DPDK logo

Elixir Cross Referencer

   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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <sys/types.h>
#include <string.h>
#include <sys/queue.h>
#include <stdarg.h>
#include <errno.h>
#include <getopt.h>

#include <rte_common.h>
#include <rte_common_vect.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_memzone.h>
#include <rte_tailq.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_launch.h>
#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_lcore.h>
#include <rte_per_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
#include <rte_pci.h>
#include <rte_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_ring.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_string_fns.h>

#define APP_LOOKUP_EXACT_MATCH          0
#define APP_LOOKUP_LPM                  1
#define DO_RFC_1812_CHECKS

#ifndef APP_LOOKUP_METHOD
#define APP_LOOKUP_METHOD             APP_LOOKUP_LPM
#endif

/*
 *  When set to zero, simple forwaring path is eanbled.
 *  When set to one, optimized forwarding path is enabled.
 *  Note that LPM optimisation path uses SSE4.1 instructions.
 */
#if ((APP_LOOKUP_METHOD == APP_LOOKUP_LPM) && !defined(__SSE4_1__))
#define ENABLE_MULTI_BUFFER_OPTIMIZE	0
#else
#define ENABLE_MULTI_BUFFER_OPTIMIZE	1
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#include <rte_hash.h>
#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
#include <rte_lpm.h>
#include <rte_lpm6.h>
#else
#error "APP_LOOKUP_METHOD set to incorrect value"
#endif

#ifndef IPv6_BYTES
#define IPv6_BYTES_FMT "%02x%02x:%02x%02x:%02x%02x:%02x%02x:"\
                       "%02x%02x:%02x%02x:%02x%02x:%02x%02x"
#define IPv6_BYTES(addr) \
	addr[0],  addr[1], addr[2],  addr[3], \
	addr[4],  addr[5], addr[6],  addr[7], \
	addr[8],  addr[9], addr[10], addr[11],\
	addr[12], addr[13],addr[14], addr[15]
#endif


#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1

#define MAX_JUMBO_PKT_LEN  9600

#define IPV6_ADDR_LEN 16

#define MEMPOOL_CACHE_SIZE 256

#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)

/*
 * This expression is used to calculate the number of mbufs needed depending on user input, taking
 *  into account memory for rx and tx hardware rings, cache per lcore and mtable per port per lcore.
 *  RTE_MAX is used to ensure that NB_MBUF never goes below a minimum value of 8192
 */

#define NB_MBUF RTE_MAX	(																	\
				(nb_ports*nb_rx_queue*RTE_TEST_RX_DESC_DEFAULT +							\
				nb_ports*nb_lcores*MAX_PKT_BURST +											\
				nb_ports*n_tx_queue*RTE_TEST_TX_DESC_DEFAULT +								\
				nb_lcores*MEMPOOL_CACHE_SIZE),												\
				(unsigned)8192)

#define MAX_PKT_BURST     32
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */

/*
 * Try to avoid TX buffering if we have at least MAX_TX_BURST packets to send.
 */
#define	MAX_TX_BURST	(MAX_PKT_BURST / 2)

#define NB_SOCKETS 8

/* Configure how many packets ahead to prefetch, when reading packets */
#define PREFETCH_OFFSET	3

/* Used to mark destination port as 'invalid'. */
#define	BAD_PORT	((uint16_t)-1)

#define FWDSTEP	4

/*
 * Configurable number of RX/TX ring descriptors
 */
#define RTE_TEST_RX_DESC_DEFAULT 128
#define RTE_TEST_TX_DESC_DEFAULT 512
static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;

/* ethernet addresses of ports */
static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];

static __m128i val_eth[RTE_MAX_ETHPORTS];

/* replace first 12B of the ethernet header. */
#define	MASK_ETH	0x3f

/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
static int promiscuous_on = 0; /**< Ports set in promiscuous mode off by default. */
static int numa_on = 1; /**< NUMA is enabled by default. */

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static int ipv6 = 0; /**< ipv6 is false by default. */
#endif

struct mbuf_table {
	uint16_t len;
	struct rte_mbuf *m_table[MAX_PKT_BURST];
};

struct lcore_rx_queue {
	uint8_t port_id;
	uint8_t queue_id;
} __rte_cache_aligned;

#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS
#define MAX_RX_QUEUE_PER_PORT 128

#define MAX_LCORE_PARAMS 1024
struct lcore_params {
	uint8_t port_id;
	uint8_t queue_id;
	uint8_t lcore_id;
} __rte_cache_aligned;

static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
static struct lcore_params lcore_params_array_default[] = {
	{0, 0, 2},
	{0, 1, 2},
	{0, 2, 2},
	{1, 0, 2},
	{1, 1, 2},
	{1, 2, 2},
	{2, 0, 2},
	{3, 0, 3},
	{3, 1, 3},
};

static struct lcore_params * lcore_params = lcore_params_array_default;
static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
				sizeof(lcore_params_array_default[0]);

static struct rte_eth_conf port_conf = {
	.rxmode = {
		.mq_mode = ETH_MQ_RX_RSS,
		.max_rx_pkt_len = ETHER_MAX_LEN,
		.split_hdr_size = 0,
		.header_split   = 0, /**< Header Split disabled */
		.hw_ip_checksum = 1, /**< IP checksum offload enabled */
		.hw_vlan_filter = 0, /**< VLAN filtering disabled */
		.jumbo_frame    = 0, /**< Jumbo Frame Support disabled */
		.hw_strip_crc   = 0, /**< CRC stripped by hardware */
	},
	.rx_adv_conf = {
		.rss_conf = {
			.rss_key = NULL,
			.rss_hf = ETH_RSS_IP,
		},
	},
	.txmode = {
		.mq_mode = ETH_MQ_TX_NONE,
	},
};

static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)

#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
#include <rte_hash_crc.h>
#define DEFAULT_HASH_FUNC       rte_hash_crc
#else
#include <rte_jhash.h>
#define DEFAULT_HASH_FUNC       rte_jhash
#endif

struct ipv4_5tuple {
        uint32_t ip_dst;
        uint32_t ip_src;
        uint16_t port_dst;
        uint16_t port_src;
        uint8_t  proto;
} __attribute__((__packed__));

union ipv4_5tuple_host {
	struct {
		uint8_t  pad0;
		uint8_t  proto;
		uint16_t pad1;
		uint32_t ip_src;
		uint32_t ip_dst;
		uint16_t port_src;
		uint16_t port_dst;
	};
	__m128i xmm;
};

#define XMM_NUM_IN_IPV6_5TUPLE 3

struct ipv6_5tuple {
        uint8_t  ip_dst[IPV6_ADDR_LEN];
        uint8_t  ip_src[IPV6_ADDR_LEN];
        uint16_t port_dst;
        uint16_t port_src;
        uint8_t  proto;
} __attribute__((__packed__));

union ipv6_5tuple_host {
	struct {
		uint16_t pad0;
		uint8_t  proto;
		uint8_t  pad1;
		uint8_t  ip_src[IPV6_ADDR_LEN];
		uint8_t  ip_dst[IPV6_ADDR_LEN];
		uint16_t port_src;
		uint16_t port_dst;
		uint64_t reserve;
	};
	__m128i xmm[XMM_NUM_IN_IPV6_5TUPLE];
};

struct ipv4_l3fwd_route {
	struct ipv4_5tuple key;
	uint8_t if_out;
};

struct ipv6_l3fwd_route {
	struct ipv6_5tuple key;
	uint8_t if_out;
};

static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
	{{IPv4(101,0,0,0), IPv4(100,10,0,1),  101, 11, IPPROTO_TCP}, 0},
	{{IPv4(201,0,0,0), IPv4(200,20,0,1),  102, 12, IPPROTO_TCP}, 1},
	{{IPv4(111,0,0,0), IPv4(100,30,0,1),  101, 11, IPPROTO_TCP}, 2},
	{{IPv4(211,0,0,0), IPv4(200,40,0,1),  102, 12, IPPROTO_TCP}, 3},
};

static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = {
	{{
	{0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
	{0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
	101, 11, IPPROTO_TCP}, 0},

	{{
	{0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
	{0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
	102, 12, IPPROTO_TCP}, 1},

	{{
	{0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
	{0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
	101, 11, IPPROTO_TCP}, 2},

	{{
	{0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
	{0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
	102, 12, IPPROTO_TCP}, 3},
};

typedef struct rte_hash lookup_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS];

#ifdef RTE_ARCH_X86_64
/* default to 4 million hash entries (approx) */
#define L3FWD_HASH_ENTRIES		1024*1024*4
#else
/* 32-bit has less address-space for hugepage memory, limit to 1M entries */
#define L3FWD_HASH_ENTRIES		1024*1024*1
#endif
#define HASH_ENTRY_NUMBER_DEFAULT	4

static uint32_t hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT;

static inline uint32_t
ipv4_hash_crc(const void *data, __rte_unused uint32_t data_len,
	uint32_t init_val)
{
	const union ipv4_5tuple_host *k;
	uint32_t t;
	const uint32_t *p;

	k = data;
	t = k->proto;
	p = (const uint32_t *)&k->port_src;

#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
	init_val = rte_hash_crc_4byte(t, init_val);
	init_val = rte_hash_crc_4byte(k->ip_src, init_val);
	init_val = rte_hash_crc_4byte(k->ip_dst, init_val);
	init_val = rte_hash_crc_4byte(*p, init_val);
#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */
	init_val = rte_jhash_1word(t, init_val);
	init_val = rte_jhash_1word(k->ip_src, init_val);
	init_val = rte_jhash_1word(k->ip_dst, init_val);
	init_val = rte_jhash_1word(*p, init_val);
#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
	return (init_val);
}

static inline uint32_t
ipv6_hash_crc(const void *data, __rte_unused uint32_t data_len, uint32_t init_val)
{
	const union ipv6_5tuple_host *k;
	uint32_t t;
	const uint32_t *p;
#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
	const uint32_t  *ip_src0, *ip_src1, *ip_src2, *ip_src3;
	const uint32_t  *ip_dst0, *ip_dst1, *ip_dst2, *ip_dst3;
#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */

	k = data;
	t = k->proto;
	p = (const uint32_t *)&k->port_src;

