aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/mlx5/mlx5_flow_tcf.c
blob: fb284c3558c2da14c6ede02a264ff4e0d42190e0 (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
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright 2018 6WIND S.A.
 * Copyright 2018 Mellanox Technologies, Ltd
 */

#include <assert.h>
#include <errno.h>
#include <libmnl/libmnl.h>
#include <linux/gen_stats.h>
#include <linux/if_ether.h>
#include <linux/netlink.h>
#include <linux/pkt_cls.h>
#include <linux/pkt_sched.h>
#include <linux/rtnetlink.h>
#include <linux/tc_act/tc_gact.h>
#include <linux/tc_act/tc_mirred.h>
#include <netinet/in.h>
#include <stdalign.h>
#include <stdbool.h>
#include <stddef.h>
#include <stdint.h>
#include <stdlib.h>
#include <sys/socket.h>

#include <rte_byteorder.h>
#include <rte_errno.h>
#include <rte_ether.h>
#include <rte_flow.h>
#include <rte_malloc.h>
#include <rte_common.h>

#include "mlx5.h"
#include "mlx5_flow.h"
#include "mlx5_autoconf.h"

#ifdef HAVE_TC_ACT_VLAN

#include <linux/tc_act/tc_vlan.h>

#else /* HAVE_TC_ACT_VLAN */

#define TCA_VLAN_ACT_POP 1
#define TCA_VLAN_ACT_PUSH 2
#define TCA_VLAN_ACT_MODIFY 3
#define TCA_VLAN_PARMS 2
#define TCA_VLAN_PUSH_VLAN_ID 3
#define TCA_VLAN_PUSH_VLAN_PROTOCOL 4
#define TCA_VLAN_PAD 5
#define TCA_VLAN_PUSH_VLAN_PRIORITY 6

struct tc_vlan {
	tc_gen;
	int v_action;
};

#endif /* HAVE_TC_ACT_VLAN */

#ifdef HAVE_TC_ACT_PEDIT

#include <linux/tc_act/tc_pedit.h>

#else /* HAVE_TC_ACT_VLAN */

enum {
	TCA_PEDIT_UNSPEC,
	TCA_PEDIT_TM,
	TCA_PEDIT_PARMS,
	TCA_PEDIT_PAD,
	TCA_PEDIT_PARMS_EX,
	TCA_PEDIT_KEYS_EX,
	TCA_PEDIT_KEY_EX,
	__TCA_PEDIT_MAX
};

enum {
	TCA_PEDIT_KEY_EX_HTYPE = 1,
	TCA_PEDIT_KEY_EX_CMD = 2,
	__TCA_PEDIT_KEY_EX_MAX
};

enum pedit_header_type {
	TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK = 0,
	TCA_PEDIT_KEY_EX_HDR_TYPE_ETH = 1,
	TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 = 2,
	TCA_PEDIT_KEY_EX_HDR_TYPE_IP6 = 3,
	TCA_PEDIT_KEY_EX_HDR_TYPE_TCP = 4,
	TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5,
	__PEDIT_HDR_TYPE_MAX,
};

enum pedit_cmd {
	TCA_PEDIT_KEY_EX_CMD_SET = 0,
	TCA_PEDIT_KEY_EX_CMD_ADD = 1,
	__PEDIT_CMD_MAX,
};

struct tc_pedit_key {
	__u32 mask; /* AND */
	__u32 val; /*XOR */
	__u32 off; /*offset */
	__u32 at;
	__u32 offmask;
	__u32 shift;
};

__extension__
struct tc_pedit_sel {
	tc_gen;
	unsigned char nkeys;
	unsigned char flags;
	struct tc_pedit_key keys[0];
};

#endif /* HAVE_TC_ACT_VLAN */

#ifdef HAVE_TC_ACT_TUNNEL_KEY

#include <linux/tc_act/tc_tunnel_key.h>

#ifndef HAVE_TCA_TUNNEL_KEY_ENC_DST_PORT
#define TCA_TUNNEL_KEY_ENC_DST_PORT 9
#endif

#ifndef HAVE_TCA_TUNNEL_KEY_NO_CSUM
#define TCA_TUNNEL_KEY_NO_CSUM 10
#endif

#else /* HAVE_TC_ACT_TUNNEL_KEY */

#define TCA_ACT_TUNNEL_KEY 17
#define TCA_TUNNEL_KEY_ACT_SET 1
#define TCA_TUNNEL_KEY_ACT_RELEASE 2
#define TCA_TUNNEL_KEY_PARMS 2
#define TCA_TUNNEL_KEY_ENC_IPV4_SRC 3
#define TCA_TUNNEL_KEY_ENC_IPV4_DST 4
#define TCA_TUNNEL_KEY_ENC_IPV6_SRC 5
#define TCA_TUNNEL_KEY_ENC_IPV6_DST 6
#define TCA_TUNNEL_KEY_ENC_KEY_ID 7
#define TCA_TUNNEL_KEY_ENC_DST_PORT 9
#define TCA_TUNNEL_KEY_NO_CSUM 10

struct tc_tunnel_key {
	tc_gen;
	int t_action;
};

#endif /* HAVE_TC_ACT_TUNNEL_KEY */

/* Normally found in linux/netlink.h. */
#ifndef NETLINK_CAP_ACK
#define NETLINK_CAP_ACK 10
#endif

/* Normally found in linux/pkt_sched.h. */
#ifndef TC_H_MIN_INGRESS
#define TC_H_MIN_INGRESS 0xfff2u
#endif

/* Normally found in linux/pkt_cls.h. */
#ifndef TCA_CLS_FLAGS_SKIP_SW
#define TCA_CLS_FLAGS_SKIP_SW (1 << 1)
#endif
#ifndef TCA_CLS_FLAGS_IN_HW
#define TCA_CLS_FLAGS_IN_HW (1 << 2)
#endif
#ifndef HAVE_TCA_CHAIN
#define TCA_CHAIN 11
#endif
#ifndef HAVE_TCA_FLOWER_ACT
#define TCA_FLOWER_ACT 3
#endif
#ifndef HAVE_TCA_FLOWER_FLAGS
#define TCA_FLOWER_FLAGS 22
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ETH_TYPE
#define TCA_FLOWER_KEY_ETH_TYPE 8
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ETH_DST
#define TCA_FLOWER_KEY_ETH_DST 4
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ETH_DST_MASK
#define TCA_FLOWER_KEY_ETH_DST_MASK 5
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ETH_SRC
#define TCA_FLOWER_KEY_ETH_SRC 6
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ETH_SRC_MASK
#define TCA_FLOWER_KEY_ETH_SRC_MASK 7
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IP_PROTO
#define TCA_FLOWER_KEY_IP_PROTO 9
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV4_SRC
#define TCA_FLOWER_KEY_IPV4_SRC 10
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV4_SRC_MASK
#define TCA_FLOWER_KEY_IPV4_SRC_MASK 11
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV4_DST
#define TCA_FLOWER_KEY_IPV4_DST 12
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV4_DST_MASK
#define TCA_FLOWER_KEY_IPV4_DST_MASK 13
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV6_SRC
#define TCA_FLOWER_KEY_IPV6_SRC 14
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV6_SRC_MASK
#define TCA_FLOWER_KEY_IPV6_SRC_MASK 15
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV6_DST
#define TCA_FLOWER_KEY_IPV6_DST 16
#endif
#ifndef HAVE_TCA_FLOWER_KEY_IPV6_DST_MASK
#define TCA_FLOWER_KEY_IPV6_DST_MASK 17
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_SRC
#define TCA_FLOWER_KEY_TCP_SRC 18
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_SRC_MASK
#define TCA_FLOWER_KEY_TCP_SRC_MASK 35
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_DST
#define TCA_FLOWER_KEY_TCP_DST 19
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_DST_MASK
#define TCA_FLOWER_KEY_TCP_DST_MASK 36
#endif
#ifndef HAVE_TCA_FLOWER_KEY_UDP_SRC
#define TCA_FLOWER_KEY_UDP_SRC 20
#endif
#ifndef HAVE_TCA_FLOWER_KEY_UDP_SRC_MASK
#define TCA_FLOWER_KEY_UDP_SRC_MASK 37
#endif
#ifndef HAVE_TCA_FLOWER_KEY_UDP_DST
#define TCA_FLOWER_KEY_UDP_DST 21
#endif
#ifndef HAVE_TCA_FLOWER_KEY_UDP_DST_MASK
#define TCA_FLOWER_KEY_UDP_DST_MASK 38
#endif
#ifndef HAVE_TCA_FLOWER_KEY_VLAN_ID
#define TCA_FLOWER_KEY_VLAN_ID 23
#endif
#ifndef HAVE_TCA_FLOWER_KEY_VLAN_PRIO
#define TCA_FLOWER_KEY_VLAN_PRIO 24
#endif
#ifndef HAVE_TCA_FLOWER_KEY_VLAN_ETH_TYPE
#define TCA_FLOWER_KEY_VLAN_ETH_TYPE 25
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_KEY_ID
#define TCA_FLOWER_KEY_ENC_KEY_ID 26
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_SRC
#define TCA_FLOWER_KEY_ENC_IPV4_SRC 27
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK
#define TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK 28
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_DST
#define TCA_FLOWER_KEY_ENC_IPV4_DST 29
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_DST_MASK
#define TCA_FLOWER_KEY_ENC_IPV4_DST_MASK 30
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_SRC
#define TCA_FLOWER_KEY_ENC_IPV6_SRC 31
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK
#define TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK 32
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_DST
#define TCA_FLOWER_KEY_ENC_IPV6_DST 33
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_DST_MASK
#define TCA_FLOWER_KEY_ENC_IPV6_DST_MASK 34
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_SRC_PORT
#define TCA_FLOWER_KEY_ENC_UDP_SRC_PORT 43
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK
#define TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK 44
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_DST_PORT
#define TCA_FLOWER_KEY_ENC_UDP_DST_PORT 45
#endif
#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK
#define TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK 46
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_FLAGS
#define TCA_FLOWER_KEY_TCP_FLAGS 71
#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_FLAGS_MASK
#define TCA_FLOWER_KEY_TCP_FLAGS_MASK 72
#endif
#ifndef HAVE_TC_ACT_GOTO_CHAIN
#define TC_ACT_GOTO_CHAIN 0x20000000
#endif

#ifndef IPV6_ADDR_LEN
#define IPV6_ADDR_LEN 16
#endif

#ifndef IPV4_ADDR_LEN
#define IPV4_ADDR_LEN 4
#endif

#ifndef TP_PORT_LEN
#define TP_PORT_LEN 2 /* Transport Port (UDP/TCP) Length */
#endif

#ifndef TTL_LEN
#define TTL_LEN 1
#endif

#ifndef TCA_ACT_MAX_PRIO
#define TCA_ACT_MAX_PRIO 32
#endif

/** UDP port range of VXLAN devices created by driver. */
#define MLX5_VXLAN_PORT_MIN 30000
#define MLX5_VXLAN_PORT_MAX 60000
#define MLX5_VXLAN_DEVICE_PFX "vmlx_"

/** Tunnel action type, used for @p type in header structure. */
enum flow_tcf_tunact_type {
	FLOW_TCF_TUNACT_VXLAN_DECAP,
	FLOW_TCF_TUNACT_VXLAN_ENCAP,
};

/** Flags used for @p mask in tunnel action encap descriptors. */
#define FLOW_TCF_ENCAP_ETH_SRC (1u << 0)
#define FLOW_TCF_ENCAP_ETH_DST (1u << 1)
#define FLOW_TCF_ENCAP_IPV4_SRC (1u << 2)
#define FLOW_TCF_ENCAP_IPV4_DST (1u << 3)
#define FLOW_TCF_ENCAP_IPV6_SRC (1u << 4)
#define FLOW_TCF_ENCAP_IPV6_DST (1u << 5)
#define FLOW_TCF_ENCAP_UDP_SRC (1u << 6)
#define FLOW_TCF_ENCAP_UDP_DST (1u << 7)
#define FLOW_TCF_ENCAP_VXLAN_VNI (1u << 8)

/**
 * Structure for holding netlink context.
 * Note the size of the message buffer which is MNL_SOCKET_BUFFER_SIZE.
 * Using this (8KB) buffer size ensures that netlink messages will never be
 * truncated.
 */
struct mlx5_flow_tcf_context {
	struct mnl_socket *nl; /* NETLINK_ROUTE libmnl socket. */
	uint32_t seq; /* Message sequence number. */
	uint32_t buf_size; /* Message buffer size. */
	uint8_t *buf; /* Message buffer. */
};

/**
 * Neigh rule structure. The neigh rule is applied via Netlink to
 * outer tunnel iface in order to provide destination MAC address
 * for the VXLAN encapsultion. The neigh rule is implicitly related
 * to the Flow itself and can be shared by multiple Flows.
 */
struct tcf_neigh_rule {
	LIST_ENTRY(tcf_neigh_rule) next;
	uint32_t refcnt;
	struct ether_addr eth;
	uint16_t mask;
	union {
		struct {
			rte_be32_t dst;
		} ipv4;
		struct {
			uint8_t dst[IPV6_ADDR_LEN];
		} ipv6;
	};
};

/**
 * Local rule structure. The local rule is applied via Netlink to
 * outer tunnel iface in order to provide local and peer IP addresses
 * of the VXLAN tunnel for encapsulation. The local rule is implicitly
 * related to the Flow itself and can be shared by multiple Flows.
 */
struct tcf_local_rule {
	LIST_ENTRY(tcf_local_rule) next;
	uint32_t refcnt;
	uint16_t mask;
	union {
		struct {
			rte_be32_t dst;
			rte_be32_t src;
		} ipv4;
		struct {
			uint8_t dst[IPV6_ADDR_LEN];
			uint8_t src[IPV6_ADDR_LEN];
		} ipv6;
	};
};

/** VXLAN virtual netdev. */
struct tcf_vtep {
	LIST_ENTRY(tcf_vtep) next;
	LIST_HEAD(, tcf_neigh_rule) neigh;
	LIST_HEAD(, tcf_local_rule) local;
	uint32_t refcnt;
	unsigned int ifindex; /**< Own interface index. */
	unsigned int ifouter; /**< Index of device attached to. */
	uint16_t port;
	uint8_t created;
};

/** Tunnel descriptor header, common for all tunnel types. */
struct flow_tcf_tunnel_hdr {
	uint32_t type; /**< Tunnel action type. */
	struct tcf_vtep *vtep; /**< Virtual tunnel endpoint device. */
	unsigned int ifindex_org; /**< Original dst/src interface */
	unsigned int *ifindex_ptr; /**< Interface ptr in message. */
};

struct flow_tcf_vxlan_decap {
	struct flow_tcf_tunnel_hdr hdr;
	uint16_t udp_port;
};

struct flow_tcf_vxlan_encap {
	struct flow_tcf_tunnel_hdr hdr;
	uint32_t mask;
	struct {
		struct ether_addr dst;
		struct ether_addr src;
	} eth;
	union {
		struct {
			rte_be32_t dst;
			rte_be32_t src;
		} ipv4;
		struct {
			uint8_t dst[IPV6_ADDR_LEN];
			uint8_t src[IPV6_ADDR_LEN];
		} ipv6;
	};
struct {
		rte_be16_t src;
		rte_be16_t dst;
	} udp;
	struct {
		uint8_t vni[3];
	} vxlan;
};

/** Structure used when extracting the values of a flow counters
 * from a netlink message.
 */
struct flow_tcf_stats_basic {
	bool valid;
	struct gnet_stats_basic counters;
};

/** Empty masks for known item types. */
static const union {
	struct rte_flow_item_port_id port_id;
	struct rte_flow_item_eth eth;
	struct rte_flow_item_vlan vlan;
	struct rte_flow_item_ipv4 ipv4;
	struct rte_flow_item_ipv6 ipv6;
	struct rte_flow_item_tcp tcp;
	struct rte_flow_item_udp udp;
	struct rte_flow_item_vxlan vxlan;
} flow_tcf_mask_empty;

/** Supported masks for known item types. */
static const struct {
	struct rte_flow_item_port_id port_id;
	struct rte_flow_item_eth eth;
	struct rte_flow_item_vlan vlan;
	struct rte_flow_item_ipv4 ipv4;
	struct rte_flow_item_ipv6 ipv6;
	struct rte_flow_item_tcp tcp;
	struct rte_flow_item_udp udp;
	struct rte_flow_item_vxlan vxlan;
} flow_tcf_mask_supported = {
	.port_id = {
		.id = 0xffffffff,
	},
	.eth = {
		.type = RTE_BE16(0xffff),
		.dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
		.src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
	},
	.vlan = {
		/* PCP and VID only, no DEI. */
		.tci = RTE_BE16(0xefff),
		.inner_type = RTE_BE16(0xffff),
	},
	.ipv4.hdr = {
		.next_proto_id = 0xff,
		.src_addr = RTE_BE32(0xffffffff),
		.dst_addr = RTE_BE32(0xffffffff),
	},
	.ipv6.hdr = {
		.proto = 0xff,
		.src_addr =
			"\xff\xff\xff\xff\xff\xff\xff\xff"
			"\xff\xff\xff\xff\xff\xff\xff\xff",
		.dst_addr =
			"\xff\xff\xff\xff\xff\xff\xff\xff"
			"\xff\xff\xff\xff\xff\xff\xff\xff",
	},
	.tcp.hdr = {
		.src_port = RTE_BE16(0xffff),
		.dst_port = RTE_BE16(0xffff),
		.tcp_flags = 0xff,
	},
	.udp.hdr = {
		.src_port = RTE_BE16(0xffff),
		.dst_port = RTE_BE16(0xffff),
	},
	.vxlan = {
	       .vni = "\xff\xff\xff",
	},
};

#define SZ_NLATTR_HDR MNL_ALIGN(sizeof(struct nlattr))
#define SZ_NLATTR_NEST SZ_NLATTR_HDR
#define SZ_NLATTR_DATA_OF(len) MNL_ALIGN(SZ_NLATTR_HDR + (len))
#define SZ_NLATTR_TYPE_OF(typ) SZ_NLATTR_DATA_OF(sizeof(typ))
#define SZ_NLATTR_STRZ_OF(str) SZ_NLATTR_DATA_OF(strlen(str) + 1)

#define PTOI_TABLE_SZ_MAX(dev) (mlx5_dev_to_port_id((dev)->device, NULL, 0) + 2)

/** DPDK port to network interface index (ifindex) conversion. */
struct flow_tcf_ptoi {
	uint16_t port_id; /**< DPDK port ID. */
	unsigned int ifindex; /**< Network interface index. */
};

/* Due to a limitation on driver/FW. */
#define MLX5_TCF_GROUP_ID_MAX 3

/*
 * Due to a limitation on driver/FW, priority ranges from 1 to 16 in kernel.
 * Priority in rte_flow attribute starts from 0 and is added by 1 in
 * translation. This is subject to be changed to determine the max priority
 * based on trial-and-error like Verbs driver once the restriction is lifted or
 * the range is extended.
 */
#define MLX5_TCF_GROUP_PRIORITY_MAX 15

#define MLX5_TCF_FATE_ACTIONS \
	(MLX5_FLOW_ACTION_DROP | MLX5_FLOW_ACTION_PORT_ID | \
	 MLX5_FLOW_ACTION_JUMP)

#define MLX5_TCF_VLAN_ACTIONS \
	(MLX5_FLOW_ACTION_OF_POP_VLAN | MLX5_FLOW_ACTION_OF_PUSH_VLAN | \
	 MLX5_FLOW_ACTION_OF_SET_VLAN_VID | MLX5_FLOW_ACTION_OF_SET_VLAN_PCP)

#define MLX5_TCF_VXLAN_ACTIONS \
	(MLX5_FLOW_ACTION_VXLAN_ENCAP | MLX5_FLOW_ACTION_VXLAN_DECAP)

#define MLX5_TCF_PEDIT_ACTIONS \
	(MLX5_FLOW_ACTION_SET_IPV4_SRC | MLX5_FLOW_ACTION_SET_IPV4_DST | \
	 MLX5_FLOW_ACTION_SET_IPV6_SRC | MLX5_FLOW_ACTION_SET_IPV6_DST | \
	 MLX5_FLOW_ACTION_SET_TP_SRC | MLX5_FLOW_ACTION_SET_TP_DST | \
	 MLX5_FLOW_ACTION_SET_TTL | MLX5_FLOW_ACTION_DEC_TTL | \
	 MLX5_FLOW_ACTION_SET_MAC_SRC | MLX5_FLOW_ACTION_SET_MAC_DST)

#define MLX5_TCF_CONFIG_ACTIONS \
	(MLX5_FLOW_ACTION_PORT_ID | MLX5_FLOW_ACTION_JUMP | \
	 MLX5_FLOW_ACTION_OF_PUSH_VLAN | MLX5_FLOW_ACTION_OF_SET_VLAN_VID | \
	 MLX5_FLOW_ACTION_OF_SET_VLAN_PCP | \
	 (MLX5_TCF_PEDIT_ACTIONS & ~MLX5_FLOW_ACTION_DEC_TTL))

#define MAX_PEDIT_KEYS 128
#define SZ_PEDIT_KEY_VAL 4

#define NUM_OF_PEDIT_KEYS(sz) \
	(((sz) / SZ_PEDIT_KEY_VAL) + (((sz) % SZ_PEDIT_KEY_VAL) ? 1 : 0))

struct pedit_key_ex {
	enum pedit_header_type htype;
	enum pedit_cmd cmd;
};

struct pedit_parser {
	struct tc_pedit_sel sel;
	struct tc_pedit_key keys[MAX_PEDIT_KEYS];
	struct pedit_key_ex keys_ex[MAX_PEDIT_KEYS];
};

/**
 * Create space for using the implicitly created TC flow counter.
 *
 * @param[in] dev
 *   Pointer to the Ethernet device structure.
 *
 * @return
 *   A pointer to the counter data structure, NULL otherwise and
 *   rte_errno is set.
 */
static struct mlx5_flow_counter *
flow_tcf_counter_new(void)
{
	struct mlx5_flow_counter *cnt;

	/*
	 * eswitch counter cannot be shared and its id is unknown.
	 * currently returning all with id 0.
	 * in the future maybe better to switch to unique numbers.
	 */
	struct mlx5_flow_counter tmpl = {
		.ref_cnt = 1,
	};
	cnt = rte_calloc(__func__, 1, sizeof(*cnt), 0);
	if (!cnt) {
		rte_errno = ENOMEM;
		return NULL;
	}
	*cnt = tmpl;
	/* Implicit counter, do not add to list. */
	return cnt;
}

