summaryrefslogtreecommitdiffstats
path: root/examples/performance-thread/l3fwd-thread/main.c
blob: 2d98473ebc1f6f0fceffc74354348460c47da936 (plain)
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
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2016 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.
 */

#define _GNU_SOURCE

#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_vect.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_memzone.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>

#include <cmdline_parse.h>
#include <cmdline_parse_etheraddr.h>

#include <lthread_api.h>

#define APP_LOOKUP_EXACT_MATCH          0
#define APP_LOOKUP_LPM                  1
#define DO_RFC_1812_CHECKS

/* Enable cpu-load stats 0-off, 1-on */
#define APP_CPU_LOAD                 1

#ifndef APP_LOOKUP_METHOD
#define APP_LOOKUP_METHOD             APP_LOOKUP_LPM
#endif

#ifndef __GLIBC__ /* sched_getcpu() is glibc specific */
#define sched_getcpu() rte_lcore_id()
#endif

static int
check_ptype(int portid)
{
	int i, ret;
	int ipv4 = 0, ipv6 = 0;

	ret = rte_eth_dev_get_supported_ptypes(portid, RTE_PTYPE_L3_MASK, NULL,
			0);
	if (ret <= 0)
		return 0;

	uint32_t ptypes[ret];

	ret = rte_eth_dev_get_supported_ptypes(portid, RTE_PTYPE_L3_MASK,
			ptypes, ret);
	for (i = 0; i < ret; ++i) {
		if (ptypes[i] & RTE_PTYPE_L3_IPV4)
			ipv4 = 1;
		if (ptypes[i] & RTE_PTYPE_L3_IPV6)
			ipv6 = 1;
	}

	if (ipv4 && ipv6)
		return 1;

	return 0;
}

static inline void
parse_ptype(struct rte_mbuf *m)
{
	struct ether_hdr *eth_hdr;
	uint32_t packet_type = RTE_PTYPE_UNKNOWN;
	uint16_t ether_type;

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
	ether_type = eth_hdr->ether_type;
	if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4))
		packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
	else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6))
		packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;

	m->packet_type = packet_type;
}

static uint16_t
cb_parse_ptype(__rte_unused uint8_t port, __rte_unused uint16_t queue,
		struct rte_mbuf *pkts[], uint16_t nb_pkts,
		__rte_unused uint16_t max_pkts, __rte_unused void *user_param)
{
	unsigned int i;

	for (i = 0; i < nb_pkts; i++)
		parse_ptype(pkts[i]);

	return nb_pkts;
}

/*
 *  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

#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1

#define MAX_JUMBO_PKT_LEN  9600

#define IPV6_ADDR_LEN 16

#define MEMPOOL_CACHE_SIZE 256

/*
 * 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 BURST_SIZE    MAX_TX_BURST

#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 128
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 uint64_t dest_eth_addr[RTE_MAX_ETHPORTS];
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;
static int promiscuous_on; /**< Set in promiscuous mode off by default. */
static int numa_on = 1;    /**< NUMA is enabled by default. */
static int parse_ptype_on;

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

#if (APP_CPU_LOAD == 1)

#define MAX_CPU RTE_MAX_LCORE
#define CPU_LOAD_TIMEOUT_US (5 * 1000 * 1000)  /**< Timeout for collecting 5s */

#define CPU_PROCESS     0
#define CPU_POLL        1
#define MAX_CPU_COUNTER 2

struct cpu_load {
	uint16_t       n_cpu;
	uint64_t       counter;
	uint64_t       hits[MAX_CPU_COUNTER][MAX_CPU];
} __rte_cache_aligned;

static struct cpu_load cpu_load;
static int cpu_load_lcore_id = -1;

#define SET_CPU_BUSY(thread, counter) \
		thread->conf.busy[counter] = 1

#define SET_CPU_IDLE(thread, counter) \
		thread->conf.busy[counter] = 0

#define IS_CPU_BUSY(thread, counter) \
		(thread->conf.busy[counter] > 0)

#else

#define SET_CPU_BUSY(thread, counter)
#define SET_CPU_IDLE(thread, counter)
#define IS_CPU_BUSY(thread, counter) 0

#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 rx_thread_params {
	uint8_t port_id;
	uint8_t queue_id;
	uint8_t lcore_id;
	uint8_t thread_id;
} __rte_cache_aligned;

static struct rx_thread_params rx_thread_params_array[MAX_LCORE_PARAMS];
static struct rx_thread_params rx_thread_params_array_default[] = {
	{0, 0, 2, 0},
	{0, 1, 2, 1},
	{0, 2, 2, 2},
	{1, 0, 2, 3},
	{1, 1, 2, 4},
	{1, 2, 2, 5},
	{2, 0, 2, 6},
	{3, 0, 3, 7},
	{3, 1, 3, 8},
};

static struct rx_thread_params *rx_thread_params =
		rx_thread_params_array_default;
static uint16_t nb_rx_thread_params = RTE_DIM(rx_thread_params_array_default);

struct tx_thread_params {
	uint8_t lcore_id;
	uint8_t thread_id;
} __rte_cache_aligned;

static struct tx_thread_params tx_thread_params_array[MAX_LCORE_PARAMS];
static struct tx_thread_params tx_thread_params_array_default[] = {
	{4, 0},
	{5, 1},
	{6, 2},
	{7, 3},
	{8, 4},
	{9, 5},
	{10, 6},
	{11, 7},
	{12, 8},
};

static struct tx_thread_params *tx_thread_params =
		tx_thread_params_array_default;
static uint16_t nb_tx_thread_params = RTE_DIM(tx_thread_params_array_default);

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   = 1, /**< CRC stripped by hardware */
	},
	.rx_adv_conf = {
		.rss_conf = {
			.rss_key = NULL,
			.rss_hf = ETH_RSS_TCP,
		},
	},
	.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 RTE_DIM(ipv4_l3fwd_route_array)
#define IPV6_L3FWD_NUM_ROUTES RTE_DIM(ipv6_l3fwd_route_array)

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 RTE_DIM(ipv4_l3fwd_route_array)
#define IPV6_L3FWD_NUM_ROUTES RTE_DIM(ipv6_l3fwd_route_array)

#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 {
	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
	void *data;
} __rte_cache_aligned;

static struct lcore_conf lcore_conf[RTE_MAX_LCORE];
RTE_DEFINE_PER_LCORE(struct lcore_conf *, lcore_conf);

#define MAX_RX_QUEUE_PER_THREAD 16
#define MAX_TX_PORT_PER_THREAD  RTE_MAX_ETHPORTS
#define MAX_TX_QUEUE_PER_PORT   RTE_MAX_ETHPORTS
#define MAX_RX_QUEUE_PER_PORT   128

#define MAX_RX_THREAD 1024
#define MAX_TX_THREAD 1024
#define MAX_THREAD    (MAX_RX_THREAD + MAX_TX_THREAD)

/**
 * Producers and consumers threads configuration
 */
static int lthreads_on = 1; /**< Use lthreads for processing*/

rte_atomic16_t rx_counter;  /**< Number of spawned rx threads */
rte_atomic16_t tx_counter;  /**< Number of spawned tx threads */

struct thread_conf {
	uint16_t lcore_id;      /**< Initial lcore for rx thread */
	uint16_t cpu_id;        /**< Cpu id for cpu load stats counter */
	uint16_t thread_id;     /**< Thread ID */

