public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob efd4037ed00806aa3b526ee750fee05153dd6da5 74062 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
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
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
 
// 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
 *
 * tcp.c - TCP L2-L4 translation state machine
 *
 * Copyright (c) 2020-2022 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

/**
 * DOC: Theory of Operation
 *
 *
 * PASST mode
 * ==========
 *
 * This implementation maps TCP traffic between a single L2 interface (tap) and
 * native TCP (L4) sockets, mimicking and reproducing as closely as possible the
 * inferred behaviour of applications running on a guest, connected via said L2
 * interface. Four connection flows are supported:
 * - from the local host to the guest behind the tap interface:
 *   - this is the main use case for proxies in service meshes
 *   - we bind to configured local ports, and relay traffic between L4 sockets
 *     with local endpoints and the L2 interface
 * - from remote hosts to the guest behind the tap interface:
 *   - this might be needed for services that need to be addressed directly,
 *     and typically configured with special port forwarding rules (which are
 *     not needed here)
 *   - we also relay traffic between L4 sockets with remote endpoints and the L2
 *     interface
 * - from the guest to the local host:
 *   - this is not observed in practice, but implemented for completeness and
 *     transparency
 * - from the guest to external hosts:
 *   - this might be needed for applications running on the guest that need to
 *     directly access internet services (e.g. NTP)
 *
 * Relevant goals are:
 * - transparency: sockets need to behave as if guest applications were running
 *   directly on the host. This is achieved by:
 *   - avoiding port and address translations whenever possible
 *   - mirroring TCP dynamics by observation of socket parameters (TCP_INFO
 *     socket option) and TCP headers of packets coming from the tap interface,
 *     reapplying those parameters in both flow directions (including TCP_MSS
 *     socket option)
 * - simplicity: only a small subset of TCP logic is implemented here and
 *   delegated as much as possible to the TCP implementations of guest and host
 *   kernel. This is achieved by:
 *   - avoiding a complete TCP stack reimplementation, with a modified TCP state
 *     machine focused on the translation of observed events instead
 *   - mirroring TCP dynamics as described above and hence avoiding the need for
 *     segmentation, explicit queueing, and reassembly of segments
 * - security:
 *   - no dynamic memory allocation is performed
 *   - TODO: synflood protection
 *
 * Portability is limited by usage of Linux-specific socket options.
 *
 *
 * Limits
 * ------
 *
 * To avoid the need for dynamic memory allocation, a maximum, reasonable amount
 * of connections is defined by TCP_MAX_CONNS (currently 128k).
 *
 * Data needs to linger on sockets as long as it's not acknowledged by the
 * guest, and is read using MSG_PEEK into preallocated static buffers sized
 * to the maximum supported window, 16 MiB ("discard" buffer, for already-sent
 * data) plus a number of maximum-MSS-sized buffers. This imposes a practical
 * limitation on window scaling, that is, the maximum factor is 256. Larger
 * factors will be accepted, but resulting, larger values are never advertised
 * to the other side, and not used while queueing data.
 *
 *
 * Ports
 * -----
 *
 * To avoid the need for ad-hoc configuration of port forwarding or allowed
 * ports, listening sockets can be opened and bound to all unbound ports on the
 * host, as far as process capabilities allow. This service needs to be started
 * after any application proxy that needs to bind to local ports. Mapped ports
 * can also be configured explicitly.
 *
 * No port translation is needed for connections initiated remotely or by the
 * local host: source port from socket is reused while establishing connections
 * to the guest.
 *
 * For connections initiated by the guest, it's not possible to force the same
 * source port as connections are established by the host kernel: that's the
 * only port translation needed.
 *
 *
 * Connection tracking and storage
 * -------------------------------
 *
 * Connections are tracked by struct tcp_tap_conn entries in the @tc
 * array, containing addresses, ports, TCP states and parameters. This
 * is statically allocated and indexed by an arbitrary connection
 * number. The array is compacted whenever a connection is closed, by
 * remapping the highest connection index in use to the one freed up.
 *
 * References used for the epoll interface report the connection index used for
 * the @tc array.
 *
 * IPv4 addresses are stored as IPv4-mapped IPv6 addresses to avoid the need for
 * separate data structures depending on the protocol version.
 *
 * - Inbound connection requests (to the guest) are mapped using the triple
 *   < source IP address, source port, destination port >
 * - Outbound connection requests (from the guest) are mapped using the triple
 *   < destination IP address, destination port, source port >
 *   where the source port is the one used by the guest, not the one used by the
 *   corresponding host socket
 *
 *
 * Initialisation
 * --------------
 *
 * Up to 2^15 + 2^14 listening sockets (excluding ephemeral ports, repeated for
 * IPv4 and IPv6) can be opened and bound to wildcard addresses. Some will fail
 * to bind (for low ports, or ports already bound, e.g. by a proxy). These are
 * added to the epoll list, with no separate storage.
 *
 *
 * Events and states
 * -----------------
 *
 * Instead of tracking connection states using a state machine, connection
 * events are used to determine state and actions for a given connection. This
 * makes the implementation simpler as most of the relevant tasks deal with
 * reactions to events, rather than state-associated actions. For user
 * convenience, approximate states are mapped in logs from events by
 * @tcp_state_str.
 *
 * The events are:
 *
 * - SOCK_ACCEPTED	connection accepted from socket, SYN sent to tap/guest
 *
 * - TAP_SYN_RCVD	tap/guest initiated connection, SYN received
 *
 * - TAP_SYN_ACK_SENT	SYN, ACK sent to tap/guest, valid for TAP_SYN_RCVD only
 *
 * - ESTABLISHED	connection established, the following events are valid:
 *
 * - SOCK_FIN_RCVD	FIN (EPOLLRDHUP) received from socket
 *
 * - SOCK_FIN_SENT	FIN (write shutdown) sent to socket
 *
 * - TAP_FIN_RCVD	FIN received from tap/guest
 *
 * - TAP_FIN_SENT	FIN sent to tap/guest
 *
 * - TAP_FIN_ACKED	ACK to FIN seen from tap/guest
 *
 * Setting any event in CONN_STATE_BITS (SOCK_ACCEPTED, TAP_SYN_RCVD,
 * ESTABLISHED) clears all the other events, as those represent the fundamental
 * connection states. No events (events == CLOSED) means the connection is
 * closed.
 *
 * Connection setup
 * ----------------
 *
 * - inbound connection (from socket to guest): on accept() from listening
 *   socket, the new socket is mapped in connection tracking table, and
 *   three-way handshake initiated towards the guest, advertising MSS and window
 *   size and scaling from socket parameters
 * - outbound connection (from guest to socket): on SYN segment from guest, a
 *   new socket is created and mapped in connection tracking table, setting
 *   MSS and window clamping from header and option of the observed SYN segment
 *
 *
 * Aging and timeout
 * -----------------
 *
 * Timeouts are implemented by means of timerfd timers, set based on flags:
 *
 * - SYN_TIMEOUT: if no ACK is received from tap/guest during handshake (flag
 *   ACK_FROM_TAP_DUE without ESTABLISHED event) within this time, reset the
 *   connection
 *
 * - ACK_TIMEOUT: if no ACK segment was received from tap/guest, after sending
 *   data (flag ACK_FROM_TAP_DUE with ESTABLISHED event), re-send data from the
 *   socket and reset sequence to what was acknowledged. If this persists for
 *   more than TCP_MAX_RETRANS times in a row, reset the connection
 *
 * - FIN_TIMEOUT: if a FIN segment was sent to tap/guest (flag ACK_FROM_TAP_DUE
 *   with TAP_FIN_SENT event), and no ACK is received within this time, reset
 *   the connection
 *
 * - FIN_TIMEOUT: if a FIN segment was acknowledged by tap/guest and a FIN
 *   segment (write shutdown) was sent via socket (events SOCK_FIN_SENT and
 *   TAP_FIN_ACKED), but no socket activity is detected from the socket within
 *   this time, reset the connection
 *
 * - ACT_TIMEOUT, in the presence of any event: if no activity is detected on
 *   either side, the connection is reset
 *
 * - ACK_INTERVAL elapsed after data segment received from tap without having
 *   sent an ACK segment, or zero-sized window advertised to tap/guest (flag
 *   ACK_TO_TAP_DUE): forcibly check if an ACK segment can be sent
 *
 *
 * Summary of data flows (with ESTABLISHED event)
 * ----------------------------------------------
 *
 * @seq_to_tap:		next sequence for packets to tap/guest
 * @seq_ack_from_tap:	last ACK number received from tap/guest
 * @seq_from_tap:	next sequence for packets from tap/guest (expected)
 * @seq_ack_to_tap:	last ACK number sent to tap/guest
 *
 * @seq_init_from_tap:	initial sequence number from tap/guest
 * @seq_init_to_tap:	initial sequence number from tap/guest
 *
 * @wnd_from_tap:	last window size received from tap, never scaled
 * @wnd_from_tap:	last window size advertised from tap, never scaled
 *
 * - from socket to tap/guest:
 *   - on new data from socket:
 *     - peek into buffer
 *     - send data to tap/guest:
 *       - starting at offset (@seq_to_tap - @seq_ack_from_tap)
 *       - in MSS-sized segments
 *       - increasing @seq_to_tap at each segment
 *       - up to window (until @seq_to_tap - @seq_ack_from_tap <= @wnd_from_tap)
 *     - on read error, send RST to tap/guest, close socket
 *     - on zero read, send FIN to tap/guest, set TAP_FIN_SENT
 *   - on ACK from tap/guest:
 *     - set @ts_ack_from_tap
 *     - check if it's the second duplicated ACK
 *     - consume buffer by difference between new ack_seq and @seq_ack_from_tap
 *     - update @seq_ack_from_tap from ack_seq in header
 *     - on two duplicated ACKs, reset @seq_to_tap to @seq_ack_from_tap, and
 *       resend with steps listed above
 *
 * - from tap/guest to socket:
 *   - on packet from tap/guest:
 *     - set @ts_tap_act
 *     - check seq from header against @seq_from_tap, if data is missing, send
 *       two ACKs with number @seq_ack_to_tap, discard packet
 *     - otherwise queue data to socket, set @seq_from_tap to seq from header
 *       plus payload length
 *     - in ESTABLISHED state, send ACK to tap as soon as we queue to the
 *       socket. In other states, query socket for TCP_INFO, set
 *       @seq_ack_to_tap to (tcpi_bytes_acked + @seq_init_from_tap) % 2^32 and
 *       send ACK to tap/guest
 *
 *
 * PASTA mode
 * ==========
 *
 * For traffic directed to TCP ports configured for mapping to the tuntap device
 * in the namespace, and for non-local traffic coming from the tuntap device,
 * the implementation is identical as the PASST mode described in the previous
 * section.
 *
 * For local traffic directed to TCP ports configured for direct mapping between
 * namespaces, see the implementation in tcp_splice.c.
 */

#include <sched.h>
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <signal.h>
#include <stdlib.h>
#include <errno.h>
#include <limits.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <stdint.h>
#include <stdbool.h>
#include <stddef.h>
#include <string.h>
#include <sys/epoll.h>
#include <sys/socket.h>
#include <sys/timerfd.h>
#include <sys/types.h>
#include <sys/uio.h>
#include <time.h>
#include <arpa/inet.h>

#include <linux/tcp.h> /* For struct tcp_info */

#include "checksum.h"
#include "util.h"
#include "iov.h"
#include "ip.h"
#include "passt.h"
#include "tap.h"
#include "siphash.h"
#include "pcap.h"
#include "tcp_splice.h"
#include "log.h"
#include "inany.h"
#include "flow.h"

#include "flow_table.h"
#include "tcp_internal.h"
#include "tcp_buf.h"

/* MSS rounding: see SET_MSS() */
#define MSS_DEFAULT			536
#define WINDOW_DEFAULT			14600		/* RFC 6928 */

