddr, *daddr;
		const struct ethhdr *eh;
		const struct udphdr *uh;
		struct ipv6hdr *ip6h;
		uint8_t proto;
		char *l4h;

		eh =   packet_get(in, i, 0,		sizeof(*eh), NULL);
		if (!eh)
			continue;

		ip6h = packet_get(in, i, sizeof(*eh),	sizeof(*ip6h), &check);
		if (!ip6h)
			continue;

		saddr = &ip6h->saddr;
		daddr = &ip6h->daddr;

		plen = ntohs(ip6h->payload_len);
		if (plen != check)
			continue;

		if (!(l4h = ipv6_l4hdr(in, i, sizeof(*eh), &proto, &l4len)))
			continue;

		if (IN6_IS_ADDR_LOOPBACK(saddr) || IN6_IS_ADDR_LOOPBACK(daddr)) {
			char sstr[INET6_ADDRSTRLEN], dstr[INET6_ADDRSTRLEN];

			debug("Loopback address on tap interface: %s -> %s",
			      inet_ntop(AF_INET6, saddr, sstr, sizeof(sstr)),
			      inet_ntop(AF_INET6, daddr, dstr, sizeof(dstr)));
			continue;
		}

		if (IN6_IS_ADDR_LINKLOCAL(saddr)) {
			c->ip6.addr_ll_seen = *saddr;

			if (IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr_seen)) {
				c->ip6.addr_seen = *saddr;
			}
		} else if (!IN6_IS_ADDR_UNSPECIFIED(saddr)){
			c->ip6.addr_seen = *saddr;
		}

		if (proto == IPPROTO_ICMPV6) {
			PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));

			if (c->no_icmp)
				continue;

			if (l4len < sizeof(struct icmp6hdr))
				continue;

			if (ndp(c, (struct icmp6hdr *)l4h, saddr))
				continue;

			tap_packet_debug(NULL, ip6h, NULL, proto, NULL, 1);

			packet_add(pkt, l4len, l4h);
			icmp_tap_handler(c, PIF_TAP, AF_INET6,
					 saddr, daddr, pkt, now);
			continue;
		}

		if (l4len < sizeof(*uh))
			continue;
		uh = (struct udphdr *)l4h;

		if (proto == IPPROTO_UDP) {
			PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));

			packet_add(pkt, l4len, l4h);

			if (dhcpv6(c, pkt, saddr, daddr))
				continue;
		}

		if (proto != IPPROTO_TCP && proto != IPPROTO_UDP) {
			tap_packet_debug(NULL, ip6h, NULL, proto, NULL, 1);
			continue;
		}

#define L4_MATCH(ip6h, proto, uh, seq)					\
	(seq->protocol == proto         &&				\
	 seq->source   == uh->source    && seq->dest  == uh->dest &&	\
	 IN6_ARE_ADDR_EQUAL(&seq->saddr, saddr)			  &&	\
	 IN6_ARE_ADDR_EQUAL(&seq->daddr, daddr))

#define L4_SET(ip6h, proto, uh, seq)					\
	do {								\
		seq->protocol	= proto;				\
		seq->source	= uh->source;				\
		seq->dest	= uh->dest;				\
		seq->saddr	= *saddr;				\
		seq->daddr	= *daddr;				\
	} while (0)

		if (seq && L4_MATCH(ip6h, proto, uh, seq) &&
		    seq->p.count < UIO_MAXIOV)
			goto append;

		if (seq_count == TAP_SEQS)
			break;	/* Resume after flushing if i < in->count */

		for (seq = tap6_l4 + seq_count - 1; seq >= tap6_l4; seq--) {
			if (L4_MATCH(ip6h, proto, uh, seq)) {
				if (seq->p.count >= UIO_MAXIOV)
					seq = NULL;
				break;
			}
		}

		if (!seq || seq < tap6_l4) {
			seq = tap6_l4 + seq_count++;
			L4_SET(ip6h, proto, uh, seq);
			pool_flush((struct pool *)&seq->p);
		}