#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
	ip_src0 = (const uint32_t *) k->ip_src;
	ip_src1 = (const uint32_t *)(k->ip_src+4);
	ip_src2 = (const uint32_t *)(k->ip_src+8);
	ip_src3 = (const uint32_t *)(k->ip_src+12);
	ip_dst0 = (const uint32_t *) k->ip_dst;
	ip_dst1 = (const uint32_t *)(k->ip_dst+4);
	ip_dst2 = (const uint32_t *)(k->ip_dst+8);
	ip_dst3 = (const uint32_t *)(k->ip_dst+12);
	init_val = rte_hash_crc_4byte(t, init_val);
	init_val = rte_hash_crc_4byte(*ip_src0, init_val);
	init_val = rte_hash_crc_4byte(*ip_src1, init_val);
	init_val = rte_hash_crc_4byte(*ip_src2, init_val);
	init_val = rte_hash_crc_4byte(*ip_src3, init_val);
	init_val = rte_hash_crc_4byte(*ip_dst0, init_val);
	init_val = rte_hash_crc_4byte(*ip_dst1, init_val);
	init_val = rte_hash_crc_4byte(*ip_dst2, init_val);
	init_val = rte_hash_crc_4byte(*ip_dst3, init_val);
	init_val = rte_hash_crc_4byte(*p, init_val);
#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */
	init_val = rte_jhash_1word(t, init_val);
	init_val = rte_jhash(k->ip_src, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val);
	init_val = rte_jhash(k->ip_dst, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val);
	init_val = rte_jhash_1word(*p, init_val);
#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
	return (init_val);
}

#define IPV4_L3FWD_NUM_ROUTES \
	(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))

#define IPV6_L3FWD_NUM_ROUTES \
	(sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0]))

static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;

#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
struct ipv4_l3fwd_route {
	uint32_t ip;
	uint8_t  depth;
	uint8_t  if_out;
};

struct ipv6_l3fwd_route {
	uint8_t ip[16];
	uint8_t  depth;
	uint8_t  if_out;
};

static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
	{IPv4(1,1,1,0), 24, 0},
	{IPv4(2,1,1,0), 24, 1},
	{IPv4(3,1,1,0), 24, 2},
	{IPv4(4,1,1,0), 24, 3},
	{IPv4(5,1,1,0), 24, 4},
	{IPv4(6,1,1,0), 24, 5},
	{IPv4(7,1,1,0), 24, 6},
	{IPv4(8,1,1,0), 24, 7},
};

static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = {
	{{1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 0},
	{{2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 1},
	{{3,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 2},
	{{4,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 3},
	{{5,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 4},
	{{6,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 5},
	{{7,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 6},
	{{8,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 7},
};

#define IPV4_L3FWD_NUM_ROUTES \
	(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))
#define IPV6_L3FWD_NUM_ROUTES \
	(sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0]))

#define IPV4_L3FWD_LPM_MAX_RULES         1024
#define IPV6_L3FWD_LPM_MAX_RULES         1024
#define IPV6_L3FWD_LPM_NUMBER_TBL8S (1 << 16)

typedef struct rte_lpm lookup_struct_t;
typedef struct rte_lpm6 lookup6_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
static lookup6_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS];
#endif

struct lcore_conf {
	uint16_t n_rx_queue;
	struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
	uint16_t tx_queue_id[RTE_MAX_ETHPORTS];
	struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS];
	lookup_struct_t * ipv4_lookup_struct;
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
	lookup6_struct_t * ipv6_lookup_struct;
#else
	lookup_struct_t * ipv6_lookup_struct;
#endif
} __rte_cache_aligned;

static struct lcore_conf lcore_conf[RTE_MAX_LCORE];

/* Send burst of packets on an output interface */
static inline int
send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port)
{
	struct rte_mbuf **m_table;
	int ret;
	uint16_t queueid;

	queueid = qconf->tx_queue_id[port];
	m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table;

	ret = rte_eth_tx_burst(port, queueid, m_table, n);
	if (unlikely(ret < n)) {
		do {
			rte_pktmbuf_free(m_table[ret]);
		} while (++ret < n);
	}

	return 0;
}

/* Enqueue a single packet, and send burst if queue is filled */
static inline int
send_single_packet(struct rte_mbuf *m, uint8_t port)
{
	uint32_t lcore_id;
	uint16_t len;
	struct lcore_conf *qconf;

	lcore_id = rte_lcore_id();

	qconf = &lcore_conf[lcore_id];
	len = qconf->tx_mbufs[port].len;
	qconf->tx_mbufs[port].m_table[len] = m;
	len++;

	/* enough pkts to be sent */
	if (unlikely(len == MAX_PKT_BURST)) {
		send_burst(qconf, MAX_PKT_BURST, port);
		len = 0;
	}

	qconf->tx_mbufs[port].len = len;
	return 0;
}

static inline __attribute__((always_inline)) void
send_packetsx4(struct lcore_conf *qconf, uint8_t port,
	struct rte_mbuf *m[], uint32_t num)
{
	uint32_t len, j, n;

	len = qconf->tx_mbufs[port].len;

	/*
	 * If TX buffer for that queue is empty, and we have enough packets,
	 * then send them straightway.
	 */
	if (num >= MAX_TX_BURST && len == 0) {
		n = rte_eth_tx_burst(port, qconf->tx_queue_id[port], m, num);
		if (unlikely(n < num)) {
			do {
				rte_pktmbuf_free(m[n]);
			} while (++n < num);
		}
		return;
	}

	/*
	 * Put packets into TX buffer for that queue.
	 */

	n = len + num;
	n = (n > MAX_PKT_BURST) ? MAX_PKT_BURST - len : num;

	j = 0;
	switch (n % FWDSTEP) {
	while (j < n) {
	case 0:
		qconf->tx_mbufs[port].m_table[len + j] = m[j];
		j++;
	case 3:
		qconf->tx_mbufs[port].m_table[len + j] = m[j];
		j++;
	case 2:
		qconf->tx_mbufs[port].m_table[len + j] = m[j];
		j++;
	case 1:
		qconf->tx_mbufs[port].m_table[len + j] = m[j];
		j++;
	}
	}

	len += n;

	/* enough pkts to be sent */
	if (unlikely(len == MAX_PKT_BURST)) {

		send_burst(qconf, MAX_PKT_BURST, port);

		/* copy rest of the packets into the TX buffer. */
		len = num - n;
		j = 0;
		switch (len % FWDSTEP) {
		while (j < len) {
		case 0:
			qconf->tx_mbufs[port].m_table[j] = m[n + j];
			j++;
		case 3:
			qconf->tx_mbufs[port].m_table[j] = m[n + j];
			j++;
		case 2:
			qconf->tx_mbufs[port].m_table[j] = m[n + j];
			j++;
		case 1:
			qconf->tx_mbufs[port].m_table[j] = m[n + j];
			j++;
		}
		}
	}

	qconf->tx_mbufs[port].len = len;
}

#ifdef DO_RFC_1812_CHECKS
static inline int
is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len)
{
	/* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */
	/*
	 * 1. The packet length reported by the Link Layer must be large
	 * enough to hold the minimum length legal IP datagram (20 bytes).
	 */
	if (link_len < sizeof(struct ipv4_hdr))
		return -1;

	/* 2. The IP checksum must be correct. */
	/* this is checked in H/W */

	/*
	 * 3. The IP version number must be 4. If the version number is not 4
	 * then the packet may be another version of IP, such as IPng or
	 * ST-II.
	 */
	if (((pkt->version_ihl) >> 4) != 4)
		return -3;
	/*
	 * 4. The IP header length field must be large enough to hold the
	 * minimum length legal IP datagram (20 bytes = 5 words).
	 */
	if ((pkt->version_ihl & 0xf) < 5)
		return -4;

	/*
	 * 5. The IP total length field must be large enough to hold the IP
	 * datagram header, whose length is specified in the IP header length
	 * field.
	 */
	if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr))
		return -5;

	return 0;
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)

static __m128i mask0;
static __m128i mask1;
static __m128i mask2;
static inline uint8_t
get_ipv4_dst_port(void *ipv4_hdr, uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
	int ret = 0;
	union ipv4_5tuple_host key;

	ipv4_hdr = (uint8_t *)ipv4_hdr + offsetof(struct ipv4_hdr, time_to_live);
	__m128i data = _mm_loadu_si128((__m128i*)(ipv4_hdr));
	/* Get 5 tuple: dst port, src port, dst IP address, src IP address and protocol */
	key.xmm = _mm_and_si128(data, mask0);
	/* Find destination port */
	ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
	return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]);
}

static inline uint8_t
get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, lookup_struct_t * ipv6_l3fwd_lookup_struct)
{
	int ret = 0;
	union ipv6_5tuple_host key;

	ipv6_hdr = (uint8_t *)ipv6_hdr + offsetof(struct ipv6_hdr, payload_len);
	__m128i data0 = _mm_loadu_si128((__m128i*)(ipv6_hdr));
	__m128i data1 = _mm_loadu_si128((__m128i*)(((uint8_t*)ipv6_hdr)+sizeof(__m128i)));
	__m128i data2 = _mm_loadu_si128((__m128i*)(((uint8_t*)ipv6_hdr)+sizeof(__m128i)+sizeof(__m128i)));
	/* Get part of 5 tuple: src IP address lower 96 bits and protocol */
	key.xmm[0] = _mm_and_si128(data0, mask1);
	/* Get part of 5 tuple: dst IP address lower 96 bits and src IP address higher 32 bits */
	key.xmm[1] = data1;
	/* Get part of 5 tuple: dst port and src port and dst IP address higher 32 bits */
	key.xmm[2] = _mm_and_si128(data2, mask2);

	/* Find destination port */
	ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
	return (uint8_t)((ret < 0)? portid : ipv6_l3fwd_out_if[ret]);
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)

static inline uint8_t
get_ipv4_dst_port(void *ipv4_hdr,  uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
	uint8_t next_hop;

	return (uint8_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
		rte_be_to_cpu_32(((struct ipv4_hdr *)ipv4_hdr)->dst_addr),
		&next_hop) == 0) ? next_hop : portid);
}

static inline uint8_t
get_ipv6_dst_port(void *ipv6_hdr,  uint8_t portid, lookup6_struct_t * ipv6_l3fwd_lookup_struct)
{
	uint8_t next_hop;
	return (uint8_t) ((rte_lpm6_lookup(ipv6_l3fwd_lookup_struct,
			((struct ipv6_hdr*)ipv6_hdr)->dst_addr, &next_hop) == 0)?
			next_hop : portid);
}
#endif

static inline void l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid,
	struct lcore_conf *qconf)  __attribute__((unused));