#define ACK_INTERVAL			10		/* ms */
#define SYN_TIMEOUT			10		/* s */
#define ACK_TIMEOUT			2
#define FIN_TIMEOUT			60
#define ACT_TIMEOUT			7200

#define LOW_RTT_TABLE_SIZE		8
#define LOW_RTT_THRESHOLD		10 /* us */

/* We need to include <linux/tcp.h> for tcpi_bytes_acked, instead of
 * <netinet/tcp.h>, but that doesn't include a definition for SOL_TCP
 */
#define SOL_TCP				IPPROTO_TCP

#define ACK_IF_NEEDED	0		/* See tcp_send_flag() */

#define CONN_IS_CLOSING(conn)						\
	(((conn)->events & ESTABLISHED) &&				\
	 ((conn)->events & (SOCK_FIN_RCVD | TAP_FIN_RCVD)))
#define CONN_HAS(conn, set)	(((conn)->events & (set)) == (set))

static const char *tcp_event_str[] __attribute((__unused__)) = {
	"SOCK_ACCEPTED", "TAP_SYN_RCVD", "ESTABLISHED", "TAP_SYN_ACK_SENT",

	"SOCK_FIN_RCVD", "SOCK_FIN_SENT", "TAP_FIN_RCVD", "TAP_FIN_SENT",
	"TAP_FIN_ACKED",
};

static const char *tcp_state_str[] __attribute((__unused__)) = {
	"SYN_RCVD", "SYN_SENT", "ESTABLISHED",
	"SYN_RCVD",	/* approximately maps to TAP_SYN_ACK_SENT */

	/* Passive close: */
	"CLOSE_WAIT", "CLOSE_WAIT", "LAST_ACK", "LAST_ACK", "LAST_ACK",
	/* Active close (+5): */
	"CLOSING", "FIN_WAIT_1", "FIN_WAIT_1", "FIN_WAIT_2", "TIME_WAIT",
};

static const char *tcp_flag_str[] __attribute((__unused__)) = {
	"STALLED", "LOCAL", "ACTIVE_CLOSE", "ACK_TO_TAP_DUE",
	"ACK_FROM_TAP_DUE",
};

/* Listening sockets, used for automatic port forwarding in pasta mode only */
static int tcp_sock_init_ext	[NUM_PORTS][IP_VERSIONS];
static int tcp_sock_ns		[NUM_PORTS][IP_VERSIONS];

/* Table of our guest side addresses with very low RTT (assumed to be local to
 * the host), LRU
 */
static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];

char		tcp_buf_discard		[MAX_WINDOW];

/* Does the kernel support TCP_PEEK_OFF? */
bool peek_offset_cap;
#ifdef HAS_SND_WND
/* Does the kernel report sending window in TCP_INFO (kernel commit
 * 8f7baad7f035)
 */
bool snd_wnd_cap;
#else
#define snd_wnd_cap	(false)
#endif

/* sendmsg() to socket */
static struct iovec	tcp_iov			[UIO_MAXIOV];

/* Pools for pre-opened sockets (in init) */
int init_sock_pool4		[TCP_SOCK_POOL_SIZE];
int init_sock_pool6		[TCP_SOCK_POOL_SIZE];

/**
 * conn_at_sidx() - Get TCP connection specific flow at given sidx
 * @sidx:	Flow and side to retrieve
 *
 * Return: TCP connection at @sidx, or NULL of @sidx is invalid.  Asserts if the
 *         flow at @sidx is not FLOW_TCP.
 */
static struct tcp_tap_conn *conn_at_sidx(flow_sidx_t sidx)
{
	union flow *flow = flow_at_sidx(sidx);

	if (!flow)
		return NULL;

	ASSERT(flow->f.type == FLOW_TCP);
	return &flow->tcp;
}

/**
 * tcp_set_peek_offset() - Set SO_PEEK_OFF offset on a socket if supported
 * @s:          Socket to update
 * @offset:     Offset in bytes
 *
 * Return:      -1 when it fails, 0 otherwise.
 */
int tcp_set_peek_offset(int s, int offset)
{
	if (!peek_offset_cap)
		return 0;

	if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset))) {
		err("Failed to set SO_PEEK_OFF to %i in socket %i", offset, s);
		return -1;
	}
	return 0;
}

/**
 * tcp_conn_epoll_events() - epoll events mask for given connection state
 * @events:	Current connection events
 * @conn_flags	Connection flags
 *
 * Return: epoll events mask corresponding to implied connection state
 */
static uint32_t tcp_conn_epoll_events(uint8_t events, uint8_t conn_flags)
{
	if (!events)
		return 0;

	if (events & ESTABLISHED) {
		if (events & TAP_FIN_SENT)
			return EPOLLET;

		if (conn_flags & STALLED)
			return EPOLLIN | EPOLLOUT | EPOLLRDHUP | EPOLLET;

		return EPOLLIN | EPOLLRDHUP;
	}

	if (events == TAP_SYN_RCVD)
		return EPOLLOUT | EPOLLET | EPOLLRDHUP;

	return EPOLLET | EPOLLRDHUP;
}

/**
 * tcp_epoll_ctl() - Add/modify/delete epoll state from connection events
 * @c:		Execution context
 * @conn:	Connection pointer
 *
 * Return: 0 on success, negative error code on failure (not on deletion)
 */
static int tcp_epoll_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
{
	int m = conn->in_epoll ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
	union epoll_ref ref = { .type = EPOLL_TYPE_TCP, .fd = conn->sock,
		                .flowside = FLOW_SIDX(conn, !TAPSIDE(conn)), };
	struct epoll_event ev = { .data.u64 = ref.u64 };

	if (conn->events == CLOSED) {
		if (conn->in_epoll)
			epoll_ctl(c->epollfd, EPOLL_CTL_DEL, conn->sock, &ev);
		if (conn->timer != -1)
			epoll_ctl(c->epollfd, EPOLL_CTL_DEL, conn->timer, &ev);
		return 0;
	}

	ev.events = tcp_conn_epoll_events(conn->events, conn->flags);

	if (epoll_ctl(c->epollfd, m, conn->sock, &ev))
		return -errno;

	conn->in_epoll = true;

	if (conn->timer != -1) {
		union epoll_ref ref_t = { .type = EPOLL_TYPE_TCP_TIMER,
					  .fd = conn->sock,
					  .flow = FLOW_IDX(conn) };
		struct epoll_event ev_t = { .data.u64 = ref_t.u64,
					    .events = EPOLLIN | EPOLLET };

		if (epoll_ctl(c->epollfd, EPOLL_CTL_MOD, conn->timer, &ev_t))
			return -errno;
	}

	return 0;
}

/**
 * tcp_timer_ctl() - Set timerfd based on flags/events, create timerfd if needed
 * @c:		Execution context
 * @conn:	Connection pointer
 *
 * #syscalls timerfd_create timerfd_settime
 */
static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
{
	struct itimerspec it = { { 0 }, { 0 } };

	if (conn->events == CLOSED)
		return;

	if (conn->timer == -1) {
		union epoll_ref ref = { .type = EPOLL_TYPE_TCP_TIMER,
					.fd = conn->sock,
					.flow = FLOW_IDX(conn) };
		struct epoll_event ev = { .data.u64 = ref.u64,
					  .events = EPOLLIN | EPOLLET };
		int fd;

		fd = timerfd_create(CLOCK_MONOTONIC, 0);
		if (fd == -1 || fd > FD_REF_MAX) {
			flow_dbg(conn, "failed to get timer: %s",
				 strerror(errno));
			if (fd > -1)
				close(fd);
			conn->timer = -1;
			return;
		}
		conn->timer = fd;

		if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, conn->timer, &ev)) {
			flow_dbg(conn, "failed to add timer: %s",
				 strerror(errno));
			close(conn->timer);
			conn->timer = -1;
			return;
		}
	}

	if (conn->flags & ACK_TO_TAP_DUE) {
		it.it_value.tv_nsec = (long)ACK_INTERVAL * 1000 * 1000;
	} else if (conn->flags & ACK_FROM_TAP_DUE) {
		if (!(conn->events & ESTABLISHED))
			it.it_value.tv_sec = SYN_TIMEOUT;
		else
			it.it_value.tv_sec = ACK_TIMEOUT;
	} else if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED)) {
		it.it_value.tv_sec = FIN_TIMEOUT;
	} else {
		it.it_value.tv_sec = ACT_TIMEOUT;
	}

	flow_dbg(conn, "timer expires in %llu.%03llus",
		 (unsigned long long)it.it_value.tv_sec,
		 (unsigned long long)it.it_value.tv_nsec / 1000 / 1000);

	timerfd_settime(conn->timer, 0, &it, NULL);
}

/**
 * conn_flag_do() - Set/unset given flag, log, update epoll on STALLED flag
 * @c:		Execution context
 * @conn:	Connection pointer
 * @flag:	Flag to set, or ~flag to unset
 */
void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
		  unsigned long flag)
{
	if (flag & (flag - 1)) {
		int flag_index = fls(~flag);

		if (!(conn->flags & ~flag))
			return;

		conn->flags &= flag;
		if (flag_index >= 0)
			flow_dbg(conn, "%s dropped", tcp_flag_str[flag_index]);
	} else {
		int flag_index = fls(flag);

		if (conn->flags & flag) {
			/* Special case: setting ACK_FROM_TAP_DUE on a
			 * connection where it's already set is used to
			 * re-schedule the existing timer.
			 * TODO: define clearer semantics for timer-related
			 * flags and factor this into the logic below.
			 */
			if (flag == ACK_FROM_TAP_DUE)
				tcp_timer_ctl(c, conn);

			return;
		}

		conn->flags |= flag;
		if (flag_index >= 0)
			flow_dbg(conn, "%s", tcp_flag_str[flag_index]);
	}

	if (flag == STALLED || flag == ~STALLED)
		tcp_epoll_ctl(c, conn);

	if (flag == ACK_FROM_TAP_DUE || flag == ACK_TO_TAP_DUE		  ||
	    (flag == ~ACK_FROM_TAP_DUE && (conn->flags & ACK_TO_TAP_DUE)) ||
	    (flag == ~ACK_TO_TAP_DUE   && (conn->flags & ACK_FROM_TAP_DUE)))
		tcp_timer_ctl(c, conn);
}

/**
 * conn_event_do() - Set and log connection events, update epoll state
 * @c:		Execution context
 * @conn:	Connection pointer
 * @event:	Connection event
 */
void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
		   unsigned long event)
{
	int prev, new, num = fls(event);

	if (conn->events & event)
		return;

	prev = fls(conn->events);
	if (conn->flags & ACTIVE_CLOSE)
		prev += 5;

	if ((conn->events & ESTABLISHED) && (conn->events != ESTABLISHED))
		prev++;		/* i.e. SOCK_FIN_RCVD, not TAP_SYN_ACK_SENT */

	if (event == CLOSED || (event & CONN_STATE_BITS))
		conn->events = event;
	else
		conn->events |= event;

	new = fls(conn->events);

	if ((conn->events & ESTABLISHED) && (conn->events != ESTABLISHED)) {
		num++;
		new++;
	}
	if (conn->flags & ACTIVE_CLOSE)
		new += 5;

	if (prev != new)
		flow_dbg(conn, "%s: %s -> %s",
			 num == -1 	       ? "CLOSED" : tcp_event_str[num],
			 prev == -1	       ? "CLOSED" : tcp_state_str[prev],
			 (new == -1 || num == -1) ? "CLOSED" : tcp_state_str[new]);
	else
		flow_dbg(conn, "%s",
			 num == -1 	       ? "CLOSED" : tcp_event_str[num]);

	if (event == CLOSED)
		flow_hash_remove(c, TAP_SIDX(conn));
	else if ((event == TAP_FIN_RCVD) && !(conn->events & SOCK_FIN_RCVD))
		conn_flag(c, conn, ACTIVE_CLOSE);
	else
		tcp_epoll_ctl(c, conn);

	if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED))
		tcp_timer_ctl(c, conn);
}