/**
 * Set pedit key of MAC address
 *
 * @param[in] actions
 *   pointer to action specification
 * @param[in,out] p_parser
 *   pointer to pedit_parser
 */
static void
flow_tcf_pedit_key_set_mac(const struct rte_flow_action *actions,
			   struct pedit_parser *p_parser)
{
	int idx = p_parser->sel.nkeys;
	uint32_t off = actions->type == RTE_FLOW_ACTION_TYPE_SET_MAC_SRC ?
					offsetof(struct ether_hdr, s_addr) :
					offsetof(struct ether_hdr, d_addr);
	const struct rte_flow_action_set_mac *conf =
		(const struct rte_flow_action_set_mac *)actions->conf;

	p_parser->keys[idx].off = off;
	p_parser->keys[idx].mask = ~UINT32_MAX;
	p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_ETH;
	p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
	memcpy(&p_parser->keys[idx].val,
		conf->mac_addr, SZ_PEDIT_KEY_VAL);
	idx++;
	p_parser->keys[idx].off = off + SZ_PEDIT_KEY_VAL;
	p_parser->keys[idx].mask = 0xFFFF0000;
	p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_ETH;
	p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
	memcpy(&p_parser->keys[idx].val,
		conf->mac_addr + SZ_PEDIT_KEY_VAL,
		ETHER_ADDR_LEN - SZ_PEDIT_KEY_VAL);
	p_parser->sel.nkeys = (++idx);
}

/**
 * Set pedit key of decrease/set ttl
 *
 * @param[in] actions
 *   pointer to action specification
 * @param[in,out] p_parser
 *   pointer to pedit_parser
 * @param[in] item_flags
 *   flags of all items presented
 */
static void
flow_tcf_pedit_key_set_dec_ttl(const struct rte_flow_action *actions,
				struct pedit_parser *p_parser,
				uint64_t item_flags)
{
	int idx = p_parser->sel.nkeys;

	p_parser->keys[idx].mask = 0xFFFFFF00;
	if (item_flags & MLX5_FLOW_LAYER_OUTER_L3_IPV4) {
		p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_IP4;
		p_parser->keys[idx].off =
			offsetof(struct ipv4_hdr, time_to_live);
	}
	if (item_flags & MLX5_FLOW_LAYER_OUTER_L3_IPV6) {
		p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_IP6;
		p_parser->keys[idx].off =
			offsetof(struct ipv6_hdr, hop_limits);
	}
	if (actions->type == RTE_FLOW_ACTION_TYPE_DEC_TTL) {
		p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_ADD;
		p_parser->keys[idx].val = 0x000000FF;
	} else {
		p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
		p_parser->keys[idx].val =
			(__u32)((const struct rte_flow_action_set_ttl *)
			 actions->conf)->ttl_value;
	}
	p_parser->sel.nkeys = (++idx);
}

/**
 * Set pedit key of transport (TCP/UDP) port value
 *
 * @param[in] actions
 *   pointer to action specification
 * @param[in,out] p_parser
 *   pointer to pedit_parser
 * @param[in] item_flags
 *   flags of all items presented
 */
static void
flow_tcf_pedit_key_set_tp_port(const struct rte_flow_action *actions,
				struct pedit_parser *p_parser,
				uint64_t item_flags)
{
	int idx = p_parser->sel.nkeys;

	if (item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP)
		p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_UDP;
	if (item_flags & MLX5_FLOW_LAYER_OUTER_L4_TCP)
		p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_TCP;
	p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
	/* offset of src/dst port is same for TCP and UDP */
	p_parser->keys[idx].off =
		actions->type == RTE_FLOW_ACTION_TYPE_SET_TP_SRC ?
		offsetof(struct tcp_hdr, src_port) :
		offsetof(struct tcp_hdr, dst_port);
	p_parser->keys[idx].mask = 0xFFFF0000;
	p_parser->keys[idx].val =
		(__u32)((const struct rte_flow_action_set_tp *)
				actions->conf)->port;
	p_parser->sel.nkeys = (++idx);
}

/**
 * Set pedit key of ipv6 address
 *
 * @param[in] actions
 *   pointer to action specification
 * @param[in,out] p_parser
 *   pointer to pedit_parser
 */
static void
flow_tcf_pedit_key_set_ipv6_addr(const struct rte_flow_action *actions,
				 struct pedit_parser *p_parser)
{
	int idx = p_parser->sel.nkeys;
	int keys = NUM_OF_PEDIT_KEYS(IPV6_ADDR_LEN);
	int off_base =
		actions->type == RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC ?
		offsetof(struct ipv6_hdr, src_addr) :
		offsetof(struct ipv6_hdr, dst_addr);
	const struct rte_flow_action_set_ipv6 *conf =
		(const struct rte_flow_action_set_ipv6 *)actions->conf;

	for (int i = 0; i < keys; i++, idx++) {
		p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_IP6;
		p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
		p_parser->keys[idx].off = off_base + i * SZ_PEDIT_KEY_VAL;
		p_parser->keys[idx].mask = ~UINT32_MAX;
		memcpy(&p_parser->keys[idx].val,
			conf->ipv6_addr + i *  SZ_PEDIT_KEY_VAL,
			SZ_PEDIT_KEY_VAL);
	}
	p_parser->sel.nkeys += keys;
}

/**
 * Set pedit key of ipv4 address
 *
 * @param[in] actions
 *   pointer to action specification
 * @param[in,out] p_parser
 *   pointer to pedit_parser
 */
static void
flow_tcf_pedit_key_set_ipv4_addr(const struct rte_flow_action *actions,
				 struct pedit_parser *p_parser)
{
	int idx = p_parser->sel.nkeys;

	p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_IP4;
	p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
	p_parser->keys[idx].off =
		actions->type == RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC ?
		offsetof(struct ipv4_hdr, src_addr) :
		offsetof(struct ipv4_hdr, dst_addr);
	p_parser->keys[idx].mask = ~UINT32_MAX;
	p_parser->keys[idx].val =
		((const struct rte_flow_action_set_ipv4 *)
		 actions->conf)->ipv4_addr;
	p_parser->sel.nkeys = (++idx);
}

/**
 * Create the pedit's na attribute in netlink message
 * on pre-allocate message buffer
 *
 * @param[in,out] nl
 *   pointer to pre-allocated netlink message buffer
 * @param[in,out] actions
 *   pointer to pointer of actions specification.
 * @param[in,out] action_flags
 *   pointer to actions flags
 * @param[in] item_flags
 *   flags of all item presented
 */
static void
flow_tcf_create_pedit_mnl_msg(struct nlmsghdr *nl,
			      const struct rte_flow_action **actions,
			      uint64_t item_flags)
{
	struct pedit_parser p_parser;
	struct nlattr *na_act_options;
	struct nlattr *na_pedit_keys;

	memset(&p_parser, 0, sizeof(p_parser));
	mnl_attr_put_strz(nl, TCA_ACT_KIND, "pedit");
	na_act_options = mnl_attr_nest_start(nl, TCA_ACT_OPTIONS);
	/* all modify header actions should be in one tc-pedit action */
	for (; (*actions)->type != RTE_FLOW_ACTION_TYPE_END; (*actions)++) {
		switch ((*actions)->type) {
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
			flow_tcf_pedit_key_set_ipv4_addr(*actions, &p_parser);
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
			flow_tcf_pedit_key_set_ipv6_addr(*actions, &p_parser);
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
			flow_tcf_pedit_key_set_tp_port(*actions,
							&p_parser, item_flags);
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TTL:
		case RTE_FLOW_ACTION_TYPE_DEC_TTL:
			flow_tcf_pedit_key_set_dec_ttl(*actions,
							&p_parser, item_flags);
			break;
		case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
			flow_tcf_pedit_key_set_mac(*actions, &p_parser);
			break;
		default:
			goto pedit_mnl_msg_done;
		}
	}
pedit_mnl_msg_done:
	p_parser.sel.action = TC_ACT_PIPE;
	mnl_attr_put(nl, TCA_PEDIT_PARMS_EX,
		     sizeof(p_parser.sel) +
		     p_parser.sel.nkeys * sizeof(struct tc_pedit_key),
		     &p_parser);
	na_pedit_keys =
		mnl_attr_nest_start(nl, TCA_PEDIT_KEYS_EX | NLA_F_NESTED);
	for (int i = 0; i < p_parser.sel.nkeys; i++) {
		struct nlattr *na_pedit_key =
			mnl_attr_nest_start(nl,
					    TCA_PEDIT_KEY_EX | NLA_F_NESTED);
		mnl_attr_put_u16(nl, TCA_PEDIT_KEY_EX_HTYPE,
				 p_parser.keys_ex[i].htype);
		mnl_attr_put_u16(nl, TCA_PEDIT_KEY_EX_CMD,
				 p_parser.keys_ex[i].cmd);
		mnl_attr_nest_end(nl, na_pedit_key);
	}
	mnl_attr_nest_end(nl, na_pedit_keys);
	mnl_attr_nest_end(nl, na_act_options);
	(*actions)--;
}

/**
 * Calculate max memory size of one TC-pedit actions.
 * One TC-pedit action can contain set of keys each defining
 * a rewrite element (rte_flow action)
 *
 * @param[in,out] actions
 *   actions specification.
 * @param[in,out] action_flags
 *   actions flags
 * @param[in,out] size
 *   accumulated size
 * @return
 *   Max memory size of one TC-pedit action
 */
static int
flow_tcf_get_pedit_actions_size(const struct rte_flow_action **actions,
				uint64_t *action_flags)
{
	int pedit_size = 0;
	int keys = 0;
	uint64_t flags = 0;

	pedit_size += SZ_NLATTR_NEST + /* na_act_index. */
		      SZ_NLATTR_STRZ_OF("pedit") +
		      SZ_NLATTR_NEST; /* TCA_ACT_OPTIONS. */
	for (; (*actions)->type != RTE_FLOW_ACTION_TYPE_END; (*actions)++) {
		switch ((*actions)->type) {
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
			keys += NUM_OF_PEDIT_KEYS(IPV4_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_IPV4_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
			keys += NUM_OF_PEDIT_KEYS(IPV4_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_IPV4_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
			keys += NUM_OF_PEDIT_KEYS(IPV6_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_IPV6_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
			keys += NUM_OF_PEDIT_KEYS(IPV6_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_IPV6_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
			/* TCP is as same as UDP */
			keys += NUM_OF_PEDIT_KEYS(TP_PORT_LEN);
			flags |= MLX5_FLOW_ACTION_SET_TP_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
			/* TCP is as same as UDP */
			keys += NUM_OF_PEDIT_KEYS(TP_PORT_LEN);
			flags |= MLX5_FLOW_ACTION_SET_TP_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TTL:
			keys += NUM_OF_PEDIT_KEYS(TTL_LEN);
			flags |= MLX5_FLOW_ACTION_SET_TTL;
			break;
		case RTE_FLOW_ACTION_TYPE_DEC_TTL:
			keys += NUM_OF_PEDIT_KEYS(TTL_LEN);
			flags |= MLX5_FLOW_ACTION_DEC_TTL;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
			keys += NUM_OF_PEDIT_KEYS(ETHER_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_MAC_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
			keys += NUM_OF_PEDIT_KEYS(ETHER_ADDR_LEN);
			flags |= MLX5_FLOW_ACTION_SET_MAC_DST;
			break;
		default:
			goto get_pedit_action_size_done;
		}
	}
get_pedit_action_size_done:
	/* TCA_PEDIT_PARAMS_EX */
	pedit_size +=
		SZ_NLATTR_DATA_OF(sizeof(struct tc_pedit_sel) +
				  keys * sizeof(struct tc_pedit_key));
	pedit_size += SZ_NLATTR_NEST; /* TCA_PEDIT_KEYS */
	pedit_size += keys *
		      /* TCA_PEDIT_KEY_EX + HTYPE + CMD */
		      (SZ_NLATTR_NEST + SZ_NLATTR_DATA_OF(2) +
		       SZ_NLATTR_DATA_OF(2));
	(*action_flags) |= flags;
	(*actions)--;
	return pedit_size;
}

/**
 * Retrieve mask for pattern item.
 *
 * This function does basic sanity checks on a pattern item in order to
 * return the most appropriate mask for it.
 *
 * @param[in] item
 *   Item specification.
 * @param[in] mask_default
 *   Default mask for pattern item as specified by the flow API.
 * @param[in] mask_supported
 *   Mask fields supported by the implementation.
 * @param[in] mask_empty
 *   Empty mask to return when there is no specification.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   Either @p item->mask or one of the mask parameters on success, NULL
 *   otherwise and rte_errno is set.
 */
static const void *
flow_tcf_item_mask(const struct rte_flow_item *item, const void *mask_default,
		   const void *mask_supported, const void *mask_empty,
		   size_t mask_size, struct rte_flow_error *error)
{
	const uint8_t *mask;
	size_t i;

	/* item->last and item->mask cannot exist without item->spec. */
	if (!item->spec && (item->mask || item->last)) {
		rte_flow_error_set(error, EINVAL,
				   RTE_FLOW_ERROR_TYPE_ITEM, item,
				   "\"mask\" or \"last\" field provided without"
				   " a corresponding \"spec\"");
		return NULL;
	}
	/* No spec, no mask, no problem. */
	if (!item->spec)
		return mask_empty;
	mask = item->mask ? item->mask : mask_default;
	assert(mask);
	/*
	 * Single-pass check to make sure that:
	 * - Mask is supported, no bits are set outside mask_supported.
	 * - Both item->spec and item->last are included in mask.
	 */
	for (i = 0; i != mask_size; ++i) {
		if (!mask[i])
			continue;
		if ((mask[i] | ((const uint8_t *)mask_supported)[i]) !=
		    ((const uint8_t *)mask_supported)[i]) {
			rte_flow_error_set(error, ENOTSUP,
					   RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					   "unsupported field found"
					   " in \"mask\"");
			return NULL;
		}
		if (item->last &&
		    (((const uint8_t *)item->spec)[i] & mask[i]) !=
		    (((const uint8_t *)item->last)[i] & mask[i])) {
			rte_flow_error_set(error, EINVAL,
					   RTE_FLOW_ERROR_TYPE_ITEM_LAST,
					   item->last,
					   "range between \"spec\" and \"last\""
					   " not comprised in \"mask\"");
			return NULL;
		}
	}
	return mask;
}

/**
 * Build a conversion table between port ID and ifindex.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[out] ptoi
 *   Pointer to ptoi table.
 * @param[in] len
 *   Size of ptoi table provided.
 *
 * @return
 *   Size of ptoi table filled.
 */
static unsigned int
flow_tcf_build_ptoi_table(struct rte_eth_dev *dev, struct flow_tcf_ptoi *ptoi,
			  unsigned int len)
{
	unsigned int n = mlx5_dev_to_port_id(dev->device, NULL, 0);
	uint16_t port_id[n + 1];
	unsigned int i;
	unsigned int own = 0;

	/* At least one port is needed when no switch domain is present. */
	if (!n) {
		n = 1;
		port_id[0] = dev->data->port_id;
	} else {
		n = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, n), n);
	}
	if (n > len)
		return 0;
	for (i = 0; i != n; ++i) {
		struct rte_eth_dev_info dev_info;

		rte_eth_dev_info_get(port_id[i], &dev_info);
		if (port_id[i] == dev->data->port_id)
			own = i;
		ptoi[i].port_id = port_id[i];
		ptoi[i].ifindex = dev_info.if_index;
	}
	/* Ensure first entry of ptoi[] is the current device. */
	if (own) {
		ptoi[n] = ptoi[0];
		ptoi[0] = ptoi[own];
		ptoi[own] = ptoi[n];
	}
	/* An entry with zero ifindex terminates ptoi[]. */
	ptoi[n].port_id = 0;
	ptoi[n].ifindex = 0;
	return n;
}

/**
 * Verify the @p attr will be correctly understood by the E-switch.
 *
 * @param[in] attr
 *   Pointer to flow attributes
 * @param[out] error
 *   Pointer to error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_validate_attributes(const struct rte_flow_attr *attr,
			     struct rte_flow_error *error)
{
	/*
	 * Supported attributes: groups, some priorities and ingress only.
	 * group is supported only if kernel supports chain. Don't care about
	 * transfer as it is the caller's problem.
	 */
	if (attr->group > MLX5_TCF_GROUP_ID_MAX)
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ATTR_GROUP, attr,
					  "group ID larger than "
					  RTE_STR(MLX5_TCF_GROUP_ID_MAX)
					  " isn't supported");
	else if (attr->priority > MLX5_TCF_GROUP_PRIORITY_MAX)
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
					  attr,
					  "priority more than "
					  RTE_STR(MLX5_TCF_GROUP_PRIORITY_MAX)
					  " is not supported");
	if (!attr->ingress)
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
					  attr, "only ingress is supported");
	if (attr->egress)
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
					  attr, "egress is not supported");
	return 0;
}

/**
 * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_ETH item for E-Switch.
 * The routine checks the L2 fields to be used in encapsulation header.
 *
 * @param[in] item
 *   Pointer to the item structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 **/
static int
flow_tcf_validate_vxlan_encap_eth(const struct rte_flow_item *item,
				  struct rte_flow_error *error)
{
	const struct rte_flow_item_eth *spec = item->spec;
	const struct rte_flow_item_eth *mask = item->mask;

	if (!spec) {
		/*
		 * Specification for L2 addresses can be empty
		 * because these ones are optional and not
		 * required directly by tc rule. Kernel tries
		 * to resolve these ones on its own
		 */
		return 0;
	}
	if (!mask) {
		/* If mask is not specified use the default one. */
		mask = &rte_flow_item_eth_mask;
	}
	if (memcmp(&mask->dst,
		   &flow_tcf_mask_empty.eth.dst,
		   sizeof(flow_tcf_mask_empty.eth.dst))) {
		if (memcmp(&mask->dst,
			   &rte_flow_item_eth_mask.dst,
			   sizeof(rte_flow_item_eth_mask.dst)))
			return rte_flow_error_set
				(error, ENOTSUP,
				 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
				 "no support for partial mask on"
				 " \"eth.dst\" field");
	}
	if (memcmp(&mask->src,
		   &flow_tcf_mask_empty.eth.src,
		   sizeof(flow_tcf_mask_empty.eth.src))) {
		if (memcmp(&mask->src,
			   &rte_flow_item_eth_mask.src,
			   sizeof(rte_flow_item_eth_mask.src)))
			return rte_flow_error_set
				(error, ENOTSUP,
				 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
				 "no support for partial mask on"
				 " \"eth.src\" field");
	}
	if (mask->type != RTE_BE16(0x0000)) {
		if (mask->type != RTE_BE16(0xffff))
			return rte_flow_error_set
				(error, ENOTSUP,
				 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
				 "no support for partial mask on"
				 " \"eth.type\" field");
		DRV_LOG(WARNING,
			"outer ethernet type field"
			" cannot be forced for vxlan"
			" encapsulation, parameter ignored");
	}
	return 0;
}

/**
 * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_IPV4 item for E-Switch.
 * The routine checks the IPv4 fields to be used in encapsulation header.
 *
 * @param[in] item
 *   Pointer to the item structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 **/
static int
flow_tcf_validate_vxlan_encap_ipv4(const struct rte_flow_item *item,
				   struct rte_flow_error *error)
{
	const struct rte_flow_item_ipv4 *spec = item->spec;
	const struct rte_flow_item_ipv4 *mask = item->mask;

	if (!spec) {
		/*
		 * Specification for IP addresses cannot be empty
		 * because it is required by tunnel_key parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "NULL outer ipv4 address"
					  " specification for vxlan"
					  " encapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_ipv4_mask;
	if (mask->hdr.dst_addr != RTE_BE32(0x00000000)) {
		if (mask->hdr.dst_addr != RTE_BE32(0xffffffff))
			return rte_flow_error_set
				(error, ENOTSUP,
				 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
				 "no support for partial mask on"
				 " \"ipv4.hdr.dst_addr\" field"
				 " for vxlan encapsulation");
		/* More IPv4 address validations can be put here. */
	} else {
		/*
		 * Kernel uses the destination IP address to determine
		 * the routing path and obtain the MAC destination
		 * address, so IP destination address must be
		 * specified in the tc rule.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer ipv4 destination address"
					  " must be specified for"
					  " vxlan encapsulation");
	}
	if (mask->hdr.src_addr != RTE_BE32(0x00000000)) {
		if (mask->hdr.src_addr != RTE_BE32(0xffffffff))
			return rte_flow_error_set
				(error, ENOTSUP,
				 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
				 "no support for partial mask on"
				 " \"ipv4.hdr.src_addr\" field"
				 " for vxlan encapsulation");
		/* More IPv4 address validations can be put here. */
	} else {
		/*
		 * Kernel uses the source IP address to select the
		 * interface for egress encapsulated traffic, so
		 * it must be specified in the tc rule.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer ipv4 source address"
					  " must be specified for"
					  " vxlan encapsulation");
	}
	return 0;
}

/**
 * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_IPV6 item for E-Switch.
 * The routine checks the IPv6 fields to be used in encapsulation header.
 *
 * @param[in] item
 *   Pointer to the item structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_encap_ipv6(const struct rte_flow_item *item,
				   struct rte_flow_error *error)
{
	const struct rte_flow_item_ipv6 *spec = item->spec;
	const struct rte_flow_item_ipv6 *mask = item->mask;

	if (!spec) {
		/*
		 * Specification for IP addresses cannot be empty
		 * because it is required by tunnel_key parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "NULL outer ipv6 address"
					  " specification for"
					  " vxlan encapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_ipv6_mask;
	if (memcmp(&mask->hdr.dst_addr,
		   &flow_tcf_mask_empty.ipv6.hdr.dst_addr,
		   IPV6_ADDR_LEN)) {
		if (memcmp(&mask->hdr.dst_addr,
			   &rte_flow_item_ipv6_mask.hdr.dst_addr,
			   IPV6_ADDR_LEN))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"ipv6.hdr.dst_addr\" field"
					 " for vxlan encapsulation");
		/* More IPv6 address validations can be put here. */
	} else {
		/*
		 * Kernel uses the destination IP address to determine
		 * the routing path and obtain the MAC destination
		 * address (heigh or gate), so IP destination address
		 * must be specified within the tc rule.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer ipv6 destination address"
					  " must be specified for"
					  " vxlan encapsulation");
	}
	if (memcmp(&mask->hdr.src_addr,
		   &flow_tcf_mask_empty.ipv6.hdr.src_addr,
		   IPV6_ADDR_LEN)) {
		if (memcmp(&mask->hdr.src_addr,
			   &rte_flow_item_ipv6_mask.hdr.src_addr,
			   IPV6_ADDR_LEN))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"ipv6.hdr.src_addr\" field"
					 " for vxlan encapsulation");
		/* More L3 address validation can be put here. */
	} else {
		/*
		 * Kernel uses the source IP address to select the
		 * interface for egress encapsulated traffic, so
		 * it must be specified in the tc rule.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer L3 source address"
					  " must be specified for"
					  " vxlan encapsulation");
	}
	return 0;
}