#if ((APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) && \
	(ENABLE_MULTI_BUFFER_OPTIMIZE == 1))

#define MASK_ALL_PKTS    0xf
#define EXECLUDE_1ST_PKT 0xe
#define EXECLUDE_2ND_PKT 0xd
#define EXECLUDE_3RD_PKT 0xb
#define EXECLUDE_4TH_PKT 0x7

static inline void
simple_ipv4_fwd_4pkts(struct rte_mbuf* m[4], uint8_t portid, struct lcore_conf *qconf)
{
	struct ether_hdr *eth_hdr[4];
	struct ipv4_hdr *ipv4_hdr[4];
	void *d_addr_bytes[4];
	uint8_t dst_port[4];
	int32_t ret[4];
	union ipv4_5tuple_host key[4];
	__m128i data[4];

	eth_hdr[0] = rte_pktmbuf_mtod(m[0], struct ether_hdr *);
	eth_hdr[1] = rte_pktmbuf_mtod(m[1], struct ether_hdr *);
	eth_hdr[2] = rte_pktmbuf_mtod(m[2], struct ether_hdr *);
	eth_hdr[3] = rte_pktmbuf_mtod(m[3], struct ether_hdr *);

	/* Handle IPv4 headers.*/
	ipv4_hdr[0] = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m[0], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv4_hdr[1] = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m[1], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv4_hdr[2] = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m[2], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv4_hdr[3] = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m[3], unsigned char *) +
			sizeof(struct ether_hdr));

#ifdef DO_RFC_1812_CHECKS
	/* Check to make sure the packet is valid (RFC1812) */
	uint8_t valid_mask = MASK_ALL_PKTS;
	if (is_valid_ipv4_pkt(ipv4_hdr[0], m[0]->pkt_len) < 0) {
		rte_pktmbuf_free(m[0]);
		valid_mask &= EXECLUDE_1ST_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[1], m[1]->pkt_len) < 0) {
		rte_pktmbuf_free(m[1]);
		valid_mask &= EXECLUDE_2ND_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[2], m[2]->pkt_len) < 0) {
		rte_pktmbuf_free(m[2]);
		valid_mask &= EXECLUDE_3RD_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[3], m[3]->pkt_len) < 0) {
		rte_pktmbuf_free(m[3]);
		valid_mask &= EXECLUDE_4TH_PKT;
	}
	if (unlikely(valid_mask != MASK_ALL_PKTS)) {
		if (valid_mask == 0){
			return;
		} else {
			uint8_t i = 0;
			for (i = 0; i < 4; i++) {
				if ((0x1 << i) & valid_mask) {
					l3fwd_simple_forward(m[i], portid, qconf);
				}
			}
			return;
		}
	}
#endif // End of #ifdef DO_RFC_1812_CHECKS

	data[0] = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m[0], unsigned char *) +
		sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
	data[1] = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m[1], unsigned char *) +
		sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
	data[2] = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m[2], unsigned char *) +
		sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
	data[3] = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m[3], unsigned char *) +
		sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));

	key[0].xmm = _mm_and_si128(data[0], mask0);
	key[1].xmm = _mm_and_si128(data[1], mask0);
	key[2].xmm = _mm_and_si128(data[2], mask0);
	key[3].xmm = _mm_and_si128(data[3], mask0);

	const void *key_array[4] = {&key[0], &key[1], &key[2],&key[3]};
	rte_hash_lookup_multi(qconf->ipv4_lookup_struct, &key_array[0], 4, ret);
	dst_port[0] = (uint8_t) ((ret[0] < 0) ? portid : ipv4_l3fwd_out_if[ret[0]]);
	dst_port[1] = (uint8_t) ((ret[1] < 0) ? portid : ipv4_l3fwd_out_if[ret[1]]);
	dst_port[2] = (uint8_t) ((ret[2] < 0) ? portid : ipv4_l3fwd_out_if[ret[2]]);
	dst_port[3] = (uint8_t) ((ret[3] < 0) ? portid : ipv4_l3fwd_out_if[ret[3]]);

	if (dst_port[0] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[0]) == 0)
		dst_port[0] = portid;
	if (dst_port[1] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[1]) == 0)
		dst_port[1] = portid;
	if (dst_port[2] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[2]) == 0)
		dst_port[2] = portid;
	if (dst_port[3] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[3]) == 0)
		dst_port[3] = portid;

	/* 02:00:00:00:00:xx */
	d_addr_bytes[0] = &eth_hdr[0]->d_addr.addr_bytes[0];
	d_addr_bytes[1] = &eth_hdr[1]->d_addr.addr_bytes[0];
	d_addr_bytes[2] = &eth_hdr[2]->d_addr.addr_bytes[0];
	d_addr_bytes[3] = &eth_hdr[3]->d_addr.addr_bytes[0];
	*((uint64_t *)d_addr_bytes[0]) = 0x000000000002 + ((uint64_t)dst_port[0] << 40);
	*((uint64_t *)d_addr_bytes[1]) = 0x000000000002 + ((uint64_t)dst_port[1] << 40);
	*((uint64_t *)d_addr_bytes[2]) = 0x000000000002 + ((uint64_t)dst_port[2] << 40);
	*((uint64_t *)d_addr_bytes[3]) = 0x000000000002 + ((uint64_t)dst_port[3] << 40);

#ifdef DO_RFC_1812_CHECKS
	/* Update time to live and header checksum */
	--(ipv4_hdr[0]->time_to_live);
	--(ipv4_hdr[1]->time_to_live);
	--(ipv4_hdr[2]->time_to_live);
	--(ipv4_hdr[3]->time_to_live);
	++(ipv4_hdr[0]->hdr_checksum);
	++(ipv4_hdr[1]->hdr_checksum);
	++(ipv4_hdr[2]->hdr_checksum);
	++(ipv4_hdr[3]->hdr_checksum);
#endif

	/* src addr */
	ether_addr_copy(&ports_eth_addr[dst_port[0]], &eth_hdr[0]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[1]], &eth_hdr[1]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[2]], &eth_hdr[2]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[3]], &eth_hdr[3]->s_addr);

	send_single_packet(m[0], (uint8_t)dst_port[0]);
	send_single_packet(m[1], (uint8_t)dst_port[1]);
	send_single_packet(m[2], (uint8_t)dst_port[2]);
	send_single_packet(m[3], (uint8_t)dst_port[3]);

}

static inline void get_ipv6_5tuple(struct rte_mbuf* m0, __m128i mask0, __m128i mask1,
				 union ipv6_5tuple_host * key)
{
        __m128i tmpdata0 = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m0, unsigned char *)
			+ sizeof(struct ether_hdr) + offsetof(struct ipv6_hdr, payload_len)));
        __m128i tmpdata1 = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m0, unsigned char *)
			+ sizeof(struct ether_hdr) + offsetof(struct ipv6_hdr, payload_len)
			+  sizeof(__m128i)));
        __m128i tmpdata2 = _mm_loadu_si128((__m128i*)(rte_pktmbuf_mtod(m0, unsigned char *)
			+ sizeof(struct ether_hdr) + offsetof(struct ipv6_hdr, payload_len)
			+ sizeof(__m128i) + sizeof(__m128i)));
        key->xmm[0] = _mm_and_si128(tmpdata0, mask0);
        key->xmm[1] = tmpdata1;
        key->xmm[2] = _mm_and_si128(tmpdata2, mask1);
	return;
}

static inline void
simple_ipv6_fwd_4pkts(struct rte_mbuf* m[4], uint8_t portid, struct lcore_conf *qconf)
{
	struct ether_hdr *eth_hdr[4];
	__attribute__((unused)) struct ipv6_hdr *ipv6_hdr[4];
	void *d_addr_bytes[4];
	uint8_t dst_port[4];
	int32_t ret[4];
	union ipv6_5tuple_host key[4];

	eth_hdr[0] = rte_pktmbuf_mtod(m[0], struct ether_hdr *);
	eth_hdr[1] = rte_pktmbuf_mtod(m[1], struct ether_hdr *);
	eth_hdr[2] = rte_pktmbuf_mtod(m[2], struct ether_hdr *);
	eth_hdr[3] = rte_pktmbuf_mtod(m[3], struct ether_hdr *);

	/* Handle IPv6 headers.*/
	ipv6_hdr[0] = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m[0], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv6_hdr[1] = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m[1], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv6_hdr[2] = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m[2], unsigned char *) +
			sizeof(struct ether_hdr));
	ipv6_hdr[3] = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m[3], unsigned char *) +
			sizeof(struct ether_hdr));

	get_ipv6_5tuple(m[0], mask1, mask2, &key[0]);
	get_ipv6_5tuple(m[1], mask1, mask2, &key[1]);
	get_ipv6_5tuple(m[2], mask1, mask2, &key[2]);
	get_ipv6_5tuple(m[3], mask1, mask2, &key[3]);

	const void *key_array[4] = {&key[0], &key[1], &key[2],&key[3]};
	rte_hash_lookup_multi(qconf->ipv6_lookup_struct, &key_array[0], 4, ret);
	dst_port[0] = (uint8_t) ((ret[0] < 0)? portid:ipv6_l3fwd_out_if[ret[0]]);
	dst_port[1] = (uint8_t) ((ret[1] < 0)? portid:ipv6_l3fwd_out_if[ret[1]]);
	dst_port[2] = (uint8_t) ((ret[2] < 0)? portid:ipv6_l3fwd_out_if[ret[2]]);
	dst_port[3] = (uint8_t) ((ret[3] < 0)? portid:ipv6_l3fwd_out_if[ret[3]]);

	if (dst_port[0] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[0]) == 0)
		dst_port[0] = portid;
	if (dst_port[1] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[1]) == 0)
		dst_port[1] = portid;
	if (dst_port[2] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[2]) == 0)
		dst_port[2] = portid;
	if (dst_port[3] >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port[3]) == 0)
		dst_port[3] = portid;

	/* 02:00:00:00:00:xx */
	d_addr_bytes[0] = &eth_hdr[0]->d_addr.addr_bytes[0];
	d_addr_bytes[1] = &eth_hdr[1]->d_addr.addr_bytes[0];
	d_addr_bytes[2] = &eth_hdr[2]->d_addr.addr_bytes[0];
	d_addr_bytes[3] = &eth_hdr[3]->d_addr.addr_bytes[0];
	*((uint64_t *)d_addr_bytes[0]) = 0x000000000002 + ((uint64_t)dst_port[0] << 40);
	*((uint64_t *)d_addr_bytes[1]) = 0x000000000002 + ((uint64_t)dst_port[1] << 40);
	*((uint64_t *)d_addr_bytes[2]) = 0x000000000002 + ((uint64_t)dst_port[2] << 40);
	*((uint64_t *)d_addr_bytes[3]) = 0x000000000002 + ((uint64_t)dst_port[3] << 40);