/**
 * tcp_rtt_dst_low() - Check if low RTT was seen for connection endpoint
 * @conn:	Connection pointer
 *
 * Return: 1 if destination is in low RTT table, 0 otherwise
 */
static int tcp_rtt_dst_low(const struct tcp_tap_conn *conn)
{
	const struct flowside *tapside = TAPFLOW(conn);
	int i;

	for (i = 0; i < LOW_RTT_TABLE_SIZE; i++)
		if (inany_equals(&tapside->oaddr, low_rtt_dst + i))
			return 1;

	return 0;
}

/**
 * tcp_rtt_dst_check() - Check tcpi_min_rtt, insert endpoint in table if low
 * @conn:	Connection pointer
 * @tinfo:	Pointer to struct tcp_info for socket
 */
static void tcp_rtt_dst_check(const struct tcp_tap_conn *conn,
			      const struct tcp_info *tinfo)
{
#ifdef HAS_MIN_RTT
	const struct flowside *tapside = TAPFLOW(conn);
	int i, hole = -1;

	if (!tinfo->tcpi_min_rtt ||
	    (int)tinfo->tcpi_min_rtt > LOW_RTT_THRESHOLD)
		return;

	for (i = 0; i < LOW_RTT_TABLE_SIZE; i++) {
		if (inany_equals(&tapside->oaddr, low_rtt_dst + i))
			return;
		if (hole == -1 && IN6_IS_ADDR_UNSPECIFIED(low_rtt_dst + i))
			hole = i;
	}

	/* Keep gcc 12 happy: this won't actually happen because the table is
	 * guaranteed to have a hole, see the second memcpy() below.
	 */
	if (hole == -1)
		return;

	low_rtt_dst[hole++] = tapside->oaddr;
	if (hole == LOW_RTT_TABLE_SIZE)
		hole = 0;
	inany_from_af(low_rtt_dst + hole, AF_INET6, &in6addr_any);
#else
	(void)conn;
	(void)tinfo;
#endif /* HAS_MIN_RTT */
}

/**
 * tcp_get_sndbuf() - Get, scale SO_SNDBUF between thresholds (1 to 0.5 usage)
 * @conn:	Connection pointer
 */
static void tcp_get_sndbuf(struct tcp_tap_conn *conn)
{
	int s = conn->sock, sndbuf;
	socklen_t sl;
	uint64_t v;

	sl = sizeof(sndbuf);
	if (getsockopt(s, SOL_SOCKET, SO_SNDBUF, &sndbuf, &sl)) {
		SNDBUF_SET(conn, WINDOW_DEFAULT);
		return;
	}

	v = sndbuf;
	if (v >= SNDBUF_BIG)
		v /= 2;
	else if (v > SNDBUF_SMALL)
		v -= v * (v - SNDBUF_SMALL) / (SNDBUF_BIG - SNDBUF_SMALL) / 2;

	SNDBUF_SET(conn, MIN(INT_MAX, v));
}

/**
 * tcp_sock_set_bufsize() - Set SO_RCVBUF and SO_SNDBUF to maximum values
 * @s:		Socket, can be -1 to avoid check in the caller
 */
static void tcp_sock_set_bufsize(const struct ctx *c, int s)
{
	int v = INT_MAX / 2; /* Kernel clamps and rounds, no need to check */

	if (s == -1)
		return;

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

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

/**
 * tcp_update_check_tcp4() - Calculate TCP checksum for IPv6
 * @src:		IPv4 source address
 * @dst:		IPv4 destination address
 * @iov:		Pointer to the array of IO vectors
 * @iov_cnt:		Length of the array
 * @payload_offset:	IPv4 payload offset in the iovec array
 */
void tcp_update_check_tcp4(struct in_addr src,
			   struct in_addr dst,
			   const struct iovec *iov, int iov_cnt,
			   size_t payload_offset)
{
	size_t check_ofs;
	__sum16 *check;
	int check_idx;
	uint32_t sum;

	sum = proto_ipv4_header_psum(iov_size(iov, iov_cnt) - payload_offset,
				     IPPROTO_TCP, src, dst);

	check_idx = iov_skip_bytes(iov, iov_cnt,
				payload_offset + offsetof(struct tcphdr, check),
				&check_ofs);

	check = (__sum16 *)((char *)iov[check_idx].iov_base + check_ofs);

	*check = 0;
	*check = csum_iov(iov, iov_cnt, payload_offset, sum);
}

/**
 * tcp_update_check_tcp6() - Calculate TCP checksum for IPv6
 * @src:		IPv6 source address
 * @dst:		IPv6 destination address
 * @iov:		Pointer to the array of IO vectors
 * @iov_cnt:		Length of the array
 * @payload_offset:	IPv6 payload offset in the iovec array
 */
void tcp_update_check_tcp6(const struct in6_addr *src,
			   const struct in6_addr *dst,
			   const struct iovec *iov, int iov_cnt,
			   size_t payload_offset)
{
	size_t check_ofs;
	__sum16 *check;
	int check_idx;
	uint32_t sum;

	sum = proto_ipv6_header_psum(iov_size(iov, iov_cnt) - payload_offset,
				     IPPROTO_TCP, src, dst);

	check_idx = iov_skip_bytes(iov, iov_cnt,
				payload_offset + offsetof(struct tcphdr, check),
				&check_ofs);

	check = (__sum16 *)((char *)iov[check_idx].iov_base + check_ofs);

	*check = 0;
	*check = csum_iov(iov, iov_cnt, payload_offset, sum);
}

/**
 * tcp_opt_get() - Get option, and value if any, from TCP header
 * @opts:	Pointer to start of TCP options in header
 * @len:	Length of buffer, excluding TCP header -- NOT checked here!
 * @type_find:	Option type to look for
 * @optlen_set:	Optional, filled with option length if passed
 * @value_set:	Optional, set to start of option value if passed
 *
 * Return: option value, meaningful for up to 4 bytes, -1 if not found
 */
static int tcp_opt_get(const char *opts, size_t len, uint8_t type_find,
		       uint8_t *optlen_set, const char **value_set)
{
	uint8_t type, optlen;

	if (!opts || !len)
		return -1;

	for (; len >= 2; opts += optlen, len -= optlen) {
		switch (*opts) {
		case OPT_EOL:
			return -1;
		case OPT_NOP:
			optlen = 1;
			break;
		default:
			type = *(opts++);

			if (*(uint8_t *)opts < 2 || *(uint8_t *)opts > len)
				return -1;

			optlen = *(opts++) - 2;
			len -= 2;

			if (type != type_find)
				break;

			if (optlen_set)
				*optlen_set = optlen;
			if (value_set)
				*value_set = opts;

			switch (optlen) {
			case 0:
				return 0;
			case 1:
				return *opts;
			case 2:
				return ntohs(*(uint16_t *)opts);
			default:
				return ntohl(*(uint32_t *)opts);
			}
		}
	}

	return -1;
}

/**
 * tcp_flow_defer() - Deferred per-flow handling (clean up closed connections)
 * @conn:	Connection to handle
 *
 * Return: true if the connection is ready to free, false otherwise
 */
bool tcp_flow_defer(const struct tcp_tap_conn *conn)
{
	if (conn->events != CLOSED)
		return false;

	close(conn->sock);
	if (conn->timer != -1)
		close(conn->timer);

	return true;
}

/**
 * tcp_defer_handler() - Handler for TCP deferred tasks
 * @c:		Execution context
 */
/* cppcheck-suppress [constParameterPointer, unmatchedSuppression] */
void tcp_defer_handler(struct ctx *c)
{
	tcp_flags_flush(c);
	tcp_payload_flush(c);
}

/**
 * tcp_fill_header() - Fill the TCP header fields for a given TCP segment.
 *
 * @th:		Pointer to the TCP header structure
 * @conn:	Pointer to the TCP connection structure
 * @seq:	Sequence number
 */
static void tcp_fill_header(struct tcphdr *th,
			    const struct tcp_tap_conn *conn, uint32_t seq)
{
	const struct flowside *tapside = TAPFLOW(conn);

	th->source = htons(tapside->oport);
	th->dest = htons(tapside->eport);
	th->seq = htonl(seq);
	th->ack_seq = htonl(conn->seq_ack_to_tap);
	if (conn->events & ESTABLISHED)	{
		th->window = htons(conn->wnd_to_tap);
	} else {
		unsigned wnd = conn->wnd_to_tap << conn->ws_to_tap;

		th->window = htons(MIN(wnd, USHRT_MAX));
	}
}

/**
 * tcp_fill_headers4() - Fill 802.3, IPv4, TCP headers in pre-cooked buffers
 * @conn:		Connection pointer
 * @taph:		tap backend specific header
 * @iph:		Pointer to IPv4 header
 * @bp:			Pointer to TCP header followed by TCP payload
 * @dlen:		TCP payload length
 * @check:		Checksum, if already known
 * @seq:		Sequence number for this segment
 * @no_tcp_csum:	Do not set TCP checksum
 *
 * Return: The IPv4 payload length, host order
 */
static size_t tcp_fill_headers4(const struct tcp_tap_conn *conn,
				struct tap_hdr *taph,
				struct iphdr *iph, struct tcp_payload_t *bp,
				size_t dlen, const uint16_t *check,
				uint32_t seq, bool no_tcp_csum)
{
	const struct flowside *tapside = TAPFLOW(conn);
	const struct in_addr *src4 = inany_v4(&tapside->oaddr);
	const struct in_addr *dst4 = inany_v4(&tapside->eaddr);
	size_t l4len = dlen + sizeof(bp->th);
	size_t l3len = l4len + sizeof(*iph);

	ASSERT(src4 && dst4);

	iph->tot_len = htons(l3len);
	iph->saddr = src4->s_addr;
	iph->daddr = dst4->s_addr;

	iph->check = check ? *check :
			     csum_ip4_header(l3len, IPPROTO_TCP, *src4, *dst4);

	tcp_fill_header(&bp->th, conn, seq);

	if (no_tcp_csum) {
		bp->th.check = 0;
	} else {
		const struct iovec iov = {
			.iov_base = bp,
			.iov_len = ntohs(iph->tot_len) - sizeof(struct iphdr),
		};
		struct in_addr saddr = { .s_addr = iph->saddr };
		struct in_addr daddr = { .s_addr = iph->daddr };

		tcp_update_check_tcp4(saddr, daddr, &iov, 1, 0);
	}

	tap_hdr_update(taph, l3len + sizeof(struct ethhdr));

	return l4len;
}

/**
 * tcp_fill_headers6() - Fill 802.3, IPv6, TCP headers in pre-cooked buffers
 * @conn:		Connection pointer
 * @taph:		tap backend specific header
 * @ip6h:		Pointer to IPv6 header
 * @bp:			Pointer to TCP header followed by TCP payload
 * @dlen:		TCP payload length
 * @check:		Checksum, if already known
 * @seq:		Sequence number for this segment
 * @no_tcp_csum:	Do not set TCP checksum
 *
 * Return: The IPv6 payload length, host order
 */
static size_t tcp_fill_headers6(const struct tcp_tap_conn *conn,
				struct tap_hdr *taph,
				struct ipv6hdr *ip6h, struct tcp_payload_t *bp,
				size_t dlen, uint32_t seq, bool no_tcp_csum)
{
	const struct flowside *tapside = TAPFLOW(conn);
	size_t l4len = dlen + sizeof(bp->th);

	ip6h->payload_len = htons(l4len);
	ip6h->saddr = tapside->oaddr.a6;
	ip6h->daddr = tapside->eaddr.a6;