/**
 * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_UDP item for E-Switch.
 * The routine checks the UDP fields to be used in encapsulation header.
 *
 * @param[in] item
 *   Pointer to the item structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_encap_udp(const struct rte_flow_item *item,
				  struct rte_flow_error *error)
{
	const struct rte_flow_item_udp *spec = item->spec;
	const struct rte_flow_item_udp *mask = item->mask;

	if (!spec) {
		/*
		 * Specification for UDP ports cannot be empty
		 * because it is required by tunnel_key parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "NULL UDP port specification "
					  " for vxlan encapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_udp_mask;
	if (mask->hdr.dst_port != RTE_BE16(0x0000)) {
		if (mask->hdr.dst_port != RTE_BE16(0xffff))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"udp.hdr.dst_port\" field"
					 " for vxlan encapsulation");
		if (!spec->hdr.dst_port)
			return rte_flow_error_set
					(error, EINVAL,
					 RTE_FLOW_ERROR_TYPE_ITEM, item,
					 "outer UDP remote port cannot be"
					 " 0 for vxlan encapsulation");
	} else {
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer UDP remote port"
					  " must be specified for"
					  " vxlan encapsulation");
	}
	if (mask->hdr.src_port != RTE_BE16(0x0000)) {
		if (mask->hdr.src_port != RTE_BE16(0xffff))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"udp.hdr.src_port\" field"
					 " for vxlan encapsulation");
		DRV_LOG(WARNING,
			"outer UDP source port cannot be"
			" forced for vxlan encapsulation,"
			" parameter ignored");
	}
	return 0;
}

/**
 * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_VXLAN item for E-Switch.
 * The routine checks the VNIP fields to be used in encapsulation header.
 *
 * @param[in] item
 *   Pointer to the item structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_encap_vni(const struct rte_flow_item *item,
				  struct rte_flow_error *error)
{
	const struct rte_flow_item_vxlan *spec = item->spec;
	const struct rte_flow_item_vxlan *mask = item->mask;

	if (!spec) {
		/* Outer VNI is required by tunnel_key parameter. */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "NULL VNI specification"
					  " for vxlan encapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_vxlan_mask;
	if (!mask->vni[0] && !mask->vni[1] && !mask->vni[2])
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "outer VNI must be specified "
					  "for vxlan encapsulation");
	if (mask->vni[0] != 0xff ||
	    mask->vni[1] != 0xff ||
	    mask->vni[2] != 0xff)
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					  "no support for partial mask on"
					  " \"vxlan.vni\" field");

	if (!spec->vni[0] && !spec->vni[1] && !spec->vni[2])
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, item,
					  "vxlan vni cannot be 0");
	return 0;
}

/**
 * Validate VXLAN_ENCAP action item list for E-Switch.
 * The routine checks items to be used in encapsulation header.
 *
 * @param[in] action
 *   Pointer to the VXLAN_ENCAP action structure.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_encap(const struct rte_flow_action *action,
			      struct rte_flow_error *error)
{
	const struct rte_flow_item *items;
	int ret;
	uint32_t item_flags = 0;

	if (!action->conf)
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, action,
					  "Missing vxlan tunnel"
					  " action configuration");
	items = ((const struct rte_flow_action_vxlan_encap *)
					action->conf)->definition;
	if (!items)
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, action,
					  "Missing vxlan tunnel"
					  " encapsulation parameters");
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			ret = mlx5_flow_validate_item_eth(items, item_flags,
							  error);
			if (ret < 0)
				return ret;
			ret = flow_tcf_validate_vxlan_encap_eth(items, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L2;
			break;
		break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			ret = mlx5_flow_validate_item_ipv4(items, item_flags,
							   error);
			if (ret < 0)
				return ret;
			ret = flow_tcf_validate_vxlan_encap_ipv4(items, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			ret = mlx5_flow_validate_item_ipv6(items, item_flags,
							   error);
			if (ret < 0)
				return ret;
			ret = flow_tcf_validate_vxlan_encap_ipv6(items, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
			break;
		case RTE_FLOW_ITEM_TYPE_UDP:
			ret = mlx5_flow_validate_item_udp(items, item_flags,
							   0xFF, error);
			if (ret < 0)
				return ret;
			ret = flow_tcf_validate_vxlan_encap_udp(items, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
			break;
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			ret = mlx5_flow_validate_item_vxlan(items,
							    item_flags, error);
			if (ret < 0)
				return ret;
			ret = flow_tcf_validate_vxlan_encap_vni(items, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_VXLAN;
			break;
		default:
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM, items,
					 "vxlan encap item not supported");
		}
	}
	if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3))
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, action,
					  "no outer IP layer found"
					  " for vxlan encapsulation");
	if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, action,
					  "no outer UDP layer found"
					  " for vxlan encapsulation");
	if (!(item_flags & MLX5_FLOW_LAYER_VXLAN))
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, action,
					  "no VXLAN VNI found"
					  " for vxlan encapsulation");
	return 0;
}

/**
 * Validate RTE_FLOW_ITEM_TYPE_IPV4 item if VXLAN_DECAP action
 * is present in actions list.
 *
 * @param[in] ipv4
 *   Outer IPv4 address item (if any, NULL otherwise).
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_decap_ipv4(const struct rte_flow_item *ipv4,
				   struct rte_flow_error *error)
{
	const struct rte_flow_item_ipv4 *spec = ipv4->spec;
	const struct rte_flow_item_ipv4 *mask = ipv4->mask;

	if (!spec) {
		/*
		 * Specification for IP addresses cannot be empty
		 * because it is required as decap parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, ipv4,
					  "NULL outer ipv4 address"
					  " specification for vxlan"
					  " for vxlan decapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_ipv4_mask;
	if (mask->hdr.dst_addr != RTE_BE32(0x00000000)) {
		if (mask->hdr.dst_addr != RTE_BE32(0xffffffff))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"ipv4.hdr.dst_addr\" field");
		/* More IP address validations can be put here. */
	} else {
		/*
		 * Kernel uses the destination IP address
		 * to determine the ingress network interface
		 * for traffic being decapsulated.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, ipv4,
					  "outer ipv4 destination address"
					  " must be specified for"
					  " vxlan decapsulation");
	}
	/* Source IP address is optional for decap. */
	if (mask->hdr.src_addr != RTE_BE32(0x00000000) &&
	    mask->hdr.src_addr != RTE_BE32(0xffffffff))
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					  "no support for partial mask on"
					  " \"ipv4.hdr.src_addr\" field");
	return 0;
}

/**
 * Validate RTE_FLOW_ITEM_TYPE_IPV6 item if VXLAN_DECAP action
 * is present in actions list.
 *
 * @param[in] ipv6
 *   Outer IPv6 address item (if any, NULL otherwise).
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_decap_ipv6(const struct rte_flow_item *ipv6,
				   struct rte_flow_error *error)
{
	const struct rte_flow_item_ipv6 *spec = ipv6->spec;
	const struct rte_flow_item_ipv6 *mask = ipv6->mask;

	if (!spec) {
		/*
		 * Specification for IP addresses cannot be empty
		 * because it is required as decap parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, ipv6,
					  "NULL outer ipv6 address"
					  " specification for vxlan"
					  " decapsulation");
	}
	if (!mask)
		mask = &rte_flow_item_ipv6_mask;
	if (memcmp(&mask->hdr.dst_addr,
		   &flow_tcf_mask_empty.ipv6.hdr.dst_addr,
		   IPV6_ADDR_LEN)) {
		if (memcmp(&mask->hdr.dst_addr,
			&rte_flow_item_ipv6_mask.hdr.dst_addr,
			IPV6_ADDR_LEN))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"ipv6.hdr.dst_addr\" field");
		/* More IP address validations can be put here. */
	} else {
		/*
		 * Kernel uses the destination IP address
		 * to determine the ingress network interface
		 * for traffic being decapsulated.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, ipv6,
					  "outer ipv6 destination address must be "
					  "specified for vxlan decapsulation");
	}
	/* Source IP address is optional for decap. */
	if (memcmp(&mask->hdr.src_addr,
		   &flow_tcf_mask_empty.ipv6.hdr.src_addr,
		   IPV6_ADDR_LEN)) {
		if (memcmp(&mask->hdr.src_addr,
			   &rte_flow_item_ipv6_mask.hdr.src_addr,
			   IPV6_ADDR_LEN))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"ipv6.hdr.src_addr\" field");
	}
	return 0;
}

/**
 * Validate RTE_FLOW_ITEM_TYPE_UDP item if VXLAN_DECAP action
 * is present in actions list.
 *
 * @param[in] udp
 *   Outer UDP layer item (if any, NULL otherwise).
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 **/
static int
flow_tcf_validate_vxlan_decap_udp(const struct rte_flow_item *udp,
				  struct rte_flow_error *error)
{
	const struct rte_flow_item_udp *spec = udp->spec;
	const struct rte_flow_item_udp *mask = udp->mask;

	if (!spec)
		/*
		 * Specification for UDP ports cannot be empty
		 * because it is required as decap parameter.
		 */
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, udp,
					  "NULL UDP port specification"
					  " for VXLAN decapsulation");
	if (!mask)
		mask = &rte_flow_item_udp_mask;
	if (mask->hdr.dst_port != RTE_BE16(0x0000)) {
		if (mask->hdr.dst_port != RTE_BE16(0xffff))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"udp.hdr.dst_port\" field");
		if (!spec->hdr.dst_port)
			return rte_flow_error_set
					(error, EINVAL,
					 RTE_FLOW_ERROR_TYPE_ITEM, udp,
					 "zero decap local UDP port");
	} else {
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ITEM, udp,
					  "outer UDP destination port must be "
					  "specified for vxlan decapsulation");
	}
	if (mask->hdr.src_port != RTE_BE16(0x0000)) {
		if (mask->hdr.src_port != RTE_BE16(0xffff))
			return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
					 "no support for partial mask on"
					 " \"udp.hdr.src_port\" field");
		DRV_LOG(WARNING,
			"outer UDP local port cannot be "
			"forced for VXLAN encapsulation, "
			"parameter ignored");
	}
	return 0;
}

/**
 * Validate flow for E-Switch.
 *
 * @param[in] priv
 *   Pointer to the priv structure.
 * @param[in] attr
 *   Pointer to the flow attributes.
 * @param[in] items
 *   Pointer to the list of items.
 * @param[in] actions
 *   Pointer to the list of actions.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 */
static int
flow_tcf_validate(struct rte_eth_dev *dev,
		  const struct rte_flow_attr *attr,
		  const struct rte_flow_item items[],
		  const struct rte_flow_action actions[],
		  struct rte_flow_error *error)
{
	union {
		const struct rte_flow_item_port_id *port_id;
		const struct rte_flow_item_eth *eth;
		const struct rte_flow_item_vlan *vlan;
		const struct rte_flow_item_ipv4 *ipv4;
		const struct rte_flow_item_ipv6 *ipv6;
		const struct rte_flow_item_tcp *tcp;
		const struct rte_flow_item_udp *udp;
		const struct rte_flow_item_vxlan *vxlan;
	} spec, mask;
	union {
		const struct rte_flow_action_port_id *port_id;
		const struct rte_flow_action_jump *jump;
		const struct rte_flow_action_of_push_vlan *of_push_vlan;
		const struct rte_flow_action_of_set_vlan_vid *
			of_set_vlan_vid;
		const struct rte_flow_action_of_set_vlan_pcp *
			of_set_vlan_pcp;
		const struct rte_flow_action_vxlan_encap *vxlan_encap;
		const struct rte_flow_action_set_ipv4 *set_ipv4;
		const struct rte_flow_action_set_ipv6 *set_ipv6;
	} conf;
	uint64_t item_flags = 0;
	uint64_t action_flags = 0;
	uint8_t next_protocol = -1;
	unsigned int tcm_ifindex = 0;
	uint8_t pedit_validated = 0;
	struct flow_tcf_ptoi ptoi[PTOI_TABLE_SZ_MAX(dev)];
	struct rte_eth_dev *port_id_dev = NULL;
	bool in_port_id_set;
	int ret;

	claim_nonzero(flow_tcf_build_ptoi_table(dev, ptoi,
						PTOI_TABLE_SZ_MAX(dev)));
	ret = flow_tcf_validate_attributes(attr, error);
	if (ret < 0)
		return ret;
	for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
		unsigned int i;
		uint64_t current_action_flag = 0;

		switch (actions->type) {
		case RTE_FLOW_ACTION_TYPE_VOID:
			break;
		case RTE_FLOW_ACTION_TYPE_PORT_ID:
			current_action_flag = MLX5_FLOW_ACTION_PORT_ID;
			if (!actions->conf)
				break;
			conf.port_id = actions->conf;
			if (conf.port_id->original)
				i = 0;
			else
				for (i = 0; ptoi[i].ifindex; ++i)
					if (ptoi[i].port_id == conf.port_id->id)
						break;
			if (!ptoi[i].ifindex)
				return rte_flow_error_set
					(error, ENODEV,
					 RTE_FLOW_ERROR_TYPE_ACTION_CONF,
					 conf.port_id,
					 "missing data to convert port ID to"
					 " ifindex");
			port_id_dev = &rte_eth_devices[conf.port_id->id];
			break;
		case RTE_FLOW_ACTION_TYPE_JUMP:
			current_action_flag = MLX5_FLOW_ACTION_JUMP;
			if (!actions->conf)
				break;
			conf.jump = actions->conf;
			if (attr->group >= conf.jump->group)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ACTION,
					 actions,
					 "can jump only to a group forward");
			break;
		case RTE_FLOW_ACTION_TYPE_DROP:
			current_action_flag = MLX5_FLOW_ACTION_DROP;
			break;
		case RTE_FLOW_ACTION_TYPE_COUNT:
			break;
		case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
			current_action_flag = MLX5_FLOW_ACTION_OF_POP_VLAN;
			break;
		case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN: {
			rte_be16_t ethertype;

			current_action_flag = MLX5_FLOW_ACTION_OF_PUSH_VLAN;
			if (!actions->conf)
				break;
			conf.of_push_vlan = actions->conf;
			ethertype = conf.of_push_vlan->ethertype;
			if (ethertype != RTE_BE16(ETH_P_8021Q) &&
			    ethertype != RTE_BE16(ETH_P_8021AD))
				return rte_flow_error_set
					(error, EINVAL,
					 RTE_FLOW_ERROR_TYPE_ACTION, actions,
					 "vlan push TPID must be "
					 "802.1Q or 802.1AD");
			break;
		}
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
			if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ACTION, actions,
					 "vlan modify is not supported,"
					 " set action must follow push action");
			current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_VID;
			break;
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
			if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ACTION, actions,
					 "vlan modify is not supported,"
					 " set action must follow push action");
			current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_PCP;
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
			current_action_flag = MLX5_FLOW_ACTION_VXLAN_DECAP;
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
			ret = flow_tcf_validate_vxlan_encap(actions, error);
			if (ret < 0)
				return ret;
			current_action_flag = MLX5_FLOW_ACTION_VXLAN_ENCAP;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
			current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
			current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
			current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
			current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
			current_action_flag = MLX5_FLOW_ACTION_SET_TP_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
			current_action_flag = MLX5_FLOW_ACTION_SET_TP_DST;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_TTL:
			current_action_flag = MLX5_FLOW_ACTION_SET_TTL;
			break;
		case RTE_FLOW_ACTION_TYPE_DEC_TTL:
			current_action_flag = MLX5_FLOW_ACTION_DEC_TTL;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
			current_action_flag = MLX5_FLOW_ACTION_SET_MAC_SRC;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
			current_action_flag = MLX5_FLOW_ACTION_SET_MAC_DST;
			break;
		default:
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "action not supported");
		}
		if (current_action_flag & MLX5_TCF_CONFIG_ACTIONS) {
			if (!actions->conf)
				return rte_flow_error_set
					(error, EINVAL,
					 RTE_FLOW_ERROR_TYPE_ACTION_CONF,
					 actions,
					 "action configuration not set");
		}
		if ((current_action_flag & MLX5_TCF_PEDIT_ACTIONS) &&
		    pedit_validated)
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "set actions should be "
						  "listed successively");
		if ((current_action_flag & ~MLX5_TCF_PEDIT_ACTIONS) &&
		    (action_flags & MLX5_TCF_PEDIT_ACTIONS))
			pedit_validated = 1;
		if ((current_action_flag & MLX5_TCF_FATE_ACTIONS) &&
		    (action_flags & MLX5_TCF_FATE_ACTIONS))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "can't have multiple fate"
						  " actions");
		if ((current_action_flag & MLX5_TCF_VXLAN_ACTIONS) &&
		    (action_flags & MLX5_TCF_VXLAN_ACTIONS))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "can't have multiple vxlan"
						  " actions");
		if ((current_action_flag & MLX5_TCF_VXLAN_ACTIONS) &&
		    (action_flags & MLX5_TCF_VLAN_ACTIONS))
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "can't have vxlan and vlan"
						  " actions in the same rule");
		action_flags |= current_action_flag;
	}
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		unsigned int i;

		if ((item_flags & MLX5_FLOW_LAYER_TUNNEL) &&
		    items->type != RTE_FLOW_ITEM_TYPE_ETH)
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ITEM,
						  items,
						  "only L2 inner item"
						  " is supported");
		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_PORT_ID:
			mask.port_id = flow_tcf_item_mask
				(items, &rte_flow_item_port_id_mask,
				 &flow_tcf_mask_supported.port_id,
				 &flow_tcf_mask_empty.port_id,
				 sizeof(flow_tcf_mask_supported.port_id),
				 error);
			if (!mask.port_id)
				return -rte_errno;
			if (mask.port_id == &flow_tcf_mask_empty.port_id) {
				in_port_id_set = 1;
				break;
			}
			spec.port_id = items->spec;
			if (mask.port_id->id && mask.port_id->id != 0xffffffff)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.port_id,
					 "no support for partial mask on"
					 " \"id\" field");
			if (!mask.port_id->id)
				i = 0;
			else
				for (i = 0; ptoi[i].ifindex; ++i)
					if (ptoi[i].port_id == spec.port_id->id)
						break;
			if (!ptoi[i].ifindex)
				return rte_flow_error_set
					(error, ENODEV,
					 RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
					 spec.port_id,
					 "missing data to convert port ID to"
					 " ifindex");
			if (in_port_id_set && ptoi[i].ifindex != tcm_ifindex)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
					 spec.port_id,
					 "cannot match traffic for"
					 " several port IDs through"
					 " a single flow rule");
			tcm_ifindex = ptoi[i].ifindex;
			in_port_id_set = 1;
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			ret = mlx5_flow_validate_item_eth(items, item_flags,
							  error);
			if (ret < 0)
				return ret;
			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
					MLX5_FLOW_LAYER_INNER_L2 :
					MLX5_FLOW_LAYER_OUTER_L2;
			/* TODO:
			 * Redundant check due to different supported mask.
			 * Same for the rest of items.
			 */
			mask.eth = flow_tcf_item_mask
				(items, &rte_flow_item_eth_mask,
				 &flow_tcf_mask_supported.eth,
				 &flow_tcf_mask_empty.eth,
				 sizeof(flow_tcf_mask_supported.eth),
				 error);
			if (!mask.eth)
				return -rte_errno;
			if (mask.eth->type && mask.eth->type !=
			    RTE_BE16(0xffff))
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.eth,
					 "no support for partial mask on"
					 " \"type\" field");
			break;
		case RTE_FLOW_ITEM_TYPE_VLAN:
			ret = mlx5_flow_validate_item_vlan(items, item_flags,
							   error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_VLAN;
			mask.vlan = flow_tcf_item_mask
				(items, &rte_flow_item_vlan_mask,
				 &flow_tcf_mask_supported.vlan,
				 &flow_tcf_mask_empty.vlan,
				 sizeof(flow_tcf_mask_supported.vlan),
				 error);
			if (!mask.vlan)
				return -rte_errno;
			if ((mask.vlan->tci & RTE_BE16(0xe000) &&
			     (mask.vlan->tci & RTE_BE16(0xe000)) !=
			      RTE_BE16(0xe000)) ||
			    (mask.vlan->tci & RTE_BE16(0x0fff) &&
			     (mask.vlan->tci & RTE_BE16(0x0fff)) !=
			      RTE_BE16(0x0fff)) ||
			    (mask.vlan->inner_type &&
			     mask.vlan->inner_type != RTE_BE16(0xffff)))
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.vlan,
					 "no support for partial masks on"
					 " \"tci\" (PCP and VID parts) and"
					 " \"inner_type\" fields");
			break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			ret = mlx5_flow_validate_item_ipv4(items, item_flags,
							   error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
			mask.ipv4 = flow_tcf_item_mask
				(items, &rte_flow_item_ipv4_mask,
				 &flow_tcf_mask_supported.ipv4,
				 &flow_tcf_mask_empty.ipv4,
				 sizeof(flow_tcf_mask_supported.ipv4),
				 error);
			if (!mask.ipv4)
				return -rte_errno;
			if (mask.ipv4->hdr.next_proto_id &&
			    mask.ipv4->hdr.next_proto_id != 0xff)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.ipv4,
					 "no support for partial mask on"
					 " \"hdr.next_proto_id\" field");
			else if (mask.ipv4->hdr.next_proto_id)
				next_protocol =
					((const struct rte_flow_item_ipv4 *)
					 (items->spec))->hdr.next_proto_id;
			if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
				ret = flow_tcf_validate_vxlan_decap_ipv4
								(items, error);
				if (ret < 0)
					return ret;
			}
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			ret = mlx5_flow_validate_item_ipv6(items, item_flags,
							   error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
			mask.ipv6 = flow_tcf_item_mask
				(items, &rte_flow_item_ipv6_mask,
				 &flow_tcf_mask_supported.ipv6,
				 &flow_tcf_mask_empty.ipv6,
				 sizeof(flow_tcf_mask_supported.ipv6),
				 error);
			if (!mask.ipv6)
				return -rte_errno;
			if (mask.ipv6->hdr.proto &&
			    mask.ipv6->hdr.proto != 0xff)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.ipv6,
					 "no support for partial mask on"
					 " \"hdr.proto\" field");
			else if (mask.ipv6->hdr.proto)
				next_protocol =
					((const struct rte_flow_item_ipv6 *)
					 (items->spec))->hdr.proto;
			if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
				ret = flow_tcf_validate_vxlan_decap_ipv6
								(items, error);
				if (ret < 0)
					return ret;
			}
			break;
		case RTE_FLOW_ITEM_TYPE_UDP:
			ret = mlx5_flow_validate_item_udp(items, item_flags,
							  next_protocol, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
			mask.udp = flow_tcf_item_mask
				(items, &rte_flow_item_udp_mask,
				 &flow_tcf_mask_supported.udp,
				 &flow_tcf_mask_empty.udp,
				 sizeof(flow_tcf_mask_supported.udp),
				 error);
			if (!mask.udp)
				return -rte_errno;
			if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
				ret = flow_tcf_validate_vxlan_decap_udp
								(items, error);
				if (ret < 0)
					return ret;
			}
			break;
		case RTE_FLOW_ITEM_TYPE_TCP:
			ret = mlx5_flow_validate_item_tcp
					     (items, item_flags,
					      next_protocol,
					      &flow_tcf_mask_supported.tcp,
					      error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
			mask.tcp = flow_tcf_item_mask
				(items, &rte_flow_item_tcp_mask,
				 &flow_tcf_mask_supported.tcp,
				 &flow_tcf_mask_empty.tcp,
				 sizeof(flow_tcf_mask_supported.tcp),
				 error);
			if (!mask.tcp)
				return -rte_errno;
			break;
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			if (!(action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP))
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM,
					 items,
					 "vni pattern should be followed by"
					 " vxlan decapsulation action");
			ret = mlx5_flow_validate_item_vxlan(items,
							    item_flags, error);
			if (ret < 0)
				return ret;
			item_flags |= MLX5_FLOW_LAYER_VXLAN;
			mask.vxlan = flow_tcf_item_mask
				(items, &rte_flow_item_vxlan_mask,
				 &flow_tcf_mask_supported.vxlan,
				 &flow_tcf_mask_empty.vxlan,
				 sizeof(flow_tcf_mask_supported.vxlan), error);
			if (!mask.vxlan)
				return -rte_errno;
			if (mask.vxlan->vni[0] != 0xff ||
			    mask.vxlan->vni[1] != 0xff ||
			    mask.vxlan->vni[2] != 0xff)
				return rte_flow_error_set
					(error, ENOTSUP,
					 RTE_FLOW_ERROR_TYPE_ITEM_MASK,
					 mask.vxlan,
					 "no support for partial or "
					 "empty mask on \"vxlan.vni\" field");
			break;
		default:
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ITEM,
						  items, "item not supported");
		}
	}
	if ((action_flags & MLX5_TCF_PEDIT_ACTIONS) &&
	    (action_flags & MLX5_FLOW_ACTION_DROP))
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION,
					  actions,
					  "set action is not compatible with "
					  "drop action");
	if ((action_flags & MLX5_TCF_PEDIT_ACTIONS) &&
	    !(action_flags & MLX5_FLOW_ACTION_PORT_ID))
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION,
					  actions,
					  "set action must be followed by "
					  "port_id action");
	if (action_flags &
	   (MLX5_FLOW_ACTION_SET_IPV4_SRC | MLX5_FLOW_ACTION_SET_IPV4_DST)) {
		if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3_IPV4))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "no ipv4 item found in"
						  " pattern");
	}
	if (action_flags &
	   (MLX5_FLOW_ACTION_SET_IPV6_SRC | MLX5_FLOW_ACTION_SET_IPV6_DST)) {
		if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3_IPV6))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "no ipv6 item found in"
						  " pattern");
	}
	if (action_flags &
	   (MLX5_FLOW_ACTION_SET_TP_SRC | MLX5_FLOW_ACTION_SET_TP_DST)) {
		if (!(item_flags &
		     (MLX5_FLOW_LAYER_OUTER_L4_UDP |
		      MLX5_FLOW_LAYER_OUTER_L4_TCP)))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "no TCP/UDP item found in"
						  " pattern");
	}
	/*
	 * FW syndrome (0xA9C090):
	 *     set_flow_table_entry: push vlan action fte in fdb can ONLY be
	 *     forward to the uplink.
	 */
	if ((action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN) &&
	    (action_flags & MLX5_FLOW_ACTION_PORT_ID) &&
	    ((struct priv *)port_id_dev->data->dev_private)->representor)
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION, actions,
					  "vlan push can only be applied"
					  " when forwarding to uplink port");
	/*
	 * FW syndrome (0x294609):
	 *     set_flow_table_entry: modify/pop/push actions in fdb flow table
	 *     are supported only while forwarding to vport.
	 */
	if ((action_flags & MLX5_TCF_VLAN_ACTIONS) &&
	    !(action_flags & MLX5_FLOW_ACTION_PORT_ID))
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION, actions,
					  "vlan actions are supported"
					  " only with port_id action");
	if ((action_flags & MLX5_TCF_VXLAN_ACTIONS) &&
	    !(action_flags & MLX5_FLOW_ACTION_PORT_ID))
		return rte_flow_error_set(error, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION, NULL,
					  "vxlan actions are supported"
					  " only with port_id action");
	if (!(action_flags & MLX5_TCF_FATE_ACTIONS))
		return rte_flow_error_set(error, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, actions,
					  "no fate action is found");
	if (action_flags &
	   (MLX5_FLOW_ACTION_SET_TTL | MLX5_FLOW_ACTION_DEC_TTL)) {
		if (!(item_flags &
		     (MLX5_FLOW_LAYER_OUTER_L3_IPV4 |
		      MLX5_FLOW_LAYER_OUTER_L3_IPV6)))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "no IP found in pattern");
	}
	if (action_flags &
	    (MLX5_FLOW_ACTION_SET_MAC_SRC | MLX5_FLOW_ACTION_SET_MAC_DST)) {
		if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L2))
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "no ethernet found in"
						  " pattern");
	}
	if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
		if (!(item_flags &
		     (MLX5_FLOW_LAYER_OUTER_L3_IPV4 |
		      MLX5_FLOW_LAYER_OUTER_L3_IPV6)))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  NULL,
						  "no outer IP pattern found"
						  " for vxlan decap action");
		if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  NULL,
						  "no outer UDP pattern found"
						  " for vxlan decap action");
		if (!(item_flags & MLX5_FLOW_LAYER_VXLAN))
			return rte_flow_error_set(error, EINVAL,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  NULL,
						  "no VNI pattern found"
						  " for vxlan decap action");
	}
	return 0;
}