	/* src addr */
	ether_addr_copy(&ports_eth_addr[dst_port[0]], &eth_hdr[0]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[1]], &eth_hdr[1]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[2]], &eth_hdr[2]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[3]], &eth_hdr[3]->s_addr);

	send_single_packet(m[0], (uint8_t)dst_port[0]);
	send_single_packet(m[1], (uint8_t)dst_port[1]);
	send_single_packet(m[2], (uint8_t)dst_port[2]);
	send_single_packet(m[3], (uint8_t)dst_port[3]);

}
#endif /* APP_LOOKUP_METHOD */

static inline __attribute__((always_inline)) void
l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, struct lcore_conf *qconf)
{
	struct ether_hdr *eth_hdr;
	struct ipv4_hdr *ipv4_hdr;
	void *d_addr_bytes;
	uint8_t dst_port;

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);

	if (m->ol_flags & PKT_RX_IPV4_HDR) {
		/* Handle IPv4 headers.*/
		ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) +
				sizeof(struct ether_hdr));

#ifdef DO_RFC_1812_CHECKS
		/* Check to make sure the packet is valid (RFC1812) */
		if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) {
			rte_pktmbuf_free(m);
			return;
		}
#endif

		 dst_port = get_ipv4_dst_port(ipv4_hdr, portid,
			qconf->ipv4_lookup_struct);
		if (dst_port >= RTE_MAX_ETHPORTS ||
				(enabled_port_mask & 1 << dst_port) == 0)
			dst_port = portid;

		/* 02:00:00:00:00:xx */
		d_addr_bytes = &eth_hdr->d_addr.addr_bytes[0];
		*((uint64_t *)d_addr_bytes) = ETHER_LOCAL_ADMIN_ADDR +
			((uint64_t)dst_port << 40);

#ifdef DO_RFC_1812_CHECKS
		/* Update time to live and header checksum */
		--(ipv4_hdr->time_to_live);
		++(ipv4_hdr->hdr_checksum);
#endif

		/* src addr */
		ether_addr_copy(&ports_eth_addr[dst_port], &eth_hdr->s_addr);

		send_single_packet(m, dst_port);

	} else {
		/* Handle IPv6 headers.*/
		struct ipv6_hdr *ipv6_hdr;

		ipv6_hdr = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) +
				sizeof(struct ether_hdr));

		dst_port = get_ipv6_dst_port(ipv6_hdr, portid, qconf->ipv6_lookup_struct);

		if (dst_port >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port) == 0)
			dst_port = portid;

		/* 02:00:00:00:00:xx */
		d_addr_bytes = &eth_hdr->d_addr.addr_bytes[0];
		*((uint64_t *)d_addr_bytes) = ETHER_LOCAL_ADMIN_ADDR +
			((uint64_t)dst_port << 40);

		/* src addr */
		ether_addr_copy(&ports_eth_addr[dst_port], &eth_hdr->s_addr);

		send_single_packet(m, dst_port);
	}

}

#ifdef DO_RFC_1812_CHECKS

#define	IPV4_MIN_VER_IHL	0x45
#define	IPV4_MAX_VER_IHL	0x4f
#define	IPV4_MAX_VER_IHL_DIFF	(IPV4_MAX_VER_IHL - IPV4_MIN_VER_IHL)

/* Minimum value of IPV4 total length (20B) in network byte order. */
#define	IPV4_MIN_LEN_BE	(sizeof(struct ipv4_hdr) << 8)

/*
 * From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2:
 * - The IP version number must be 4.
 * - The IP header length field must be large enough to hold the
 *    minimum length legal IP datagram (20 bytes = 5 words).
 * - The IP total length field must be large enough to hold the IP
 *   datagram header, whose length is specified in the IP header length
 *   field.
 * If we encounter invalid IPV4 packet, then set destination port for it
 * to BAD_PORT value.
 */
static inline __attribute__((always_inline)) void
rfc1812_process(struct ipv4_hdr *ipv4_hdr, uint16_t *dp, uint32_t flags)
{
	uint8_t ihl;

	if ((flags & PKT_RX_IPV4_HDR) != 0) {

		ihl = ipv4_hdr->version_ihl - IPV4_MIN_VER_IHL;

		ipv4_hdr->time_to_live--;
		ipv4_hdr->hdr_checksum++;

		if (ihl > IPV4_MAX_VER_IHL_DIFF ||
				((uint8_t)ipv4_hdr->total_length == 0 &&
				ipv4_hdr->total_length < IPV4_MIN_LEN_BE)) {
			dp[0] = BAD_PORT;
		}
	}
}

#else
#define	rfc1812_process(mb, dp)	do { } while (0)
#endif /* DO_RFC_1812_CHECKS */


#if ((APP_LOOKUP_METHOD == APP_LOOKUP_LPM) && \
	(ENABLE_MULTI_BUFFER_OPTIMIZE == 1))

static inline __attribute__((always_inline)) uint16_t
get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
	uint32_t dst_ipv4, uint8_t portid)
{
	uint8_t next_hop;
	struct ipv6_hdr *ipv6_hdr;
	struct ether_hdr *eth_hdr;

	if (pkt->ol_flags & PKT_RX_IPV4_HDR) {
		if (rte_lpm_lookup(qconf->ipv4_lookup_struct, dst_ipv4,
				&next_hop) != 0)
			next_hop = portid;
	} else if (pkt->ol_flags & PKT_RX_IPV6_HDR) {
		eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
		ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1);
		if (rte_lpm6_lookup(qconf->ipv6_lookup_struct,
				ipv6_hdr->dst_addr, &next_hop) != 0)
			next_hop = portid;
	} else {
		next_hop = portid;
	}

	return next_hop;
}

static inline void
process_packet(struct lcore_conf *qconf, struct rte_mbuf *pkt,
	uint16_t *dst_port, uint8_t portid)
{
	struct ether_hdr *eth_hdr;
	struct ipv4_hdr *ipv4_hdr;
	uint32_t dst_ipv4;
	uint16_t dp;
	__m128i te, ve;

	eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);

	dst_ipv4 = ipv4_hdr->dst_addr;
	dst_ipv4 = rte_be_to_cpu_32(dst_ipv4);
	dp = get_dst_port(qconf, pkt, dst_ipv4, portid);

	te = _mm_load_si128((__m128i *)eth_hdr);
	ve = val_eth[dp];

	dst_port[0] = dp;
	rfc1812_process(ipv4_hdr, dst_port, pkt->ol_flags);

	te =  _mm_blend_epi16(te, ve, MASK_ETH);
	_mm_store_si128((__m128i *)eth_hdr, te);
}

/*
 * Read ol_flags and destination IPV4 addresses from 4 mbufs.
 */
static inline void
processx4_step1(struct rte_mbuf *pkt[FWDSTEP], __m128i *dip, uint32_t *flag)
{
	struct ipv4_hdr *ipv4_hdr;
	struct ether_hdr *eth_hdr;
	uint32_t x0, x1, x2, x3;

	eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x0 = ipv4_hdr->dst_addr;
	flag[0] = pkt[0]->ol_flags & PKT_RX_IPV4_HDR;

	eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x1 = ipv4_hdr->dst_addr;
	flag[0] &= pkt[1]->ol_flags;

	eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x2 = ipv4_hdr->dst_addr;
	flag[0] &= pkt[2]->ol_flags;

	eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x3 = ipv4_hdr->dst_addr;
	flag[0] &= pkt[3]->ol_flags;

	dip[0] = _mm_set_epi32(x3, x2, x1, x0);
}

/*
 * Lookup into LPM for destination port.
 * If lookup fails, use incoming port (portid) as destination port.
 */
static inline void
processx4_step2(const struct lcore_conf *qconf, __m128i dip, uint32_t flag,
	uint8_t portid, struct rte_mbuf *pkt[FWDSTEP], uint16_t dprt[FWDSTEP])
{
	rte_xmm_t dst;
	const  __m128i bswap_mask = _mm_set_epi8(12, 13, 14, 15, 8, 9, 10, 11,
						4, 5, 6, 7, 0, 1, 2, 3);

	/* Byte swap 4 IPV4 addresses. */
	dip = _mm_shuffle_epi8(dip, bswap_mask);

	/* if all 4 packets are IPV4. */
	if (likely(flag != 0)) {
		rte_lpm_lookupx4(qconf->ipv4_lookup_struct, dip, dprt, portid);
	} else {
		dst.m = dip;
		dprt[0] = get_dst_port(qconf, pkt[0], dst.u32[0], portid);
		dprt[1] = get_dst_port(qconf, pkt[1], dst.u32[1], portid);
		dprt[2] = get_dst_port(qconf, pkt[2], dst.u32[2], portid);
		dprt[3] = get_dst_port(qconf, pkt[3], dst.u32[3], portid);
	}
}

/*
 * Update source and destination MAC addresses in the ethernet header.
 * Perform RFC1812 checks and updates for IPV4 packets.
 */
static inline void
processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP])
{
	__m128i te[FWDSTEP];
	__m128i ve[FWDSTEP];
	__m128i *p[FWDSTEP];

	p[0] = (rte_pktmbuf_mtod(pkt[0], __m128i *));
	p[1] = (rte_pktmbuf_mtod(pkt[1], __m128i *));
	p[2] = (rte_pktmbuf_mtod(pkt[2], __m128i *));
	p[3] = (rte_pktmbuf_mtod(pkt[3], __m128i *));

	ve[0] = val_eth[dst_port[0]];
	te[0] = _mm_load_si128(p[0]);

	ve[1] = val_eth[dst_port[1]];
	te[1] = _mm_load_si128(p[1]);

	ve[2] = val_eth[dst_port[2]];
	te[2] = _mm_load_si128(p[2]);

	ve[3] = val_eth[dst_port[3]];
	te[3] = _mm_load_si128(p[3]);

	/* Update first 12 bytes, keep rest bytes intact. */
	te[0] =  _mm_blend_epi16(te[0], ve[0], MASK_ETH);
	te[1] =  _mm_blend_epi16(te[1], ve[1], MASK_ETH);
	te[2] =  _mm_blend_epi16(te[2], ve[2], MASK_ETH);
	te[3] =  _mm_blend_epi16(te[3], ve[3], MASK_ETH);