	ip6h->hop_limit = 255;
	ip6h->version = 6;
	ip6h->nexthdr = IPPROTO_TCP;

	ip6h->flow_lbl[0] = (conn->sock >> 16) & 0xf;
	ip6h->flow_lbl[1] = (conn->sock >> 8) & 0xff;
	ip6h->flow_lbl[2] = (conn->sock >> 0) & 0xff;

	tcp_fill_header(&bp->th, conn, seq);

	if (no_tcp_csum) {
		bp->th.check = 0;
	} else {
		const struct iovec iov = {
			.iov_base = bp,
			.iov_len = ntohs(ip6h->payload_len)
		};

		tcp_update_check_tcp6(&ip6h->saddr, &ip6h->daddr,
				      &iov, 1, 0);
	}

	tap_hdr_update(taph, l4len + sizeof(*ip6h) + sizeof(struct ethhdr));

	return l4len;
}

/**
 * tcp_l2_buf_fill_headers() - Fill 802.3, IP, TCP headers in pre-cooked buffers
 * @conn:	Connection pointer
 * @iov:	Pointer to an array of iovec of TCP pre-cooked buffers
 * @dlen:	TCP payload length
 * @check:	Checksum, if already known
 * @seq:	Sequence number for this segment
 * @no_tcp_csum: Do not set TCP checksum
 *
 * Return: IP payload length, host order
 */
size_t tcp_l2_buf_fill_headers(const struct tcp_tap_conn *conn,
			       struct iovec *iov, size_t dlen,
			       const uint16_t *check, uint32_t seq,
			       bool no_tcp_csum)
{
	const struct flowside *tapside = TAPFLOW(conn);
	const struct in_addr *a4 = inany_v4(&tapside->oaddr);

	if (a4) {
		return tcp_fill_headers4(conn, iov[TCP_IOV_TAP].iov_base,
					 iov[TCP_IOV_IP].iov_base,
					 iov[TCP_IOV_PAYLOAD].iov_base, dlen,
					 check, seq, no_tcp_csum);
	}

	return tcp_fill_headers6(conn, iov[TCP_IOV_TAP].iov_base,
				 iov[TCP_IOV_IP].iov_base,
				 iov[TCP_IOV_PAYLOAD].iov_base, dlen,
				 seq, no_tcp_csum);
}

/**
 * tcp_update_seqack_wnd() - Update ACK sequence and window to guest/tap
 * @c:		Execution context
 * @conn:	Connection pointer
 * @force_seq:	Force ACK sequence to latest segment, instead of checking socket
 * @tinfo:	tcp_info from kernel, can be NULL if not pre-fetched
 *
 * Return: 1 if sequence or window were updated, 0 otherwise
 */
int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn,
			  bool force_seq, struct tcp_info *tinfo)
{
	uint32_t prev_wnd_to_tap = conn->wnd_to_tap << conn->ws_to_tap;
	uint32_t prev_ack_to_tap = conn->seq_ack_to_tap;
	/* cppcheck-suppress [ctunullpointer, unmatchedSuppression] */
	socklen_t sl = sizeof(*tinfo);
	struct tcp_info tinfo_new;
	uint32_t new_wnd_to_tap = prev_wnd_to_tap;
	int s = conn->sock;

#ifndef HAS_BYTES_ACKED
	(void)force_seq;

	conn->seq_ack_to_tap = conn->seq_from_tap;
	if (SEQ_LT(conn->seq_ack_to_tap, prev_ack_to_tap))
		conn->seq_ack_to_tap = prev_ack_to_tap;
#else
	if ((unsigned)SNDBUF_GET(conn) < SNDBUF_SMALL || tcp_rtt_dst_low(conn)
	    || CONN_IS_CLOSING(conn) || (conn->flags & LOCAL) || force_seq) {
		conn->seq_ack_to_tap = conn->seq_from_tap;
	} else if (conn->seq_ack_to_tap != conn->seq_from_tap) {
		if (!tinfo) {
			tinfo = &tinfo_new;
			if (getsockopt(s, SOL_TCP, TCP_INFO, tinfo, &sl))
				return 0;
		}

		conn->seq_ack_to_tap = tinfo->tcpi_bytes_acked +
				       conn->seq_init_from_tap;

		if (SEQ_LT(conn->seq_ack_to_tap, prev_ack_to_tap))
			conn->seq_ack_to_tap = prev_ack_to_tap;
	}
#endif /* !HAS_BYTES_ACKED */

	if (!snd_wnd_cap) {
		tcp_get_sndbuf(conn);
		new_wnd_to_tap = MIN(SNDBUF_GET(conn), MAX_WINDOW);
		conn->wnd_to_tap = MIN(new_wnd_to_tap >> conn->ws_to_tap,
				       USHRT_MAX);
		goto out;
	}

	if (!tinfo) {
		if (prev_wnd_to_tap > WINDOW_DEFAULT) {
			goto out;
		}
		tinfo = &tinfo_new;
		if (getsockopt(s, SOL_TCP, TCP_INFO, tinfo, &sl)) {
			goto out;
		}
	}

	if ((conn->flags & LOCAL) || tcp_rtt_dst_low(conn)) {
		new_wnd_to_tap = tinfo->tcpi_snd_wnd;
	} else {
		tcp_get_sndbuf(conn);
		new_wnd_to_tap = MIN((int)tinfo->tcpi_snd_wnd,
				     SNDBUF_GET(conn));
	}

	new_wnd_to_tap = MIN(new_wnd_to_tap, MAX_WINDOW);
	if (!(conn->events & ESTABLISHED))
		new_wnd_to_tap = MAX(new_wnd_to_tap, WINDOW_DEFAULT);

	conn->wnd_to_tap = MIN(new_wnd_to_tap >> conn->ws_to_tap, USHRT_MAX);

	/* Certain cppcheck versions, e.g. 2.12.0 have a bug where they think
	 * the MIN() above restricts conn->wnd_to_tap to be zero.  That's
	 * clearly incorrect, but until the bug is fixed, work around it.
	 *   https://bugzilla.redhat.com/show_bug.cgi?id=2240705
	 *   https://sourceforge.net/p/cppcheck/discussion/general/thread/f5b1a00646/
	 */
	/* cppcheck-suppress [knownConditionTrueFalse, unmatchedSuppression] */
	if (!conn->wnd_to_tap)
		conn_flag(c, conn, ACK_TO_TAP_DUE);

out:
	return new_wnd_to_tap       != prev_wnd_to_tap ||
	       conn->seq_ack_to_tap != prev_ack_to_tap;
}

/**
 * tcp_update_seqack_from_tap() - ACK number from tap and related flags/counters
 * @c:		Execution context
 * @conn:	Connection pointer
 * @seq		Current ACK sequence, host order
 */
static void tcp_update_seqack_from_tap(const struct ctx *c,
				       struct tcp_tap_conn *conn, uint32_t seq)
{
	if (seq == conn->seq_to_tap)
		conn_flag(c, conn, ~ACK_FROM_TAP_DUE);

	if (SEQ_GT(seq, conn->seq_ack_from_tap)) {
		/* Forward progress, but more data to acknowledge: reschedule */
		if (SEQ_LT(seq, conn->seq_to_tap))
			conn_flag(c, conn, ACK_FROM_TAP_DUE);

		conn->retrans = 0;
		conn->seq_ack_from_tap = seq;
	}
}

/**
 * tcp_prepare_flags() - Prepare header for flags-only segment (no payload)
 * @c:		Execution context
 * @conn:	Connection pointer
 * @flags:	TCP flags: if not set, send segment only if ACK is due
 * @th:		TCP header to update
 * @data:	buffer to store TCP option
 * @optlen:	size of the TCP option buffer (output parameter)
 *
 * Return: < 0 error code on connection reset,
 *	     0 if there is no flag to send
 *	     1 otherwise
 */
int tcp_prepare_flags(const struct ctx *c, struct tcp_tap_conn *conn,
		      int flags, struct tcphdr *th, char *data,
		      size_t *optlen)
{
	struct tcp_info tinfo = { 0 };
	socklen_t sl = sizeof(tinfo);
	int s = conn->sock;

	if (SEQ_GE(conn->seq_ack_to_tap, conn->seq_from_tap) &&
	    !flags && conn->wnd_to_tap)
		return 0;

	if (getsockopt(s, SOL_TCP, TCP_INFO, &tinfo, &sl)) {
		conn_event(c, conn, CLOSED);
		return -ECONNRESET;
	}

	if (!(conn->flags & LOCAL))
		tcp_rtt_dst_check(conn, &tinfo);

	if (!tcp_update_seqack_wnd(c, conn, !!flags, &tinfo) && !flags)
		return 0;

	*optlen = 0;
	if (flags & SYN) {
		int mss;

		/* Options: MSS, NOP and window scale (8 bytes) */
		*optlen = OPT_MSS_LEN + 1 + OPT_WS_LEN;

		*data++ = OPT_MSS;
		*data++ = OPT_MSS_LEN;

		if (c->mtu == -1) {
			mss = tinfo.tcpi_snd_mss;
		} else {
			mss = c->mtu - sizeof(struct tcphdr);
			if (CONN_V4(conn))
				mss -= sizeof(struct iphdr);
			else
				mss -= sizeof(struct ipv6hdr);

			if (c->low_wmem &&
			    !(conn->flags & LOCAL) && !tcp_rtt_dst_low(conn))
				mss = MIN(mss, PAGE_SIZE);
			else if (mss > PAGE_SIZE)
				mss = ROUND_DOWN(mss, PAGE_SIZE);
		}
		*(uint16_t *)data = htons(MIN(USHRT_MAX, mss));

		data += OPT_MSS_LEN - 2;

		conn->ws_to_tap = MIN(MAX_WS, tinfo.tcpi_snd_wscale);

		*data++ = OPT_NOP;
		*data++ = OPT_WS;
		*data++ = OPT_WS_LEN;
		*data++ = conn->ws_to_tap;
	} else if (!(flags & RST)) {
		flags |= ACK;
	}

	th->doff = (sizeof(*th) + *optlen) / 4;

	th->ack = !!(flags & ACK);
	th->rst = !!(flags & RST);
	th->syn = !!(flags & SYN);
	th->fin = !!(flags & FIN);

	if (th->ack) {
		if (SEQ_GE(conn->seq_ack_to_tap, conn->seq_from_tap))
			conn_flag(c, conn, ~ACK_TO_TAP_DUE);
		else
			conn_flag(c, conn, ACK_TO_TAP_DUE);
	}

	if (th->fin)
		conn_flag(c, conn, ACK_FROM_TAP_DUE);

	/* RFC 793, 3.1: "[...] and the first data octet is ISN+1." */
	if (th->fin || th->syn)
		conn->seq_to_tap++;

	return 1;
}

/**
 * tcp_send_flag() - Send segment with flags to tap (no payload)
 * @c:         Execution context
 * @conn:      Connection pointer
 * @flags:     TCP flags: if not set, send segment only if ACK is due
 *
 * Return: negative error code on connection reset, 0 otherwise
 */
static int tcp_send_flag(const struct ctx *c, struct tcp_tap_conn *conn,
			 int flags)
{
	return tcp_buf_send_flag(c, conn, flags);
}

/**
 * tcp_rst_do() - Reset a tap connection: send RST segment to tap, close socket
 * @c:		Execution context
 * @conn:	Connection pointer
 */
void tcp_rst_do(const struct ctx *c, struct tcp_tap_conn *conn)
{
	if (conn->events == CLOSED)
		return;

	if (!tcp_send_flag(c, conn, RST))
		conn_event(c, conn, CLOSED);
}

/**
 * tcp_get_tap_ws() - Get Window Scaling option for connection from tap/guest
 * @conn:	Connection pointer
 * @opts:	Pointer to start of TCP options
 * @optlen:	Bytes in options: caller MUST ensure available length
 */
static void tcp_get_tap_ws(struct tcp_tap_conn *conn,
			   const char *opts, size_t optlen)
{
	int ws = tcp_opt_get(opts, optlen, OPT_WS, NULL, NULL);

	if (ws >= 0 && ws <= TCP_WS_MAX)
		conn->ws_from_tap = ws;
	else
		conn->ws_from_tap = 0;
}