/**
 * Calculate maximum size of memory for flow items of Linux TC flower.
 *
 * @param[in] attr
 *   Pointer to the flow attributes.
 * @param[in] items
 *   Pointer to the list of items.
 *
 * @return
 *   Maximum size of memory for items.
 */
static int
flow_tcf_get_items_size(const struct rte_flow_attr *attr,
			const struct rte_flow_item items[])
{
	int size = 0;

	size += SZ_NLATTR_STRZ_OF("flower") +
		SZ_NLATTR_NEST + /* TCA_OPTIONS. */
		SZ_NLATTR_TYPE_OF(uint32_t); /* TCA_CLS_FLAGS_SKIP_SW. */
	if (attr->group > 0)
		size += SZ_NLATTR_TYPE_OF(uint32_t); /* TCA_CHAIN. */
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_PORT_ID:
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */
				SZ_NLATTR_DATA_OF(ETHER_ADDR_LEN) * 4;
				/* dst/src MAC addr and mask. */
			break;
		case RTE_FLOW_ITEM_TYPE_VLAN:
			size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */
				SZ_NLATTR_TYPE_OF(uint16_t) +
				/* VLAN Ether type. */
				SZ_NLATTR_TYPE_OF(uint8_t) + /* VLAN prio. */
				SZ_NLATTR_TYPE_OF(uint16_t); /* VLAN ID. */
			break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */
				SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */
				SZ_NLATTR_TYPE_OF(uint32_t) * 4;
				/* dst/src IP addr and mask. */
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */
				SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */
				SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) * 4;
				/* dst/src IP addr and mask. */
			break;
		case RTE_FLOW_ITEM_TYPE_UDP:
			size += SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */
				SZ_NLATTR_TYPE_OF(uint16_t) * 4;
				/* dst/src port and mask. */
			break;
		case RTE_FLOW_ITEM_TYPE_TCP:
			size += SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */
				SZ_NLATTR_TYPE_OF(uint16_t) * 4;
				/* dst/src port and mask. */
			break;
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			size += SZ_NLATTR_TYPE_OF(uint32_t);
			break;
		default:
			DRV_LOG(WARNING,
				"unsupported item %p type %d,"
				" items must be validated before flow creation",
				(const void *)items, items->type);
			break;
		}
	}
	return size;
}

/**
 * Calculate size of memory to store the VXLAN encapsultion
 * related items in the Netlink message buffer. Items list
 * is specified by RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action.
 * The item list should be validated.
 *
 * @param[in] action
 *   RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action object.
 *   List of pattern items to scan data from.
 *
 * @return
 *   The size the part of Netlink message buffer to store the
 *   VXLAN encapsulation item attributes.
 */
static int
flow_tcf_vxlan_encap_size(const struct rte_flow_action *action)
{
	const struct rte_flow_item *items;
	int size = 0;

	assert(action->type == RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP);
	assert(action->conf);

	items = ((const struct rte_flow_action_vxlan_encap *)
					action->conf)->definition;
	assert(items);
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			/* This item does not require message buffer. */
			break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			size += SZ_NLATTR_DATA_OF(IPV4_ADDR_LEN) * 2;
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			size += SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) * 2;
			break;
		case RTE_FLOW_ITEM_TYPE_UDP: {
			const struct rte_flow_item_udp *udp = items->mask;

			size += SZ_NLATTR_TYPE_OF(uint16_t);
			if (!udp || udp->hdr.src_port != RTE_BE16(0x0000))
				size += SZ_NLATTR_TYPE_OF(uint16_t);
			break;
		}
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			size +=	SZ_NLATTR_TYPE_OF(uint32_t);
			break;
		default:
			assert(false);
			DRV_LOG(WARNING,
				"unsupported item %p type %d,"
				" items must be validated"
				" before flow creation",
				(const void *)items, items->type);
			return 0;
		}
	}
	return size;
}

/**
 * Calculate maximum size of memory for flow actions of Linux TC flower and
 * extract specified actions.
 *
 * @param[in] actions
 *   Pointer to the list of actions.
 * @param[out] action_flags
 *   Pointer to the detected actions.
 *
 * @return
 *   Maximum size of memory for actions.
 */
static int
flow_tcf_get_actions_and_size(const struct rte_flow_action actions[],
			      uint64_t *action_flags)
{
	int size = 0;
	uint64_t flags = 0;

	size += SZ_NLATTR_NEST; /* TCA_FLOWER_ACT. */
	for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
		switch (actions->type) {
		case RTE_FLOW_ACTION_TYPE_VOID:
			break;
		case RTE_FLOW_ACTION_TYPE_PORT_ID:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("mirred") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(struct tc_mirred);
			flags |= MLX5_FLOW_ACTION_PORT_ID;
			break;
		case RTE_FLOW_ACTION_TYPE_JUMP:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("gact") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(struct tc_gact);
			flags |= MLX5_FLOW_ACTION_JUMP;
			break;
		case RTE_FLOW_ACTION_TYPE_DROP:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("gact") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(struct tc_gact);
			flags |= MLX5_FLOW_ACTION_DROP;
			break;
		case RTE_FLOW_ACTION_TYPE_COUNT:
			break;
		case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
			flags |= MLX5_FLOW_ACTION_OF_POP_VLAN;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
			flags |= MLX5_FLOW_ACTION_OF_PUSH_VLAN;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
			flags |= MLX5_FLOW_ACTION_OF_SET_VLAN_VID;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
			flags |= MLX5_FLOW_ACTION_OF_SET_VLAN_PCP;
			goto action_of_vlan;
action_of_vlan:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("vlan") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(struct tc_vlan) +
				SZ_NLATTR_TYPE_OF(uint16_t) +
				/* VLAN protocol. */
				SZ_NLATTR_TYPE_OF(uint16_t) + /* VLAN ID. */
				SZ_NLATTR_TYPE_OF(uint8_t); /* VLAN prio. */
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("tunnel_key") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(uint8_t);
			size += SZ_NLATTR_TYPE_OF(struct tc_tunnel_key);
			size +=	flow_tcf_vxlan_encap_size(actions) +
				RTE_ALIGN_CEIL /* preceding encap params. */
				(sizeof(struct flow_tcf_vxlan_encap),
				MNL_ALIGNTO);
			flags |= MLX5_FLOW_ACTION_VXLAN_ENCAP;
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
			size += SZ_NLATTR_NEST + /* na_act_index. */
				SZ_NLATTR_STRZ_OF("tunnel_key") +
				SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
				SZ_NLATTR_TYPE_OF(uint8_t);
			size +=	SZ_NLATTR_TYPE_OF(struct tc_tunnel_key);
			size +=	RTE_ALIGN_CEIL /* preceding decap params. */
				(sizeof(struct flow_tcf_vxlan_decap),
				MNL_ALIGNTO);
			flags |= MLX5_FLOW_ACTION_VXLAN_DECAP;
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
		case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
		case RTE_FLOW_ACTION_TYPE_SET_TTL:
		case RTE_FLOW_ACTION_TYPE_DEC_TTL:
		case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
			size += flow_tcf_get_pedit_actions_size(&actions,
								&flags);
			break;
		default:
			DRV_LOG(WARNING,
				"unsupported action %p type %d,"
				" items must be validated before flow creation",
				(const void *)actions, actions->type);
			break;
		}
	}
	*action_flags = flags;
	return size;
}

/**
 * Brand rtnetlink buffer with unique handle.
 *
 * This handle should be unique for a given network interface to avoid
 * collisions.
 *
 * @param nlh
 *   Pointer to Netlink message.
 * @param handle
 *   Unique 32-bit handle to use.
 */
static void
flow_tcf_nl_brand(struct nlmsghdr *nlh, uint32_t handle)
{
	struct tcmsg *tcm = mnl_nlmsg_get_payload(nlh);

	tcm->tcm_handle = handle;
	DRV_LOG(DEBUG, "Netlink msg %p is branded with handle %x",
		(void *)nlh, handle);
}

/**
 * Prepare a flow object for Linux TC flower. It calculates the maximum size of
 * memory required, allocates the memory, initializes Netlink message headers
 * and set unique TC message handle.
 *
 * @param[in] attr
 *   Pointer to the flow attributes.
 * @param[in] items
 *   Pointer to the list of items.
 * @param[in] actions
 *   Pointer to the list of actions.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   Pointer to mlx5_flow object on success,
 *   otherwise NULL and rte_ernno is set.
 */
static struct mlx5_flow *
flow_tcf_prepare(const struct rte_flow_attr *attr,
		 const struct rte_flow_item items[],
		 const struct rte_flow_action actions[],
		 struct rte_flow_error *error)
{
	size_t size = RTE_ALIGN_CEIL
			(sizeof(struct mlx5_flow),
			 alignof(struct flow_tcf_tunnel_hdr)) +
		      MNL_ALIGN(sizeof(struct nlmsghdr)) +
		      MNL_ALIGN(sizeof(struct tcmsg));
	struct mlx5_flow *dev_flow;
	uint64_t action_flags = 0;
	struct nlmsghdr *nlh;
	struct tcmsg *tcm;
	uint8_t *sp, *tun = NULL;

	size += flow_tcf_get_items_size(attr, items);
	size += flow_tcf_get_actions_and_size(actions, &action_flags);
	dev_flow = rte_zmalloc(__func__, size, MNL_ALIGNTO);
	if (!dev_flow) {
		rte_flow_error_set(error, ENOMEM,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "not enough memory to create E-Switch flow");
		return NULL;
	}
	sp = (uint8_t *)(dev_flow + 1);
	if (action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) {
		sp = RTE_PTR_ALIGN
			(sp, alignof(struct flow_tcf_tunnel_hdr));
		tun = sp;
		sp += RTE_ALIGN_CEIL
			(sizeof(struct flow_tcf_vxlan_encap),
			MNL_ALIGNTO);
#ifndef NDEBUG
		size -= RTE_ALIGN_CEIL
			(sizeof(struct flow_tcf_vxlan_encap),
			MNL_ALIGNTO);
#endif
	} else if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
		sp = RTE_PTR_ALIGN
			(sp, alignof(struct flow_tcf_tunnel_hdr));
		tun = sp;
		sp += RTE_ALIGN_CEIL
			(sizeof(struct flow_tcf_vxlan_decap),
			MNL_ALIGNTO);
#ifndef NDEBUG
		size -= RTE_ALIGN_CEIL
			(sizeof(struct flow_tcf_vxlan_decap),
			MNL_ALIGNTO);
#endif
	} else {
		sp = RTE_PTR_ALIGN(sp, MNL_ALIGNTO);
	}
	nlh = mnl_nlmsg_put_header(sp);
	tcm = mnl_nlmsg_put_extra_header(nlh, sizeof(*tcm));
	*dev_flow = (struct mlx5_flow){
		.tcf = (struct mlx5_flow_tcf){
#ifndef NDEBUG
			.nlsize = size - RTE_ALIGN_CEIL
				(sizeof(struct mlx5_flow),
				 alignof(struct flow_tcf_tunnel_hdr)),
#endif
			.tunnel = (struct flow_tcf_tunnel_hdr *)tun,
			.nlh = nlh,
			.tcm = tcm,
		},
	};
	if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP)
		dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_DECAP;
	else if (action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP)
		dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_ENCAP;
	/*
	 * Generate a reasonably unique handle based on the address of the
	 * target buffer.
	 *
	 * This is straightforward on 32-bit systems where the flow pointer can
	 * be used directly. Otherwise, its least significant part is taken
	 * after shifting it by the previous power of two of the pointed buffer
	 * size.
	 */
	if (sizeof(dev_flow) <= 4)
		flow_tcf_nl_brand(nlh, (uintptr_t)dev_flow);
	else
		flow_tcf_nl_brand(nlh, (uintptr_t)dev_flow >>
				       rte_log2_u32(rte_align32prevpow2(size)));
	return dev_flow;
}

/**
 * Make adjustments for supporting count actions.
 *
 * @param[in] dev
 *   Pointer to the Ethernet device structure.
 * @param[in] dev_flow
 *   Pointer to mlx5_flow.
 * @param[out] error
 *   Pointer to error structure.
 *
 * @return
 *   0 On success else a negative errno value is returned and rte_errno is set.
 */
static int
flow_tcf_translate_action_count(struct rte_eth_dev *dev __rte_unused,
				  struct mlx5_flow *dev_flow,
				  struct rte_flow_error *error)
{
	struct rte_flow *flow = dev_flow->flow;

	if (!flow->counter) {
		flow->counter = flow_tcf_counter_new();
		if (!flow->counter)
			return rte_flow_error_set(error, rte_errno,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  NULL,
						  "cannot get counter"
						  " context.");
	}
	return 0;
}

/**
 * Convert VXLAN VNI to 32-bit integer.
 *
 * @param[in] vni
 *   VXLAN VNI in 24-bit wire format.
 *
 * @return
 *   VXLAN VNI as a 32-bit integer value in network endian.
 */
static inline rte_be32_t
vxlan_vni_as_be32(const uint8_t vni[3])
{
	union {
		uint8_t vni[4];
		rte_be32_t dword;
	} ret = {
		.vni = { 0, vni[0], vni[1], vni[2] },
	};
	return ret.dword;
}

/**
 * Helper function to process RTE_FLOW_ITEM_TYPE_ETH entry in configuration
 * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the MAC address fields
 * in the encapsulation parameters structure. The item must be prevalidated,
 * no any validation checks performed by function.
 *
 * @param[in] spec
 *   RTE_FLOW_ITEM_TYPE_ETH entry specification.
 * @param[in] mask
 *   RTE_FLOW_ITEM_TYPE_ETH entry mask.
 * @param[out] encap
 *   Structure to fill the gathered MAC address data.
 */
static void
flow_tcf_parse_vxlan_encap_eth(const struct rte_flow_item_eth *spec,
			       const struct rte_flow_item_eth *mask,
			       struct flow_tcf_vxlan_encap *encap)
{
	/* Item must be validated before. No redundant checks. */
	assert(spec);
	if (!mask || !memcmp(&mask->dst,
			     &rte_flow_item_eth_mask.dst,
			     sizeof(rte_flow_item_eth_mask.dst))) {
		/*
		 * Ethernet addresses are not supported by
		 * tc as tunnel_key parameters. Destination
		 * address is needed to form encap packet
		 * header and retrieved by kernel from
		 * implicit sources (ARP table, etc),
		 * address masks are not supported at all.
		 */
		encap->eth.dst = spec->dst;
		encap->mask |= FLOW_TCF_ENCAP_ETH_DST;
	}
	if (!mask || !memcmp(&mask->src,
			     &rte_flow_item_eth_mask.src,
			     sizeof(rte_flow_item_eth_mask.src))) {
		/*
		 * Ethernet addresses are not supported by
		 * tc as tunnel_key parameters. Source ethernet
		 * address is ignored anyway.
		 */
		encap->eth.src = spec->src;
		encap->mask |= FLOW_TCF_ENCAP_ETH_SRC;
	}
}

/**
 * Helper function to process RTE_FLOW_ITEM_TYPE_IPV4 entry in configuration
 * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the IPV4 address fields
 * in the encapsulation parameters structure. The item must be prevalidated,
 * no any validation checks performed by function.
 *
 * @param[in] spec
 *   RTE_FLOW_ITEM_TYPE_IPV4 entry specification.
 * @param[out] encap
 *   Structure to fill the gathered IPV4 address data.
 */
static void
flow_tcf_parse_vxlan_encap_ipv4(const struct rte_flow_item_ipv4 *spec,
				struct flow_tcf_vxlan_encap *encap)
{
	/* Item must be validated before. No redundant checks. */
	assert(spec);
	encap->ipv4.dst = spec->hdr.dst_addr;
	encap->ipv4.src = spec->hdr.src_addr;
	encap->mask |= FLOW_TCF_ENCAP_IPV4_SRC |
		       FLOW_TCF_ENCAP_IPV4_DST;
}

/**
 * Helper function to process RTE_FLOW_ITEM_TYPE_IPV6 entry in configuration
 * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the IPV6 address fields
 * in the encapsulation parameters structure. The item must be prevalidated,
 * no any validation checks performed by function.
 *
 * @param[in] spec
 *   RTE_FLOW_ITEM_TYPE_IPV6 entry specification.
 * @param[out] encap
 *   Structure to fill the gathered IPV6 address data.
 */
static void
flow_tcf_parse_vxlan_encap_ipv6(const struct rte_flow_item_ipv6 *spec,
				struct flow_tcf_vxlan_encap *encap)
{
	/* Item must be validated before. No redundant checks. */
	assert(spec);
	memcpy(encap->ipv6.dst, spec->hdr.dst_addr, IPV6_ADDR_LEN);
	memcpy(encap->ipv6.src, spec->hdr.src_addr, IPV6_ADDR_LEN);
	encap->mask |= FLOW_TCF_ENCAP_IPV6_SRC |
		       FLOW_TCF_ENCAP_IPV6_DST;
}