	_mm_store_si128(p[0], te[0]);
	_mm_store_si128(p[1], te[1]);
	_mm_store_si128(p[2], te[2]);
	_mm_store_si128(p[3], te[3]);

	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[0] + 1),
		&dst_port[0], pkt[0]->ol_flags);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1),
		&dst_port[1], pkt[1]->ol_flags);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1),
		&dst_port[2], pkt[2]->ol_flags);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1),
		&dst_port[3], pkt[3]->ol_flags);
}

/*
 * We group consecutive packets with the same destionation port into one burst.
 * To avoid extra latency this is done together with some other packet
 * processing, but after we made a final decision about packet's destination.
 * To do this we maintain:
 * pnum - array of number of consecutive packets with the same dest port for
 * each packet in the input burst.
 * lp - pointer to the last updated element in the pnum.
 * dlp - dest port value lp corresponds to.
 */

#define	GRPSZ	(1 << FWDSTEP)
#define	GRPMSK	(GRPSZ - 1)

#define GROUP_PORT_STEP(dlp, dcp, lp, pn, idx)	do { \
	if (likely((dlp) == (dcp)[(idx)])) {         \
		(lp)[0]++;                           \
	} else {                                     \
		(dlp) = (dcp)[idx];                  \
		(lp) = (pn) + (idx);                 \
		(lp)[0] = 1;                         \
	}                                            \
} while (0)

/*
 * Group consecutive packets with the same destination port in bursts of 4.
 * Suppose we have array of destionation ports:
 * dst_port[] = {a, b, c, d,, e, ... }
 * dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>.
 * We doing 4 comparisions at once and the result is 4 bit mask.
 * This mask is used as an index into prebuild array of pnum values.
 */
static inline uint16_t *
port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2)
{
	static const struct {
		uint64_t pnum; /* prebuild 4 values for pnum[]. */
		int32_t  idx;  /* index for new last updated elemnet. */
		uint16_t lpv;  /* add value to the last updated element. */
	} gptbl[GRPSZ] = {
	{
		/* 0: a != b, b != c, c != d, d != e */
		.pnum = UINT64_C(0x0001000100010001),
		.idx = 4,
		.lpv = 0,
	},
	{
		/* 1: a == b, b != c, c != d, d != e */
		.pnum = UINT64_C(0x0001000100010002),
		.idx = 4,
		.lpv = 1,
	},
	{
		/* 2: a != b, b == c, c != d, d != e */
		.pnum = UINT64_C(0x0001000100020001),
		.idx = 4,
		.lpv = 0,
	},
	{
		/* 3: a == b, b == c, c != d, d != e */
		.pnum = UINT64_C(0x0001000100020003),
		.idx = 4,
		.lpv = 2,
	},
	{
		/* 4: a != b, b != c, c == d, d != e */
		.pnum = UINT64_C(0x0001000200010001),
		.idx = 4,
		.lpv = 0,
	},
	{
		/* 5: a == b, b != c, c == d, d != e */
		.pnum = UINT64_C(0x0001000200010002),
		.idx = 4,
		.lpv = 1,
	},
	{
		/* 6: a != b, b == c, c == d, d != e */
		.pnum = UINT64_C(0x0001000200030001),
		.idx = 4,
		.lpv = 0,
	},
	{
		/* 7: a == b, b == c, c == d, d != e */
		.pnum = UINT64_C(0x0001000200030004),
		.idx = 4,
		.lpv = 3,
	},
	{
		/* 8: a != b, b != c, c != d, d == e */
		.pnum = UINT64_C(0x0002000100010001),
		.idx = 3,
		.lpv = 0,
	},
	{
		/* 9: a == b, b != c, c != d, d == e */
		.pnum = UINT64_C(0x0002000100010002),
		.idx = 3,
		.lpv = 1,
	},
	{
		/* 0xa: a != b, b == c, c != d, d == e */
		.pnum = UINT64_C(0x0002000100020001),
		.idx = 3,
		.lpv = 0,
	},
	{
		/* 0xb: a == b, b == c, c != d, d == e */
		.pnum = UINT64_C(0x0002000100020003),
		.idx = 3,
		.lpv = 2,
	},
	{
		/* 0xc: a != b, b != c, c == d, d == e */
		.pnum = UINT64_C(0x0002000300010001),
		.idx = 2,
		.lpv = 0,
	},
	{
		/* 0xd: a == b, b != c, c == d, d == e */
		.pnum = UINT64_C(0x0002000300010002),
		.idx = 2,
		.lpv = 1,
	},
	{
		/* 0xe: a != b, b == c, c == d, d == e */
		.pnum = UINT64_C(0x0002000300040001),
		.idx = 1,
		.lpv = 0,
	},
	{
		/* 0xf: a == b, b == c, c == d, d == e */
		.pnum = UINT64_C(0x0002000300040005),
		.idx = 0,
		.lpv = 4,
	},
	};

	union {
		uint16_t u16[FWDSTEP + 1];
		uint64_t u64;
	} *pnum = (void *)pn;

	int32_t v;

	dp1 = _mm_cmpeq_epi16(dp1, dp2);
	dp1 = _mm_unpacklo_epi16(dp1, dp1);
	v = _mm_movemask_ps((__m128)dp1);

	/* update last port counter. */
	lp[0] += gptbl[v].lpv;

	/* if dest port value has changed. */
	if (v != GRPMSK) {
		lp = pnum->u16 + gptbl[v].idx;
		lp[0] = 1;
		pnum->u64 = gptbl[v].pnum;
	}

	return lp;
}

#endif /* APP_LOOKUP_METHOD */

/* main processing loop */
static int
main_loop(__attribute__((unused)) void *dummy)
{
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	unsigned lcore_id;
	uint64_t prev_tsc, diff_tsc, cur_tsc;
	int i, j, nb_rx;
	uint8_t portid, queueid;
	struct lcore_conf *qconf;
	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
		US_PER_S * BURST_TX_DRAIN_US;

#if ((APP_LOOKUP_METHOD == APP_LOOKUP_LPM) && \
	(ENABLE_MULTI_BUFFER_OPTIMIZE == 1))
	int32_t k;
	uint16_t dlp;
	uint16_t *lp;
	uint16_t dst_port[MAX_PKT_BURST];
	__m128i dip[MAX_PKT_BURST / FWDSTEP];
	uint32_t flag[MAX_PKT_BURST / FWDSTEP];
	uint16_t pnum[MAX_PKT_BURST + 1];
#endif

	prev_tsc = 0;

	lcore_id = rte_lcore_id();
	qconf = &lcore_conf[lcore_id];

	if (qconf->n_rx_queue == 0) {
		RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id);
		return 0;
	}

	RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id);

	for (i = 0; i < qconf->n_rx_queue; i++) {

		portid = qconf->rx_queue_list[i].port_id;
		queueid = qconf->rx_queue_list[i].queue_id;
		RTE_LOG(INFO, L3FWD, " -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n", lcore_id,
			portid, queueid);
	}

	while (1) {

		cur_tsc = rte_rdtsc();

		/*
		 * TX burst queue drain
		 */
		diff_tsc = cur_tsc - prev_tsc;
		if (unlikely(diff_tsc > drain_tsc)) {

			/*
			 * This could be optimized (use queueid instead of
			 * portid), but it is not called so often
			 */
			for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
				if (qconf->tx_mbufs[portid].len == 0)
					continue;
				send_burst(qconf,
					qconf->tx_mbufs[portid].len,
					portid);
				qconf->tx_mbufs[portid].len = 0;
			}

			prev_tsc = cur_tsc;
		}

		/*
		 * Read packet from RX queues
		 */
		for (i = 0; i < qconf->n_rx_queue; ++i) {
			portid = qconf->rx_queue_list[i].port_id;
			queueid = qconf->rx_queue_list[i].queue_id;
			nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
				MAX_PKT_BURST);
			if (nb_rx == 0)
				continue;

#if (ENABLE_MULTI_BUFFER_OPTIMIZE == 1)
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
			{
				/*
				 * Send nb_rx - nb_rx%4 packets
				 * in groups of 4.
				 */
				int32_t n = RTE_ALIGN_FLOOR(nb_rx, 4);
				for (j = 0; j < n ; j+=4) {
					uint32_t ol_flag = pkts_burst[j]->ol_flags
							& pkts_burst[j+1]->ol_flags
							& pkts_burst[j+2]->ol_flags
							& pkts_burst[j+3]->ol_flags;
					if (ol_flag & PKT_RX_IPV4_HDR ) {
						simple_ipv4_fwd_4pkts(&pkts_burst[j],
									portid, qconf);
					} else if (ol_flag & PKT_RX_IPV6_HDR) {
						simple_ipv6_fwd_4pkts(&pkts_burst[j],
									portid, qconf);
					} else {
						l3fwd_simple_forward(pkts_burst[j],
									portid, qconf);
						l3fwd_simple_forward(pkts_burst[j+1],
									portid, qconf);
						l3fwd_simple_forward(pkts_burst[j+2],
									portid, qconf);
						l3fwd_simple_forward(pkts_burst[j+3],
									portid, qconf);
					}
				}
				for (; j < nb_rx ; j++) {
					l3fwd_simple_forward(pkts_burst[j],
								portid, qconf);
				}
			}
#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)

			k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
			for (j = 0; j != k; j += FWDSTEP) {
				processx4_step1(&pkts_burst[j],
					&dip[j / FWDSTEP],
					&flag[j / FWDSTEP]);
			}

			k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
			for (j = 0; j != k; j += FWDSTEP) {
				processx4_step2(qconf, dip[j / FWDSTEP],
					flag[j / FWDSTEP], portid,
					&pkts_burst[j], &dst_port[j]);
			}

			/*
			 * Finish packet processing and group consecutive
			 * packets with the same destination port.
			 */
			k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
			if (k != 0) {
				__m128i dp1, dp2;

				lp = pnum;
				lp[0] = 1;

				processx4_step3(pkts_burst, dst_port);

				/* dp1: <d[0], d[1], d[2], d[3], ... > */
				dp1 = _mm_loadu_si128((__m128i *)dst_port);

				for (j = FWDSTEP; j != k; j += FWDSTEP) {
					processx4_step3(&pkts_burst[j],
						&dst_port[j]);