#undef L4_MATCH
#undef L4_SET

append:
		packet_add((struct pool *)&seq->p, l4len, l4h);
	}

	for (j = 0, seq = tap6_l4; j < seq_count; j++, seq++) {
		const struct pool *p = (const struct pool *)&seq->p;
		size_t k;

		tap_packet_debug(NULL, NULL, NULL, seq->protocol, seq,
				 p->count);

		if (seq->protocol == IPPROTO_TCP) {
			if (c->no_tcp)
				continue;
			for (k = 0; k < p->count; )
				k += tcp_tap_handler(c, PIF_TAP, AF_INET6,
						     &seq->saddr, &seq->daddr,
						     p, k, now);
		} else if (seq->protocol == IPPROTO_UDP) {
			if (c->no_udp)
				continue;
			for (k = 0; k < p->count; )
				k += udp_tap_handler(c, PIF_TAP, AF_INET6,
						     &seq->saddr, &seq->daddr,
						     p, k, now);
		}
	}

	if (i < in->count)
		goto resume;

	return in->count;
}

/**
 * tap_sock_reset() - Handle closing or failure of connect AF_UNIX socket
 * @c:		Execution context
 */
static void tap_sock_reset(struct ctx *c)
{
	if (c->one_off) {
		info("Client closed connection, exiting");
		exit(EXIT_SUCCESS);
	}

	/* Close the connected socket, wait for a new connection */
	epoll_ctl(c->epollfd, EPOLL_CTL_DEL, c->fd_tap, NULL);
	close(c->fd_tap);
	c->fd_tap = -1;
}

/**
 * tap_handler_passt() - Packet handler for AF_UNIX file descriptor
 * @c:		Execution context
 * @events:	epoll events
 * @now:	Current timestamp
 */
void tap_handler_passt(struct ctx *c, uint32_t events,
		       const struct timespec *now)
{
	const struct ethhdr *eh;
	ssize_t n, rem;
	char *p;

	if (events & (EPOLLRDHUP | EPOLLHUP | EPOLLERR)) {
		tap_sock_reset(c);
		return;
	}

redo:
	p = pkt_buf;
	rem = 0;

	pool_flush(pool_tap4);
	pool_flush(pool_tap6);

	n = recv(c->fd_tap, p, TAP_BUF_FILL, MSG_DONTWAIT);
	if (n < 0) {
		if (errno != EINTR && errno != EAGAIN && errno != EWOULDBLOCK)
			tap_sock_reset(c);
		return;
	}

	while (n > (ssize_t)sizeof(uint32_t)) {
		ssize_t len = ntohl(*(uint32_t *)p);

		p += sizeof(uint32_t);
		n -= sizeof(uint32_t);

		/* At most one packet might not fit in a single read, and this
		 * needs to be blocking.
		 */
		if (len > n) {
			rem = recv(c->fd_tap, p + n, len - n, 0);
			if ((n += rem) != len)
				return;
		}

		/* Complete the partial read above before discarding a malformed
		 * frame, otherwise the stream will be inconsistent.
		 */
		if (len < (ssize_t)sizeof(*eh) || len > (ssize_t)ETH_MAX_MTU)
			goto next;

		pcap(p, len);

		eh = (struct ethhdr *)p;

		if (memcmp(c->mac_guest, eh->h_source, ETH_ALEN)) {
			memcpy(c->mac_guest, eh->h_source, ETH_ALEN);
			proto_update_l2_buf(c->mac_guest, NULL);
		}

		switch (ntohs(eh->h_proto)) {
		case ETH_P_ARP:
		case ETH_P_IP:
			packet_add(pool_tap4, len, p);
			break;
		case ETH_P_IPV6:
			packet_add(pool_tap6, len, p);
			break;
		default:
			break;
		}

next:
		p += len;
		n -= len;
	}

	tap4_handler(c, pool_tap4, now);
	tap6_handler(c, pool_tap6, now);

	/* We can't use EPOLLET otherwise. */
	if (rem)
		goto redo;
}

/**
 * tap_handler_pasta() - Packet handler for /dev/net/tun file descriptor
 * @c:		Execution context
 * @events:	epoll events
 * @now:	Current timestamp
 */
void tap_handler_pasta(struct ctx *c, uint32_t events,
		       const struct timespec *now)
{
	ssize_t n, len;
	int ret;

	if (events & (EPOLLRDHUP | EPOLLHUP | EPOLLERR))
		die("Disconnect event on /dev/net/tun device, exiting");

redo:
	n = 0;

	pool_flush(pool_tap4);
	pool_flush(pool_tap6);
restart:
	while ((len = read(c->fd_tap, pkt_buf + n, TAP_BUF_BYTES - n)) > 0) {
		const struct ethhdr *eh = (struct ethhdr *)(pkt_buf + n);

		if (len < (ssize_t)sizeof(*eh) || len > (ssize_t)ETH_MAX_MTU) {
			n += len;
			continue;
		}

		pcap(pkt_buf + n, len);

		if (memcmp(c->mac_guest, eh->h_source, ETH_ALEN)) {
			memcpy(c->mac_guest, eh->h_source, ETH_ALEN);
			proto_update_l2_buf(c->mac_guest, NULL);
		}