/**
 * Helper function to process RTE_FLOW_ITEM_TYPE_UDP entry in configuration
 * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the UDP port fields
 * in the encapsulation parameters structure. The item must be prevalidated,
 * no any validation checks performed by function.
 *
 * @param[in] spec
 *   RTE_FLOW_ITEM_TYPE_UDP entry specification.
 * @param[in] mask
 *   RTE_FLOW_ITEM_TYPE_UDP entry mask.
 * @param[out] encap
 *   Structure to fill the gathered UDP port data.
 */
static void
flow_tcf_parse_vxlan_encap_udp(const struct rte_flow_item_udp *spec,
			       const struct rte_flow_item_udp *mask,
			       struct flow_tcf_vxlan_encap *encap)
{
	assert(spec);
	encap->udp.dst = spec->hdr.dst_port;
	encap->mask |= FLOW_TCF_ENCAP_UDP_DST;
	if (!mask || mask->hdr.src_port != RTE_BE16(0x0000)) {
		encap->udp.src = spec->hdr.src_port;
		encap->mask |= FLOW_TCF_ENCAP_IPV4_SRC;
	}
}

/**
 * Helper function to process RTE_FLOW_ITEM_TYPE_VXLAN entry in configuration
 * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the VNI fields
 * in the encapsulation parameters structure. The item must be prevalidated,
 * no any validation checks performed by function.
 *
 * @param[in] spec
 *   RTE_FLOW_ITEM_TYPE_VXLAN entry specification.
 * @param[out] encap
 *   Structure to fill the gathered VNI address data.
 */
static void
flow_tcf_parse_vxlan_encap_vni(const struct rte_flow_item_vxlan *spec,
			       struct flow_tcf_vxlan_encap *encap)
{
	/* Item must be validated before. Do not redundant checks. */
	assert(spec);
	memcpy(encap->vxlan.vni, spec->vni, sizeof(encap->vxlan.vni));
	encap->mask |= FLOW_TCF_ENCAP_VXLAN_VNI;
}

/**
 * Populate consolidated encapsulation object from list of pattern items.
 *
 * Helper function to process configuration of action such as
 * RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. The item list should be
 * validated, there is no way to return an meaningful error.
 *
 * @param[in] action
 *   RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action object.
 *   List of pattern items to gather data from.
 * @param[out] src
 *   Structure to fill gathered data.
 */
static void
flow_tcf_vxlan_encap_parse(const struct rte_flow_action *action,
			   struct flow_tcf_vxlan_encap *encap)
{
	union {
		const struct rte_flow_item_eth *eth;
		const struct rte_flow_item_ipv4 *ipv4;
		const struct rte_flow_item_ipv6 *ipv6;
		const struct rte_flow_item_udp *udp;
		const struct rte_flow_item_vxlan *vxlan;
	} spec, mask;
	const struct rte_flow_item *items;

	assert(action->type == RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP);
	assert(action->conf);

	items = ((const struct rte_flow_action_vxlan_encap *)
					action->conf)->definition;
	assert(items);
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			mask.eth = items->mask;
			spec.eth = items->spec;
			flow_tcf_parse_vxlan_encap_eth(spec.eth, mask.eth,
						       encap);
			break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			spec.ipv4 = items->spec;
			flow_tcf_parse_vxlan_encap_ipv4(spec.ipv4, encap);
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			spec.ipv6 = items->spec;
			flow_tcf_parse_vxlan_encap_ipv6(spec.ipv6, encap);
			break;
		case RTE_FLOW_ITEM_TYPE_UDP:
			mask.udp = items->mask;
			spec.udp = items->spec;
			flow_tcf_parse_vxlan_encap_udp(spec.udp, mask.udp,
						       encap);
			break;
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			spec.vxlan = items->spec;
			flow_tcf_parse_vxlan_encap_vni(spec.vxlan, encap);
			break;
		default:
			assert(false);
			DRV_LOG(WARNING,
				"unsupported item %p type %d,"
				" items must be validated"
				" before flow creation",
				(const void *)items, items->type);
			encap->mask = 0;
			return;
		}
	}
}

/**
 * Translate flow for Linux TC flower and construct Netlink message.
 *
 * @param[in] priv
 *   Pointer to the priv structure.
 * @param[in, out] flow
 *   Pointer to the sub flow.
 * @param[in] attr
 *   Pointer to the flow attributes.
 * @param[in] items
 *   Pointer to the list of items.
 * @param[in] actions
 *   Pointer to the list of actions.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 */
static int
flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
		   const struct rte_flow_attr *attr,
		   const struct rte_flow_item items[],
		   const struct rte_flow_action actions[],
		   struct rte_flow_error *error)
{
	union {
		const struct rte_flow_item_port_id *port_id;
		const struct rte_flow_item_eth *eth;
		const struct rte_flow_item_vlan *vlan;
		const struct rte_flow_item_ipv4 *ipv4;
		const struct rte_flow_item_ipv6 *ipv6;
		const struct rte_flow_item_tcp *tcp;
		const struct rte_flow_item_udp *udp;
		const struct rte_flow_item_vxlan *vxlan;
	} spec, mask;
	union {
		const struct rte_flow_action_port_id *port_id;
		const struct rte_flow_action_jump *jump;
		const struct rte_flow_action_of_push_vlan *of_push_vlan;
		const struct rte_flow_action_of_set_vlan_vid *
			of_set_vlan_vid;
		const struct rte_flow_action_of_set_vlan_pcp *
			of_set_vlan_pcp;
	} conf;
	union {
		struct flow_tcf_tunnel_hdr *hdr;
		struct flow_tcf_vxlan_decap *vxlan;
	} decap = {
		.hdr = NULL,
	};
	union {
		struct flow_tcf_tunnel_hdr *hdr;
		struct flow_tcf_vxlan_encap *vxlan;
	} encap = {
		.hdr = NULL,
	};
	struct flow_tcf_ptoi ptoi[PTOI_TABLE_SZ_MAX(dev)];
	struct nlmsghdr *nlh = dev_flow->tcf.nlh;
	struct tcmsg *tcm = dev_flow->tcf.tcm;
	uint32_t na_act_index_cur;
	bool eth_type_set = 0;
	bool vlan_present = 0;
	bool vlan_eth_type_set = 0;
	bool ip_proto_set = 0;
	struct nlattr *na_flower;
	struct nlattr *na_flower_act;
	struct nlattr *na_vlan_id = NULL;
	struct nlattr *na_vlan_priority = NULL;
	uint64_t item_flags = 0;
	int ret;

	claim_nonzero(flow_tcf_build_ptoi_table(dev, ptoi,
						PTOI_TABLE_SZ_MAX(dev)));
	if (dev_flow->tcf.tunnel) {
		switch (dev_flow->tcf.tunnel->type) {
		case FLOW_TCF_TUNACT_VXLAN_DECAP:
			decap.vxlan = dev_flow->tcf.vxlan_decap;
			break;
		case FLOW_TCF_TUNACT_VXLAN_ENCAP:
			encap.vxlan = dev_flow->tcf.vxlan_encap;
			break;
		/* New tunnel actions can be added here. */
		default:
			assert(false);
			break;
		}
	}
	nlh = dev_flow->tcf.nlh;
	tcm = dev_flow->tcf.tcm;
	/* Prepare API must have been called beforehand. */
	assert(nlh != NULL && tcm != NULL);
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm_ifindex = ptoi[0].ifindex;
	tcm->tcm_parent = TC_H_MAKE(TC_H_INGRESS, TC_H_MIN_INGRESS);
	/*
	 * Priority cannot be zero to prevent the kernel from picking one
	 * automatically.
	 */
	tcm->tcm_info = TC_H_MAKE((attr->priority + 1) << 16,
				  RTE_BE16(ETH_P_ALL));
	if (attr->group > 0)
		mnl_attr_put_u32(nlh, TCA_CHAIN, attr->group);
	mnl_attr_put_strz(nlh, TCA_KIND, "flower");
	na_flower = mnl_attr_nest_start(nlh, TCA_OPTIONS);
	for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
		unsigned int i;

		switch (items->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			break;
		case RTE_FLOW_ITEM_TYPE_PORT_ID:
			mask.port_id = flow_tcf_item_mask
				(items, &rte_flow_item_port_id_mask,
				 &flow_tcf_mask_supported.port_id,
				 &flow_tcf_mask_empty.port_id,
				 sizeof(flow_tcf_mask_supported.port_id),
				 error);
			assert(mask.port_id);
			if (mask.port_id == &flow_tcf_mask_empty.port_id)
				break;
			spec.port_id = items->spec;
			if (!mask.port_id->id)
				i = 0;
			else
				for (i = 0; ptoi[i].ifindex; ++i)
					if (ptoi[i].port_id == spec.port_id->id)
						break;
			assert(ptoi[i].ifindex);
			tcm->tcm_ifindex = ptoi[i].ifindex;
			break;
		case RTE_FLOW_ITEM_TYPE_ETH:
			item_flags |= (item_flags & MLX5_FLOW_LAYER_VXLAN) ?
				      MLX5_FLOW_LAYER_INNER_L2 :
				      MLX5_FLOW_LAYER_OUTER_L2;
			mask.eth = flow_tcf_item_mask
				(items, &rte_flow_item_eth_mask,
				 &flow_tcf_mask_supported.eth,
				 &flow_tcf_mask_empty.eth,
				 sizeof(flow_tcf_mask_supported.eth),
				 error);
			assert(mask.eth);
			if (mask.eth == &flow_tcf_mask_empty.eth)
				break;
			spec.eth = items->spec;
			if (decap.vxlan &&
			    !(item_flags & MLX5_FLOW_LAYER_VXLAN)) {
				DRV_LOG(WARNING,
					"outer L2 addresses cannot be forced"
					" for vxlan decapsulation, parameter"
					" ignored");
				break;
			}
			if (mask.eth->type) {
				mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_ETH_TYPE,
						 spec.eth->type);
				eth_type_set = 1;
			}
			if (!is_zero_ether_addr(&mask.eth->dst)) {
				mnl_attr_put(nlh, TCA_FLOWER_KEY_ETH_DST,
					     ETHER_ADDR_LEN,
					     spec.eth->dst.addr_bytes);
				mnl_attr_put(nlh, TCA_FLOWER_KEY_ETH_DST_MASK,
					     ETHER_ADDR_LEN,
					     mask.eth->dst.addr_bytes);
			}
			if (!is_zero_ether_addr(&mask.eth->src)) {
				mnl_attr_put(nlh, TCA_FLOWER_KEY_ETH_SRC,
					     ETHER_ADDR_LEN,
					     spec.eth->src.addr_bytes);
				mnl_attr_put(nlh, TCA_FLOWER_KEY_ETH_SRC_MASK,
					     ETHER_ADDR_LEN,
					     mask.eth->src.addr_bytes);
			}
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_VLAN:
			assert(!encap.hdr);
			assert(!decap.hdr);
			item_flags |= MLX5_FLOW_LAYER_OUTER_VLAN;
			mask.vlan = flow_tcf_item_mask
				(items, &rte_flow_item_vlan_mask,
				 &flow_tcf_mask_supported.vlan,
				 &flow_tcf_mask_empty.vlan,
				 sizeof(flow_tcf_mask_supported.vlan),
				 error);
			assert(mask.vlan);
			if (!eth_type_set)
				mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_ETH_TYPE,
						 RTE_BE16(ETH_P_8021Q));
			eth_type_set = 1;
			vlan_present = 1;
			if (mask.vlan == &flow_tcf_mask_empty.vlan)
				break;
			spec.vlan = items->spec;
			if (mask.vlan->inner_type) {
				mnl_attr_put_u16(nlh,
						 TCA_FLOWER_KEY_VLAN_ETH_TYPE,
						 spec.vlan->inner_type);
				vlan_eth_type_set = 1;
			}
			if (mask.vlan->tci & RTE_BE16(0xe000))
				mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_VLAN_PRIO,
						(rte_be_to_cpu_16
						 (spec.vlan->tci) >> 13) & 0x7);
			if (mask.vlan->tci & RTE_BE16(0x0fff))
				mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_VLAN_ID,
						 rte_be_to_cpu_16
						 (spec.vlan->tci &
						  RTE_BE16(0x0fff)));
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_IPV4:
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
			mask.ipv4 = flow_tcf_item_mask
				(items, &rte_flow_item_ipv4_mask,
				 &flow_tcf_mask_supported.ipv4,
				 &flow_tcf_mask_empty.ipv4,
				 sizeof(flow_tcf_mask_supported.ipv4),
				 error);
			assert(mask.ipv4);
			spec.ipv4 = items->spec;
			if (!decap.vxlan) {
				if (!eth_type_set ||
				    (!vlan_eth_type_set && vlan_present))
					mnl_attr_put_u16
						(nlh,
						 vlan_present ?
						 TCA_FLOWER_KEY_VLAN_ETH_TYPE :
						 TCA_FLOWER_KEY_ETH_TYPE,
						 RTE_BE16(ETH_P_IP));
				eth_type_set = 1;
				vlan_eth_type_set = 1;
				if (mask.ipv4 == &flow_tcf_mask_empty.ipv4)
					break;
				if (mask.ipv4->hdr.next_proto_id) {
					mnl_attr_put_u8
						(nlh, TCA_FLOWER_KEY_IP_PROTO,
						 spec.ipv4->hdr.next_proto_id);
					ip_proto_set = 1;
				}
			} else {
				assert(mask.ipv4 != &flow_tcf_mask_empty.ipv4);
			}
			if (mask.ipv4->hdr.src_addr) {
				mnl_attr_put_u32
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_IPV4_SRC :
					 TCA_FLOWER_KEY_IPV4_SRC,
					 spec.ipv4->hdr.src_addr);
				mnl_attr_put_u32
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK :
					 TCA_FLOWER_KEY_IPV4_SRC_MASK,
					 mask.ipv4->hdr.src_addr);
			}
			if (mask.ipv4->hdr.dst_addr) {
				mnl_attr_put_u32
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_IPV4_DST :
					 TCA_FLOWER_KEY_IPV4_DST,
					 spec.ipv4->hdr.dst_addr);
				mnl_attr_put_u32
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_IPV4_DST_MASK :
					 TCA_FLOWER_KEY_IPV4_DST_MASK,
					 mask.ipv4->hdr.dst_addr);
			}
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_IPV6:
			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
			mask.ipv6 = flow_tcf_item_mask
				(items, &rte_flow_item_ipv6_mask,
				 &flow_tcf_mask_supported.ipv6,
				 &flow_tcf_mask_empty.ipv6,
				 sizeof(flow_tcf_mask_supported.ipv6),
				 error);
			assert(mask.ipv6);
			spec.ipv6 = items->spec;
			if (!decap.vxlan) {
				if (!eth_type_set ||
				    (!vlan_eth_type_set && vlan_present))
					mnl_attr_put_u16
						(nlh,
						 vlan_present ?
						 TCA_FLOWER_KEY_VLAN_ETH_TYPE :
						 TCA_FLOWER_KEY_ETH_TYPE,
						 RTE_BE16(ETH_P_IPV6));
				eth_type_set = 1;
				vlan_eth_type_set = 1;
				if (mask.ipv6 == &flow_tcf_mask_empty.ipv6)
					break;
				if (mask.ipv6->hdr.proto) {
					mnl_attr_put_u8
						(nlh, TCA_FLOWER_KEY_IP_PROTO,
						 spec.ipv6->hdr.proto);
					ip_proto_set = 1;
				}
			} else {
				assert(mask.ipv6 != &flow_tcf_mask_empty.ipv6);
			}
			if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.src_addr)) {
				mnl_attr_put(nlh, decap.vxlan ?
					     TCA_FLOWER_KEY_ENC_IPV6_SRC :
					     TCA_FLOWER_KEY_IPV6_SRC,
					     IPV6_ADDR_LEN,
					     spec.ipv6->hdr.src_addr);
				mnl_attr_put(nlh, decap.vxlan ?
					     TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK :
					     TCA_FLOWER_KEY_IPV6_SRC_MASK,
					     IPV6_ADDR_LEN,
					     mask.ipv6->hdr.src_addr);
			}
			if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.dst_addr)) {
				mnl_attr_put(nlh, decap.vxlan ?
					     TCA_FLOWER_KEY_ENC_IPV6_DST :
					     TCA_FLOWER_KEY_IPV6_DST,
					     IPV6_ADDR_LEN,
					     spec.ipv6->hdr.dst_addr);
				mnl_attr_put(nlh, decap.vxlan ?
					     TCA_FLOWER_KEY_ENC_IPV6_DST_MASK :
					     TCA_FLOWER_KEY_IPV6_DST_MASK,
					     IPV6_ADDR_LEN,
					     mask.ipv6->hdr.dst_addr);
			}
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_UDP:
			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
			mask.udp = flow_tcf_item_mask
				(items, &rte_flow_item_udp_mask,
				 &flow_tcf_mask_supported.udp,
				 &flow_tcf_mask_empty.udp,
				 sizeof(flow_tcf_mask_supported.udp),
				 error);
			assert(mask.udp);
			spec.udp = items->spec;
			if (!decap.vxlan) {
				if (!ip_proto_set)
					mnl_attr_put_u8
						(nlh, TCA_FLOWER_KEY_IP_PROTO,
						IPPROTO_UDP);
				if (mask.udp == &flow_tcf_mask_empty.udp)
					break;
			} else {
				assert(mask.udp != &flow_tcf_mask_empty.udp);
				decap.vxlan->udp_port =
					rte_be_to_cpu_16
						(spec.udp->hdr.dst_port);
			}
			if (mask.udp->hdr.src_port) {
				mnl_attr_put_u16
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_UDP_SRC_PORT :
					 TCA_FLOWER_KEY_UDP_SRC,
					 spec.udp->hdr.src_port);
				mnl_attr_put_u16
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK :
					 TCA_FLOWER_KEY_UDP_SRC_MASK,
					 mask.udp->hdr.src_port);
			}
			if (mask.udp->hdr.dst_port) {
				mnl_attr_put_u16
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_UDP_DST_PORT :
					 TCA_FLOWER_KEY_UDP_DST,
					 spec.udp->hdr.dst_port);
				mnl_attr_put_u16
					(nlh, decap.vxlan ?
					 TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK :
					 TCA_FLOWER_KEY_UDP_DST_MASK,
					 mask.udp->hdr.dst_port);
			}
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_TCP:
			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
			mask.tcp = flow_tcf_item_mask
				(items, &rte_flow_item_tcp_mask,
				 &flow_tcf_mask_supported.tcp,
				 &flow_tcf_mask_empty.tcp,
				 sizeof(flow_tcf_mask_supported.tcp),
				 error);
			assert(mask.tcp);
			if (!ip_proto_set)
				mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
						IPPROTO_TCP);
			if (mask.tcp == &flow_tcf_mask_empty.tcp)
				break;
			spec.tcp = items->spec;
			if (mask.tcp->hdr.src_port) {
				mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_TCP_SRC,
						 spec.tcp->hdr.src_port);
				mnl_attr_put_u16(nlh,
						 TCA_FLOWER_KEY_TCP_SRC_MASK,
						 mask.tcp->hdr.src_port);
			}
			if (mask.tcp->hdr.dst_port) {
				mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_TCP_DST,
						 spec.tcp->hdr.dst_port);
				mnl_attr_put_u16(nlh,
						 TCA_FLOWER_KEY_TCP_DST_MASK,
						 mask.tcp->hdr.dst_port);
			}
			if (mask.tcp->hdr.tcp_flags) {
				mnl_attr_put_u16
					(nlh,
					 TCA_FLOWER_KEY_TCP_FLAGS,
					 rte_cpu_to_be_16
						(spec.tcp->hdr.tcp_flags));
				mnl_attr_put_u16
					(nlh,
					 TCA_FLOWER_KEY_TCP_FLAGS_MASK,
					 rte_cpu_to_be_16
						(mask.tcp->hdr.tcp_flags));
			}
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ITEM_TYPE_VXLAN:
			assert(decap.vxlan);
			item_flags |= MLX5_FLOW_LAYER_VXLAN;
			spec.vxlan = items->spec;
			mnl_attr_put_u32(nlh,
					 TCA_FLOWER_KEY_ENC_KEY_ID,
					 vxlan_vni_as_be32(spec.vxlan->vni));
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		default:
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ITEM,
						  NULL, "item not supported");
		}
	}
	na_flower_act = mnl_attr_nest_start(nlh, TCA_FLOWER_ACT);
	na_act_index_cur = 1;
	for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
		struct nlattr *na_act_index;
		struct nlattr *na_act;
		unsigned int vlan_act;
		unsigned int i;