					/*
					 * dp2:
					 * <d[j-3], d[j-2], d[j-1], d[j], ... >
					 */
					dp2 = _mm_loadu_si128((__m128i *)
						&dst_port[j - FWDSTEP + 1]);
					lp  = port_groupx4(&pnum[j - FWDSTEP],
						lp, dp1, dp2);

					/*
					 * dp1:
					 * <d[j], d[j+1], d[j+2], d[j+3], ... >
					 */
					dp1 = _mm_srli_si128(dp2,
						(FWDSTEP - 1) *
						sizeof(dst_port[0]));
				}

				/*
				 * dp2: <d[j-3], d[j-2], d[j-1], d[j-1], ... >
				 */
				dp2 = _mm_shufflelo_epi16(dp1, 0xf9);
				lp  = port_groupx4(&pnum[j - FWDSTEP], lp,
					dp1, dp2);

				/*
				 * remove values added by the last repeated
				 * dst port.
				 */
				lp[0]--;
				dlp = dst_port[j - 1];
			} else {
				/* set dlp and lp to the never used values. */
				dlp = BAD_PORT - 1;
				lp = pnum + MAX_PKT_BURST;
			}

			/* Process up to last 3 packets one by one. */
			switch (nb_rx % FWDSTEP) {
			case 3:
				process_packet(qconf, pkts_burst[j],
					dst_port + j, portid);
				GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
				j++;
			case 2:
				process_packet(qconf, pkts_burst[j],
					dst_port + j, portid);
				GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
				j++;
			case 1:
				process_packet(qconf, pkts_burst[j],
					dst_port + j, portid);
				GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
				j++;
			}

			/*
			 * Send packets out, through destination port.
			 * Consecuteve pacekts with the same destination port
			 * are already grouped together.
			 * If destination port for the packet equals BAD_PORT,
			 * then free the packet without sending it out.
			 */
			for (j = 0; j < nb_rx; j += k) {

				int32_t m;
				uint16_t pn;

				pn = dst_port[j];
				k = pnum[j];

				if (likely(pn != BAD_PORT)) {
					send_packetsx4(qconf, pn,
						pkts_burst + j, k);
				} else {
					for (m = j; m != j + k; m++)
						rte_pktmbuf_free(pkts_burst[m]);
				}
			}

#endif /* APP_LOOKUP_METHOD */
#else /* ENABLE_MULTI_BUFFER_OPTIMIZE == 0 */

			/* Prefetch first packets */
			for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) {
				rte_prefetch0(rte_pktmbuf_mtod(
						pkts_burst[j], void *));
			}

			/* Prefetch and forward already prefetched packets */
			for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
				rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[
						j + PREFETCH_OFFSET], void *));
				l3fwd_simple_forward(pkts_burst[j], portid,
					qconf);
			}

			/* Forward remaining prefetched packets */
			for (; j < nb_rx; j++) {
				l3fwd_simple_forward(pkts_burst[j], portid,
					qconf);
			}
#endif /* ENABLE_MULTI_BUFFER_OPTIMIZE */

		}
	}
}

static int
check_lcore_params(void)
{
	uint8_t queue, lcore;
	uint16_t i;
	int socketid;

	for (i = 0; i < nb_lcore_params; ++i) {
		queue = lcore_params[i].queue_id;
		if (queue >= MAX_RX_QUEUE_PER_PORT) {
			printf("invalid queue number: %hhu\n", queue);
			return -1;
		}
		lcore = lcore_params[i].lcore_id;
		if (!rte_lcore_is_enabled(lcore)) {
			printf("error: lcore %hhu is not enabled in lcore mask\n", lcore);
			return -1;
		}
		if ((socketid = rte_lcore_to_socket_id(lcore) != 0) &&
			(numa_on == 0)) {
			printf("warning: lcore %hhu is on socket %d with numa off \n",
				lcore, socketid);
		}
	}
	return 0;
}

static int
check_port_config(const unsigned nb_ports)
{
	unsigned portid;
	uint16_t i;

	for (i = 0; i < nb_lcore_params; ++i) {
		portid = lcore_params[i].port_id;
		if ((enabled_port_mask & (1 << portid)) == 0) {
			printf("port %u is not enabled in port mask\n", portid);
			return -1;
		}
		if (portid >= nb_ports) {
			printf("port %u is not present on the board\n", portid);
			return -1;
		}
	}
	return 0;
}

static uint8_t
get_port_n_rx_queues(const uint8_t port)
{
	int queue = -1;
	uint16_t i;

	for (i = 0; i < nb_lcore_params; ++i) {
		if (lcore_params[i].port_id == port && lcore_params[i].queue_id > queue)
			queue = lcore_params[i].queue_id;
	}
	return (uint8_t)(++queue);
}

static int
init_lcore_rx_queues(void)
{
	uint16_t i, nb_rx_queue;
	uint8_t lcore;

	for (i = 0; i < nb_lcore_params; ++i) {
		lcore = lcore_params[i].lcore_id;
		nb_rx_queue = lcore_conf[lcore].n_rx_queue;
		if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
			printf("error: too many queues (%u) for lcore: %u\n",
				(unsigned)nb_rx_queue + 1, (unsigned)lcore);
			return -1;
		} else {
			lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
				lcore_params[i].port_id;
			lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
				lcore_params[i].queue_id;
			lcore_conf[lcore].n_rx_queue++;
		}
	}
	return 0;
}

/* display usage */
static void
print_usage(const char *prgname)
{
	printf ("%s [EAL options] -- -p PORTMASK -P"
		"  [--config (port,queue,lcore)[,(port,queue,lcore]]"
		"  [--enable-jumbo [--max-pkt-len PKTLEN]]\n"
		"  -p PORTMASK: hexadecimal bitmask of ports to configure\n"
		"  -P : enable promiscuous mode\n"
		"  --config (port,queue,lcore): rx queues configuration\n"
		"  --no-numa: optional, disable numa awareness\n"
		"  --ipv6: optional, specify it if running ipv6 packets\n"
		"  --enable-jumbo: enable jumbo frame"
		" which max packet len is PKTLEN in decimal (64-9600)\n"
		"  --hash-entry-num: specify the hash entry number in hexadecimal to be setup\n",
		prgname);
}

static int parse_max_pkt_len(const char *pktlen)
{
	char *end = NULL;
	unsigned long len;

	/* parse decimal string */
	len = strtoul(pktlen, &end, 10);
	if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	if (len == 0)
		return -1;

	return len;
}

static int
parse_portmask(const char *portmask)
{
	char *end = NULL;
	unsigned long pm;

	/* parse hexadecimal string */
	pm = strtoul(portmask, &end, 16);
	if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	if (pm == 0)
		return -1;

	return pm;
}

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static int
parse_hash_entry_number(const char *hash_entry_num)
{
	char *end = NULL;
	unsigned long hash_en;
	/* parse hexadecimal string */
	hash_en = strtoul(hash_entry_num, &end, 16);
	if ((hash_entry_num[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	if (hash_en == 0)
		return -1;

	return hash_en;
}
#endif

static int
parse_config(const char *q_arg)
{
	char s[256];
	const char *p, *p0 = q_arg;
	char *end;
	enum fieldnames {
		FLD_PORT = 0,
		FLD_QUEUE,
		FLD_LCORE,
		_NUM_FLD
	};
	unsigned long int_fld[_NUM_FLD];
	char *str_fld[_NUM_FLD];
	int i;
	unsigned size;

	nb_lcore_params = 0;

	while ((p = strchr(p0,'(')) != NULL) {
		++p;
		if((p0 = strchr(p,')')) == NULL)
			return -1;

		size = p0 - p;
		if(size >= sizeof(s))
			return -1;

		snprintf(s, sizeof(s), "%.*s", size, p);
		if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _NUM_FLD)
			return -1;
		for (i = 0; i < _NUM_FLD; i++){
			errno = 0;
			int_fld[i] = strtoul(str_fld[i], &end, 0);
			if (errno != 0 || end == str_fld[i] || int_fld[i] > 255)
				return -1;
		}
		if (nb_lcore_params >= MAX_LCORE_PARAMS) {
			printf("exceeded max number of lcore params: %hu\n",
				nb_lcore_params);
			return -1;
		}
		lcore_params_array[nb_lcore_params].port_id = (uint8_t)int_fld[FLD_PORT];
		lcore_params_array[nb_lcore_params].queue_id = (uint8_t)int_fld[FLD_QUEUE];
		lcore_params_array[nb_lcore_params].lcore_id = (uint8_t)int_fld[FLD_LCORE];
		++nb_lcore_params;
	}
	lcore_params = lcore_params_array;
	return 0;
}

#define CMD_LINE_OPT_CONFIG "config"
#define CMD_LINE_OPT_NO_NUMA "no-numa"
#define CMD_LINE_OPT_IPV6 "ipv6"
#define CMD_LINE_OPT_ENABLE_JUMBO "enable-jumbo"
#define CMD_LINE_OPT_HASH_ENTRY_NUM "hash-entry-num"

/* Parse the argument given in the command line of the application */
static int
parse_args(int argc, char **argv)
{
	int opt, ret;
	char **argvopt;
	int option_index;
	char *prgname = argv[0];
	static struct option lgopts[] = {
		{CMD_LINE_OPT_CONFIG, 1, 0, 0},
		{CMD_LINE_OPT_NO_NUMA, 0, 0, 0},
		{CMD_LINE_OPT_IPV6, 0, 0, 0},
		{CMD_LINE_OPT_ENABLE_JUMBO, 0, 0, 0},
		{CMD_LINE_OPT_HASH_ENTRY_NUM, 1, 0, 0},
		{NULL, 0, 0, 0}
	};

	argvopt = argv;

	while ((opt = getopt_long(argc, argvopt, "p:P",
				lgopts, &option_index)) != EOF) {

		switch (opt) {
		/* portmask */
		case 'p':
			enabled_port_mask = parse_portmask(optarg);
			if (enabled_port_mask == 0) {
				printf("invalid portmask\n");
				print_usage(prgname);
				return -1;
			}
			break;
		case 'P':
			printf("Promiscuous mode selected\n");
			promiscuous_on = 1;
			break;

		/* long options */
		case 0:
			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_CONFIG,
				sizeof (CMD_LINE_OPT_CONFIG))) {
				ret = parse_config(optarg);
				if (ret) {
					printf("invalid config\n");
					print_usage(prgname);
					return -1;
				}
			}

			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_NO_NUMA,
				sizeof(CMD_LINE_OPT_NO_NUMA))) {
				printf("numa is disabled \n");
				numa_on = 0;
			}