#if (APP_CPU_LOAD > 0)
	int busy[MAX_CPU_COUNTER];
#endif
};

struct thread_rx_conf {
	struct thread_conf conf;

	uint16_t n_rx_queue;
	struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];

	uint16_t n_ring;        /**< Number of output rings */
	struct rte_ring *ring[RTE_MAX_LCORE];
	struct lthread_cond *ready[RTE_MAX_LCORE];

#if (APP_CPU_LOAD > 0)
	int busy[MAX_CPU_COUNTER];
#endif
} __rte_cache_aligned;

uint16_t n_rx_thread;
struct thread_rx_conf rx_thread[MAX_RX_THREAD];

struct thread_tx_conf {
	struct thread_conf conf;

	uint16_t tx_queue_id[RTE_MAX_LCORE];
	struct mbuf_table tx_mbufs[RTE_MAX_LCORE];

	struct rte_ring *ring;
	struct lthread_cond **ready;

} __rte_cache_aligned;

uint16_t n_tx_thread;
struct thread_tx_conf tx_thread[MAX_TX_THREAD];

/* Send burst of packets on an output interface */
static inline int
send_burst(struct thread_tx_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)
{
	uint16_t len;
	struct thread_tx_conf *qconf;

	if (lthreads_on)
		qconf = (struct thread_tx_conf *)lthread_get_data();
	else
		qconf = (struct thread_tx_conf *)RTE_PER_LCORE(lcore_conf)->data;

	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;
}

#if ((APP_LOOKUP_METHOD == APP_LOOKUP_LPM) && \
	(ENABLE_MULTI_BUFFER_OPTIMIZE == 1))
static inline __attribute__((always_inline)) void
send_packetsx4(uint8_t port,
	struct rte_mbuf *m[], uint32_t num)
{
	uint32_t len, j, n;
	struct thread_tx_conf *qconf;

	if (lthreads_on)
		qconf = (struct thread_tx_conf *)lthread_get_data();
	else
		qconf = (struct thread_tx_conf *)RTE_PER_LCORE(lcore_conf)->data;

	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;
}
#endif /* APP_LOOKUP_LPM */

#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)
{
	uint32_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)
{
	uint32_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)
		__attribute__((unused));

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

#define MASK_ALL_PKTS   0xff
#define EXCLUDE_1ST_PKT 0xfe
#define EXCLUDE_2ND_PKT 0xfd
#define EXCLUDE_3RD_PKT 0xfb
#define EXCLUDE_4TH_PKT 0xf7
#define EXCLUDE_5TH_PKT 0xef
#define EXCLUDE_6TH_PKT 0xdf
#define EXCLUDE_7TH_PKT 0xbf
#define EXCLUDE_8TH_PKT 0x7f

static inline void
simple_ipv4_fwd_8pkts(struct rte_mbuf *m[8], uint8_t portid)
{
	struct ether_hdr *eth_hdr[8];
	struct ipv4_hdr *ipv4_hdr[8];
	uint8_t dst_port[8];
	int32_t ret[8];
	union ipv4_5tuple_host key[8];
	__m128i data[8];

	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 *);
	eth_hdr[4] = rte_pktmbuf_mtod(m[4], struct ether_hdr *);
	eth_hdr[5] = rte_pktmbuf_mtod(m[5], struct ether_hdr *);
	eth_hdr[6] = rte_pktmbuf_mtod(m[6], struct ether_hdr *);
	eth_hdr[7] = rte_pktmbuf_mtod(m[7], struct ether_hdr *);

	/* Handle IPv4 headers.*/
	ipv4_hdr[0] = rte_pktmbuf_mtod_offset(m[0], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[1] = rte_pktmbuf_mtod_offset(m[1], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[2] = rte_pktmbuf_mtod_offset(m[2], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[3] = rte_pktmbuf_mtod_offset(m[3], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[4] = rte_pktmbuf_mtod_offset(m[4], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[5] = rte_pktmbuf_mtod_offset(m[5], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[6] = rte_pktmbuf_mtod_offset(m[6], struct ipv4_hdr *,
			sizeof(struct ether_hdr));
	ipv4_hdr[7] = rte_pktmbuf_mtod_offset(m[7], struct ipv4_hdr *,
			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 &= EXCLUDE_1ST_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[1], m[1]->pkt_len) < 0) {
		rte_pktmbuf_free(m[1]);
		valid_mask &= EXCLUDE_2ND_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[2], m[2]->pkt_len) < 0) {
		rte_pktmbuf_free(m[2]);
		valid_mask &= EXCLUDE_3RD_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[3], m[3]->pkt_len) < 0) {
		rte_pktmbuf_free(m[3]);
		valid_mask &= EXCLUDE_4TH_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[4], m[4]->pkt_len) < 0) {
		rte_pktmbuf_free(m[4]);
		valid_mask &= EXCLUDE_5TH_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[5], m[5]->pkt_len) < 0) {
		rte_pktmbuf_free(m[5]);
		valid_mask &= EXCLUDE_6TH_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[6], m[6]->pkt_len) < 0) {
		rte_pktmbuf_free(m[6]);
		valid_mask &= EXCLUDE_7TH_PKT;
	}
	if (is_valid_ipv4_pkt(ipv4_hdr[7], m[7]->pkt_len) < 0) {
		rte_pktmbuf_free(m[7]);
		valid_mask &= EXCLUDE_8TH_PKT;
	}
	if (unlikely(valid_mask != MASK_ALL_PKTS)) {
		if (valid_mask == 0)
			return;

		uint8_t i = 0;

		for (i = 0; i < 8; i++)
			if ((0x1 << i) & valid_mask)
				l3fwd_simple_forward(m[i], portid);
	}
#endif /* End of #ifdef DO_RFC_1812_CHECKS */

	data[0] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[0], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[1] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[1], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[2] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[2], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[3] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[3], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[4] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[4], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[5] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[5], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[6] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[6], __m128i *,
			sizeof(struct ether_hdr) +
			offsetof(struct ipv4_hdr, time_to_live)));
	data[7] = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m[7], __m128i *,
			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);
	key[4].xmm = _mm_and_si128(data[4], mask0);
	key[5].xmm = _mm_and_si128(data[5], mask0);
	key[6].xmm = _mm_and_si128(data[6], mask0);
	key[7].xmm = _mm_and_si128(data[7], mask0);

	const void *key_array[8] = {&key[0], &key[1], &key[2], &key[3],
			&key[4], &key[5], &key[6], &key[7]};

	rte_hash_lookup_bulk(RTE_PER_LCORE(lcore_conf)->ipv4_lookup_struct,
			&key_array[0], 8, 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]]);
	dst_port[4] = (uint8_t) ((ret[4] < 0) ? portid : ipv4_l3fwd_out_if[ret[4]]);
	dst_port[5] = (uint8_t) ((ret[5] < 0) ? portid : ipv4_l3fwd_out_if[ret[5]]);
	dst_port[6] = (uint8_t) ((ret[6] < 0) ? portid : ipv4_l3fwd_out_if[ret[6]]);
	dst_port[7] = (uint8_t) ((ret[7] < 0) ? portid : ipv4_l3fwd_out_if[ret[7]]);

	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;
	if (dst_port[4] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[4]) == 0)
		dst_port[4] = portid;
	if (dst_port[5] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[5]) == 0)
		dst_port[5] = portid;
	if (dst_port[6] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[6]) == 0)
		dst_port[6] = portid;
	if (dst_port[7] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[7]) == 0)
		dst_port[7] = portid;