/**
 * tcp_tap_window_update() - Process an updated window from tap side
 * @conn:	Connection pointer
 * @window:	Window value, host order, unscaled
 */
static void tcp_tap_window_update(struct tcp_tap_conn *conn, unsigned wnd)
{
	wnd = MIN(MAX_WINDOW, wnd << conn->ws_from_tap);

	/* Work-around for bug introduced in peer kernel code, commit
	 * e2142825c120 ("net: tcp: send zero-window ACK when no memory").
	 * We don't update if window shrank to zero.
	 */
	if (!wnd && SEQ_LT(conn->seq_ack_from_tap, conn->seq_to_tap))
		return;

	conn->wnd_from_tap = MIN(wnd >> conn->ws_from_tap, USHRT_MAX);

	/* FIXME: reflect the tap-side receiver's window back to the sock-side
	 * sender by adjusting SO_RCVBUF? */
}

/**
 * tcp_init_seq() - Calculate initial sequence number according to RFC 6528
 * @hash:	Hash of connection details
 * @now:	Current timestamp
 */
static uint32_t tcp_init_seq(uint64_t hash, const struct timespec *now)
{
	/* 32ns ticks, overflows 32 bits every 137s */
	uint32_t ns = (now->tv_sec * 1000000000 + now->tv_nsec) >> 5;

	return ((uint32_t)(hash >> 32) ^ (uint32_t)hash) + ns;
}

/**
 * tcp_conn_pool_sock() - Get socket for new connection from pre-opened pool
 * @pool:	Pool of pre-opened sockets
 *
 * Return: socket number if available, negative code if pool is empty
 */
int tcp_conn_pool_sock(int pool[])
{
	int s = -1, i;

	for (i = 0; i < TCP_SOCK_POOL_SIZE; i++) {
		SWAP(s, pool[i]);
		if (s >= 0)
			return s;
	}
	return -1;
}

/**
 * tcp_conn_new_sock() - Open and prepare new socket for connection
 * @c:		Execution context
 * @af:		Address family
 *
 * Return: socket number on success, negative code if socket creation failed
 */
static int tcp_conn_new_sock(const struct ctx *c, sa_family_t af)
{
	int s;

	s = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP);

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

	if (s < 0)
		return -errno;

	tcp_sock_set_bufsize(c, s);

	return s;
}

/**
 * tcp_conn_sock() - Obtain a connectable socket in the host/init namespace
 * @c:		Execution context
 * @af:		Address family (AF_INET or AF_INET6)
 *
 * Return: Socket fd on success, -errno on failure
 */
int tcp_conn_sock(const struct ctx *c, sa_family_t af)
{
	int *pool = af == AF_INET6 ? init_sock_pool6 : init_sock_pool4;
	int s;

	if ((s = tcp_conn_pool_sock(pool)) >= 0)
		return s;

	/* If the pool is empty we just open a new one without refilling the
	 * pool to keep latency down.
	 */
	if ((s = tcp_conn_new_sock(c, af)) >= 0)
		return s;

	err("TCP: Unable to open socket for new connection: %s",
	    strerror(-s));
	return -1;
}

/**
 * tcp_conn_tap_mss() - Get MSS value advertised by tap/guest
 * @conn:	Connection pointer
 * @opts:	Pointer to start of TCP options
 * @optlen:	Bytes in options: caller MUST ensure available length
 *
 * Return: clamped MSS value
 */
static uint16_t tcp_conn_tap_mss(const struct tcp_tap_conn *conn,
				 const char *opts, size_t optlen)
{
	unsigned int mss;
	int ret;

	if ((ret = tcp_opt_get(opts, optlen, OPT_MSS, NULL, NULL)) < 0)
		mss = MSS_DEFAULT;
	else
		mss = ret;

	if (CONN_V4(conn))
		mss = MIN(MSS4, mss);
	else
		mss = MIN(MSS6, mss);

	return MIN(mss, USHRT_MAX);
}

/**
 * tcp_bind_outbound() - Bind socket to outbound address and interface if given
 * @c:		Execution context
 * @conn:	Connection entry for socket to bind
 * @s:		Outbound TCP socket
 */
static void tcp_bind_outbound(const struct ctx *c,
			      const struct tcp_tap_conn *conn, int s)
{
	const struct flowside *tgt = &conn->f.side[TGTSIDE];
	union sockaddr_inany bind_sa;
	socklen_t sl;


	pif_sockaddr(c, &bind_sa, &sl, PIF_HOST, &tgt->oaddr, tgt->oport);
	if (!inany_is_unspecified(&tgt->oaddr) || tgt->oport) {
		if (bind(s, &bind_sa.sa, sl)) {
			char sstr[INANY_ADDRSTRLEN];

			flow_dbg(conn,
				 "Can't bind TCP outbound socket to %s:%hu: %s",
				 inany_ntop(&tgt->oaddr, sstr, sizeof(sstr)),
				 tgt->oport, strerror(errno));
		}
	}

	if (bind_sa.sa_family == AF_INET) {
		if (*c->ip4.ifname_out) {
			if (setsockopt(s, SOL_SOCKET, SO_BINDTODEVICE,
				       c->ip4.ifname_out,
				       strlen(c->ip4.ifname_out))) {
				flow_dbg(conn, "Can't bind IPv4 TCP socket to"
					 " interface %s: %s", c->ip4.ifname_out,
					 strerror(errno));
			}
		}
	} else if (bind_sa.sa_family == AF_INET6) {
		if (*c->ip6.ifname_out) {
			if (setsockopt(s, SOL_SOCKET, SO_BINDTODEVICE,
				       c->ip6.ifname_out,
				       strlen(c->ip6.ifname_out))) {
				flow_dbg(conn, "Can't bind IPv6 TCP socket to"
					 " interface %s: %s", c->ip6.ifname_out,
					 strerror(errno));
			}
		}
	}
}

/**
 * tcp_conn_from_tap() - Handle connection request (SYN segment) from tap
 * @c:		Execution context
 * @af:		Address family, AF_INET or AF_INET6
 * @saddr:	Source address, pointer to in_addr or in6_addr
 * @daddr:	Destination address, pointer to in_addr or in6_addr
 * @th:		TCP header from tap: caller MUST ensure it's there
 * @opts:	Pointer to start of options
 * @optlen:	Bytes in options: caller MUST ensure available length
 * @now:	Current timestamp
 */
static void tcp_conn_from_tap(const struct ctx *c, sa_family_t af,
			      const void *saddr, const void *daddr,
			      const struct tcphdr *th, const char *opts,
			      size_t optlen, const struct timespec *now)
{
	in_port_t srcport = ntohs(th->source);
	in_port_t dstport = ntohs(th->dest);
	const struct flowside *ini, *tgt;
	struct tcp_tap_conn *conn;
	union sockaddr_inany sa;
	union flow *flow;
	int s = -1, mss;
	uint64_t hash;
	socklen_t sl;

	if (!(flow = flow_alloc()))
		return;

	ini = flow_initiate_af(flow, PIF_TAP,
			       af, saddr, srcport, daddr, dstport);

	if (!(tgt = flow_target(c, flow, IPPROTO_TCP)))
		goto cancel;

	if (flow->f.pif[TGTSIDE] != PIF_HOST) {
		flow_err(flow, "No support for forwarding TCP from %s to %s",
			 pif_name(flow->f.pif[INISIDE]),
			 pif_name(flow->f.pif[TGTSIDE]));
		goto cancel;
	}

	conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp);

	if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0 ||
	    !inany_is_unicast(&ini->oaddr) || ini->oport == 0) {
		char sstr[INANY_ADDRSTRLEN], dstr[INANY_ADDRSTRLEN];

		debug("Invalid endpoint in TCP SYN: %s:%hu -> %s:%hu",
		      inany_ntop(&ini->eaddr, sstr, sizeof(sstr)), ini->eport,
		      inany_ntop(&ini->oaddr, dstr, sizeof(dstr)), ini->oport);
		goto cancel;
	}

	if ((s = tcp_conn_sock(c, af)) < 0)
		goto cancel;

	pif_sockaddr(c, &sa, &sl, PIF_HOST, &tgt->eaddr, tgt->eport);

	/* Use bind() to check if the target address is local (EADDRINUSE or
	 * similar) and already bound, and set the LOCAL flag in that case.
	 *
	 * If bind() succeeds, in general, we could infer that nobody (else) is
	 * listening on that address and port and reset the connection attempt
	 * early, but we can't rely on that if non-local binds are enabled,
	 * because bind() would succeed for any non-local address we can reach.
	 *
	 * So, if bind() succeeds, close the socket, get a new one, and proceed.
	 */
	if (bind(s, &sa.sa, sl)) {
		if (errno != EADDRNOTAVAIL && errno != EACCES)
			conn_flag(c, conn, LOCAL);
	} else {
		/* Not a local, bound destination, inconclusive test */
		close(s);
		if ((s = tcp_conn_sock(c, af)) < 0)
			goto cancel;
	}

	conn->sock = s;
	conn->timer = -1;
	conn_event(c, conn, TAP_SYN_RCVD);

	conn->wnd_to_tap = WINDOW_DEFAULT;

	mss = tcp_conn_tap_mss(conn, opts, optlen);
	if (setsockopt(s, SOL_TCP, TCP_MAXSEG, &mss, sizeof(mss)))
		flow_trace(conn, "failed to set TCP_MAXSEG on socket %i", s);
	MSS_SET(conn, mss);

	tcp_get_tap_ws(conn, opts, optlen);

	/* RFC 7323, 2.2: first value is not scaled. Also, don't clamp yet, to
	 * avoid getting a zero scale just because we set a small window now.
	 */
	if (!(conn->wnd_from_tap = (htons(th->window) >> conn->ws_from_tap)))
		conn->wnd_from_tap = 1;

	conn->seq_init_from_tap = ntohl(th->seq);
	conn->seq_from_tap = conn->seq_init_from_tap + 1;
	conn->seq_ack_to_tap = conn->seq_from_tap;

	hash = flow_hash_insert(c, TAP_SIDX(conn));
	conn->seq_to_tap = tcp_init_seq(hash, now);
	conn->seq_ack_from_tap = conn->seq_to_tap;

	tcp_bind_outbound(c, conn, s);

	if (connect(s, &sa.sa, sl)) {
		if (errno != EINPROGRESS) {
			tcp_rst(c, conn);
			goto cancel;
		}

		tcp_get_sndbuf(conn);
	} else {
		tcp_get_sndbuf(conn);

		if (tcp_send_flag(c, conn, SYN | ACK))
			goto cancel;

		conn_event(c, conn, TAP_SYN_ACK_SENT);
	}

	tcp_epoll_ctl(c, conn);
	FLOW_ACTIVATE(conn);
	return;

cancel:
	if (s >= 0)
		close(s);
	flow_alloc_cancel(flow);
}

/**
 * tcp_sock_consume() - Consume (discard) data from buffer
 * @conn:	Connection pointer
 * @ack_seq:	ACK sequence, host order
 *
 * Return: 0 on success, negative error code from recv() on failure
 */
#ifdef VALGRIND
/* valgrind doesn't realise that passing a NULL buffer to recv() is ok if using
 * MSG_TRUNC.  We have a suppression for this in the tests, but it relies on
 * valgrind being able to see the tcp_sock_consume() stack frame, which it won't
 * if this gets inlined.  This has a single caller making it a likely inlining
 * candidate, and certain compiler versions will do so even at -O0.
 */
 __attribute__((noinline))
#endif /* VALGRIND */
static int tcp_sock_consume(const struct tcp_tap_conn *conn, uint32_t ack_seq)
{
	/* Simply ignore out-of-order ACKs: we already consumed the data we
	 * needed from the buffer, and we won't rewind back to a lower ACK
	 * sequence.
	 */
	if (SEQ_LE(ack_seq, conn->seq_ack_from_tap))
		return 0;