		switch (actions->type) {
		case RTE_FLOW_ACTION_TYPE_VOID:
			break;
		case RTE_FLOW_ACTION_TYPE_PORT_ID:
			conf.port_id = actions->conf;
			if (conf.port_id->original)
				i = 0;
			else
				for (i = 0; ptoi[i].ifindex; ++i)
					if (ptoi[i].port_id == conf.port_id->id)
						break;
			assert(ptoi[i].ifindex);
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "mirred");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			if (encap.hdr) {
				assert(dev_flow->tcf.tunnel);
				dev_flow->tcf.tunnel->ifindex_ptr =
					&((struct tc_mirred *)
					mnl_attr_get_payload
					(mnl_nlmsg_get_payload_tail
						(nlh)))->ifindex;
			}
			mnl_attr_put(nlh, TCA_MIRRED_PARMS,
				     sizeof(struct tc_mirred),
				     &(struct tc_mirred){
					.action = TC_ACT_STOLEN,
					.eaction = TCA_EGRESS_REDIR,
					.ifindex = ptoi[i].ifindex,
				     });
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			break;
		case RTE_FLOW_ACTION_TYPE_JUMP:
			conf.jump = actions->conf;
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "gact");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			mnl_attr_put(nlh, TCA_GACT_PARMS,
				     sizeof(struct tc_gact),
				     &(struct tc_gact){
					.action = TC_ACT_GOTO_CHAIN |
						  conf.jump->group,
				     });
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			break;
		case RTE_FLOW_ACTION_TYPE_DROP:
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "gact");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			mnl_attr_put(nlh, TCA_GACT_PARMS,
				     sizeof(struct tc_gact),
				     &(struct tc_gact){
					.action = TC_ACT_SHOT,
				     });
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			break;
		case RTE_FLOW_ACTION_TYPE_COUNT:
			/*
			 * Driver adds the count action implicitly for
			 * each rule it creates.
			 */
			ret = flow_tcf_translate_action_count(dev,
							      dev_flow, error);
			if (ret < 0)
				return ret;
			break;
		case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
			conf.of_push_vlan = NULL;
			vlan_act = TCA_VLAN_ACT_POP;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
			conf.of_push_vlan = actions->conf;
			vlan_act = TCA_VLAN_ACT_PUSH;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
			conf.of_set_vlan_vid = actions->conf;
			if (na_vlan_id)
				goto override_na_vlan_id;
			vlan_act = TCA_VLAN_ACT_MODIFY;
			goto action_of_vlan;
		case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
			conf.of_set_vlan_pcp = actions->conf;
			if (na_vlan_priority)
				goto override_na_vlan_priority;
			vlan_act = TCA_VLAN_ACT_MODIFY;
			goto action_of_vlan;
action_of_vlan:
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "vlan");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			mnl_attr_put(nlh, TCA_VLAN_PARMS,
				     sizeof(struct tc_vlan),
				     &(struct tc_vlan){
					.action = TC_ACT_PIPE,
					.v_action = vlan_act,
				     });
			if (vlan_act == TCA_VLAN_ACT_POP) {
				mnl_attr_nest_end(nlh, na_act);
				mnl_attr_nest_end(nlh, na_act_index);
				break;
			}
			if (vlan_act == TCA_VLAN_ACT_PUSH)
				mnl_attr_put_u16(nlh,
						 TCA_VLAN_PUSH_VLAN_PROTOCOL,
						 conf.of_push_vlan->ethertype);
			na_vlan_id = mnl_nlmsg_get_payload_tail(nlh);
			mnl_attr_put_u16(nlh, TCA_VLAN_PAD, 0);
			na_vlan_priority = mnl_nlmsg_get_payload_tail(nlh);
			mnl_attr_put_u8(nlh, TCA_VLAN_PAD, 0);
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			if (actions->type ==
			    RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID) {
override_na_vlan_id:
				na_vlan_id->nla_type = TCA_VLAN_PUSH_VLAN_ID;
				*(uint16_t *)mnl_attr_get_payload(na_vlan_id) =
					rte_be_to_cpu_16
					(conf.of_set_vlan_vid->vlan_vid);
			} else if (actions->type ==
				   RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP) {
override_na_vlan_priority:
				na_vlan_priority->nla_type =
					TCA_VLAN_PUSH_VLAN_PRIORITY;
				*(uint8_t *)mnl_attr_get_payload
					(na_vlan_priority) =
					conf.of_set_vlan_pcp->vlan_pcp;
			}
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
			assert(decap.vxlan);
			assert(dev_flow->tcf.tunnel);
			dev_flow->tcf.tunnel->ifindex_ptr =
				(unsigned int *)&tcm->tcm_ifindex;
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "tunnel_key");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			mnl_attr_put(nlh, TCA_TUNNEL_KEY_PARMS,
				sizeof(struct tc_tunnel_key),
				&(struct tc_tunnel_key){
					.action = TC_ACT_PIPE,
					.t_action = TCA_TUNNEL_KEY_ACT_RELEASE,
					});
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
			assert(encap.vxlan);
			flow_tcf_vxlan_encap_parse(actions, encap.vxlan);
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			assert(na_act_index);
			mnl_attr_put_strz(nlh, TCA_ACT_KIND, "tunnel_key");
			na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
			assert(na_act);
			mnl_attr_put(nlh, TCA_TUNNEL_KEY_PARMS,
				sizeof(struct tc_tunnel_key),
				&(struct tc_tunnel_key){
					.action = TC_ACT_PIPE,
					.t_action = TCA_TUNNEL_KEY_ACT_SET,
					});
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_UDP_DST)
				mnl_attr_put_u16(nlh,
					 TCA_TUNNEL_KEY_ENC_DST_PORT,
					 encap.vxlan->udp.dst);
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV4_SRC)
				mnl_attr_put_u32(nlh,
					 TCA_TUNNEL_KEY_ENC_IPV4_SRC,
					 encap.vxlan->ipv4.src);
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV4_DST)
				mnl_attr_put_u32(nlh,
					 TCA_TUNNEL_KEY_ENC_IPV4_DST,
					 encap.vxlan->ipv4.dst);
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV6_SRC)
				mnl_attr_put(nlh,
					 TCA_TUNNEL_KEY_ENC_IPV6_SRC,
					 sizeof(encap.vxlan->ipv6.src),
					 &encap.vxlan->ipv6.src);
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV6_DST)
				mnl_attr_put(nlh,
					 TCA_TUNNEL_KEY_ENC_IPV6_DST,
					 sizeof(encap.vxlan->ipv6.dst),
					 &encap.vxlan->ipv6.dst);
			if (encap.vxlan->mask & FLOW_TCF_ENCAP_VXLAN_VNI)
				mnl_attr_put_u32(nlh,
					 TCA_TUNNEL_KEY_ENC_KEY_ID,
					 vxlan_vni_as_be32
						(encap.vxlan->vxlan.vni));
			mnl_attr_put_u8(nlh, TCA_TUNNEL_KEY_NO_CSUM, 0);
			mnl_attr_nest_end(nlh, na_act);
			mnl_attr_nest_end(nlh, na_act_index);
			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
			break;
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
		case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
		case RTE_FLOW_ACTION_TYPE_SET_TTL:
		case RTE_FLOW_ACTION_TYPE_DEC_TTL:
		case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
		case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
			na_act_index =
				mnl_attr_nest_start(nlh, na_act_index_cur++);
			flow_tcf_create_pedit_mnl_msg(nlh,
						      &actions, item_flags);
			mnl_attr_nest_end(nlh, na_act_index);
			break;
		default:
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "action not supported");
		}
	}
	assert(na_flower);
	assert(na_flower_act);
	mnl_attr_nest_end(nlh, na_flower_act);
	dev_flow->tcf.ptc_flags = mnl_attr_get_payload
					(mnl_nlmsg_get_payload_tail(nlh));
	mnl_attr_put_u32(nlh, TCA_FLOWER_FLAGS,	decap.vxlan ?
						0 : TCA_CLS_FLAGS_SKIP_SW);
	mnl_attr_nest_end(nlh, na_flower);
	if (dev_flow->tcf.tunnel && dev_flow->tcf.tunnel->ifindex_ptr)
		dev_flow->tcf.tunnel->ifindex_org =
			*dev_flow->tcf.tunnel->ifindex_ptr;
	assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
	return 0;
}

/**
 * Send Netlink message with acknowledgment.
 *
 * @param tcf
 *   Flow context to use.
 * @param nlh
 *   Message to send. This function always raises the NLM_F_ACK flag before
 *   sending.
 * @param[in] cb
 *   Callback handler for received message.
 * @param[in] arg
 *   Context pointer for callback handler.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_nl_ack(struct mlx5_flow_tcf_context *tcf,
		struct nlmsghdr *nlh,
		mnl_cb_t cb, void *arg)
{
	unsigned int portid = mnl_socket_get_portid(tcf->nl);
	uint32_t seq = tcf->seq++;
	int ret, err = 0;

	assert(tcf->nl);
	assert(tcf->buf);
	if (!seq) {
		/* seq 0 is reserved for kernel event-driven notifications. */
		seq = tcf->seq++;
	}
	nlh->nlmsg_seq = seq;
	nlh->nlmsg_flags |= NLM_F_ACK;
	ret = mnl_socket_sendto(tcf->nl, nlh, nlh->nlmsg_len);
	if (ret <= 0) {
		/* Message send error occurres. */
		rte_errno = errno;
		return -rte_errno;
	}
	nlh = (struct nlmsghdr *)(tcf->buf);
	/*
	 * The following loop postpones non-fatal errors until multipart
	 * messages are complete.
	 */
	while (true) {
		ret = mnl_socket_recvfrom(tcf->nl, tcf->buf, tcf->buf_size);
		if (ret < 0) {
			err = errno;
			/*
			 * In case of overflow Will receive till
			 * end of multipart message. We may lost part
			 * of reply messages but mark and return an error.
			 */
			if (err != ENOSPC ||
			    !(nlh->nlmsg_flags & NLM_F_MULTI) ||
			    nlh->nlmsg_type == NLMSG_DONE)
				break;
		} else {
			ret = mnl_cb_run(nlh, ret, seq, portid, cb, arg);
			if (!ret) {
				/*
				 * libmnl returns 0 if DONE or
				 * success ACK message found.
				 */
				break;
			}
			if (ret < 0) {
				/*
				 * ACK message with error found
				 * or some error occurred.
				 */
				err = errno;
				break;
			}
			/* We should continue receiving. */
		}
	}
	if (!err)
		return 0;
	rte_errno = err;
	return -err;
}

#define MNL_BUF_EXTRA_SPACE 16
#define MNL_REQUEST_SIZE_MIN 256
#define MNL_REQUEST_SIZE_MAX 2048
#define MNL_REQUEST_SIZE RTE_MIN(RTE_MAX(sysconf(_SC_PAGESIZE), \
				 MNL_REQUEST_SIZE_MIN), MNL_REQUEST_SIZE_MAX)

/* Data structures used by flow_tcf_xxx_cb() routines. */
struct tcf_nlcb_buf {
	LIST_ENTRY(tcf_nlcb_buf) next;
	uint32_t size;
	alignas(struct nlmsghdr)
	uint8_t msg[]; /**< Netlink message data. */
};

struct tcf_nlcb_context {
	unsigned int ifindex; /**< Base interface index. */
	uint32_t bufsize;
	LIST_HEAD(, tcf_nlcb_buf) nlbuf;
};

/**
 * Allocate space for netlink command in buffer list
 *
 * @param[in, out] ctx
 *   Pointer to callback context with command buffers list.
 * @param[in] size
 *   Required size of data buffer to be allocated.
 *
 * @return
 *   Pointer to allocated memory, aligned as message header.
 *   NULL if some error occurred.
 */
static struct nlmsghdr *
flow_tcf_alloc_nlcmd(struct tcf_nlcb_context *ctx, uint32_t size)
{
	struct tcf_nlcb_buf *buf;
	struct nlmsghdr *nlh;

	size = NLMSG_ALIGN(size);
	buf = LIST_FIRST(&ctx->nlbuf);
	if (buf && (buf->size + size) <= ctx->bufsize) {
		nlh = (struct nlmsghdr *)&buf->msg[buf->size];
		buf->size += size;
		return nlh;
	}
	if (size > ctx->bufsize) {
		DRV_LOG(WARNING, "netlink: too long command buffer requested");
		return NULL;
	}
	buf = rte_malloc(__func__,
			ctx->bufsize + sizeof(struct tcf_nlcb_buf),
			alignof(struct tcf_nlcb_buf));
	if (!buf) {
		DRV_LOG(WARNING, "netlink: no memory for command buffer");
		return NULL;
	}
	LIST_INSERT_HEAD(&ctx->nlbuf, buf, next);
	buf->size = size;
	nlh = (struct nlmsghdr *)&buf->msg[0];
	return nlh;
}

/**
 * Send the buffers with prepared netlink commands. Scans the list and
 * sends all found buffers. Buffers are sent and freed anyway in order
 * to prevent memory leakage if some every message in received packet.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in, out] ctx
 *   Pointer to callback context with command buffers list.
 *
 * @return
 *   Zero value on success, negative errno value otherwise
 *   and rte_errno is set.
 */
static int
flow_tcf_send_nlcmd(struct mlx5_flow_tcf_context *tcf,
		    struct tcf_nlcb_context *ctx)
{
	struct tcf_nlcb_buf *bc = LIST_FIRST(&ctx->nlbuf);
	int ret = 0;

	while (bc) {
		struct tcf_nlcb_buf *bn = LIST_NEXT(bc, next);
		struct nlmsghdr *nlh;
		uint32_t msg = 0;
		int rc;

		while (msg < bc->size) {
			/*
			 * Send Netlink commands from buffer in one by one
			 * fashion. If we send multiple rule deletion commands
			 * in one Netlink message and some error occurs it may
			 * cause multiple ACK error messages and break sequence
			 * numbers of Netlink communication, because we expect
			 * the only one ACK reply.
			 */
			assert((bc->size - msg) >= sizeof(struct nlmsghdr));
			nlh = (struct nlmsghdr *)&bc->msg[msg];
			assert((bc->size - msg) >= nlh->nlmsg_len);
			msg += nlh->nlmsg_len;
			rc = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
			if (rc) {
				DRV_LOG(WARNING,
					"netlink: cleanup error %d", rc);
				if (!ret)
					ret = rc;
			}
		}
		rte_free(bc);
		bc = bn;
	}
	LIST_INIT(&ctx->nlbuf);
	return ret;
}

/**
 * Collect local IP address rules with scope link attribute  on specified
 * network device. This is callback routine called by libmnl mnl_cb_run()
 * in loop for every message in received packet.
 *
 * @param[in] nlh
 *   Pointer to reply header.
 * @param[in, out] arg
 *   Opaque data pointer for this callback.
 *
 * @return
 *   A positive, nonzero value on success, negative errno value otherwise
 *   and rte_errno is set.
 */
static int
flow_tcf_collect_local_cb(const struct nlmsghdr *nlh, void *arg)
{
	struct tcf_nlcb_context *ctx = arg;
	struct nlmsghdr *cmd;
	struct ifaddrmsg *ifa;
	struct nlattr *na;
	struct nlattr *na_local = NULL;
	struct nlattr *na_peer = NULL;
	unsigned char family;
	uint32_t size;

	if (nlh->nlmsg_type != RTM_NEWADDR) {
		rte_errno = EINVAL;
		return -rte_errno;
	}
	ifa = mnl_nlmsg_get_payload(nlh);
	family = ifa->ifa_family;
	if (ifa->ifa_index != ctx->ifindex ||
	    ifa->ifa_scope != RT_SCOPE_LINK ||
	    !(ifa->ifa_flags & IFA_F_PERMANENT) ||
	    (family != AF_INET && family != AF_INET6))
		return 1;
	mnl_attr_for_each(na, nlh, sizeof(*ifa)) {
		switch (mnl_attr_get_type(na)) {
		case IFA_LOCAL:
			na_local = na;
			break;
		case IFA_ADDRESS:
			na_peer = na;
			break;
		}
		if (na_local && na_peer)
			break;
	}
	if (!na_local || !na_peer)
		return 1;
	/* Local rule found with scope link, permanent and assigned peer. */
	size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
	       MNL_ALIGN(sizeof(struct ifaddrmsg)) +
	       (family == AF_INET6 ? 2 * SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN)
				   : 2 * SZ_NLATTR_TYPE_OF(uint32_t));
	cmd = flow_tcf_alloc_nlcmd(ctx, size);
	if (!cmd) {
		rte_errno = ENOMEM;
		return -rte_errno;
	}
	cmd = mnl_nlmsg_put_header(cmd);
	cmd->nlmsg_type = RTM_DELADDR;
	cmd->nlmsg_flags = NLM_F_REQUEST;
	ifa = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifa));
	ifa->ifa_flags = IFA_F_PERMANENT;
	ifa->ifa_scope = RT_SCOPE_LINK;
	ifa->ifa_index = ctx->ifindex;
	if (family == AF_INET) {
		ifa->ifa_family = AF_INET;
		ifa->ifa_prefixlen = 32;
		mnl_attr_put_u32(cmd, IFA_LOCAL, mnl_attr_get_u32(na_local));
		mnl_attr_put_u32(cmd, IFA_ADDRESS, mnl_attr_get_u32(na_peer));
	} else {
		ifa->ifa_family = AF_INET6;
		ifa->ifa_prefixlen = 128;
		mnl_attr_put(cmd, IFA_LOCAL, IPV6_ADDR_LEN,
			mnl_attr_get_payload(na_local));
		mnl_attr_put(cmd, IFA_ADDRESS, IPV6_ADDR_LEN,
			mnl_attr_get_payload(na_peer));
	}
	assert(size == cmd->nlmsg_len);
	return 1;
}

/**
 * Cleanup the local IP addresses on outer interface.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifindex
 *   Network inferface index to perform cleanup.
 */
static void
flow_tcf_encap_local_cleanup(struct mlx5_flow_tcf_context *tcf,
			    unsigned int ifindex)
{
	struct nlmsghdr *nlh;
	struct ifaddrmsg *ifa;
	struct tcf_nlcb_context ctx = {
		.ifindex = ifindex,
		.bufsize = MNL_REQUEST_SIZE,
		.nlbuf = LIST_HEAD_INITIALIZER(),
	};
	int ret;

	assert(ifindex);
	/*
	 * Seek and destroy leftovers of local IP addresses with
	 * matching properties "scope link".
	 */
	nlh = mnl_nlmsg_put_header(tcf->buf);
	nlh->nlmsg_type = RTM_GETADDR;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
	ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa));
	ifa->ifa_family = AF_UNSPEC;
	ifa->ifa_index = ifindex;
	ifa->ifa_scope = RT_SCOPE_LINK;
	ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_local_cb, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: query device list error %d", ret);
	ret = flow_tcf_send_nlcmd(tcf, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: device delete error %d", ret);
}

/**
 * Collect neigh permament rules on specified network device.
 * This is callback routine called by libmnl mnl_cb_run() in loop for
 * every message in received packet.
 *
 * @param[in] nlh
 *   Pointer to reply header.
 * @param[in, out] arg
 *   Opaque data pointer for this callback.
 *
 * @return
 *   A positive, nonzero value on success, negative errno value otherwise
 *   and rte_errno is set.
 */
static int
flow_tcf_collect_neigh_cb(const struct nlmsghdr *nlh, void *arg)
{
	struct tcf_nlcb_context *ctx = arg;
	struct nlmsghdr *cmd;
	struct ndmsg *ndm;
	struct nlattr *na;
	struct nlattr *na_ip = NULL;
	struct nlattr *na_mac = NULL;
	unsigned char family;
	uint32_t size;

	if (nlh->nlmsg_type != RTM_NEWNEIGH) {
		rte_errno = EINVAL;
		return -rte_errno;
	}
	ndm = mnl_nlmsg_get_payload(nlh);
	family = ndm->ndm_family;
	if (ndm->ndm_ifindex != (int)ctx->ifindex ||
	   !(ndm->ndm_state & NUD_PERMANENT) ||
	   (family != AF_INET && family != AF_INET6))
		return 1;
	mnl_attr_for_each(na, nlh, sizeof(*ndm)) {
		switch (mnl_attr_get_type(na)) {
		case NDA_DST:
			na_ip = na;
			break;
		case NDA_LLADDR:
			na_mac = na;
			break;
		}
		if (na_mac && na_ip)
			break;
	}
	if (!na_mac || !na_ip)
		return 1;
	/* Neigh rule with permenent attribute found. */
	size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
	       MNL_ALIGN(sizeof(struct ndmsg)) +
	       SZ_NLATTR_DATA_OF(ETHER_ADDR_LEN) +
	       (family == AF_INET6 ? SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN)
				   : SZ_NLATTR_TYPE_OF(uint32_t));
	cmd = flow_tcf_alloc_nlcmd(ctx, size);
	if (!cmd) {
		rte_errno = ENOMEM;
		return -rte_errno;
	}
	cmd = mnl_nlmsg_put_header(cmd);
	cmd->nlmsg_type = RTM_DELNEIGH;
	cmd->nlmsg_flags = NLM_F_REQUEST;
	ndm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ndm));
	ndm->ndm_ifindex = ctx->ifindex;
	ndm->ndm_state = NUD_PERMANENT;
	ndm->ndm_flags = 0;
	ndm->ndm_type = 0;
	if (family == AF_INET) {
		ndm->ndm_family = AF_INET;
		mnl_attr_put_u32(cmd, NDA_DST, mnl_attr_get_u32(na_ip));
	} else {
		ndm->ndm_family = AF_INET6;
		mnl_attr_put(cmd, NDA_DST, IPV6_ADDR_LEN,
			     mnl_attr_get_payload(na_ip));
	}
	mnl_attr_put(cmd, NDA_LLADDR, ETHER_ADDR_LEN,
		     mnl_attr_get_payload(na_mac));
	assert(size == cmd->nlmsg_len);
	return 1;
}

/**
 * Cleanup the neigh rules on outer interface.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifindex
 *   Network inferface index to perform cleanup.
 */
static void
flow_tcf_encap_neigh_cleanup(struct mlx5_flow_tcf_context *tcf,
			    unsigned int ifindex)
{
	struct nlmsghdr *nlh;
	struct ndmsg *ndm;
	struct tcf_nlcb_context ctx = {
		.ifindex = ifindex,
		.bufsize = MNL_REQUEST_SIZE,
		.nlbuf = LIST_HEAD_INITIALIZER(),
	};
	int ret;

	assert(ifindex);
	/* Seek and destroy leftovers of neigh rules. */
	nlh = mnl_nlmsg_put_header(tcf->buf);
	nlh->nlmsg_type = RTM_GETNEIGH;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
	ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm));
	ndm->ndm_family = AF_UNSPEC;
	ndm->ndm_ifindex = ifindex;
	ndm->ndm_state = NUD_PERMANENT;
	ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_neigh_cb, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: query device list error %d", ret);
	ret = flow_tcf_send_nlcmd(tcf, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: device delete error %d", ret);
}

/**
 * Collect indices of VXLAN encap/decap interfaces associated with device.
 * This is callback routine called by libmnl mnl_cb_run() in loop for
 * every message in received packet.
 *
 * @param[in] nlh
 *   Pointer to reply header.
 * @param[in, out] arg
 *   Opaque data pointer for this callback.
 *
 * @return
 *   A positive, nonzero value on success, negative errno value otherwise
 *   and rte_errno is set.
 */
static int
flow_tcf_collect_vxlan_cb(const struct nlmsghdr *nlh, void *arg)
{
	struct tcf_nlcb_context *ctx = arg;
	struct nlmsghdr *cmd;
	struct ifinfomsg *ifm;
	struct nlattr *na;
	struct nlattr *na_info = NULL;
	struct nlattr *na_vxlan = NULL;
	bool found = false;
	unsigned int vxindex;
	uint32_t size;

	if (nlh->nlmsg_type != RTM_NEWLINK) {
		rte_errno = EINVAL;
		return -rte_errno;
	}
	ifm = mnl_nlmsg_get_payload(nlh);
	if (!ifm->ifi_index) {
		rte_errno = EINVAL;
		return -rte_errno;
	}
	mnl_attr_for_each(na, nlh, sizeof(*ifm))
		if (mnl_attr_get_type(na) == IFLA_LINKINFO) {
			na_info = na;
			break;
		}
	if (!na_info)
		return 1;
	mnl_attr_for_each_nested(na, na_info) {
		switch (mnl_attr_get_type(na)) {
		case IFLA_INFO_KIND:
			if (!strncmp("vxlan", mnl_attr_get_str(na),
				     mnl_attr_get_len(na)))
				found = true;
			break;
		case IFLA_INFO_DATA:
			na_vxlan = na;
			break;
		}
		if (found && na_vxlan)
			break;
	}
	if (!found || !na_vxlan)
		return 1;
	found = false;
	mnl_attr_for_each_nested(na, na_vxlan) {
		if (mnl_attr_get_type(na) == IFLA_VXLAN_LINK &&
		    mnl_attr_get_u32(na) == ctx->ifindex) {
			found = true;
			break;
		}
	}
	if (!found)
		return 1;
	/* Attached VXLAN device found, store the command to delete. */
	vxindex = ifm->ifi_index;
	size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
	       MNL_ALIGN(sizeof(struct ifinfomsg));
	cmd = flow_tcf_alloc_nlcmd(ctx, size);
	if (!cmd) {
		rte_errno = ENOMEM;
		return -rte_errno;
	}
	cmd = mnl_nlmsg_put_header(cmd);
	cmd->nlmsg_type = RTM_DELLINK;
	cmd->nlmsg_flags = NLM_F_REQUEST;
	ifm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifm));
	ifm->ifi_family = AF_UNSPEC;
	ifm->ifi_index = vxindex;
	assert(size == cmd->nlmsg_len);
	return 1;
}