#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);
	--(ipv4_hdr[4]->time_to_live);
	--(ipv4_hdr[5]->time_to_live);
	--(ipv4_hdr[6]->time_to_live);
	--(ipv4_hdr[7]->time_to_live);
	++(ipv4_hdr[4]->hdr_checksum);
	++(ipv4_hdr[5]->hdr_checksum);
	++(ipv4_hdr[6]->hdr_checksum);
	++(ipv4_hdr[7]->hdr_checksum);
#endif

	/* dst addr */
	*(uint64_t *)&eth_hdr[0]->d_addr = dest_eth_addr[dst_port[0]];
	*(uint64_t *)&eth_hdr[1]->d_addr = dest_eth_addr[dst_port[1]];
	*(uint64_t *)&eth_hdr[2]->d_addr = dest_eth_addr[dst_port[2]];
	*(uint64_t *)&eth_hdr[3]->d_addr = dest_eth_addr[dst_port[3]];
	*(uint64_t *)&eth_hdr[4]->d_addr = dest_eth_addr[dst_port[4]];
	*(uint64_t *)&eth_hdr[5]->d_addr = dest_eth_addr[dst_port[5]];
	*(uint64_t *)&eth_hdr[6]->d_addr = dest_eth_addr[dst_port[6]];
	*(uint64_t *)&eth_hdr[7]->d_addr = dest_eth_addr[dst_port[7]];

	/* 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);
	ether_addr_copy(&ports_eth_addr[dst_port[4]], &eth_hdr[4]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[5]], &eth_hdr[5]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[6]], &eth_hdr[6]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[7]], &eth_hdr[7]->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]);
	send_single_packet(m[4], (uint8_t)dst_port[4]);
	send_single_packet(m[5], (uint8_t)dst_port[5]);
	send_single_packet(m[6], (uint8_t)dst_port[6]);
	send_single_packet(m[7], (uint8_t)dst_port[7]);

}

static inline void get_ipv6_5tuple(struct rte_mbuf *m0, __m128i mask0,
		__m128i mask1, union ipv6_5tuple_host *key)
{
	__m128i tmpdata0 = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m0,
			__m128i *, sizeof(struct ether_hdr) +
			offsetof(struct ipv6_hdr, payload_len)));
	__m128i tmpdata1 = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m0,
			__m128i *, sizeof(struct ether_hdr) +
			offsetof(struct ipv6_hdr, payload_len) + sizeof(__m128i)));
	__m128i tmpdata2 = _mm_loadu_si128(rte_pktmbuf_mtod_offset(m0,
			__m128i *, 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);
}

static inline void
simple_ipv6_fwd_8pkts(struct rte_mbuf *m[8], uint8_t portid)
{
	int32_t ret[8];
	uint8_t dst_port[8];
	struct ether_hdr *eth_hdr[8];
	union ipv6_5tuple_host key[8];

	__attribute__((unused)) struct ipv6_hdr *ipv6_hdr[8];

	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 *);
	eth_hdr[4] = rte_pktmbuf_mtod(m[4], struct ether_hdr *);
	eth_hdr[5] = rte_pktmbuf_mtod(m[5], struct ether_hdr *);
	eth_hdr[6] = rte_pktmbuf_mtod(m[6], struct ether_hdr *);
	eth_hdr[7] = rte_pktmbuf_mtod(m[7], struct ether_hdr *);

	/* Handle IPv6 headers.*/
	ipv6_hdr[0] = rte_pktmbuf_mtod_offset(m[0], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[1] = rte_pktmbuf_mtod_offset(m[1], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[2] = rte_pktmbuf_mtod_offset(m[2], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[3] = rte_pktmbuf_mtod_offset(m[3], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[4] = rte_pktmbuf_mtod_offset(m[4], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[5] = rte_pktmbuf_mtod_offset(m[5], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[6] = rte_pktmbuf_mtod_offset(m[6], struct ipv6_hdr *,
			sizeof(struct ether_hdr));
	ipv6_hdr[7] = rte_pktmbuf_mtod_offset(m[7], struct ipv6_hdr *,
			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]);
	get_ipv6_5tuple(m[4], mask1, mask2, &key[4]);
	get_ipv6_5tuple(m[5], mask1, mask2, &key[5]);
	get_ipv6_5tuple(m[6], mask1, mask2, &key[6]);
	get_ipv6_5tuple(m[7], mask1, mask2, &key[7]);

	const void *key_array[8] = {&key[0], &key[1], &key[2], &key[3],
			&key[4], &key[5], &key[6], &key[7]};

	rte_hash_lookup_bulk(RTE_PER_LCORE(lcore_conf)->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]]);
	dst_port[4] = (uint8_t) ((ret[4] < 0) ? portid : ipv6_l3fwd_out_if[ret[4]]);
	dst_port[5] = (uint8_t) ((ret[5] < 0) ? portid : ipv6_l3fwd_out_if[ret[5]]);
	dst_port[6] = (uint8_t) ((ret[6] < 0) ? portid : ipv6_l3fwd_out_if[ret[6]]);
	dst_port[7] = (uint8_t) ((ret[7] < 0) ? portid : ipv6_l3fwd_out_if[ret[7]]);

	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;
	if (dst_port[4] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[4]) == 0)
		dst_port[4] = portid;
	if (dst_port[5] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[5]) == 0)
		dst_port[5] = portid;
	if (dst_port[6] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[6]) == 0)
		dst_port[6] = portid;
	if (dst_port[7] >= RTE_MAX_ETHPORTS ||
			(enabled_port_mask & 1 << dst_port[7]) == 0)
		dst_port[7] = portid;

	/* dst addr */
	*(uint64_t *)&eth_hdr[0]->d_addr = dest_eth_addr[dst_port[0]];
	*(uint64_t *)&eth_hdr[1]->d_addr = dest_eth_addr[dst_port[1]];
	*(uint64_t *)&eth_hdr[2]->d_addr = dest_eth_addr[dst_port[2]];
	*(uint64_t *)&eth_hdr[3]->d_addr = dest_eth_addr[dst_port[3]];
	*(uint64_t *)&eth_hdr[4]->d_addr = dest_eth_addr[dst_port[4]];
	*(uint64_t *)&eth_hdr[5]->d_addr = dest_eth_addr[dst_port[5]];
	*(uint64_t *)&eth_hdr[6]->d_addr = dest_eth_addr[dst_port[6]];
	*(uint64_t *)&eth_hdr[7]->d_addr = dest_eth_addr[dst_port[7]];

	/* 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);
	ether_addr_copy(&ports_eth_addr[dst_port[4]], &eth_hdr[4]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[5]], &eth_hdr[5]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[6]], &eth_hdr[6]->s_addr);
	ether_addr_copy(&ports_eth_addr[dst_port[7]], &eth_hdr[7]->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]);
	send_single_packet(m[4], (uint8_t)dst_port[4]);
	send_single_packet(m[5], (uint8_t)dst_port[5]);
	send_single_packet(m[6], (uint8_t)dst_port[6]);
	send_single_packet(m[7], (uint8_t)dst_port[7]);

}
#endif /* APP_LOOKUP_METHOD */

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

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);

	if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) {
		/* Handle IPv4 headers.*/
		ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *,
				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,
			RTE_PER_LCORE(lcore_conf)->ipv4_lookup_struct);
		if (dst_port >= RTE_MAX_ETHPORTS ||
				(enabled_port_mask & 1 << dst_port) == 0)
			dst_port = portid;

#ifdef DO_RFC_1812_CHECKS
		/* Update time to live and header checksum */
		--(ipv4_hdr->time_to_live);
		++(ipv4_hdr->hdr_checksum);
#endif
		/* dst addr */
		*(uint64_t *)&eth_hdr->d_addr = dest_eth_addr[dst_port];