	/* cppcheck-suppress [nullPointer, unmatchedSuppression] */
	if (recv(conn->sock, NULL, ack_seq - conn->seq_ack_from_tap,
		 MSG_DONTWAIT | MSG_TRUNC) < 0)
		return -errno;

	return 0;
}

/**
 * tcp_data_from_sock() - Handle new data from socket, queue to tap, in window
 * @c:		Execution context
 * @conn:	Connection pointer
 *
 * Return: negative on connection reset, 0 otherwise
 *
 * #syscalls recvmsg
 */
static int tcp_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
{
	return tcp_buf_data_from_sock(c, conn);
}

/**
 * tcp_data_from_tap() - tap/guest data for established connection
 * @c:		Execution context
 * @conn:	Connection pointer
 * @p:		Pool of TCP packets, with TCP headers
 * @idx:	Index of first data packet in pool
 *
 * #syscalls sendmsg
 *
 * Return: count of consumed packets
 */
static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
			     const struct pool *p, int idx)
{
	int i, iov_i, ack = 0, fin = 0, retr = 0, keep = -1, partial_send = 0;
	uint16_t max_ack_seq_wnd = conn->wnd_from_tap;
	uint32_t max_ack_seq = conn->seq_ack_from_tap;
	uint32_t seq_from_tap = conn->seq_from_tap;
	struct msghdr mh = { .msg_iov = tcp_iov };
	size_t len;
	ssize_t n;

	if (conn->events == CLOSED)
		return p->count - idx;

	ASSERT(conn->events & ESTABLISHED);

	for (i = idx, iov_i = 0; i < (int)p->count; i++) {
		uint32_t seq, seq_offset, ack_seq;
		const struct tcphdr *th;
		char *data;
		size_t off;

		th = packet_get(p, i, 0, sizeof(*th), &len);
		if (!th)
			return -1;
		len += sizeof(*th);

		off = th->doff * 4UL;
		if (off < sizeof(*th) || off > len)
			return -1;

		if (th->rst) {
			conn_event(c, conn, CLOSED);
			return 1;
		}

		len -= off;
		data = packet_get(p, i, off, len, NULL);
		if (!data)
			continue;

		seq = ntohl(th->seq);
		ack_seq = ntohl(th->ack_seq);

		if (th->ack) {
			ack = 1;

			if (SEQ_GE(ack_seq, conn->seq_ack_from_tap) &&
			    SEQ_GE(ack_seq, max_ack_seq)) {
				/* Fast re-transmit */
				retr = !len && !th->fin &&
				       ack_seq == max_ack_seq &&
				       ntohs(th->window) == max_ack_seq_wnd;

				max_ack_seq_wnd = ntohs(th->window);
				max_ack_seq = ack_seq;
			}
		}

		if (th->fin)
			fin = 1;

		if (!len)
			continue;

		seq_offset = seq_from_tap - seq;
		/* Use data from this buffer only in these two cases:
		 *
		 *      , seq_from_tap           , seq_from_tap
		 * |--------| <-- len            |--------| <-- len
		 * '----' <-- offset             ' <-- offset
		 * ^ seq                         ^ seq
		 *    (offset >= 0, seq + len > seq_from_tap)
		 *
		 * discard in these two cases:
		 *          , seq_from_tap                , seq_from_tap
		 * |--------| <-- len            |--------| <-- len
		 * '--------' <-- offset            '-----| <- offset
		 * ^ seq                            ^ seq
		 *    (offset >= 0, seq + len <= seq_from_tap)
		 *
		 * keep, look for another buffer, then go back, in this case:
		 *      , seq_from_tap
		 *          |--------| <-- len
		 *      '===' <-- offset
		 *          ^ seq
		 *    (offset < 0)
		 */
		if (SEQ_GE(seq_offset, 0) && SEQ_LE(seq + len, seq_from_tap))
			continue;

		if (SEQ_LT(seq_offset, 0)) {
			if (keep == -1)
				keep = i;
			continue;
		}

		tcp_iov[iov_i].iov_base = data + seq_offset;
		tcp_iov[iov_i].iov_len = len - seq_offset;
		seq_from_tap += tcp_iov[iov_i].iov_len;
		iov_i++;

		if (keep == i)
			keep = -1;

		if (keep != -1)
			i = keep - 1;
	}

	/* On socket flush failure, pretend there was no ACK, try again later */
	if (ack && !tcp_sock_consume(conn, max_ack_seq))
		tcp_update_seqack_from_tap(c, conn, max_ack_seq);

	tcp_tap_window_update(conn, max_ack_seq_wnd);

	if (retr) {
		flow_trace(conn,
			   "fast re-transmit, ACK: %u, previous sequence: %u",
			   max_ack_seq, conn->seq_to_tap);
		conn->seq_to_tap = max_ack_seq;
		if (tcp_set_peek_offset(conn->sock, 0)) {
			tcp_rst(c, conn);
			return -1;
		}
		tcp_data_from_sock(c, conn);
	}

	if (!iov_i)
		goto out;

	mh.msg_iovlen = iov_i;
eintr:
	n = sendmsg(conn->sock, &mh, MSG_DONTWAIT | MSG_NOSIGNAL);
	if (n < 0) {
		if (errno == EPIPE) {
			/* Here's the wrap, said the tap.
			 * In my pocket, said the socket.
			 *   Then swiftly looked away and left.
			 */
			conn->seq_from_tap = seq_from_tap;
			tcp_send_flag(c, conn, ACK);
		}

		if (errno == EINTR)
			goto eintr;

		if (errno == EAGAIN || errno == EWOULDBLOCK) {
			tcp_send_flag(c, conn, ACK_IF_NEEDED);
			return p->count - idx;

		}
		return -1;
	}

	if (n < (int)(seq_from_tap - conn->seq_from_tap)) {
		partial_send = 1;
		conn->seq_from_tap += n;
		tcp_send_flag(c, conn, ACK_IF_NEEDED);
	} else {
		conn->seq_from_tap += n;
	}

out:
	if (keep != -1) {
		/* We use an 8-bit approximation here: the associated risk is
		 * that we skip a duplicate ACK on 8-bit sequence number
		 * collision. Fast retransmit is a SHOULD in RFC 5681, 3.2.
		 */
		if (conn->seq_dup_ack_approx != (conn->seq_from_tap & 0xff)) {
			conn->seq_dup_ack_approx = conn->seq_from_tap & 0xff;
			tcp_send_flag(c, conn, ACK | DUP_ACK);
		}
		return p->count - idx;
	}

	if (ack && conn->events & TAP_FIN_SENT &&
	    conn->seq_ack_from_tap == conn->seq_to_tap)
		conn_event(c, conn, TAP_FIN_ACKED);

	if (fin && !partial_send) {
		conn->seq_from_tap++;

		conn_event(c, conn, TAP_FIN_RCVD);
	} else {
		tcp_send_flag(c, conn, ACK_IF_NEEDED);
	}

	return p->count - idx;
}

/**
 * tcp_conn_from_sock_finish() - Complete connection setup after connect()
 * @c:		Execution context
 * @conn:	Connection pointer
 * @th:		TCP header of SYN, ACK segment: caller MUST ensure it's there
 * @opts:	Pointer to start of options
 * @optlen:	Bytes in options: caller MUST ensure available length
 */
static void tcp_conn_from_sock_finish(const struct ctx *c,
				      struct tcp_tap_conn *conn,
				      const struct tcphdr *th,
				      const char *opts, size_t optlen)
{
	tcp_tap_window_update(conn, ntohs(th->window));
	tcp_get_tap_ws(conn, opts, optlen);

	/* First value is not scaled */
	if (!(conn->wnd_from_tap >>= conn->ws_from_tap))
		conn->wnd_from_tap = 1;

	MSS_SET(conn, tcp_conn_tap_mss(conn, opts, optlen));

	conn->seq_init_from_tap = ntohl(th->seq) + 1;
	conn->seq_from_tap = conn->seq_init_from_tap;
	conn->seq_ack_to_tap = conn->seq_from_tap;

	conn_event(c, conn, ESTABLISHED);
	if (tcp_set_peek_offset(conn->sock, 0)) {
		tcp_rst(c, conn);
		return;
	}

	/* The client might have sent data already, which we didn't
	 * dequeue waiting for SYN,ACK from tap -- check now.
	 */
	tcp_data_from_sock(c, conn);
	tcp_send_flag(c, conn, ACK);
}

/**
 * tcp_tap_handler() - Handle packets from tap and state transitions
 * @c:		Execution context
 * @pif:	pif on which the packet is arriving
 * @af:		Address family, AF_INET or AF_INET6
 * @saddr:	Source address
 * @daddr:	Destination address
 * @p:		Pool of TCP packets, with TCP headers
 * @idx:	Index of first packet in pool to process
 * @now:	Current timestamp
 *
 * Return: count of consumed packets
 */
int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
		    const void *saddr, const void *daddr,
		    const struct pool *p, int idx, const struct timespec *now)
{
	struct tcp_tap_conn *conn;
	const struct tcphdr *th;
	size_t optlen, len;
	const char *opts;
	union flow *flow;
	flow_sidx_t sidx;
	int ack_due = 0;
	int count;

	(void)pif;

	th = packet_get(p, idx, 0, sizeof(*th), &len);
	if (!th)
		return 1;
	len += sizeof(*th);

	optlen = th->doff * 4UL - sizeof(*th);
	/* Static checkers might fail to see this: */
	optlen = MIN(optlen, ((1UL << 4) /* from doff width */ - 6) * 4UL);
	opts = packet_get(p, idx, sizeof(*th), optlen, NULL);

	sidx = flow_lookup_af(c, IPPROTO_TCP, PIF_TAP, af, saddr, daddr,
			      ntohs(th->source), ntohs(th->dest));
	flow = flow_at_sidx(sidx);

	/* New connection from tap */
	if (!flow) {
		if (opts && th->syn && !th->ack)
			tcp_conn_from_tap(c, af, saddr, daddr, th,
					  opts, optlen, now);
		return 1;
	}

	ASSERT(flow->f.type == FLOW_TCP);
	ASSERT(pif_at_sidx(sidx) == PIF_TAP);
	conn = &flow->tcp;

	flow_trace(conn, "packet length %zu from tap", len);

	if (th->rst) {
		conn_event(c, conn, CLOSED);
		return 1;
	}

	if (th->ack && !(conn->events & ESTABLISHED))
		tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));