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_IPV6,
				sizeof(CMD_LINE_OPT_IPV6))) {
				printf("ipv6 is specified \n");
				ipv6 = 1;
			}
#endif

			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_ENABLE_JUMBO,
				sizeof (CMD_LINE_OPT_ENABLE_JUMBO))) {
				struct option lenopts = {"max-pkt-len", required_argument, 0, 0};

				printf("jumbo frame is enabled - disabling simple TX path\n");
				port_conf.rxmode.jumbo_frame = 1;

				/* if no max-pkt-len set, use the default value ETHER_MAX_LEN */
				if (0 == getopt_long(argc, argvopt, "", &lenopts, &option_index)) {
					ret = parse_max_pkt_len(optarg);
					if ((ret < 64) || (ret > MAX_JUMBO_PKT_LEN)){
						printf("invalid packet length\n");
						print_usage(prgname);
						return -1;
					}
					port_conf.rxmode.max_rx_pkt_len = ret;
				}
				printf("set jumbo frame max packet length to %u\n",
						(unsigned int)port_conf.rxmode.max_rx_pkt_len);
			}
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_HASH_ENTRY_NUM,
				sizeof(CMD_LINE_OPT_HASH_ENTRY_NUM))) {
				ret = parse_hash_entry_number(optarg);
				if ((ret > 0) && (ret <= L3FWD_HASH_ENTRIES)) {
					hash_entry_number = ret;
				} else {
					printf("invalid hash entry number\n");
					print_usage(prgname);
					return -1;
				}
			}
#endif
			break;

		default:
			print_usage(prgname);
			return -1;
		}
	}

	if (optind >= 0)
		argv[optind-1] = prgname;

	ret = optind-1;
	optind = 0; /* reset getopt lib */
	return ret;
}

static void
print_ethaddr(const char *name, const struct ether_addr *eth_addr)
{
	char buf[ETHER_ADDR_FMT_SIZE];
	ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr);
	printf("%s%s", name, buf);
}

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)

static void convert_ipv4_5tuple(struct ipv4_5tuple* key1,
		union ipv4_5tuple_host* key2)
{
	key2->ip_dst = rte_cpu_to_be_32(key1->ip_dst);
	key2->ip_src = rte_cpu_to_be_32(key1->ip_src);
	key2->port_dst = rte_cpu_to_be_16(key1->port_dst);
	key2->port_src = rte_cpu_to_be_16(key1->port_src);
	key2->proto = key1->proto;
	key2->pad0 = 0;
	key2->pad1 = 0;
	return;
}

static void convert_ipv6_5tuple(struct ipv6_5tuple* key1,
                union ipv6_5tuple_host* key2)
{
	uint32_t i;
	for (i = 0; i < 16; i++)
	{
		key2->ip_dst[i] = key1->ip_dst[i];
		key2->ip_src[i] = key1->ip_src[i];
	}
	key2->port_dst = rte_cpu_to_be_16(key1->port_dst);
	key2->port_src = rte_cpu_to_be_16(key1->port_src);
	key2->proto = key1->proto;
	key2->pad0 = 0;
	key2->pad1 = 0;
	key2->reserve = 0;
	return;
}

#define BYTE_VALUE_MAX 256
#define ALL_32_BITS 0xffffffff
#define BIT_8_TO_15 0x0000ff00
static inline void
populate_ipv4_few_flow_into_table(const struct rte_hash* h)
{
	uint32_t i;
	int32_t ret;
	uint32_t array_len = sizeof(ipv4_l3fwd_route_array)/sizeof(ipv4_l3fwd_route_array[0]);

	mask0 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS, ALL_32_BITS, BIT_8_TO_15);
	for (i = 0; i < array_len; i++) {
		struct ipv4_l3fwd_route  entry;
		union ipv4_5tuple_host newkey;
		entry = ipv4_l3fwd_route_array[i];
		convert_ipv4_5tuple(&entry.key, &newkey);
		ret = rte_hash_add_key (h,(void *) &newkey);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %" PRIu32
				" to the l3fwd hash.\n", i);
		}
		ipv4_l3fwd_out_if[ret] = entry.if_out;
	}
	printf("Hash: Adding 0x%" PRIx32 " keys\n", array_len);
}

#define BIT_16_TO_23 0x00ff0000
static inline void
populate_ipv6_few_flow_into_table(const struct rte_hash* h)
{
	uint32_t i;
	int32_t ret;
	uint32_t array_len = sizeof(ipv6_l3fwd_route_array)/sizeof(ipv6_l3fwd_route_array[0]);

	mask1 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS, ALL_32_BITS, BIT_16_TO_23);
	mask2 = _mm_set_epi32(0, 0, ALL_32_BITS, ALL_32_BITS);
	for (i = 0; i < array_len; i++) {
		struct ipv6_l3fwd_route entry;
		union ipv6_5tuple_host newkey;
		entry = ipv6_l3fwd_route_array[i];
		convert_ipv6_5tuple(&entry.key, &newkey);
		ret = rte_hash_add_key (h, (void *) &newkey);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %" PRIu32
				" to the l3fwd hash.\n", i);
		}
		ipv6_l3fwd_out_if[ret] = entry.if_out;
	}
	printf("Hash: Adding 0x%" PRIx32 "keys\n", array_len);
}

#define NUMBER_PORT_USED 4
static inline void
populate_ipv4_many_flow_into_table(const struct rte_hash* h,
                unsigned int nr_flow)
{
	unsigned i;
	mask0 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS, ALL_32_BITS, BIT_8_TO_15);
	for (i = 0; i < nr_flow; i++) {
		struct ipv4_l3fwd_route entry;
		union ipv4_5tuple_host newkey;
		uint8_t a = (uint8_t) ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX);
		uint8_t b = (uint8_t) (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX);
		uint8_t c = (uint8_t) ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX));
		/* Create the ipv4 exact match flow */
		memset(&entry, 0, sizeof(entry));
		switch (i & (NUMBER_PORT_USED -1)) {
		case 0:
			entry = ipv4_l3fwd_route_array[0];
			entry.key.ip_dst = IPv4(101,c,b,a);
			break;
		case 1:
			entry = ipv4_l3fwd_route_array[1];
			entry.key.ip_dst = IPv4(201,c,b,a);
			break;
		case 2:
			entry = ipv4_l3fwd_route_array[2];
			entry.key.ip_dst = IPv4(111,c,b,a);
			break;
		case 3:
			entry = ipv4_l3fwd_route_array[3];
			entry.key.ip_dst = IPv4(211,c,b,a);
			break;
		};
		convert_ipv4_5tuple(&entry.key, &newkey);
		int32_t ret = rte_hash_add_key(h,(void *) &newkey);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u\n", i);
		}
		ipv4_l3fwd_out_if[ret] = (uint8_t) entry.if_out;

	}
	printf("Hash: Adding 0x%x keys\n", nr_flow);
}

static inline void
populate_ipv6_many_flow_into_table(const struct rte_hash* h,
                unsigned int nr_flow)
{
	unsigned i;
	mask1 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS, ALL_32_BITS, BIT_16_TO_23);
	mask2 = _mm_set_epi32(0, 0, ALL_32_BITS, ALL_32_BITS);
	for (i = 0; i < nr_flow; i++) {
		struct ipv6_l3fwd_route entry;
		union ipv6_5tuple_host newkey;
		uint8_t a = (uint8_t) ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX);
		uint8_t b = (uint8_t) (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX);
		uint8_t c = (uint8_t) ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX));
		/* Create the ipv6 exact match flow */
		memset(&entry, 0, sizeof(entry));
		switch (i & (NUMBER_PORT_USED - 1)) {
		case 0: entry = ipv6_l3fwd_route_array[0]; break;
		case 1: entry = ipv6_l3fwd_route_array[1]; break;
		case 2: entry = ipv6_l3fwd_route_array[2]; break;
		case 3: entry = ipv6_l3fwd_route_array[3]; break;
		};
		entry.key.ip_dst[13] = c;
		entry.key.ip_dst[14] = b;
		entry.key.ip_dst[15] = a;
		convert_ipv6_5tuple(&entry.key, &newkey);
		int32_t ret = rte_hash_add_key(h,(void *) &newkey);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u\n", i);
		}
		ipv6_l3fwd_out_if[ret] = (uint8_t) entry.if_out;

	}
	printf("Hash: Adding 0x%x keys\n", nr_flow);
}

static void
setup_hash(int socketid)
{
    struct rte_hash_parameters ipv4_l3fwd_hash_params = {
        .name = NULL,
        .entries = L3FWD_HASH_ENTRIES,
        .bucket_entries = 4,
        .key_len = sizeof(union ipv4_5tuple_host),
        .hash_func = ipv4_hash_crc,
        .hash_func_init_val = 0,
    };

    struct rte_hash_parameters ipv6_l3fwd_hash_params = {
        .name = NULL,
        .entries = L3FWD_HASH_ENTRIES,
        .bucket_entries = 4,
        .key_len = sizeof(union ipv6_5tuple_host),
        .hash_func = ipv6_hash_crc,
        .hash_func_init_val = 0,
    };

    char s[64];

	/* create ipv4 hash */
	snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid);
	ipv4_l3fwd_hash_params.name = s;
	ipv4_l3fwd_hash_params.socket_id = socketid;
	ipv4_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv4_l3fwd_hash_params);
	if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on "
				"socket %d\n", socketid);

	/* create ipv6 hash */
	snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid);
	ipv6_l3fwd_hash_params.name = s;
	ipv6_l3fwd_hash_params.socket_id = socketid;
	ipv6_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv6_l3fwd_hash_params);
	if (ipv6_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on "
				"socket %d\n", socketid);

	if (hash_entry_number != HASH_ENTRY_NUMBER_DEFAULT) {
		/* For testing hash matching with a large number of flows we
		 * generate millions of IP 5-tuples with an incremented dst
		 * address to initialize the hash table. */
		if (ipv6 == 0) {
			/* populate the ipv4 hash */
			populate_ipv4_many_flow_into_table(
				ipv4_l3fwd_lookup_struct[socketid], hash_entry_number);
		} else {
			/* populate the ipv6 hash */
			populate_ipv6_many_flow_into_table(
				ipv6_l3fwd_lookup_struct[socketid], hash_entry_number);
		}
	} else {
		/* Use data in ipv4/ipv6 l3fwd lookup table directly to initialize the hash table */
		if (ipv6 == 0) {
			/* populate the ipv4 hash */
			populate_ipv4_few_flow_into_table(ipv4_l3fwd_lookup_struct[socketid]);
		} else {
			/* populate the ipv6 hash */
			populate_ipv6_few_flow_into_table(ipv6_l3fwd_lookup_struct[socketid]);
		}
	}
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
static void
setup_lpm(int socketid)
{
	struct rte_lpm6_config config;
	unsigned i;
	int ret;
	char s[64];