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

		send_single_packet(m, dst_port);
	} else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) {
		/* Handle IPv6 headers.*/
		struct ipv6_hdr *ipv6_hdr;

		ipv6_hdr = rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *,
				sizeof(struct ether_hdr));

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

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

		/* dst addr */
		*(uint64_t *)&eth_hdr->d_addr = dest_eth_addr[dst_port];

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

		send_single_packet(m, dst_port);
	} else
		/* Free the mbuf that contains non-IPV4/IPV6 packet */
		rte_pktmbuf_free(m);
}

#if ((APP_LOOKUP_METHOD == APP_LOOKUP_LPM) && \
	(ENABLE_MULTI_BUFFER_OPTIMIZE == 1))
#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 ptype)
{
	uint8_t ihl;

	if (RTE_ETH_IS_IPV4_HDR(ptype)) {
		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, ptype)	do { } while (0)
#endif /* DO_RFC_1812_CHECKS */
#endif /* APP_LOOKUP_LPM && ENABLE_MULTI_BUFFER_OPTIMIZE */


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

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

	if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) {
		return (uint16_t) ((rte_lpm_lookup(
				RTE_PER_LCORE(lcore_conf)->ipv4_lookup_struct, dst_ipv4,
				&next_hop) == 0) ? next_hop : portid);

	} else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) {

		eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
		ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1);

		return (uint16_t) ((rte_lpm6_lookup(
				RTE_PER_LCORE(lcore_conf)->ipv6_lookup_struct,
				ipv6_hdr->dst_addr, &next_hop) == 0) ?
				next_hop : portid);

	}

	return portid;
}

static inline void
process_packet(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(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->packet_type);

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

/*
 * Read packet_type and destination IPV4 addresses from 4 mbufs.
 */
static inline void
processx4_step1(struct rte_mbuf *pkt[FWDSTEP],
		__m128i *dip,
		uint32_t *ipv4_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;
	ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4;

	eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x1 = ipv4_hdr->dst_addr;
	ipv4_flag[0] &= pkt[1]->packet_type;

	eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x2 = ipv4_hdr->dst_addr;
	ipv4_flag[0] &= pkt[2]->packet_type;

	eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *);
	ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
	x3 = ipv4_hdr->dst_addr;
	ipv4_flag[0] &= pkt[3]->packet_type;

	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(__m128i dip,
		uint32_t ipv4_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(ipv4_flag)) {
		rte_lpm_lookupx4(RTE_PER_LCORE(lcore_conf)->ipv4_lookup_struct, dip,
				dst.u32, portid);

		/* get rid of unused upper 16 bit for each dport. */
		dst.x = _mm_packs_epi32(dst.x, dst.x);
		*(uint64_t *)dprt = dst.u64[0];
	} else {
		dst.x = dip;
		dprt[0] = get_dst_port(pkt[0], dst.u32[0], portid);
		dprt[1] = get_dst_port(pkt[1], dst.u32[1], portid);
		dprt[2] = get_dst_port(pkt[2], dst.u32[2], portid);
		dprt[3] = get_dst_port(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]->packet_type);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1),
			&dst_port[1], pkt[1]->packet_type);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1),
			&dst_port[2], pkt[2]->packet_type);
	rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1),
			&dst_port[3], pkt[3]->packet_type);
}

/*
 * 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) {
		pnum->u64 = gptbl[v].pnum;
		pnum->u16[FWDSTEP] = 1;
		lp = pnum->u16 + gptbl[v].idx;
	}

	return lp;
}

#endif /* APP_LOOKUP_METHOD */

static void
process_burst(struct rte_mbuf *pkts_burst[MAX_PKT_BURST], int nb_rx,
		uint8_t portid) {

	int j;

#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 ipv4_flag[MAX_PKT_BURST / FWDSTEP];
	uint16_t pnum[MAX_PKT_BURST + 1];
#endif


#if (ENABLE_MULTI_BUFFER_OPTIMIZE == 1)
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
	{
		/*
		 * Send nb_rx - nb_rx%8 packets
		 * in groups of 8.
		 */
		int32_t n = RTE_ALIGN_FLOOR(nb_rx, 8);

		for (j = 0; j < n; j += 8) {
			uint32_t pkt_type =
				pkts_burst[j]->packet_type &
				pkts_burst[j+1]->packet_type &
				pkts_burst[j+2]->packet_type &
				pkts_burst[j+3]->packet_type &
				pkts_burst[j+4]->packet_type &
				pkts_burst[j+5]->packet_type &
				pkts_burst[j+6]->packet_type &
				pkts_burst[j+7]->packet_type;
			if (pkt_type & RTE_PTYPE_L3_IPV4) {
				simple_ipv4_fwd_8pkts(&pkts_burst[j], portid);
			} else if (pkt_type &
				RTE_PTYPE_L3_IPV6) {
				simple_ipv6_fwd_8pkts(&pkts_burst[j], portid);
			} else {
				l3fwd_simple_forward(pkts_burst[j], portid);
				l3fwd_simple_forward(pkts_burst[j+1], portid);
				l3fwd_simple_forward(pkts_burst[j+2], portid);
				l3fwd_simple_forward(pkts_burst[j+3], portid);
				l3fwd_simple_forward(pkts_burst[j+4], portid);
				l3fwd_simple_forward(pkts_burst[j+5], portid);
				l3fwd_simple_forward(pkts_burst[j+6], portid);
				l3fwd_simple_forward(pkts_burst[j+7], portid);
			}
		}
		for (; j < nb_rx ; j++)
			l3fwd_simple_forward(pkts_burst[j], portid);
	}
#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],
				&ipv4_flag[j / FWDSTEP]);

	k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
	for (j = 0; j != k; j += FWDSTEP)
		processx4_step2(dip[j / FWDSTEP], ipv4_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(pkts_burst[j], dst_port + j, portid);
		GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
		j++;
	case 2:
		process_packet(pkts_burst[j], dst_port + j, portid);
		GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
		j++;
	case 1:
		process_packet(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(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);
	}

	/* Forward remaining prefetched packets */
	for (; j < nb_rx; j++)
		l3fwd_simple_forward(pkts_burst[j], portid);

#endif /* ENABLE_MULTI_BUFFER_OPTIMIZE */

}

#if (APP_CPU_LOAD > 0)

/*
 * CPU-load stats collector
 */
static int
cpu_load_collector(__rte_unused void *arg) {
	unsigned i, j, k;
	uint64_t hits;
	uint64_t prev_tsc, diff_tsc, cur_tsc;
	uint64_t total[MAX_CPU] = { 0 };
	unsigned min_cpu = MAX_CPU;
	unsigned max_cpu = 0;
	unsigned cpu_id;
	int busy_total = 0;
	int busy_flag = 0;

	unsigned int n_thread_per_cpu[MAX_CPU] = { 0 };
	struct thread_conf *thread_per_cpu[MAX_CPU][MAX_THREAD];

	struct thread_conf *thread_conf;

	const uint64_t interval_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
		US_PER_S * CPU_LOAD_TIMEOUT_US;

	prev_tsc = 0;
	/*
	 * Wait for all threads
	 */

	printf("Waiting for %d rx threads and %d tx threads\n", n_rx_thread,
			n_tx_thread);

	while (rte_atomic16_read(&rx_counter) < n_rx_thread)
		rte_pause();

	while (rte_atomic16_read(&tx_counter) < n_tx_thread)
		rte_pause();

	for (i = 0; i < n_rx_thread; i++) {

		thread_conf = &rx_thread[i].conf;
		cpu_id = thread_conf->cpu_id;
		thread_per_cpu[cpu_id][n_thread_per_cpu[cpu_id]++] = thread_conf;