	/* Establishing connection from socket */
	if (conn->events & SOCK_ACCEPTED) {
		if (th->syn && th->ack && !th->fin) {
			tcp_conn_from_sock_finish(c, conn, th, opts, optlen);
			return 1;
		}

		goto reset;
	}

	/* Establishing connection from tap */
	if (conn->events & TAP_SYN_RCVD) {
		if (!(conn->events & TAP_SYN_ACK_SENT))
			goto reset;

		conn_event(c, conn, ESTABLISHED);
		if (tcp_set_peek_offset(conn->sock, 0))
			goto reset;

		if (th->fin) {
			conn->seq_from_tap++;

			shutdown(conn->sock, SHUT_WR);
			tcp_send_flag(c, conn, ACK);
			conn_event(c, conn, SOCK_FIN_SENT);

			return 1;
		}

		if (!th->ack)
			goto reset;

		tcp_tap_window_update(conn, ntohs(th->window));

		tcp_data_from_sock(c, conn);

		if (p->count - idx == 1)
			return 1;
	}

	/* Established connections not accepting data from tap */
	if (conn->events & TAP_FIN_RCVD) {
		tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));

		if (conn->events & SOCK_FIN_RCVD &&
		    conn->seq_ack_from_tap == conn->seq_to_tap)
			conn_event(c, conn, CLOSED);

		return 1;
	}

	/* Established connections accepting data from tap */
	count = tcp_data_from_tap(c, conn, p, idx);
	if (count == -1)
		goto reset;

	conn_flag(c, conn, ~STALLED);

	if (conn->seq_ack_to_tap != conn->seq_from_tap)
		ack_due = 1;

	if ((conn->events & TAP_FIN_RCVD) && !(conn->events & SOCK_FIN_SENT)) {
		shutdown(conn->sock, SHUT_WR);
		conn_event(c, conn, SOCK_FIN_SENT);
		tcp_send_flag(c, conn, ACK);
		ack_due = 0;
	}

	if (ack_due)
		conn_flag(c, conn, ACK_TO_TAP_DUE);

	return count;

reset:
	/* Something's gone wrong, so reset the connection.  We discard
	 * remaining packets in the batch, since they'd be invalidated when our
	 * RST is received, even if otherwise good.
	 */
	tcp_rst(c, conn);
	return p->count - idx;
}

/**
 * tcp_connect_finish() - Handle completion of connect() from EPOLLOUT event
 * @c:		Execution context
 * @conn:	Connection pointer
 */
static void tcp_connect_finish(const struct ctx *c, struct tcp_tap_conn *conn)
{
	socklen_t sl;
	int so;

	sl = sizeof(so);
	if (getsockopt(conn->sock, SOL_SOCKET, SO_ERROR, &so, &sl) || so) {
		tcp_rst(c, conn);
		return;
	}

	if (tcp_send_flag(c, conn, SYN | ACK))
		return;

	conn_event(c, conn, TAP_SYN_ACK_SENT);
	conn_flag(c, conn, ACK_FROM_TAP_DUE);
}

/**
 * tcp_tap_conn_from_sock() - Initialize state for non-spliced connection
 * @c:		Execution context
 * @flow:	flow to initialise
 * @s:		Accepted socket
 * @sa:		Peer socket address (from accept())
 * @now:	Current timestamp
 */
static void tcp_tap_conn_from_sock(const struct ctx *c, union flow *flow,
				   int s, const struct timespec *now)
{
	struct tcp_tap_conn *conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp);
	uint64_t hash;

	conn->sock = s;
	conn->timer = -1;
	conn->ws_to_tap = conn->ws_from_tap = 0;
	conn_event(c, conn, SOCK_ACCEPTED);

	hash = flow_hash_insert(c, TAP_SIDX(conn));
	conn->seq_to_tap = tcp_init_seq(hash, now);

	conn->seq_ack_from_tap = conn->seq_to_tap;

	conn->wnd_from_tap = WINDOW_DEFAULT;

	tcp_send_flag(c, conn, SYN);
	conn_flag(c, conn, ACK_FROM_TAP_DUE);

	tcp_get_sndbuf(conn);

	FLOW_ACTIVATE(conn);
}

/**
 * tcp_listen_handler() - Handle new connection request from listening socket
 * @c:		Execution context
 * @ref:	epoll reference of listening socket
 * @now:	Current timestamp
 */
void tcp_listen_handler(const struct ctx *c, union epoll_ref ref,
			const struct timespec *now)
{
	const struct flowside *ini;
	union sockaddr_inany sa;
	socklen_t sl = sizeof(sa);
	union flow *flow;
	int s;

	ASSERT(!c->no_tcp);

	if (!(flow = flow_alloc()))
		return;

	s = accept4(ref.fd, &sa.sa, &sl, SOCK_NONBLOCK);
	if (s < 0)
		goto cancel;

	/* FIXME: When listening port has a specific bound address, record that
	 * as our address
	 */
	ini = flow_initiate_sa(flow, ref.tcp_listen.pif, &sa,
			       ref.tcp_listen.port);

	if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0) {
		char sastr[SOCKADDR_STRLEN];

		err("Invalid endpoint from TCP accept(): %s",
		    sockaddr_ntop(&sa, sastr, sizeof(sastr)));
		goto cancel;
	}

	if (!flow_target(c, flow, IPPROTO_TCP))
		goto cancel;

	switch (flow->f.pif[TGTSIDE]) {
	case PIF_SPLICE:
	case PIF_HOST:
		tcp_splice_conn_from_sock(c, flow, s);
		break;

	case PIF_TAP:
		tcp_tap_conn_from_sock(c, flow, s, now);
		break;

	default:
		flow_err(flow, "No support for forwarding TCP from %s to %s",
			 pif_name(flow->f.pif[INISIDE]),
			 pif_name(flow->f.pif[TGTSIDE]));
		goto cancel;
	}

	return;

cancel:
	flow_alloc_cancel(flow);
}

/**
 * tcp_timer_handler() - timerfd events: close, send ACK, retransmit, or reset
 * @c:		Execution context
 * @ref:	epoll reference of timer (not connection)
 *
 * #syscalls timerfd_gettime arm:timerfd_gettime64 i686:timerfd_gettime64
 */
void tcp_timer_handler(const struct ctx *c, union epoll_ref ref)
{
	struct itimerspec check_armed = { { 0 }, { 0 } };
	struct tcp_tap_conn *conn = &FLOW(ref.flow)->tcp;

	ASSERT(!c->no_tcp);
	ASSERT(conn->f.type == FLOW_TCP);

	/* We don't reset timers on ~ACK_FROM_TAP_DUE, ~ACK_TO_TAP_DUE. If the
	 * timer is currently armed, this event came from a previous setting,
	 * and we just set the timer to a new point in the future: discard it.
	 */
	timerfd_gettime(conn->timer, &check_armed);
	if (check_armed.it_value.tv_sec || check_armed.it_value.tv_nsec)
		return;

	if (conn->flags & ACK_TO_TAP_DUE) {
		tcp_send_flag(c, conn, ACK_IF_NEEDED);
		tcp_timer_ctl(c, conn);
	} else if (conn->flags & ACK_FROM_TAP_DUE) {
		if (!(conn->events & ESTABLISHED)) {
			flow_dbg(conn, "handshake timeout");
			tcp_rst(c, conn);
		} else if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED)) {
			flow_dbg(conn, "FIN timeout");
			tcp_rst(c, conn);
		} else if (conn->retrans == TCP_MAX_RETRANS) {
			flow_dbg(conn, "retransmissions count exceeded");
			tcp_rst(c, conn);
		} else {
			flow_dbg(conn, "ACK timeout, retry");
			conn->retrans++;
			conn->seq_to_tap = conn->seq_ack_from_tap;
			if (tcp_set_peek_offset(conn->sock, 0)) {
				tcp_rst(c, conn);
			} else {
				tcp_data_from_sock(c, conn);
				tcp_timer_ctl(c, conn);
			}
		}
	} else {
		struct itimerspec new = { { 0 }, { ACT_TIMEOUT, 0 } };
		struct itimerspec old = { { 0 }, { 0 } };

		/* Activity timeout: if it was already set, reset the
		 * connection, otherwise, it was a left-over from ACK_TO_TAP_DUE
		 * or ACK_FROM_TAP_DUE, so just set the long timeout in that
		 * case. This avoids having to preemptively reset the timer on
		 * ~ACK_TO_TAP_DUE or ~ACK_FROM_TAP_DUE.
		 */
		timerfd_settime(conn->timer, 0, &new, &old);
		if (old.it_value.tv_sec == ACT_TIMEOUT) {
			flow_dbg(conn, "activity timeout");
			tcp_rst(c, conn);
		}
	}
}

/**
 * tcp_sock_handler() - Handle new data from non-spliced socket
 * @c:		Execution context
 * @ref:	epoll reference
 * @events:	epoll events bitmap
 */
void tcp_sock_handler(const struct ctx *c, union epoll_ref ref,
		      uint32_t events)
{
	struct tcp_tap_conn *conn = conn_at_sidx(ref.flowside);

	ASSERT(!c->no_tcp);
	ASSERT(pif_at_sidx(ref.flowside) != PIF_TAP);

	if (conn->events == CLOSED)
		return;

	if (events & EPOLLERR) {
		tcp_rst(c, conn);
		return;
	}

	if ((conn->events & TAP_FIN_SENT) && (events & EPOLLHUP)) {
		conn_event(c, conn, CLOSED);
		return;
	}

	if (conn->events & ESTABLISHED) {
		if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED))
			conn_event(c, conn, CLOSED);

		if (events & (EPOLLRDHUP | EPOLLHUP))
			conn_event(c, conn, SOCK_FIN_RCVD);

		if (events & EPOLLIN)
			tcp_data_from_sock(c, conn);

		if (events & EPOLLOUT)
			tcp_update_seqack_wnd(c, conn, false, NULL);

		return;
	}

	/* EPOLLHUP during handshake: reset */
	if (events & EPOLLHUP) {
		tcp_rst(c, conn);
		return;
	}

	/* Data during handshake tap-side: check later */
	if (conn->events & SOCK_ACCEPTED)
		return;

	if (conn->events == TAP_SYN_RCVD) {
		if (events & EPOLLOUT)
			tcp_connect_finish(c, conn);
		/* Data? Check later */
	}
}

/**
 * tcp_sock_init_af() - Initialise listening socket for a given af and port
 * @c:		Execution context
 * @af:		Address family to listen on
 * @port:	Port, host order
 * @addr:	Pointer to address for binding, NULL if not configured
 * @ifname:	Name of interface to bind to, NULL if not configured
 *
 * Return: fd for the new listening socket, negative error code on failure
 */
static int tcp_sock_init_af(const struct ctx *c, sa_family_t af, in_port_t port,
			    const void *addr, const char *ifname)
{
	union tcp_listen_epoll_ref tref = {
		.port = port,
		.pif = PIF_HOST,
	};
	int s;

	s = sock_l4(c, af, EPOLL_TYPE_TCP_LISTEN, addr, ifname, port, tref.u32);

	if (c->tcp.fwd_in.mode == FWD_AUTO) {
		if (af == AF_INET  || af == AF_UNSPEC)
			tcp_sock_init_ext[port][V4] = s < 0 ? -1 : s;
		if (af == AF_INET6 || af == AF_UNSPEC)
			tcp_sock_init_ext[port][V6] = s < 0 ? -1 : s;
	}

	if (s < 0)
		return s;

	tcp_sock_set_bufsize(c, s);
	return s;
}

/**
 * tcp_sock_init() - Create listening sockets for a given host ("inbound") port
 * @c:		Execution context
 * @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
 *
 * Return: 0 on (partial) success, negative error code on (complete) failure
 */
int tcp_sock_init(const struct ctx *c, sa_family_t af, const void *addr,
		  const char *ifname, in_port_t port)
{
	int r4 = FD_REF_MAX + 1, r6 = FD_REF_MAX + 1;

	ASSERT(!c->no_tcp);

	if (af == AF_UNSPEC && c->ifi4 && c->ifi6)
		/* Attempt to get a dual stack socket */
		if (tcp_sock_init_af(c, AF_UNSPEC, port, addr, ifname) >= 0)
			return 0;