/**
 * Cleanup the outer interface. Removes all found vxlan devices
 * attached to specified index, flushes the meigh and local IP
 * datavase.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifindex
 *   Network inferface index to perform cleanup.
 */
static void
flow_tcf_encap_iface_cleanup(struct mlx5_flow_tcf_context *tcf,
			    unsigned int ifindex)
{
	struct nlmsghdr *nlh;
	struct ifinfomsg *ifm;
	struct tcf_nlcb_context ctx = {
		.ifindex = ifindex,
		.bufsize = MNL_REQUEST_SIZE,
		.nlbuf = LIST_HEAD_INITIALIZER(),
	};
	int ret;

	assert(ifindex);
	/*
	 * Seek and destroy leftover VXLAN encap/decap interfaces with
	 * matching properties.
	 */
	nlh = mnl_nlmsg_put_header(tcf->buf);
	nlh->nlmsg_type = RTM_GETLINK;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
	ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
	ifm->ifi_family = AF_UNSPEC;
	ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_vxlan_cb, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: query device list error %d", ret);
	ret = flow_tcf_send_nlcmd(tcf, &ctx);
	if (ret)
		DRV_LOG(WARNING, "netlink: device delete error %d", ret);
}

/**
 * Emit Netlink message to add/remove local address to the outer device.
 * The address being added is visible within the link only (scope link).
 *
 * Note that an implicit route is maintained by the kernel due to the
 * presence of a peer address (IFA_ADDRESS).
 *
 * These rules are used for encapsultion only and allow to assign
 * the outer tunnel source IP address.
 *
 * @param[in] tcf
 *   Libmnl socket context object.
 * @param[in] encap
 *   Encapsulation properties (source address and its peer).
 * @param[in] ifindex
 *   Network interface to apply rule.
 * @param[in] enable
 *   Toggle between add and remove.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_rule_local(struct mlx5_flow_tcf_context *tcf,
		    const struct flow_tcf_vxlan_encap *encap,
		    unsigned int ifindex,
		    bool enable,
		    struct rte_flow_error *error)
{
	struct nlmsghdr *nlh;
	struct ifaddrmsg *ifa;
	alignas(struct nlmsghdr)
	uint8_t buf[mnl_nlmsg_size(sizeof(*ifa) + 128)];

	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = enable ? RTM_NEWADDR : RTM_DELADDR;
	nlh->nlmsg_flags =
		NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0);
	nlh->nlmsg_seq = 0;
	ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa));
	ifa->ifa_flags = IFA_F_PERMANENT;
	ifa->ifa_scope = RT_SCOPE_LINK;
	ifa->ifa_index = ifindex;
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
		ifa->ifa_family = AF_INET;
		ifa->ifa_prefixlen = 32;
		mnl_attr_put_u32(nlh, IFA_LOCAL, encap->ipv4.src);
		if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST)
			mnl_attr_put_u32(nlh, IFA_ADDRESS,
					      encap->ipv4.dst);
	} else {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
		ifa->ifa_family = AF_INET6;
		ifa->ifa_prefixlen = 128;
		mnl_attr_put(nlh, IFA_LOCAL,
				  sizeof(encap->ipv6.src),
				  &encap->ipv6.src);
		if (encap->mask & FLOW_TCF_ENCAP_IPV6_DST)
			mnl_attr_put(nlh, IFA_ADDRESS,
					  sizeof(encap->ipv6.dst),
					  &encap->ipv6.dst);
	}
	if (!flow_tcf_nl_ack(tcf, nlh, NULL, NULL))
		return 0;
	return rte_flow_error_set(error, rte_errno,
				  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				  "netlink: cannot complete IFA request"
				  " (ip addr add)");
}

/**
 * Emit Netlink message to add/remove neighbor.
 *
 * @param[in] tcf
 *   Libmnl socket context object.
 * @param[in] encap
 *   Encapsulation properties (destination address).
 * @param[in] ifindex
 *   Network interface.
 * @param[in] enable
 *   Toggle between add and remove.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_rule_neigh(struct mlx5_flow_tcf_context *tcf,
		     const struct flow_tcf_vxlan_encap *encap,
		     unsigned int ifindex,
		     bool enable,
		     struct rte_flow_error *error)
{
	struct nlmsghdr *nlh;
	struct ndmsg *ndm;
	alignas(struct nlmsghdr)
	uint8_t buf[mnl_nlmsg_size(sizeof(*ndm) + 128)];

	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = enable ? RTM_NEWNEIGH : RTM_DELNEIGH;
	nlh->nlmsg_flags =
		NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0);
	nlh->nlmsg_seq = 0;
	ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm));
	ndm->ndm_ifindex = ifindex;
	ndm->ndm_state = NUD_PERMANENT;
	ndm->ndm_flags = 0;
	ndm->ndm_type = 0;
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
		ndm->ndm_family = AF_INET;
		mnl_attr_put_u32(nlh, NDA_DST, encap->ipv4.dst);
	} else {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
		ndm->ndm_family = AF_INET6;
		mnl_attr_put(nlh, NDA_DST, sizeof(encap->ipv6.dst),
						 &encap->ipv6.dst);
	}
	if (encap->mask & FLOW_TCF_ENCAP_ETH_SRC && enable)
		DRV_LOG(WARNING,
			"outer ethernet source address cannot be "
			"forced for VXLAN encapsulation");
	if (encap->mask & FLOW_TCF_ENCAP_ETH_DST)
		mnl_attr_put(nlh, NDA_LLADDR, sizeof(encap->eth.dst),
						    &encap->eth.dst);
	if (!flow_tcf_nl_ack(tcf, nlh, NULL, NULL))
		return 0;
	return rte_flow_error_set(error, rte_errno,
				  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				  "netlink: cannot complete ND request"
				  " (ip neigh)");
}

/**
 * Manage the local IP addresses and their peers IP addresses on the
 * outer interface for encapsulation purposes. The kernel searches the
 * appropriate device for tunnel egress traffic using the outer source
 * IP, this IP should be assigned to the outer network device, otherwise
 * kernel rejects the rule.
 *
 * Adds or removes the addresses using the Netlink command like this:
 *   ip addr add <src_ip> peer <dst_ip> scope link dev <ifouter>
 *
 * The addresses are local to the netdev ("scope link"), this reduces
 * the risk of conflicts. Note that an implicit route is maintained by
 * the kernel due to the presence of a peer address (IFA_ADDRESS).
 *
 * @param[in] tcf
 *   Libmnl socket context object.
 * @param[in] vtep
 *   VTEP object, contains rule database and ifouter index.
 * @param[in] dev_flow
 *   Flow object, contains the tunnel parameters (for encap only).
 * @param[in] enable
 *   Toggle between add and remove.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_encap_local(struct mlx5_flow_tcf_context *tcf,
		     struct tcf_vtep *vtep,
		     struct mlx5_flow *dev_flow,
		     bool enable,
		     struct rte_flow_error *error)
{
	const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap;
	struct tcf_local_rule *rule;
	bool found = false;
	int ret;

	assert(encap);
	assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP);
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV4_DST);
		LIST_FOREACH(rule, &vtep->local, next) {
			if (rule->mask & FLOW_TCF_ENCAP_IPV4_SRC &&
			    encap->ipv4.src == rule->ipv4.src &&
			    encap->ipv4.dst == rule->ipv4.dst) {
				found = true;
				break;
			}
		}
	} else {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
		LIST_FOREACH(rule, &vtep->local, next) {
			if (rule->mask & FLOW_TCF_ENCAP_IPV6_SRC &&
			    !memcmp(&encap->ipv6.src, &rule->ipv6.src,
					    sizeof(encap->ipv6.src)) &&
			    !memcmp(&encap->ipv6.dst, &rule->ipv6.dst,
					    sizeof(encap->ipv6.dst))) {
				found = true;
				break;
			}
		}
	}
	if (found) {
		if (enable) {
			rule->refcnt++;
			return 0;
		}
		if (!rule->refcnt || !--rule->refcnt) {
			LIST_REMOVE(rule, next);
			return flow_tcf_rule_local(tcf, encap,
					vtep->ifouter, false, error);
		}
		return 0;
	}
	if (!enable) {
		DRV_LOG(WARNING, "disabling not existing local rule");
		rte_flow_error_set(error, ENOENT,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "disabling not existing local rule");
		return -ENOENT;
	}
	rule = rte_zmalloc(__func__, sizeof(struct tcf_local_rule),
				alignof(struct tcf_local_rule));
	if (!rule) {
		rte_flow_error_set(error, ENOMEM,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "unable to allocate memory for local rule");
		return -rte_errno;
	}
	*rule = (struct tcf_local_rule){.refcnt = 0,
					.mask = 0,
					};
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
		rule->mask = FLOW_TCF_ENCAP_IPV4_SRC
			   | FLOW_TCF_ENCAP_IPV4_DST;
		rule->ipv4.src = encap->ipv4.src;
		rule->ipv4.dst = encap->ipv4.dst;
	} else {
		rule->mask = FLOW_TCF_ENCAP_IPV6_SRC
			   | FLOW_TCF_ENCAP_IPV6_DST;
		memcpy(&rule->ipv6.src, &encap->ipv6.src, IPV6_ADDR_LEN);
		memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN);
	}
	ret = flow_tcf_rule_local(tcf, encap, vtep->ifouter, true, error);
	if (ret) {
		rte_free(rule);
		return ret;
	}
	rule->refcnt++;
	LIST_INSERT_HEAD(&vtep->local, rule, next);
	return 0;
}

/**
 * Manage the destination MAC/IP addresses neigh database, kernel uses
 * this one to determine the destination MAC address within encapsulation
 * header. Adds or removes the entries using the Netlink command like this:
 *   ip neigh add dev <ifouter> lladdr <dst_mac> to <dst_ip> nud permanent
 *
 * @param[in] tcf
 *   Libmnl socket context object.
 * @param[in] vtep
 *   VTEP object, contains rule database and ifouter index.
 * @param[in] dev_flow
 *   Flow object, contains the tunnel parameters (for encap only).
 * @param[in] enable
 *   Toggle between add and remove.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_encap_neigh(struct mlx5_flow_tcf_context *tcf,
		     struct tcf_vtep *vtep,
		     struct mlx5_flow *dev_flow,
		     bool enable,
		     struct rte_flow_error *error)
{
	const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap;
	struct tcf_neigh_rule *rule;
	bool found = false;
	int ret;

	assert(encap);
	assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP);
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV4_SRC);
		LIST_FOREACH(rule, &vtep->neigh, next) {
			if (rule->mask & FLOW_TCF_ENCAP_IPV4_DST &&
			    encap->ipv4.dst == rule->ipv4.dst) {
				found = true;
				break;
			}
		}
	} else {
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
		assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
		LIST_FOREACH(rule, &vtep->neigh, next) {
			if (rule->mask & FLOW_TCF_ENCAP_IPV6_DST &&
			    !memcmp(&encap->ipv6.dst, &rule->ipv6.dst,
						sizeof(encap->ipv6.dst))) {
				found = true;
				break;
			}
		}
	}
	if (found) {
		if (memcmp(&encap->eth.dst, &rule->eth,
			   sizeof(encap->eth.dst))) {
			DRV_LOG(WARNING, "Destination MAC differs"
					 " in neigh rule");
			rte_flow_error_set(error, EEXIST,
					   RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
					   NULL, "Different MAC address"
					   " neigh rule for the same"
					   " destination IP");
					return -EEXIST;
		}
		if (enable) {
			rule->refcnt++;
			return 0;
		}
		if (!rule->refcnt || !--rule->refcnt) {
			LIST_REMOVE(rule, next);
			return flow_tcf_rule_neigh(tcf, encap,
						   vtep->ifouter,
						   false, error);
		}
		return 0;
	}
	if (!enable) {
		DRV_LOG(WARNING, "Disabling not existing neigh rule");
		rte_flow_error_set(error, ENOENT,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "unable to allocate memory for neigh rule");
		return -ENOENT;
	}
	rule = rte_zmalloc(__func__, sizeof(struct tcf_neigh_rule),
				alignof(struct tcf_neigh_rule));
	if (!rule) {
		rte_flow_error_set(error, ENOMEM,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "unable to allocate memory for neigh rule");
		return -rte_errno;
	}
	*rule = (struct tcf_neigh_rule){.refcnt = 0,
					.mask = 0,
					};
	if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
		rule->mask = FLOW_TCF_ENCAP_IPV4_DST;
		rule->ipv4.dst = encap->ipv4.dst;
	} else {
		rule->mask = FLOW_TCF_ENCAP_IPV6_DST;
		memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN);
	}
	memcpy(&rule->eth, &encap->eth.dst, sizeof(rule->eth));
	ret = flow_tcf_rule_neigh(tcf, encap, vtep->ifouter, true, error);
	if (ret) {
		rte_free(rule);
		return ret;
	}
	rule->refcnt++;
	LIST_INSERT_HEAD(&vtep->neigh, rule, next);
	return 0;
}

/* VTEP device list is shared between PMD port instances. */
static LIST_HEAD(, tcf_vtep) vtep_list_vxlan = LIST_HEAD_INITIALIZER();
static pthread_mutex_t vtep_list_mutex = PTHREAD_MUTEX_INITIALIZER;

/**
 * Deletes VTEP network device.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] vtep
 *   Object represinting the network device to delete. Memory
 *   allocated for this object is freed by routine.
 */
static void
flow_tcf_vtep_delete(struct mlx5_flow_tcf_context *tcf,
		     struct tcf_vtep *vtep)
{
	struct nlmsghdr *nlh;
	struct ifinfomsg *ifm;
	alignas(struct nlmsghdr)
	uint8_t buf[mnl_nlmsg_size(MNL_ALIGN(sizeof(*ifm))) +
		    MNL_BUF_EXTRA_SPACE];
	int ret;

	assert(!vtep->refcnt);
	/* Delete only ifaces those we actually created. */
	if (vtep->created && vtep->ifindex) {
		DRV_LOG(INFO, "VTEP delete (%d)", vtep->ifindex);
		nlh = mnl_nlmsg_put_header(buf);
		nlh->nlmsg_type = RTM_DELLINK;
		nlh->nlmsg_flags = NLM_F_REQUEST;
		ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
		ifm->ifi_family = AF_UNSPEC;
		ifm->ifi_index = vtep->ifindex;
		assert(sizeof(buf) >= nlh->nlmsg_len);
		ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
		if (ret)
			DRV_LOG(WARNING, "netlink: error deleting vxlan"
					 " encap/decap ifindex %u",
					 ifm->ifi_index);
	}
	rte_free(vtep);
}

/**
 * Creates VTEP network device.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifouter
 *   Outer interface to attach new-created VXLAN device
 *   If zero the VXLAN device will not be attached to any device.
 *   These VTEPs are used for decapsulation and can be precreated
 *   and shared between processes.
 * @param[in] port
 *   UDP port of created VTEP device.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 * Pointer to created device structure on success,
 * NULL otherwise and rte_errno is set.
 */
#ifdef HAVE_IFLA_VXLAN_COLLECT_METADATA
static struct tcf_vtep*
flow_tcf_vtep_create(struct mlx5_flow_tcf_context *tcf,
		     unsigned int ifouter,
		     uint16_t port, struct rte_flow_error *error)
{
	struct tcf_vtep *vtep;
	struct nlmsghdr *nlh;
	struct ifinfomsg *ifm;
	char name[sizeof(MLX5_VXLAN_DEVICE_PFX) + 24];
	alignas(struct nlmsghdr)
	uint8_t buf[mnl_nlmsg_size(sizeof(*ifm)) +
		    SZ_NLATTR_DATA_OF(sizeof(name)) +
		    SZ_NLATTR_NEST * 2 +
		    SZ_NLATTR_STRZ_OF("vxlan") +
		    SZ_NLATTR_DATA_OF(sizeof(uint32_t)) +
		    SZ_NLATTR_DATA_OF(sizeof(uint16_t)) +
		    SZ_NLATTR_DATA_OF(sizeof(uint8_t)) * 3 +
		    MNL_BUF_EXTRA_SPACE];
	struct nlattr *na_info;
	struct nlattr *na_vxlan;
	rte_be16_t vxlan_port = rte_cpu_to_be_16(port);
	int ret;

	vtep = rte_zmalloc(__func__, sizeof(*vtep), alignof(struct tcf_vtep));
	if (!vtep) {
		rte_flow_error_set(error, ENOMEM,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "unable to allocate memory for VTEP");
		return NULL;
	}
	*vtep = (struct tcf_vtep){
			.port = port,
			.local = LIST_HEAD_INITIALIZER(),
			.neigh = LIST_HEAD_INITIALIZER(),
	};
	memset(buf, 0, sizeof(buf));
	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = RTM_NEWLINK;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE  | NLM_F_EXCL;
	ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
	ifm->ifi_family = AF_UNSPEC;
	ifm->ifi_type = 0;
	ifm->ifi_index = 0;
	ifm->ifi_flags = IFF_UP;
	ifm->ifi_change = 0xffffffff;
	snprintf(name, sizeof(name), "%s%u", MLX5_VXLAN_DEVICE_PFX, port);
	mnl_attr_put_strz(nlh, IFLA_IFNAME, name);
	na_info = mnl_attr_nest_start(nlh, IFLA_LINKINFO);
	assert(na_info);
	mnl_attr_put_strz(nlh, IFLA_INFO_KIND, "vxlan");
	na_vxlan = mnl_attr_nest_start(nlh, IFLA_INFO_DATA);
	if (ifouter)
		mnl_attr_put_u32(nlh, IFLA_VXLAN_LINK, ifouter);
	assert(na_vxlan);
	mnl_attr_put_u8(nlh, IFLA_VXLAN_COLLECT_METADATA, 1);
	mnl_attr_put_u8(nlh, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, 1);
	mnl_attr_put_u8(nlh, IFLA_VXLAN_LEARNING, 0);
	mnl_attr_put_u16(nlh, IFLA_VXLAN_PORT, vxlan_port);
	mnl_attr_nest_end(nlh, na_vxlan);
	mnl_attr_nest_end(nlh, na_info);
	assert(sizeof(buf) >= nlh->nlmsg_len);
	ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
	if (ret) {
		DRV_LOG(WARNING,
			"netlink: VTEP %s create failure (%d)",
			name, rte_errno);
		if (rte_errno != EEXIST || ifouter)
			/*
			 * Some unhandled error occurred or device is
			 * for encapsulation and cannot be shared.
			 */
			goto error;
	} else {
		/*
		 * Mark device we actually created.
		 * We should explicitly delete
		 * when we do not need it anymore.
		 */
		vtep->created = 1;
	}
	/* Try to get ifindex of created of pre-existing device. */
	ret = if_nametoindex(name);
	if (!ret) {
		DRV_LOG(WARNING,
			"VTEP %s failed to get index (%d)", name, errno);
		rte_flow_error_set
			(error, -errno,
			 RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
			 "netlink: failed to retrieve VTEP ifindex");
		goto error;
	}
	vtep->ifindex = ret;
	vtep->ifouter = ifouter;
	memset(buf, 0, sizeof(buf));
	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = RTM_NEWLINK;
	nlh->nlmsg_flags = NLM_F_REQUEST;
	ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
	ifm->ifi_family = AF_UNSPEC;
	ifm->ifi_type = 0;
	ifm->ifi_index = vtep->ifindex;
	ifm->ifi_flags = IFF_UP;
	ifm->ifi_change = IFF_UP;
	ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
	if (ret) {
		rte_flow_error_set(error, -errno,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "netlink: failed to set VTEP link up");
		DRV_LOG(WARNING, "netlink: VTEP %s set link up failure (%d)",
			name, rte_errno);
		goto clean;
	}
	ret = mlx5_flow_tcf_init(tcf, vtep->ifindex, error);
	if (ret) {
		DRV_LOG(WARNING, "VTEP %s init failure (%d)", name, rte_errno);
		goto clean;
	}
	DRV_LOG(INFO, "VTEP create (%d, %d)", vtep->port, vtep->ifindex);
	vtep->refcnt = 1;
	return vtep;
clean:
	flow_tcf_vtep_delete(tcf, vtep);
	return NULL;
error:
	rte_free(vtep);
	return NULL;
}
#else
static struct tcf_vtep*
flow_tcf_vtep_create(struct mlx5_flow_tcf_context *tcf __rte_unused,
		     unsigned int ifouter __rte_unused,
		     uint16_t port __rte_unused,
		     struct rte_flow_error *error)
{
	rte_flow_error_set(error, ENOTSUP,
			   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
			   "netlink: failed to create VTEP, "
			   "vxlan metadata are not supported by kernel");
	return NULL;
}
#endif /* HAVE_IFLA_VXLAN_COLLECT_METADATA */

/**
 * Acquire target interface index for VXLAN tunneling decapsulation.
 * In order to share the UDP port within the other interfaces the
 * VXLAN device created as not attached to any interface (if created).
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] dev_flow
 *   Flow tcf object with tunnel structure pointer set.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 * @return
 *   Interface descriptor pointer on success,
 *   NULL otherwise and rte_errno is set.
 */
static struct tcf_vtep*
flow_tcf_decap_vtep_acquire(struct mlx5_flow_tcf_context *tcf,
			    struct mlx5_flow *dev_flow,
			    struct rte_flow_error *error)
{
	struct tcf_vtep *vtep;
	uint16_t port = dev_flow->tcf.vxlan_decap->udp_port;

	LIST_FOREACH(vtep, &vtep_list_vxlan, next) {
		if (vtep->port == port)
			break;
	}
	if (vtep && vtep->ifouter) {
		rte_flow_error_set(error, -errno,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "Failed to create decap VTEP with specified"
				   " UDP port, atatched device exists");
		return NULL;
	}
	if (vtep) {
		/* Device exists, just increment the reference counter. */
		vtep->refcnt++;
		assert(vtep->ifindex);
		return vtep;
	}
	/* No decapsulation device exists, try to create the new one. */
	vtep = flow_tcf_vtep_create(tcf, 0, port, error);
	if (vtep)
		LIST_INSERT_HEAD(&vtep_list_vxlan, vtep, next);
	return vtep;
}

/**
 * Aqcuire target interface index for VXLAN tunneling encapsulation.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifouter
 *   Network interface index to attach VXLAN encap device to.
 * @param[in] dev_flow
 *   Flow tcf object with tunnel structure pointer set.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 * @return
 *   Interface descriptor pointer on success,
 *   NULL otherwise and rte_errno is set.
 */
static struct tcf_vtep*
flow_tcf_encap_vtep_acquire(struct mlx5_flow_tcf_context *tcf,
			    unsigned int ifouter,
			    struct mlx5_flow *dev_flow __rte_unused,
			    struct rte_flow_error *error)
{
	static uint16_t encap_port = MLX5_VXLAN_PORT_MIN - 1;
	struct tcf_vtep *vtep;
	int ret;

	assert(ifouter);
	/* Look whether the attached VTEP for encap is created. */
	LIST_FOREACH(vtep, &vtep_list_vxlan, next) {
		if (vtep->ifouter == ifouter)
			break;
	}
	if (vtep) {
		/* VTEP already exists, just increment the reference. */
		vtep->refcnt++;
	} else {
		uint16_t pcnt;