		if (cpu_id > max_cpu)
			max_cpu = cpu_id;
		if (cpu_id < min_cpu)
			min_cpu = cpu_id;
	}
	for (i = 0; i < n_tx_thread; i++) {

		thread_conf = &tx_thread[i].conf;
		cpu_id = thread_conf->cpu_id;
		thread_per_cpu[cpu_id][n_thread_per_cpu[cpu_id]++] = thread_conf;

		if (thread_conf->cpu_id > max_cpu)
			max_cpu = thread_conf->cpu_id;
		if (thread_conf->cpu_id < min_cpu)
			min_cpu = thread_conf->cpu_id;
	}

	while (1) {

		cpu_load.counter++;
		for (i = min_cpu; i <= max_cpu; i++) {
			for (j = 0; j < MAX_CPU_COUNTER; j++) {
				for (k = 0; k < n_thread_per_cpu[i]; k++)
					if (thread_per_cpu[i][k]->busy[j]) {
						busy_flag = 1;
						break;
					}
				if (busy_flag) {
					cpu_load.hits[j][i]++;
					busy_total = 1;
					busy_flag = 0;
				}
			}

			if (busy_total) {
				total[i]++;
				busy_total = 0;
			}
		}

		cur_tsc = rte_rdtsc();

		diff_tsc = cur_tsc - prev_tsc;
		if (unlikely(diff_tsc > interval_tsc)) {

			printf("\033c");

			printf("Cpu usage for %d rx threads and %d tx threads:\n\n",
					n_rx_thread, n_tx_thread);

			printf("cpu#     proc%%  poll%%  overhead%%\n\n");

			for (i = min_cpu; i <= max_cpu; i++) {
				hits = 0;
				printf("CPU %d:", i);
				for (j = 0; j < MAX_CPU_COUNTER; j++) {
					printf("%7" PRIu64 "",
							cpu_load.hits[j][i] * 100 / cpu_load.counter);
					hits += cpu_load.hits[j][i];
					cpu_load.hits[j][i] = 0;
				}
				printf("%7" PRIu64 "\n",
						100 - total[i] * 100 / cpu_load.counter);
				total[i] = 0;
			}
			cpu_load.counter = 0;

			prev_tsc = cur_tsc;
		}

	}
}
#endif /* APP_CPU_LOAD */

/*
 * Null processing lthread loop
 *
 * This loop is used to start empty scheduler on lcore.
 */
static void
lthread_null(__rte_unused void *args)
{
	int lcore_id = rte_lcore_id();

	RTE_LOG(INFO, L3FWD, "Starting scheduler on lcore %d.\n", lcore_id);
	lthread_exit(NULL);
}

/* main processing loop */
static void
lthread_tx_per_ring(void *dummy)
{
	int nb_rx;
	uint8_t portid;
	struct rte_ring *ring;
	struct thread_tx_conf *tx_conf;
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	struct lthread_cond *ready;

	tx_conf = (struct thread_tx_conf *)dummy;
	ring = tx_conf->ring;
	ready = *tx_conf->ready;

	lthread_set_data((void *)tx_conf);

	/*
	 * Move this lthread to lcore
	 */
	lthread_set_affinity(tx_conf->conf.lcore_id);

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

	nb_rx = 0;
	rte_atomic16_inc(&tx_counter);
	while (1) {

		/*
		 * Read packet from ring
		 */
		SET_CPU_BUSY(tx_conf, CPU_POLL);
		nb_rx = rte_ring_sc_dequeue_burst(ring, (void **)pkts_burst,
				MAX_PKT_BURST, NULL);
		SET_CPU_IDLE(tx_conf, CPU_POLL);

		if (nb_rx > 0) {
			SET_CPU_BUSY(tx_conf, CPU_PROCESS);
			portid = pkts_burst[0]->port;
			process_burst(pkts_burst, nb_rx, portid);
			SET_CPU_IDLE(tx_conf, CPU_PROCESS);
			lthread_yield();
		} else
			lthread_cond_wait(ready, 0);

	}
}

/*
 * Main tx-lthreads spawner lthread.
 *
 * This lthread is used to spawn one new lthread per ring from producers.
 *
 */
static void
lthread_tx(void *args)
{
	struct lthread *lt;

	unsigned lcore_id;
	uint8_t portid;
	struct thread_tx_conf *tx_conf;

	tx_conf = (struct thread_tx_conf *)args;
	lthread_set_data((void *)tx_conf);

	/*
	 * Move this lthread to the selected lcore
	 */
	lthread_set_affinity(tx_conf->conf.lcore_id);

	/*
	 * Spawn tx readers (one per input ring)
	 */
	lthread_create(&lt, tx_conf->conf.lcore_id, lthread_tx_per_ring,
			(void *)tx_conf);

	lcore_id = rte_lcore_id();

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

	tx_conf->conf.cpu_id = sched_getcpu();
	while (1) {

		lthread_sleep(BURST_TX_DRAIN_US * 1000);

		/*
		 * TX burst queue drain
		 */
		for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
			if (tx_conf->tx_mbufs[portid].len == 0)
				continue;
			SET_CPU_BUSY(tx_conf, CPU_PROCESS);
			send_burst(tx_conf, tx_conf->tx_mbufs[portid].len, portid);
			SET_CPU_IDLE(tx_conf, CPU_PROCESS);
			tx_conf->tx_mbufs[portid].len = 0;
		}

	}
}

static void
lthread_rx(void *dummy)
{
	int ret;
	uint16_t nb_rx;
	int i;
	uint8_t portid, queueid;
	int worker_id;
	int len[RTE_MAX_LCORE] = { 0 };
	int old_len, new_len;
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	struct thread_rx_conf *rx_conf;

	rx_conf = (struct thread_rx_conf *)dummy;
	lthread_set_data((void *)rx_conf);

	/*
	 * Move this lthread to lcore
	 */
	lthread_set_affinity(rx_conf->conf.lcore_id);

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

	RTE_LOG(INFO, L3FWD, "Entering main Rx loop on lcore %u\n", rte_lcore_id());

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

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

	/*
	 * Init all condition variables (one per rx thread)
	 */
	for (i = 0; i < rx_conf->n_rx_queue; i++)
		lthread_cond_init(NULL, &rx_conf->ready[i], NULL);

	worker_id = 0;

	rx_conf->conf.cpu_id = sched_getcpu();
	rte_atomic16_inc(&rx_counter);
	while (1) {

		/*
		 * Read packet from RX queues
		 */
		for (i = 0; i < rx_conf->n_rx_queue; ++i) {
			portid = rx_conf->rx_queue_list[i].port_id;
			queueid = rx_conf->rx_queue_list[i].queue_id;

			SET_CPU_BUSY(rx_conf, CPU_POLL);
			nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
				MAX_PKT_BURST);
			SET_CPU_IDLE(rx_conf, CPU_POLL);

			if (nb_rx != 0) {
				worker_id = (worker_id + 1) % rx_conf->n_ring;
				old_len = len[worker_id];