		switch (ntohs(eh->h_proto)) {
		case ETH_P_ARP:
		case ETH_P_IP:
			packet_add(pool_tap4, len, pkt_buf + n);
			break;
		case ETH_P_IPV6:
			packet_add(pool_tap6, len, pkt_buf + n);
			break;
		default:
			break;
		}

		if ((n += len) == TAP_BUF_BYTES)
			break;
	}

	if (len < 0 && errno == EINTR)
		goto restart;

	ret = errno;

	tap4_handler(c, pool_tap4, now);
	tap6_handler(c, pool_tap6, now);

	if (len > 0 || ret == EAGAIN)
		return;

	if (n == TAP_BUF_BYTES)
		goto redo;

	die("Error on tap device, exiting");
}

/**
 * tap_sock_unix_init() - Create and bind AF_UNIX socket, listen for connection
 * @c:		Execution context
 */
static void tap_sock_unix_init(struct ctx *c)
{
	int fd = socket(AF_UNIX, SOCK_STREAM, 0);
	union epoll_ref ref = { .type = EPOLL_TYPE_TAP_LISTEN };
	struct epoll_event ev = { 0 };
	struct sockaddr_un addr = {
		.sun_family = AF_UNIX,
	};
	int i;

	if (fd < 0)
		die("UNIX socket: %s", strerror(errno));

	/* In passt mode, we don't know the guest's MAC until it sends
	 * us packets.  Use the broadcast address so our first packets
	 * will reach it.
	 */
	memset(&c->mac_guest, 0xff, sizeof(c->mac_guest));

	for (i = 1; i < UNIX_SOCK_MAX; i++) {
		char *path = addr.sun_path;
		int ex, ret;

		if (*c->sock_path)
			memcpy(path, c->sock_path, UNIX_PATH_MAX);
		else
			snprintf(path, UNIX_PATH_MAX - 1, UNIX_SOCK_PATH, i);

		ex = socket(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0);
		if (ex < 0)
			die("UNIX domain socket check: %s", strerror(errno));

		ret = connect(ex, (const struct sockaddr *)&addr, sizeof(addr));
		if (!ret || (errno != ENOENT && errno != ECONNREFUSED &&
			     errno != EACCES)) {
			if (*c->sock_path)
				die("Socket path %s already in use", path);

			close(ex);
			continue;
		}
		close(ex);

		unlink(path);
		if (!bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) ||
		    *c->sock_path)
			break;
	}

	if (i == UNIX_SOCK_MAX)
		die("UNIX socket bind: %s", strerror(errno));

	info("UNIX domain socket bound at %s\n", addr.sun_path);

	listen(fd, 0);

	ref.fd = c->fd_tap_listen = fd;
	ev.events = EPOLLIN | EPOLLET;
	ev.data.u64 = ref.u64;
	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap_listen, &ev);

	info("You can now start qemu (>= 7.2, with commit 13c6be96618c):");
	info("    kvm ... -device virtio-net-pci,netdev=s -netdev stream,id=s,server=off,addr.type=unix,addr.path=%s",
	     addr.sun_path);
	info("or qrap, for earlier qemu versions:");
	info("    ./qrap 5 kvm ... -net socket,fd=5 -net nic,model=virtio");
}

/**
 * tap_listen_handler() - Handle new connection on listening socket
 * @c:		Execution context
 * @events:	epoll events
 */
void tap_listen_handler(struct ctx *c, uint32_t events)
{
	union epoll_ref ref = { .type = EPOLL_TYPE_TAP_PASST };
	struct epoll_event ev = { 0 };
	int v = INT_MAX / 2;
	struct ucred ucred;
	socklen_t len;

	if (events != EPOLLIN)
		die("Error on listening Unix socket, exiting");

	len = sizeof(ucred);

	/* Another client is already connected: accept and close right away. */
	if (c->fd_tap != -1) {
		int discard = accept4(c->fd_tap_listen, NULL, NULL,
				      SOCK_NONBLOCK);

		if (discard == -1)
			return;

		if (!getsockopt(discard, SOL_SOCKET, SO_PEERCRED, &ucred, &len))
			info("discarding connection from PID %i", ucred.pid);

		close(discard);

		return;
	}

	c->fd_tap = accept4(c->fd_tap_listen, NULL, NULL, 0);

	if (!getsockopt(c->fd_tap, SOL_SOCKET, SO_PEERCRED, &ucred, &len))
		info("accepted connection from PID %i", ucred.pid);

	if (!c->low_rmem &&
	    setsockopt(c->fd_tap, SOL_SOCKET, SO_RCVBUF, &v, sizeof(v)))
		trace("tap: failed to set SO_RCVBUF to %i", v);

	if (!c->low_wmem &&
	    setsockopt(c->fd_tap, SOL_SOCKET, SO_SNDBUF, &v, sizeof(v)))
		trace("tap: failed to set SO_SNDBUF to %i", v);

	ref.fd = c->fd_tap;
	ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP;
	ev.data.u64 = ref.u64;
	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev);
}