	/* Otherwise create a socket per IP version */
	if ((af == AF_INET  || af == AF_UNSPEC) && c->ifi4)
		r4 = tcp_sock_init_af(c, AF_INET, port, addr, ifname);

	if ((af == AF_INET6 || af == AF_UNSPEC) && c->ifi6)
		r6 = tcp_sock_init_af(c, AF_INET6, port, addr, ifname);

	if (IN_INTERVAL(0, FD_REF_MAX, r4) || IN_INTERVAL(0, FD_REF_MAX, r6))
		return 0;

	return r4 < 0 ? r4 : r6;
}

/**
 * tcp_ns_sock_init4() - Init socket to listen for outbound IPv4 connections
 * @c:		Execution context
 * @port:	Port, host order
 */
static void tcp_ns_sock_init4(const struct ctx *c, in_port_t port)
{
	union tcp_listen_epoll_ref tref = {
		.port = port,
		.pif = PIF_SPLICE,
	};
	int s;

	ASSERT(c->mode == MODE_PASTA);

	s = sock_l4(c, AF_INET, EPOLL_TYPE_TCP_LISTEN, &in4addr_loopback,
		    NULL, port, tref.u32);
	if (s >= 0)
		tcp_sock_set_bufsize(c, s);
	else
		s = -1;

	if (c->tcp.fwd_out.mode == FWD_AUTO)
		tcp_sock_ns[port][V4] = s;
}

/**
 * tcp_ns_sock_init6() - Init socket to listen for outbound IPv6 connections
 * @c:		Execution context
 * @port:	Port, host order
 */
static void tcp_ns_sock_init6(const struct ctx *c, in_port_t port)
{
	union tcp_listen_epoll_ref tref = {
		.port = port,
		.pif = PIF_SPLICE,
	};
	int s;

	ASSERT(c->mode == MODE_PASTA);

	s = sock_l4(c, AF_INET6, EPOLL_TYPE_TCP_LISTEN, &in6addr_loopback,
		    NULL, port, tref.u32);
	if (s >= 0)
		tcp_sock_set_bufsize(c, s);
	else
		s = -1;

	if (c->tcp.fwd_out.mode == FWD_AUTO)
		tcp_sock_ns[port][V6] = s;
}

/**
 * tcp_ns_sock_init() - Init socket to listen for spliced outbound connections
 * @c:		Execution context
 * @port:	Port, host order
 */
void tcp_ns_sock_init(const struct ctx *c, in_port_t port)
{
	ASSERT(!c->no_tcp);

	if (c->ifi4)
		tcp_ns_sock_init4(c, port);
	if (c->ifi6)
		tcp_ns_sock_init6(c, port);
}

/**
 * tcp_ns_socks_init() - Bind sockets in namespace for outbound connections
 * @arg:	Execution context
 *
 * Return: 0
 */
/* cppcheck-suppress [constParameterCallback, unmatchedSuppression] */
static int tcp_ns_socks_init(void *arg)
{
	const struct ctx *c = (const struct ctx *)arg;
	unsigned port;

	ns_enter(c);

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

		tcp_ns_sock_init(c, port);
	}

	return 0;
}

/**
 * tcp_sock_refill_pool() - Refill one pool of pre-opened sockets
 * @c:		Execution context
 * @pool:	Pool of sockets to refill
 * @af:		Address family to use
 *
 * Return: 0 on success, negative error code if there was at least one error
 */
int tcp_sock_refill_pool(const struct ctx *c, int pool[], sa_family_t af)
{
	int i;

	for (i = 0; i < TCP_SOCK_POOL_SIZE; i++) {
		int fd;

		if (pool[i] >= 0)
			continue;

		if ((fd = tcp_conn_new_sock(c, af)) < 0)
			return fd;

		pool[i] = fd;
	}

	return 0;
}

/**
 * tcp_sock_refill_init() - Refill pools of pre-opened sockets in init ns
 * @c:		Execution context
 */
static void tcp_sock_refill_init(const struct ctx *c)
{
	if (c->ifi4) {
		int rc = tcp_sock_refill_pool(c, init_sock_pool4, AF_INET);
		if (rc < 0)
			warn("TCP: Error refilling IPv4 host socket pool: %s",
			     strerror(-rc));
	}
	if (c->ifi6) {
		int rc = tcp_sock_refill_pool(c, init_sock_pool6, AF_INET6);
		if (rc < 0)
			warn("TCP: Error refilling IPv6 host socket pool: %s",
			     strerror(-rc));
	}
}

/**
 * tcp_probe_peek_offset_cap() - Check if SO_PEEK_OFF is supported by kernel
 * @af:		Address family, IPv4 or IPv6
 *
 * Return: true if supported, false otherwise
 */
static bool tcp_probe_peek_offset_cap(sa_family_t af)
{
	bool ret = false;
	int s, optv = 0;

	s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
	if (s < 0) {
		warn_perror("Temporary TCP socket creation failed");
	} else {
		if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int)))
			ret = true;
		close(s);
	}

	return ret;
}

#ifdef HAS_SND_WND
/**
 * tcp_probe_snd_wnd_cap() - Check if TCP_INFO reports tcpi_snd_wnd
 *
 * Return: true if supported, false otherwise
 */
static bool tcp_probe_snd_wnd_cap(void)
{
	struct tcp_info tinfo;
	socklen_t sl = sizeof(tinfo);
	int s;

	s = socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
	if (s < 0) {
		warn_perror("Temporary TCP socket creation failed");
		return false;
	}

	if (getsockopt(s, SOL_TCP, TCP_INFO, &tinfo, &sl)) {
		warn_perror("Failed to get TCP_INFO on temporary socket");
		close(s);
		return false;
	}

	close(s);

	if (sl < (offsetof(struct tcp_info, tcpi_snd_wnd) +
		  sizeof(tinfo.tcpi_snd_wnd)))
		return false;

	return true;
}
#endif /* HAS_SND_WND */

/**
 * tcp_init() - Get initial sequence, hash secret, initialise per-socket data
 * @c:		Execution context
 *
 * Return: 0, doesn't return on failure
 */
int tcp_init(struct ctx *c)
{
	ASSERT(!c->no_tcp);

	if (c->ifi4)
		tcp_sock4_iov_init(c);

	if (c->ifi6)
		tcp_sock6_iov_init(c);

	memset(init_sock_pool4,		0xff,	sizeof(init_sock_pool4));
	memset(init_sock_pool6,		0xff,	sizeof(init_sock_pool6));
	memset(tcp_sock_init_ext,	0xff,	sizeof(tcp_sock_init_ext));
	memset(tcp_sock_ns,		0xff,	sizeof(tcp_sock_ns));

	tcp_sock_refill_init(c);

	if (c->mode == MODE_PASTA) {
		tcp_splice_init(c);

		NS_CALL(tcp_ns_socks_init, c);
	}

	peek_offset_cap = (!c->ifi4 || tcp_probe_peek_offset_cap(AF_INET)) &&
			  (!c->ifi6 || tcp_probe_peek_offset_cap(AF_INET6));
	debug("SO_PEEK_OFF%ssupported", peek_offset_cap ? " " : " not ");

#ifdef HAS_SND_WND
	snd_wnd_cap = tcp_probe_snd_wnd_cap();
#endif
	debug("TCP_INFO tcpi_snd_wnd field%ssupported",
	      snd_wnd_cap ? " " : " not ");

	return 0;
}

/**
 * tcp_port_rebind() - Rebind ports to match forward maps
 * @c:		Execution context
 * @outbound:	True to remap outbound forwards, otherwise inbound
 *
 * Must be called in namespace context if @outbound is true.
 */
static void tcp_port_rebind(struct ctx *c, bool outbound)
{
	const uint8_t *fmap = outbound ? c->tcp.fwd_out.map : c->tcp.fwd_in.map;
	const uint8_t *rmap = outbound ? c->tcp.fwd_in.map : c->tcp.fwd_out.map;
	int (*socks)[IP_VERSIONS] = outbound ? tcp_sock_ns : tcp_sock_init_ext;
	unsigned port;

	for (port = 0; port < NUM_PORTS; port++) {
		if (!bitmap_isset(fmap, port)) {
			if (socks[port][V4] >= 0) {
				close(socks[port][V4]);
				socks[port][V4] = -1;
			}

			if (socks[port][V6] >= 0) {
				close(socks[port][V6]);
				socks[port][V6] = -1;
			}

			continue;
		}

		/* Don't loop back our own ports */
		if (bitmap_isset(rmap, port))
			continue;

		if ((c->ifi4 && socks[port][V4] == -1) ||
		    (c->ifi6 && socks[port][V6] == -1)) {
			if (outbound)
				tcp_ns_sock_init(c, port);
			else
				tcp_sock_init(c, AF_UNSPEC, NULL, NULL, port);
		}
	}
}

/**
 * tcp_port_rebind_outbound() - Rebind ports in namespace
 * @arg:	Execution context
 *
 * Called with NS_CALL()
 *
 * Return: 0
 */
static int tcp_port_rebind_outbound(void *arg)
{
	struct ctx *c = (struct ctx *)arg;

	ns_enter(c);
	tcp_port_rebind(c, true);

	return 0;
}

/**
 * tcp_timer() - Periodic tasks: port detection, closed connections, pool refill
 * @c:		Execution context
 * @now:	Current timestamp
 */
void tcp_timer(struct ctx *c, const struct timespec *now)
{
	(void)now;

	if (c->mode == MODE_PASTA) {
		if (c->tcp.fwd_out.mode == FWD_AUTO) {
			fwd_scan_ports_tcp(&c->tcp.fwd_out, &c->tcp.fwd_in);
			NS_CALL(tcp_port_rebind_outbound, c);
		}

		if (c->tcp.fwd_in.mode == FWD_AUTO) {
			fwd_scan_ports_tcp(&c->tcp.fwd_in, &c->tcp.fwd_out);
			tcp_port_rebind(c, false);
		}
	}

	tcp_sock_refill_init(c);
	if (c->mode == MODE_PASTA)
		tcp_splice_refill(c);
}

debug log:

solving efd4037ed008 ...
found efd4037ed008 in https://archives.passt.top/passt-dev/20240924154642.182857-5-lvivier@redhat.com/
found c9472d905520 in https://archives.passt.top/passt-dev/20240920095631.3911625-1-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20240924154642.182857-2-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20241003145108.2227355-2-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20240927135349.675850-2-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20240926140415.441208-2-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20240926132942.434962-2-lvivier@redhat.com/ ||
	https://archives.passt.top/passt-dev/20240925081125.205974-2-lvivier@redhat.com/
found 1962fcc469ed in https://passt.top/passt
preparing index
index prepared:
100644 1962fcc469ed9ae353fa80fe1e7c38053836ee3a	tcp.c

applying [1/2] https://archives.passt.top/passt-dev/20240920095631.3911625-1-lvivier@redhat.com/
diff --git a/tcp.c b/tcp.c
index 1962fcc469ed..c9472d905520 100644

Checking patch tcp.c...
Applied patch tcp.c cleanly.

skipping https://archives.passt.top/passt-dev/20240924154642.182857-2-lvivier@redhat.com/ for c9472d905520
skipping https://archives.passt.top/passt-dev/20241003145108.2227355-2-lvivier@redhat.com/ for c9472d905520
skipping https://archives.passt.top/passt-dev/20240927135349.675850-2-lvivier@redhat.com/ for c9472d905520
skipping https://archives.passt.top/passt-dev/20240926140415.441208-2-lvivier@redhat.com/ for c9472d905520
skipping https://archives.passt.top/passt-dev/20240926132942.434962-2-lvivier@redhat.com/ for c9472d905520
skipping https://archives.passt.top/passt-dev/20240925081125.205974-2-lvivier@redhat.com/ for c9472d905520
index at:
100644 c9472d905520f7fb15a7154b1ec5d74fdb47d76c	tcp.c

applying [2/2] https://archives.passt.top/passt-dev/20240924154642.182857-5-lvivier@redhat.com/
diff --git a/tcp.c b/tcp.c
index c9472d905520..efd4037ed008 100644

Checking patch tcp.c...
Applied patch tcp.c cleanly.

index at:
100644 efd4037ed00806aa3b526ee750fee05153dd6da5	tcp.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).