				SET_CPU_BUSY(rx_conf, CPU_PROCESS);
				ret = rte_ring_sp_enqueue_burst(
						rx_conf->ring[worker_id],
						(void **) pkts_burst,
						nb_rx, NULL);

				new_len = old_len + ret;

				if (new_len >= BURST_SIZE) {
					lthread_cond_signal(rx_conf->ready[worker_id]);
					new_len = 0;
				}

				len[worker_id] = new_len;

				if (unlikely(ret < nb_rx)) {
					uint32_t k;

					for (k = ret; k < nb_rx; k++) {
						struct rte_mbuf *m = pkts_burst[k];

						rte_pktmbuf_free(m);
					}
				}
				SET_CPU_IDLE(rx_conf, CPU_PROCESS);
			}

			lthread_yield();
		}
	}
}

/*
 * Start scheduler with initial lthread on lcore
 *
 * This lthread loop spawns all rx and tx lthreads on master lcore
 */

static void
lthread_spawner(__rte_unused void *arg) {
	struct lthread *lt[MAX_THREAD];
	int i;
	int n_thread = 0;

	printf("Entering lthread_spawner\n");

	/*
	 * Create producers (rx threads) on default lcore
	 */
	for (i = 0; i < n_rx_thread; i++) {
		rx_thread[i].conf.thread_id = i;
		lthread_create(&lt[n_thread], -1, lthread_rx,
				(void *)&rx_thread[i]);
		n_thread++;
	}

	/*
	 * Wait for all producers. Until some producers can be started on the same
	 * scheduler as this lthread, yielding is required to let them to run and
	 * prevent deadlock here.
	 */
	while (rte_atomic16_read(&rx_counter) < n_rx_thread)
		lthread_sleep(100000);

	/*
	 * Create consumers (tx threads) on default lcore_id
	 */
	for (i = 0; i < n_tx_thread; i++) {
		tx_thread[i].conf.thread_id = i;
		lthread_create(&lt[n_thread], -1, lthread_tx,
				(void *)&tx_thread[i]);
		n_thread++;
	}

	/*
	 * Wait for all threads finished
	 */
	for (i = 0; i < n_thread; i++)
		lthread_join(lt[i], NULL);

}

/*
 * Start master scheduler with initial lthread spawning rx and tx lthreads
 * (main_lthread_master).
 */
static int
lthread_master_spawner(__rte_unused void *arg) {
	struct lthread *lt;
	int lcore_id = rte_lcore_id();

	RTE_PER_LCORE(lcore_conf) = &lcore_conf[lcore_id];
	lthread_create(&lt, -1, lthread_spawner, NULL);
	lthread_run();

	return 0;
}

/*
 * Start scheduler on lcore.
 */
static int
sched_spawner(__rte_unused void *arg) {
	struct lthread *lt;
	int lcore_id = rte_lcore_id();

#if (APP_CPU_LOAD)
	if (lcore_id == cpu_load_lcore_id) {
		cpu_load_collector(arg);
		return 0;
	}
#endif /* APP_CPU_LOAD */

	RTE_PER_LCORE(lcore_conf) = &lcore_conf[lcore_id];
	lthread_create(&lt, -1, lthread_null, NULL);
	lthread_run();

	return 0;
}

/* main processing loop */
static int
pthread_tx(void *dummy)
{
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	uint64_t prev_tsc, diff_tsc, cur_tsc;
	int nb_rx;
	uint8_t portid;
	struct thread_tx_conf *tx_conf;

	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
		US_PER_S * BURST_TX_DRAIN_US;

	prev_tsc = 0;

	tx_conf = (struct thread_tx_conf *)dummy;

	RTE_LOG(INFO, L3FWD, "Entering main Tx loop on lcore %u\n", rte_lcore_id());

	tx_conf->conf.cpu_id = sched_getcpu();
	rte_atomic16_inc(&tx_counter);
	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
			 */
			SET_CPU_BUSY(tx_conf, CPU_PROCESS);
			for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
				if (tx_conf->tx_mbufs[portid].len == 0)
					continue;
				send_burst(tx_conf, tx_conf->tx_mbufs[portid].len, portid);
				tx_conf->tx_mbufs[portid].len = 0;
			}
			SET_CPU_IDLE(tx_conf, CPU_PROCESS);

			prev_tsc = cur_tsc;
		}

		/*
		 * Read packet from ring
		 */
		SET_CPU_BUSY(tx_conf, CPU_POLL);
		nb_rx = rte_ring_sc_dequeue_burst(tx_conf->ring,
				(void **)pkts_burst, MAX_PKT_BURST, NULL);
		SET_CPU_IDLE(tx_conf, CPU_POLL);

		if (unlikely(nb_rx == 0)) {
			sched_yield();
			continue;
		}

		SET_CPU_BUSY(tx_conf, CPU_PROCESS);
		portid = pkts_burst[0]->port;
		process_burst(pkts_burst, nb_rx, portid);
		SET_CPU_IDLE(tx_conf, CPU_PROCESS);

	}
}

static int
pthread_rx(void *dummy)
{
	int i;
	int worker_id;
	uint32_t n;
	uint32_t nb_rx;
	unsigned lcore_id;
	uint8_t portid, queueid;
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];

	struct thread_rx_conf *rx_conf;

	lcore_id = rte_lcore_id();
	rx_conf = (struct thread_rx_conf *)dummy;

	if (rx_conf->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 rx loop on lcore %u\n", lcore_id);

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

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

	worker_id = 0;
	rx_conf->conf.cpu_id = sched_getcpu();
	rte_atomic16_inc(&rx_counter);
	while (1) {

		/*
		 * Read packet from RX queues
		 */
		for (i = 0; i < rx_conf->n_rx_queue; ++i) {
			portid = rx_conf->rx_queue_list[i].port_id;
			queueid = rx_conf->rx_queue_list[i].queue_id;

			SET_CPU_BUSY(rx_conf, CPU_POLL);
			nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
				MAX_PKT_BURST);
			SET_CPU_IDLE(rx_conf, CPU_POLL);

			if (nb_rx == 0) {
				sched_yield();
				continue;
			}

			SET_CPU_BUSY(rx_conf, CPU_PROCESS);
			worker_id = (worker_id + 1) % rx_conf->n_ring;
			n = rte_ring_sp_enqueue_burst(rx_conf->ring[worker_id],
					(void **)pkts_burst, nb_rx, NULL);

			if (unlikely(n != nb_rx)) {
				uint32_t k;

				for (k = n; k < nb_rx; k++) {
					struct rte_mbuf *m = pkts_burst[k];

					rte_pktmbuf_free(m);
				}
			}

			SET_CPU_IDLE(rx_conf, CPU_PROCESS);

		}
	}
}

/*
 * P-Thread spawner.
 */
static int
pthread_run(__rte_unused void *arg) {
	int lcore_id = rte_lcore_id();
	int i;

	for (i = 0; i < n_rx_thread; i++)
		if (rx_thread[i].conf.lcore_id == lcore_id) {
			printf("Start rx thread on %d...\n", lcore_id);
			RTE_PER_LCORE(lcore_conf) = &lcore_conf[lcore_id];
			RTE_PER_LCORE(lcore_conf)->data = (void *)&rx_thread[i];
			pthread_rx((void *)&rx_thread[i]);
			return 0;
		}

	for (i = 0; i < n_tx_thread; i++)
		if (tx_thread[i].conf.lcore_id == lcore_id) {
			printf("Start tx thread on %d...\n", lcore_id);
			RTE_PER_LCORE(lcore_conf) = &lcore_conf[lcore_id];
			RTE_PER_LCORE(lcore_conf)->data = (void *)&tx_thread[i];
			pthread_tx((void *)&tx_thread[i]);
			return 0;
		}