/**
 * tap_ns_tun() - Get tuntap fd in namespace
 * @c:		Execution context
 *
 * Return: 0 on success, exits on failure
 *
 * #syscalls:pasta ioctl openat
 */
static int tap_ns_tun(void *arg)
{
	struct ifreq ifr = { .ifr_flags = IFF_TAP | IFF_NO_PI };
	int flags = O_RDWR | O_NONBLOCK | O_CLOEXEC;
	struct ctx *c = (struct ctx *)arg;
	int fd, rc;

	c->fd_tap = -1;
	memcpy(ifr.ifr_name, c->pasta_ifn, IFNAMSIZ);
	ns_enter(c);

	fd = open("/dev/net/tun", flags);
	if (fd < 0)
		die("Failed to open() /dev/net/tun: %s", strerror(errno));

	rc = ioctl(fd, TUNSETIFF, &ifr);
	if (rc < 0)
		die("TUNSETIFF failed: %s", strerror(errno));

	if (!(c->pasta_ifi = if_nametoindex(c->pasta_ifn)))
		die("Tap device opened but no network interface found");

	c->fd_tap = fd;

	return 0;
}

/**
 * tap_sock_tun_init() - Set up /dev/net/tun file descriptor
 * @c:		Execution context
 */
static void tap_sock_tun_init(struct ctx *c)
{
	union epoll_ref ref = { .type = EPOLL_TYPE_TAP_PASTA };
	struct epoll_event ev = { 0 };

	NS_CALL(tap_ns_tun, c);
	if (c->fd_tap == -1)
		die("Failed to set up tap device in namespace");

	pasta_ns_conf(c);

	ref.fd = c->fd_tap;
	ev.events = EPOLLIN | EPOLLRDHUP;
	ev.data.u64 = ref.u64;
	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev);
}

/**
 * tap_sock_init() - Create and set up AF_UNIX socket or tuntap file descriptor
 * @c:		Execution context
 */
void tap_sock_init(struct ctx *c)
{
	size_t sz = sizeof(pkt_buf);
	int i;

	pool_tap4_storage = PACKET_INIT(pool_tap4, TAP_MSGS, pkt_buf, sz);
	pool_tap6_storage = PACKET_INIT(pool_tap6, TAP_MSGS, pkt_buf, sz);

	for (i = 0; i < TAP_SEQS; i++) {
		tap4_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz);
		tap6_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz);
	}

	if (c->fd_tap != -1) { /* Passed as --fd */
		struct epoll_event ev = { 0 };
		union epoll_ref ref;

		ASSERT(c->one_off);
		ref.fd = c->fd_tap;
		if (c->mode == MODE_PASST)
			ref.type = EPOLL_TYPE_TAP_PASST;
		else
			ref.type = EPOLL_TYPE_TAP_PASTA;

		ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP;
		ev.data.u64 = ref.u64;
		epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev);
		return;
	}

	if (c->mode == MODE_PASST) {
		if (c->fd_tap_listen == -1)
			tap_sock_unix_init(c);
	} else {
		tap_sock_tun_init(c);
	}
}

debug log:

solving 5db7b169 ...
found 5db7b169 in https://archives.passt.top/passt-dev/20240429070933.1366881-7-david@gibson.dropbear.id.au/
found 6a08cca6 in https://archives.passt.top/passt-dev/20240429070933.1366881-4-david@gibson.dropbear.id.au/
found 13e4da79 in https://passt.top/passt
preparing index
index prepared:
100644 13e4da79d690a316ac3c2f12ed46dac2c901a97e	tap.c

applying [1/2] https://archives.passt.top/passt-dev/20240429070933.1366881-4-david@gibson.dropbear.id.au/
diff --git a/tap.c b/tap.c
index 13e4da79..6a08cca6 100644


applying [2/2] https://archives.passt.top/passt-dev/20240429070933.1366881-7-david@gibson.dropbear.id.au/
diff --git a/tap.c b/tap.c
index 6a08cca6..5db7b169 100644

Checking patch tap.c...
Applied patch tap.c cleanly.
Checking patch tap.c...
Applied patch tap.c cleanly.

index at:
100644 5db7b1698ce385bf22aa7221d1e7cbe088a865aa	tap.c

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).