	/* create the LPM table */
	snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid);
	ipv4_l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid,
				IPV4_L3FWD_LPM_MAX_RULES, 0);
	if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table"
				" on socket %d\n", socketid);

	/* populate the LPM table */
	for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {

		/* skip unused ports */
		if ((1 << ipv4_l3fwd_route_array[i].if_out &
				enabled_port_mask) == 0)
			continue;

		ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid],
			ipv4_l3fwd_route_array[i].ip,
			ipv4_l3fwd_route_array[i].depth,
			ipv4_l3fwd_route_array[i].if_out);

		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u to the "
				"l3fwd LPM table on socket %d\n",
				i, socketid);
		}

		printf("LPM: Adding route 0x%08x / %d (%d)\n",
			(unsigned)ipv4_l3fwd_route_array[i].ip,
			ipv4_l3fwd_route_array[i].depth,
			ipv4_l3fwd_route_array[i].if_out);
	}

	/* create the LPM6 table */
	snprintf(s, sizeof(s), "IPV6_L3FWD_LPM_%d", socketid);

	config.max_rules = IPV6_L3FWD_LPM_MAX_RULES;
	config.number_tbl8s = IPV6_L3FWD_LPM_NUMBER_TBL8S;
	config.flags = 0;
	ipv6_l3fwd_lookup_struct[socketid] = rte_lpm6_create(s, socketid,
				&config);
	if (ipv6_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table"
				" on socket %d\n", socketid);

	/* populate the LPM table */
	for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) {

		/* skip unused ports */
		if ((1 << ipv6_l3fwd_route_array[i].if_out &
				enabled_port_mask) == 0)
			continue;

		ret = rte_lpm6_add(ipv6_l3fwd_lookup_struct[socketid],
			ipv6_l3fwd_route_array[i].ip,
			ipv6_l3fwd_route_array[i].depth,
			ipv6_l3fwd_route_array[i].if_out);

		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u to the "
				"l3fwd LPM table on socket %d\n",
				i, socketid);
		}

		printf("LPM: Adding route %s / %d (%d)\n",
			"IPV6",
			ipv6_l3fwd_route_array[i].depth,
			ipv6_l3fwd_route_array[i].if_out);
	}
}
#endif

static int
init_mem(unsigned nb_mbuf)
{
	struct lcore_conf *qconf;
	int socketid;
	unsigned lcore_id;
	char s[64];

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		if (rte_lcore_is_enabled(lcore_id) == 0)
			continue;

		if (numa_on)
			socketid = rte_lcore_to_socket_id(lcore_id);
		else
			socketid = 0;

		if (socketid >= NB_SOCKETS) {
			rte_exit(EXIT_FAILURE, "Socket %d of lcore %u is out of range %d\n",
				socketid, lcore_id, NB_SOCKETS);
		}
		if (pktmbuf_pool[socketid] == NULL) {
			snprintf(s, sizeof(s), "mbuf_pool_%d", socketid);
			pktmbuf_pool[socketid] =
				rte_mempool_create(s, nb_mbuf, MBUF_SIZE, MEMPOOL_CACHE_SIZE,
					sizeof(struct rte_pktmbuf_pool_private),
					rte_pktmbuf_pool_init, NULL,
					rte_pktmbuf_init, NULL,
					socketid, 0);
			if (pktmbuf_pool[socketid] == NULL)
				rte_exit(EXIT_FAILURE,
						"Cannot init mbuf pool on socket %d\n", socketid);
			else
				printf("Allocated mbuf pool on socket %d\n", socketid);

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
			setup_lpm(socketid);
#else
			setup_hash(socketid);
#endif
		}
		qconf = &lcore_conf[lcore_id];
		qconf->ipv4_lookup_struct = ipv4_l3fwd_lookup_struct[socketid];
		qconf->ipv6_lookup_struct = ipv6_l3fwd_lookup_struct[socketid];
	}
	return 0;
}

/* Check the link status of all ports in up to 9s, and print them finally */
static void
check_all_ports_link_status(uint8_t port_num, uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
	uint8_t portid, count, all_ports_up, print_flag = 0;
	struct rte_eth_link link;

	printf("\nChecking link status");
	fflush(stdout);
	for (count = 0; count <= MAX_CHECK_TIME; count++) {
		all_ports_up = 1;
		for (portid = 0; portid < port_num; portid++) {
			if ((port_mask & (1 << portid)) == 0)
				continue;
			memset(&link, 0, sizeof(link));
			rte_eth_link_get_nowait(portid, &link);
			/* print link status if flag set */
			if (print_flag == 1) {
				if (link.link_status)
					printf("Port %d Link Up - speed %u "
						"Mbps - %s\n", (uint8_t)portid,
						(unsigned)link.link_speed,
				(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
					("full-duplex") : ("half-duplex\n"));
				else
					printf("Port %d Link Down\n",
						(uint8_t)portid);
				continue;
			}
			/* clear all_ports_up flag if any link down */
			if (link.link_status == 0) {
				all_ports_up = 0;
				break;
			}
		}
		/* after finally printing all link status, get out */
		if (print_flag == 1)
			break;

		if (all_ports_up == 0) {
			printf(".");
			fflush(stdout);
			rte_delay_ms(CHECK_INTERVAL);
		}

		/* set the print_flag if all ports up or timeout */
		if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) {
			print_flag = 1;
			printf("done\n");
		}
	}
}

int
main(int argc, char **argv)
{
	struct lcore_conf *qconf;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_txconf *txconf;
	int ret;
	unsigned nb_ports;
	uint16_t queueid;
	unsigned lcore_id;
	uint32_t n_tx_queue, nb_lcores;
	uint8_t portid, nb_rx_queue, queue, socketid;

	/* init EAL */
	ret = rte_eal_init(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n");
	argc -= ret;
	argv += ret;

	/* parse application arguments (after the EAL ones) */
	ret = parse_args(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n");

	if (check_lcore_params() < 0)
		rte_exit(EXIT_FAILURE, "check_lcore_params failed\n");

	ret = init_lcore_rx_queues();
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n");

	nb_ports = rte_eth_dev_count();
	if (nb_ports > RTE_MAX_ETHPORTS)
		nb_ports = RTE_MAX_ETHPORTS;

	if (check_port_config(nb_ports) < 0)
		rte_exit(EXIT_FAILURE, "check_port_config failed\n");

	nb_lcores = rte_lcore_count();

	/* initialize all ports */
	for (portid = 0; portid < nb_ports; portid++) {
		/* skip ports that are not enabled */
		if ((enabled_port_mask & (1 << portid)) == 0) {
			printf("\nSkipping disabled port %d\n", portid);
			continue;
		}

		/* init port */
		printf("Initializing port %d ... ", portid );
		fflush(stdout);

		nb_rx_queue = get_port_n_rx_queues(portid);
		n_tx_queue = nb_lcores;
		if (n_tx_queue > MAX_TX_QUEUE_PER_PORT)
			n_tx_queue = MAX_TX_QUEUE_PER_PORT;
		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
			nb_rx_queue, (unsigned)n_tx_queue );
		ret = rte_eth_dev_configure(portid, nb_rx_queue,
					(uint16_t)n_tx_queue, &port_conf);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%d\n",
				ret, portid);

		rte_eth_macaddr_get(portid, &ports_eth_addr[portid]);
		print_ethaddr(" Address:", &ports_eth_addr[portid]);
		printf(", ");

		/*
		 * prepare dst and src MACs for each port.
		 */
		*(uint64_t *)(val_eth + portid) =
			ETHER_LOCAL_ADMIN_ADDR + ((uint64_t)portid << 40);
		ether_addr_copy(&ports_eth_addr[portid],
			(struct ether_addr *)(val_eth + portid) + 1);

		/* init memory */
		ret = init_mem(NB_MBUF);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "init_mem failed\n");

		/* init one TX queue per couple (lcore,port) */
		queueid = 0;
		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
			if (rte_lcore_is_enabled(lcore_id) == 0)
				continue;

			if (numa_on)
				socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id);
			else
				socketid = 0;

			printf("txq=%u,%d,%d ", lcore_id, queueid, socketid);
			fflush(stdout);

			rte_eth_dev_info_get(portid, &dev_info);
			txconf = &dev_info.default_txconf;
			if (port_conf.rxmode.jumbo_frame)
				txconf->txq_flags = 0;
			ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
						     socketid, txconf);
			if (ret < 0)
				rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, "
					"port=%d\n", ret, portid);

			qconf = &lcore_conf[lcore_id];
			qconf->tx_queue_id[portid] = queueid;
			queueid++;
		}
		printf("\n");
	}

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		if (rte_lcore_is_enabled(lcore_id) == 0)
			continue;
		qconf = &lcore_conf[lcore_id];
		printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
		fflush(stdout);
		/* init RX queues */
		for(queue = 0; queue < qconf->n_rx_queue; ++queue) {
			portid = qconf->rx_queue_list[queue].port_id;
			queueid = qconf->rx_queue_list[queue].queue_id;

			if (numa_on)
				socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id);
			else
				socketid = 0;

			printf("rxq=%d,%d,%d ", portid, queueid, socketid);
			fflush(stdout);

			ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd,
					socketid,
					NULL,
					pktmbuf_pool[socketid]);
			if (ret < 0)
				rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d,"
						"port=%d\n", ret, portid);
		}
	}

	printf("\n");

	/* start ports */
	for (portid = 0; portid < nb_ports; portid++) {
		if ((enabled_port_mask & (1 << portid)) == 0) {
			continue;
		}
		/* Start device */
		ret = rte_eth_dev_start(portid);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, port=%d\n",
				ret, portid);

		/*
		 * If enabled, put device in promiscuous mode.
		 * This allows IO forwarding mode to forward packets
		 * to itself through 2 cross-connected  ports of the
		 * target machine.
		 */
		if (promiscuous_on)
			rte_eth_promiscuous_enable(portid);
	}

	check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);

	/* launch per-lcore init on every lcore */
	rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (rte_eal_wait_lcore(lcore_id) < 0)
			return -1;
	}

	return 0;
}