#if (APP_CPU_LOAD)
	if (lcore_id == cpu_load_lcore_id)
		cpu_load_collector(arg);
#endif /* APP_CPU_LOAD */

	return 0;
}

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

	for (i = 0; i < nb_rx_thread_params; ++i) {
		queue = rx_thread_params[i].queue_id;
		if (queue >= MAX_RX_QUEUE_PER_PORT) {
			printf("invalid queue number: %hhu\n", queue);
			return -1;
		}
		lcore = rx_thread_params[i].lcore_id;
		if (!rte_lcore_is_enabled(lcore)) {
			printf("error: lcore %hhu is not enabled in lcore mask\n", lcore);
			return -1;
		}
		socketid = rte_lcore_to_socket_id(lcore);
		if ((socketid != 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_rx_thread_params; ++i) {
		portid = rx_thread_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_rx_thread_params; ++i)
		if (rx_thread_params[i].port_id == port &&
				rx_thread_params[i].queue_id > queue)
			queue = rx_thread_params[i].queue_id;

	return (uint8_t)(++queue);
}

static int
init_rx_rings(void)
{
	unsigned socket_io;
	struct thread_rx_conf *rx_conf;
	struct thread_tx_conf *tx_conf;
	unsigned rx_thread_id, tx_thread_id;
	char name[256];
	struct rte_ring *ring = NULL;

	for (tx_thread_id = 0; tx_thread_id < n_tx_thread; tx_thread_id++) {

		tx_conf = &tx_thread[tx_thread_id];

		printf("Connecting tx-thread %d with rx-thread %d\n", tx_thread_id,
				tx_conf->conf.thread_id);

		rx_thread_id = tx_conf->conf.thread_id;
		if (rx_thread_id > n_tx_thread) {
			printf("connection from tx-thread %u to rx-thread %u fails "
					"(rx-thread not defined)\n", tx_thread_id, rx_thread_id);
			return -1;
		}

		rx_conf = &rx_thread[rx_thread_id];
		socket_io = rte_lcore_to_socket_id(rx_conf->conf.lcore_id);

		snprintf(name, sizeof(name), "app_ring_s%u_rx%u_tx%u",
				socket_io, rx_thread_id, tx_thread_id);

		ring = rte_ring_create(name, 1024 * 4, socket_io,
				RING_F_SP_ENQ | RING_F_SC_DEQ);

		if (ring == NULL) {
			rte_panic("Cannot create ring to connect rx-thread %u "
					"with tx-thread %u\n", rx_thread_id, tx_thread_id);
		}

		rx_conf->ring[rx_conf->n_ring] = ring;

		tx_conf->ring = ring;
		tx_conf->ready = &rx_conf->ready[rx_conf->n_ring];

		rx_conf->n_ring++;
	}
	return 0;
}

static int
init_rx_queues(void)
{
	uint16_t i, nb_rx_queue;
	uint8_t thread;

	n_rx_thread = 0;

	for (i = 0; i < nb_rx_thread_params; ++i) {
		thread = rx_thread_params[i].thread_id;
		nb_rx_queue = rx_thread[thread].n_rx_queue;

		if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
			printf("error: too many queues (%u) for thread: %u\n",
				(unsigned)nb_rx_queue + 1, (unsigned)thread);
			return -1;
		}

		rx_thread[thread].conf.thread_id = thread;
		rx_thread[thread].conf.lcore_id = rx_thread_params[i].lcore_id;
		rx_thread[thread].rx_queue_list[nb_rx_queue].port_id =
			rx_thread_params[i].port_id;
		rx_thread[thread].rx_queue_list[nb_rx_queue].queue_id =
			rx_thread_params[i].queue_id;
		rx_thread[thread].n_rx_queue++;

		if (thread >= n_rx_thread)
			n_rx_thread = thread + 1;

	}
	return 0;
}

static int
init_tx_threads(void)
{
	int i;

	n_tx_thread = 0;
	for (i = 0; i < nb_tx_thread_params; ++i) {
		tx_thread[n_tx_thread].conf.thread_id = tx_thread_params[i].thread_id;
		tx_thread[n_tx_thread].conf.lcore_id = tx_thread_params[i].lcore_id;
		n_tx_thread++;
	}
	return 0;
}

/* display usage */
static void
print_usage(const char *prgname)
{
	printf("%s [EAL options] -- -p PORTMASK -P"
		"  [--rx (port,queue,lcore,thread)[,(port,queue,lcore,thread]]"
		"  [--tx (lcore,thread)[,(lcore,thread]]"
		"  [--enable-jumbo [--max-pkt-len PKTLEN]]\n"
		"  [--parse-ptype]\n\n"
		"  -p PORTMASK: hexadecimal bitmask of ports to configure\n"
		"  -P : enable promiscuous mode\n"
		"  --rx (port,queue,lcore,thread): rx queues configuration\n"
		"  --tx (lcore,thread): tx threads configuration\n"
		"  --stat-lcore LCORE: use lcore for stat collector\n"
		"  --eth-dest=X,MM:MM:MM:MM:MM:MM: optional, ethernet destination for port X\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"
		"  --no-lthreads: turn off lthread model\n"
		"  --parse-ptype: set to use software to analyze packet type\n\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_rx_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,
		FLD_THREAD,
		_NUM_FLD
	};
	unsigned long int_fld[_NUM_FLD];
	char *str_fld[_NUM_FLD];
	int i;
	unsigned size;

	nb_rx_thread_params = 0;

	while ((p = strchr(p0, '(')) != NULL) {
		++p;
		p0 = strchr(p, ')');
		if (p0 == 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_rx_thread_params >= MAX_LCORE_PARAMS) {
			printf("exceeded max number of rx params: %hu\n",
					nb_rx_thread_params);
			return -1;
		}
		rx_thread_params_array[nb_rx_thread_params].port_id =
				(uint8_t)int_fld[FLD_PORT];
		rx_thread_params_array[nb_rx_thread_params].queue_id =
				(uint8_t)int_fld[FLD_QUEUE];
		rx_thread_params_array[nb_rx_thread_params].lcore_id =
				(uint8_t)int_fld[FLD_LCORE];
		rx_thread_params_array[nb_rx_thread_params].thread_id =
				(uint8_t)int_fld[FLD_THREAD];
		++nb_rx_thread_params;
	}
	rx_thread_params = rx_thread_params_array;
	return 0;
}

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

	nb_tx_thread_params = 0;

	while ((p = strchr(p0, '(')) != NULL) {
		++p;
		p0 = strchr(p, ')');
		if (p0 == 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_tx_thread_params >= MAX_LCORE_PARAMS) {
			printf("exceeded max number of tx params: %hu\n",
				nb_tx_thread_params);
			return -1;
		}
		tx_thread_params_array[nb_tx_thread_params].lcore_id =
				(uint8_t)int_fld[FLD_LCORE];
		tx_thread_params_array[nb_tx_thread_params].thread_id =
				(uint8_t)int_fld[FLD_THREAD];
		++nb_tx_thread_params;
	}
	tx_thread_params = tx_thread_params_array;

	return 0;
}

#if (APP_CPU_LOAD > 0)
static int
parse_stat_lcore(const char *stat_lcore)
{
	char *end = NULL;
	unsigned long lcore_id;

	lcore_id = strtoul(stat_lcore, &end, 10);
	if ((stat_lcore[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	return lcore_id;
}
#endif

static void
parse_eth_dest(const char *optarg)
{
	uint8_t portid;
	char *port_end;
	uint8_t c, *dest, peer_addr[6];

	errno = 0;
	portid = strtoul(optarg, &port_end, 10);
	if (errno != 0 || port_end == optarg || *port_end++ != ',')
		rte_exit(EXIT_FAILURE,
		"Invalid eth-dest: %s", optarg);
	if (portid >= RTE_MAX_ETHPORTS)
		rte_exit(EXIT_FAILURE,
		"eth-dest: port %d >= RTE_MAX_ETHPORTS(%d)\n",
		portid, RTE_MAX_ETHPORTS);

	if (cmdline_parse_etheraddr(NULL, port_end,
		&peer_addr, sizeof(peer_addr)) < 0)
		rte_exit(EXIT_FAILURE,
		"Invalid ethernet address: %s\n",
		port_end);
	dest = (uint8_t *)&dest_eth_addr[portid];
	for (c = 0; c < 6; c++)
		dest[c] = peer_addr[c];
	*(uint64_t *)(val_eth + portid) = dest_eth_addr[portid];
}

#define CMD_LINE_OPT_RX_CONFIG "rx"
#define CMD_LINE_OPT_TX_CONFIG "tx"
#define CMD_LINE_OPT_STAT_LCORE "stat-lcore"
#define CMD_LINE_OPT_ETH_DEST "eth-dest"
#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"
#define CMD_LINE_OPT_NO_LTHREADS "no-lthreads"
#define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype"

/* 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_RX_CONFIG, 1, 0, 0},
		{CMD_LINE_OPT_TX_CONFIG, 1, 0, 0},
		{CMD_LINE_OPT_STAT_LCORE, 1, 0, 0},
		{CMD_LINE_OPT_ETH_DEST, 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},
		{CMD_LINE_OPT_NO_LTHREADS, 0, 0, 0},
		{CMD_LINE_OPT_PARSE_PTYPE, 0, 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_RX_CONFIG,
				sizeof(CMD_LINE_OPT_RX_CONFIG))) {
				ret = parse_rx_config(optarg);
				if (ret) {
					printf("invalid rx-config\n");
					print_usage(prgname);
					return -1;
				}
			}

			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_TX_CONFIG,
				sizeof(CMD_LINE_OPT_TX_CONFIG))) {
				ret = parse_tx_config(optarg);
				if (ret) {
					printf("invalid tx-config\n");
					print_usage(prgname);
					return -1;
				}
			}

#if (APP_CPU_LOAD > 0)
			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_STAT_LCORE,
					sizeof(CMD_LINE_OPT_STAT_LCORE))) {
				cpu_load_lcore_id = parse_stat_lcore(optarg);
			}
#endif

			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_ETH_DEST,
				sizeof(CMD_LINE_OPT_ETH_DEST)))
					parse_eth_dest(optarg);

			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_NO_LTHREADS,
					sizeof(CMD_LINE_OPT_NO_LTHREADS))) {
				printf("l-threads model is disabled\n");
				lthreads_on = 0;
			}

			if (!strncmp(lgopts[option_index].name, CMD_LINE_OPT_PARSE_PTYPE,
					sizeof(CMD_LINE_OPT_PARSE_PTYPE))) {
				printf("software packet type parsing enabled\n");
				parse_ptype_on = 1;
			}

			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 = 1; /* 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;
}

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;
}

#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 = RTE_DIM(ipv4_l3fwd_route_array);

	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 = RTE_DIM(ipv6_l3fwd_route_array);

	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,
		.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,
		.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;
	struct rte_lpm_config lpm_ipv4_config;
	unsigned i;
	int ret;
	char s[64];

	/* create the LPM table */
	snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid);
	lpm_ipv4_config.max_rules = IPV4_L3FWD_LPM_MAX_RULES;
	lpm_ipv4_config.number_tbl8s = 256;
	lpm_ipv4_config.flags = 0;
	ipv4_l3fwd_lookup_struct[socketid] =
			rte_lpm_create(s, socketid, &lpm_ipv4_config);
	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_pktmbuf_pool_create(s, nb_mbuf,
					MEMPOOL_CACHE_SIZE, 0,
					RTE_MBUF_DEFAULT_BUF_SIZE, socketid);
			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 == ETH_LINK_DOWN) {
				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 rte_eth_dev_info dev_info;
	struct rte_eth_txconf *txconf;
	int ret;
	int i;
	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;

	/* pre-init dst MACs for all ports to 02:00:00:00:00:xx */
	for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
		dest_eth_addr[portid] = ETHER_LOCAL_ADMIN_ADDR +
				((uint64_t)portid << 40);
		*(uint64_t *)(val_eth + portid) = dest_eth_addr[portid];
	}

	/* 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");

	printf("Initializing rx-queues...\n");
	ret = init_rx_queues();
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "init_rx_queues failed\n");

	printf("Initializing tx-threads...\n");
	ret = init_tx_threads();
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "init_tx_threads failed\n");

	printf("Initializing rings...\n");
	ret = init_rx_rings();
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "init_rx_rings failed\n");

	nb_ports = rte_eth_dev_count();

	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(", ");
		print_ethaddr("Destination:",
			(const struct ether_addr *)&dest_eth_addr[portid]);
		printf(", ");

		/*
		 * prepare src MACs for each port.
		 */
		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);

			tx_thread[lcore_id].tx_queue_id[portid] = queueid;
			queueid++;
		}
		printf("\n");
	}

	for (i = 0; i < n_rx_thread; i++) {
		lcore_id = rx_thread[i].conf.lcore_id;

		if (rte_lcore_is_enabled(lcore_id) == 0) {
			rte_exit(EXIT_FAILURE,
					"Cannot start Rx thread on lcore %u: lcore disabled\n",
					lcore_id
				);
		}

		printf("\nInitializing rx queues for Rx thread %d on lcore %u ... ",
				i, lcore_id);
		fflush(stdout);

		/* init RX queues */
		for (queue = 0; queue < rx_thread[i].n_rx_queue; ++queue) {
			portid = rx_thread[i].rx_queue_list[queue].port_id;
			queueid = rx_thread[i].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);
	}

	for (i = 0; i < n_rx_thread; i++) {
		lcore_id = rx_thread[i].conf.lcore_id;
		if (rte_lcore_is_enabled(lcore_id) == 0)
			continue;

		/* check if hw packet type is supported */
		for (queue = 0; queue < rx_thread[i].n_rx_queue; ++queue) {
			portid = rx_thread[i].rx_queue_list[queue].port_id;
			queueid = rx_thread[i].rx_queue_list[queue].queue_id;

			if (parse_ptype_on) {
				if (!rte_eth_add_rx_callback(portid, queueid,
						cb_parse_ptype, NULL))
					rte_exit(EXIT_FAILURE,
						"Failed to add rx callback: "
						"port=%d\n", portid);
			} else if (!check_ptype(portid))
				rte_exit(EXIT_FAILURE,
					"Port %d cannot parse packet type.\n\n"
					"Please add --parse-ptype to use sw "
					"packet type analyzer.\n\n",
					portid);
		}
	}

	check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);

	if (lthreads_on) {
		printf("Starting L-Threading Model\n");

#if (APP_CPU_LOAD > 0)
		if (cpu_load_lcore_id > 0)
			/* Use one lcore for cpu load collector */
			nb_lcores--;
#endif

		lthread_num_schedulers_set(nb_lcores);
		rte_eal_mp_remote_launch(sched_spawner, NULL, SKIP_MASTER);
		lthread_master_spawner(NULL);

	} else {
		printf("Starting P-Threading Model\n");
		/* launch per-lcore init on every lcore */
		rte_eal_mp_remote_launch(pthread_run, NULL, CALL_MASTER);
		RTE_LCORE_FOREACH_SLAVE(lcore_id) {
			if (rte_eal_wait_lcore(lcore_id) < 0)
				return -1;
		}
	}

	return 0;
}