		/* Not found, we should create the new attached VTEP. */
		flow_tcf_encap_iface_cleanup(tcf, ifouter);
		flow_tcf_encap_local_cleanup(tcf, ifouter);
		flow_tcf_encap_neigh_cleanup(tcf, ifouter);
		for (pcnt = 0; pcnt <= (MLX5_VXLAN_PORT_MAX
				     - MLX5_VXLAN_PORT_MIN); pcnt++) {
			encap_port++;
			/* Wraparound the UDP port index. */
			if (encap_port < MLX5_VXLAN_PORT_MIN ||
			    encap_port > MLX5_VXLAN_PORT_MAX)
				encap_port = MLX5_VXLAN_PORT_MIN;
			/* Check whether UDP port is in already in use. */
			LIST_FOREACH(vtep, &vtep_list_vxlan, next) {
				if (vtep->port == encap_port)
					break;
			}
			if (vtep) {
				/* Port is in use, try the next one. */
				vtep = NULL;
				continue;
			}
			vtep = flow_tcf_vtep_create(tcf, ifouter,
						    encap_port, error);
			if (vtep) {
				LIST_INSERT_HEAD(&vtep_list_vxlan, vtep, next);
				break;
			}
			if (rte_errno != EEXIST)
				break;
		}
		if (!vtep)
			return NULL;
	}
	assert(vtep->ifouter == ifouter);
	assert(vtep->ifindex);
	/* Create local ipaddr with peer to specify the outer IPs. */
	ret = flow_tcf_encap_local(tcf, vtep, dev_flow, true, error);
	if (!ret) {
		/* Create neigh rule to specify outer destination MAC. */
		ret = flow_tcf_encap_neigh(tcf, vtep, dev_flow, true, error);
		if (ret)
			flow_tcf_encap_local(tcf, vtep,
					     dev_flow, false, error);
	}
	if (ret) {
		if (--vtep->refcnt == 0)
			flow_tcf_vtep_delete(tcf, vtep);
		return NULL;
	}
	return vtep;
}

/**
 * Acquires target interface index for tunneling of any type.
 * Creates the new VTEP if needed.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] ifouter
 *   Network interface index to attach VXLAN encap device to.
 * @param[in] dev_flow
 *   Flow tcf object with tunnel structure pointer set.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 * @return
 *   Interface descriptor pointer on success,
 *   NULL otherwise and rte_errno is set.
 */
static struct tcf_vtep*
flow_tcf_vtep_acquire(struct mlx5_flow_tcf_context *tcf,
		      unsigned int ifouter,
		      struct mlx5_flow *dev_flow,
		      struct rte_flow_error *error)
{
	struct tcf_vtep *vtep = NULL;

	assert(dev_flow->tcf.tunnel);
	pthread_mutex_lock(&vtep_list_mutex);
	switch (dev_flow->tcf.tunnel->type) {
	case FLOW_TCF_TUNACT_VXLAN_ENCAP:
		vtep = flow_tcf_encap_vtep_acquire(tcf, ifouter,
						  dev_flow, error);
		break;
	case FLOW_TCF_TUNACT_VXLAN_DECAP:
		vtep = flow_tcf_decap_vtep_acquire(tcf, dev_flow, error);
		break;
	default:
		rte_flow_error_set(error, ENOTSUP,
				   RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				   "unsupported tunnel type");
		break;
	}
	pthread_mutex_unlock(&vtep_list_mutex);
	return vtep;
}

/**
 * Release tunneling interface by ifindex. Decrements reference
 * counter and actually removes the device if counter is zero.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] vtep
 *   VTEP device descriptor structure.
 * @param[in] dev_flow
 *   Flow tcf object with tunnel structure pointer set.
 */
static void
flow_tcf_vtep_release(struct mlx5_flow_tcf_context *tcf,
		      struct tcf_vtep *vtep,
		      struct mlx5_flow *dev_flow)
{
	assert(dev_flow->tcf.tunnel);
	pthread_mutex_lock(&vtep_list_mutex);
	switch (dev_flow->tcf.tunnel->type) {
	case FLOW_TCF_TUNACT_VXLAN_DECAP:
		break;
	case FLOW_TCF_TUNACT_VXLAN_ENCAP:
		/* Remove the encap ancillary rules first. */
		flow_tcf_encap_neigh(tcf, vtep, dev_flow, false, NULL);
		flow_tcf_encap_local(tcf, vtep, dev_flow, false, NULL);
		break;
	default:
		assert(false);
		DRV_LOG(WARNING, "Unsupported tunnel type");
		break;
	}
	assert(vtep->refcnt);
	if (--vtep->refcnt == 0) {
		LIST_REMOVE(vtep, next);
		flow_tcf_vtep_delete(tcf, vtep);
	}
	pthread_mutex_unlock(&vtep_list_mutex);
}

struct tcf_nlcb_query {
	uint32_t handle;
	uint32_t tc_flags;
	uint32_t flags_valid:1;
};

/**
 * Collect queried rule attributes. This is callback routine called by
 * libmnl mnl_cb_run() in loop for every message in received packet.
 * Current implementation collects the flower flags only.
 *
 * @param[in] nlh
 *   Pointer to reply header.
 * @param[in, out] arg
 *   Context pointer for this callback.
 *
 * @return
 *   A positive, nonzero value on success (required by libmnl
 *   to continue messages processing).
 */
static int
flow_tcf_collect_query_cb(const struct nlmsghdr *nlh, void *arg)
{
	struct tcf_nlcb_query *query = arg;
	struct tcmsg *tcm = mnl_nlmsg_get_payload(nlh);
	struct nlattr *na, *na_opt;
	bool flower = false;

	if (nlh->nlmsg_type != RTM_NEWTFILTER ||
	    tcm->tcm_handle != query->handle)
		return 1;
	mnl_attr_for_each(na, nlh, sizeof(*tcm)) {
		switch (mnl_attr_get_type(na)) {
		case TCA_KIND:
			if (strcmp(mnl_attr_get_payload(na), "flower")) {
				/* Not flower filter, drop entire message. */
				return 1;
			}
			flower = true;
			break;
		case TCA_OPTIONS:
			if (!flower) {
				/* Not flower options, drop entire message. */
				return 1;
			}
			/* Check nested flower options. */
			mnl_attr_for_each_nested(na_opt, na) {
				switch (mnl_attr_get_type(na_opt)) {
				case TCA_FLOWER_FLAGS:
					query->flags_valid = 1;
					query->tc_flags =
						mnl_attr_get_u32(na_opt);
					break;
				}
			}
			break;
		}
	}
	return 1;
}

/**
 * Query a TC flower rule flags via netlink.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] dev_flow
 *   Pointer to the flow.
 * @param[out] pflags
 *   pointer to the data retrieved by the query.
 *
 * @return
 *   0 on success, a negative errno value otherwise.
 */
static int
flow_tcf_query_flags(struct mlx5_flow_tcf_context *tcf,
		     struct mlx5_flow *dev_flow,
		     uint32_t *pflags)
{
	struct nlmsghdr *nlh;
	struct tcmsg *tcm;
	struct tcf_nlcb_query query = {
		.handle = dev_flow->tcf.tcm->tcm_handle,
	};

	nlh = mnl_nlmsg_put_header(tcf->buf);
	nlh->nlmsg_type = RTM_GETTFILTER;
	nlh->nlmsg_flags = NLM_F_REQUEST;
	tcm = mnl_nlmsg_put_extra_header(nlh, sizeof(*tcm));
	memcpy(tcm, dev_flow->tcf.tcm, sizeof(*tcm));
	/*
	 * Ignore Netlink error for filter query operations.
	 * The reply length is sent by kernel as errno.
	 * Just check we got the flags option.
	 */
	flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_query_cb, &query);
	if (!query.flags_valid) {
		*pflags = 0;
		return -ENOENT;
	}
	*pflags = query.tc_flags;
	return 0;
}

/**
 * Query and check the in_hw set for specified rule.
 *
 * @param[in] tcf
 *   Context object initialized by mlx5_flow_tcf_context_create().
 * @param[in] dev_flow
 *   Pointer to the flow to check.
 *
 * @return
 *   0 on success, a negative errno value otherwise.
 */
static int
flow_tcf_check_inhw(struct mlx5_flow_tcf_context *tcf,
		    struct mlx5_flow *dev_flow)
{
	uint32_t flags;
	int ret;

	ret = flow_tcf_query_flags(tcf, dev_flow, &flags);
	if (ret)
		return ret;
	return  (flags & TCA_CLS_FLAGS_IN_HW) ? 0 : -ENOENT;
}

/**
 * Remove flow from E-Switch by sending Netlink message.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[in, out] flow
 *   Pointer to the sub flow.
 */
static void
flow_tcf_remove(struct rte_eth_dev *dev, struct rte_flow *flow)
{
	struct priv *priv = dev->data->dev_private;
	struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
	struct mlx5_flow *dev_flow;
	struct nlmsghdr *nlh;

	if (!flow)
		return;
	dev_flow = LIST_FIRST(&flow->dev_flows);
	if (!dev_flow)
		return;
	/* E-Switch flow can't be expanded. */
	assert(!LIST_NEXT(dev_flow, next));
	if (dev_flow->tcf.applied) {
		nlh = dev_flow->tcf.nlh;
		nlh->nlmsg_type = RTM_DELTFILTER;
		nlh->nlmsg_flags = NLM_F_REQUEST;
		flow_tcf_nl_ack(ctx, nlh, NULL, NULL);
		if (dev_flow->tcf.tunnel) {
			assert(dev_flow->tcf.tunnel->vtep);
			flow_tcf_vtep_release(ctx,
				dev_flow->tcf.tunnel->vtep,
				dev_flow);
			dev_flow->tcf.tunnel->vtep = NULL;
		}
		dev_flow->tcf.applied = 0;
	}
}

/**
 * Apply flow to E-Switch by sending Netlink message.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[in, out] flow
 *   Pointer to the sub flow.
 * @param[out] error
 *   Pointer to the error structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_ernno is set.
 */
static int
flow_tcf_apply(struct rte_eth_dev *dev, struct rte_flow *flow,
	       struct rte_flow_error *error)
{
	struct priv *priv = dev->data->dev_private;
	struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
	struct mlx5_flow *dev_flow;
	struct nlmsghdr *nlh;

	dev_flow = LIST_FIRST(&flow->dev_flows);
	/* E-Switch flow can't be expanded. */
	assert(!LIST_NEXT(dev_flow, next));
	if (dev_flow->tcf.applied)
		return 0;
	nlh = dev_flow->tcf.nlh;
	nlh->nlmsg_type = RTM_NEWTFILTER;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
	if (dev_flow->tcf.tunnel) {
		/*
		 * Replace the interface index, target for
		 * encapsulation, source for decapsulation.
		 */
		assert(!dev_flow->tcf.tunnel->vtep);
		assert(dev_flow->tcf.tunnel->ifindex_ptr);
		/* Acquire actual VTEP device when rule is being applied. */
		dev_flow->tcf.tunnel->vtep =
			flow_tcf_vtep_acquire(ctx,
					dev_flow->tcf.tunnel->ifindex_org,
					dev_flow, error);
		if (!dev_flow->tcf.tunnel->vtep)
			return -rte_errno;
		DRV_LOG(INFO, "Replace ifindex: %d->%d",
				dev_flow->tcf.tunnel->vtep->ifindex,
				dev_flow->tcf.tunnel->ifindex_org);
		*dev_flow->tcf.tunnel->ifindex_ptr =
			dev_flow->tcf.tunnel->vtep->ifindex;
	}
	if (!flow_tcf_nl_ack(ctx, nlh, NULL, NULL)) {
		dev_flow->tcf.applied = 1;
		if (*dev_flow->tcf.ptc_flags & TCA_CLS_FLAGS_SKIP_SW)
			return 0;
		/*
		 * Rule was applied without skip_sw flag set.
		 * We should check whether the rule was acctually
		 * accepted by hardware (have look at in_hw flag).
		 */
		if (flow_tcf_check_inhw(ctx, dev_flow)) {
			flow_tcf_remove(dev, flow);
			return rte_flow_error_set
				(error, ENOENT,
				 RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				 "netlink: rule has no in_hw flag set");
		}
		return 0;
	}
	if (dev_flow->tcf.tunnel) {
		/* Rollback the VTEP configuration if rule apply failed. */
		assert(dev_flow->tcf.tunnel->vtep);
		flow_tcf_vtep_release(ctx, dev_flow->tcf.tunnel->vtep,
				      dev_flow);
		dev_flow->tcf.tunnel->vtep = NULL;
	}
	return rte_flow_error_set(error, rte_errno,
				  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
				  "netlink: failed to create TC flow rule");
}

/**
 * Remove flow from E-Switch and release resources of the device flow.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[in, out] flow
 *   Pointer to the sub flow.
 */
static void
flow_tcf_destroy(struct rte_eth_dev *dev, struct rte_flow *flow)
{
	struct mlx5_flow *dev_flow;

	if (!flow)
		return;
	flow_tcf_remove(dev, flow);
	if (flow->counter) {
		if (--flow->counter->ref_cnt == 0) {
			rte_free(flow->counter);
			flow->counter = NULL;
		}
	}
	dev_flow = LIST_FIRST(&flow->dev_flows);
	if (!dev_flow)
		return;
	/* E-Switch flow can't be expanded. */
	assert(!LIST_NEXT(dev_flow, next));
	LIST_REMOVE(dev_flow, next);
	rte_free(dev_flow);
}

/**
 * Helper routine for figuring the space size required for a parse buffer.
 *
 * @param array
 *   array of values to use.
 * @param idx
 *   Current location in array.
 * @param value
 *   Value to compare with.
 *
 * @return
 *   The maximum between the given value and the array value on index.
 */
static uint16_t
flow_tcf_arr_val_max(uint16_t array[], int idx, uint16_t value)
{
	return idx < 0 ? (value) : RTE_MAX((array)[idx], value);
}

/**
 * Parse rtnetlink message attributes filling the attribute table with the info
 * retrieved.
 *
 * @param tb
 *   Attribute table to be filled.
 * @param[out] max
 *   Maxinum entry in the attribute table.
 * @param rte
 *   The attributes section in the message to be parsed.
 * @param len
 *   The length of the attributes section in the message.
 */
static void
flow_tcf_nl_parse_rtattr(struct rtattr *tb[], int max,
			 struct rtattr *rta, int len)
{
	unsigned short type;
	memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
	while (RTA_OK(rta, len)) {
		type = rta->rta_type;
		if (type <= max && !tb[type])
			tb[type] = rta;
		rta = RTA_NEXT(rta, len);
	}
}

/**
 * Extract flow counters from flower action.
 *
 * @param rta
 *   flower action stats properties in the Netlink message received.
 * @param rta_type
 *   The backward sequence of rta_types, as written in the attribute table,
 *   we need to traverse in order to get to the requested object.
 * @param idx
 *   Current location in rta_type table.
 * @param[out] data
 *   data holding the count statistics of the rte_flow retrieved from
 *   the message.
 *
 * @return
 *   0 if data was found and retrieved, -1 otherwise.
 */
static int
flow_tcf_nl_action_stats_parse_and_get(struct rtattr *rta,
				       uint16_t rta_type[], int idx,
				       struct gnet_stats_basic *data)
{
	int tca_stats_max = flow_tcf_arr_val_max(rta_type, idx,
						 TCA_STATS_BASIC);
	struct rtattr *tbs[tca_stats_max + 1];

	if (rta == NULL || idx < 0)
		return -1;
	flow_tcf_nl_parse_rtattr(tbs, tca_stats_max,
				 RTA_DATA(rta), RTA_PAYLOAD(rta));
	switch (rta_type[idx]) {
	case TCA_STATS_BASIC:
		if (tbs[TCA_STATS_BASIC]) {
			memcpy(data, RTA_DATA(tbs[TCA_STATS_BASIC]),
			       RTE_MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC]),
			       sizeof(*data)));
			return 0;
		}
		break;
	default:
		break;
	}
	return -1;
}

/**
 * Parse flower single action retrieving the requested action attribute,
 * if found.
 *
 * @param arg
 *   flower action properties in the Netlink message received.
 * @param rta_type
 *   The backward sequence of rta_types, as written in the attribute table,
 *   we need to traverse in order to get to the requested object.
 * @param idx
 *   Current location in rta_type table.
 * @param[out] data
 *   Count statistics retrieved from the message query.
 *
 * @return
 *   0 if data was found and retrieved, -1 otherwise.
 */
static int
flow_tcf_nl_parse_one_action_and_get(struct rtattr *arg,
				     uint16_t rta_type[], int idx, void *data)
{
	int tca_act_max = flow_tcf_arr_val_max(rta_type, idx, TCA_ACT_STATS);
	struct rtattr *tb[tca_act_max + 1];

	if (arg == NULL || idx < 0)
		return -1;
	flow_tcf_nl_parse_rtattr(tb, tca_act_max,
				 RTA_DATA(arg), RTA_PAYLOAD(arg));
	if (tb[TCA_ACT_KIND] == NULL)
		return -1;
	switch (rta_type[idx]) {
	case TCA_ACT_STATS:
		if (tb[TCA_ACT_STATS])
			return flow_tcf_nl_action_stats_parse_and_get
					(tb[TCA_ACT_STATS],
					 rta_type, --idx,
					 (struct gnet_stats_basic *)data);
		break;
	default:
		break;
	}
	return -1;
}

/**
 * Parse flower action section in the message retrieving the requested
 * attribute from the first action that provides it.
 *
 * @param opt
 *   flower section in the Netlink message received.
 * @param rta_type
 *   The backward sequence of rta_types, as written in the attribute table,
 *   we need to traverse in order to get to the requested object.
 * @param idx
 *   Current location in rta_type table.
 * @param[out] data
 *   data retrieved from the message query.
 *
 * @return
 *   0 if data was found and retrieved, -1 otherwise.
 */
static int
flow_tcf_nl_action_parse_and_get(struct rtattr *arg,
				 uint16_t rta_type[], int idx, void *data)
{
	struct rtattr *tb[TCA_ACT_MAX_PRIO + 1];
	int i;

	if (arg == NULL || idx < 0)
		return -1;
	flow_tcf_nl_parse_rtattr(tb, TCA_ACT_MAX_PRIO,
				 RTA_DATA(arg), RTA_PAYLOAD(arg));
	switch (rta_type[idx]) {
	/*
	 * flow counters are stored in the actions defined by the flow
	 * and not in the flow itself, therefore we need to traverse the
	 * flower chain of actions in search for them.
	 *
	 * Note that the index is not decremented here.
	 */
	case TCA_ACT_STATS:
		for (i = 0; i <= TCA_ACT_MAX_PRIO; i++) {
			if (tb[i] &&
			!flow_tcf_nl_parse_one_action_and_get(tb[i],
							      rta_type,
							      idx, data))
				return 0;
		}
		break;
	default:
		break;
	}
	return -1;
}

/**
 * Parse flower classifier options in the message, retrieving the requested
 * attribute if found.
 *
 * @param opt
 *   flower section in the Netlink message received.
 * @param rta_type
 *   The backward sequence of rta_types, as written in the attribute table,
 *   we need to traverse in order to get to the requested object.
 * @param idx
 *   Current location in rta_type table.
 * @param[out] data
 *   data retrieved from the message query.
 *
 * @return
 *   0 if data was found and retrieved, -1 otherwise.
 */
static int
flow_tcf_nl_opts_parse_and_get(struct rtattr *opt,
			       uint16_t rta_type[], int idx, void *data)
{
	int tca_flower_max = flow_tcf_arr_val_max(rta_type, idx,
						  TCA_FLOWER_ACT);
	struct rtattr *tb[tca_flower_max + 1];

	if (!opt || idx < 0)
		return -1;
	flow_tcf_nl_parse_rtattr(tb, tca_flower_max,
				 RTA_DATA(opt), RTA_PAYLOAD(opt));
	switch (rta_type[idx]) {
	case TCA_FLOWER_ACT:
		if (tb[TCA_FLOWER_ACT])
			return flow_tcf_nl_action_parse_and_get
							(tb[TCA_FLOWER_ACT],
							 rta_type, --idx, data);
		break;
	default:
		break;
	}
	return -1;
}

/**
 * Parse Netlink reply on filter query, retrieving the flow counters.
 *
 * @param nlh
 *   Message received from Netlink.
 * @param rta_type
 *   The backward sequence of rta_types, as written in the attribute table,
 *   we need to traverse in order to get to the requested object.
 * @param idx
 *   Current location in rta_type table.
 * @param[out] data
 *   data retrieved from the message query.
 *
 * @return
 *   0 if data was found and retrieved, -1 otherwise.
 */
static int
flow_tcf_nl_filter_parse_and_get(struct nlmsghdr *cnlh,
				 uint16_t rta_type[], int idx, void *data)
{
	struct nlmsghdr *nlh = cnlh;
	struct tcmsg *t = NLMSG_DATA(nlh);
	int len = nlh->nlmsg_len;
	int tca_max = flow_tcf_arr_val_max(rta_type, idx, TCA_OPTIONS);
	struct rtattr *tb[tca_max + 1];

	if (idx < 0)
		return -1;
	if (nlh->nlmsg_type != RTM_NEWTFILTER &&
	    nlh->nlmsg_type != RTM_GETTFILTER &&
	    nlh->nlmsg_type != RTM_DELTFILTER)
		return -1;
	len -= NLMSG_LENGTH(sizeof(*t));
	if (len < 0)
		return -1;
	flow_tcf_nl_parse_rtattr(tb, tca_max, TCA_RTA(t), len);
	/* Not a TC flower flow - bail out */
	if (!tb[TCA_KIND] ||
	    strcmp(RTA_DATA(tb[TCA_KIND]), "flower"))
		return -1;
	switch (rta_type[idx]) {
	case TCA_OPTIONS:
		if (tb[TCA_OPTIONS])
			return flow_tcf_nl_opts_parse_and_get(tb[TCA_OPTIONS],
							      rta_type,
							      --idx, data);
		break;
	default:
		break;
	}
	return -1;
}

/**
 * A callback to parse Netlink reply on TC flower query.
 *
 * @param nlh
 *   Message received from Netlink.
 * @param[out] data
 *   Pointer to data area to be filled by the parsing routine.
 *   assumed to be a pointer to struct flow_tcf_stats_basic.
 *
 * @return
 *   MNL_CB_OK value.
 */
static int
flow_tcf_nl_message_get_stats_basic(const struct nlmsghdr *nlh, void *data)
{
	/*
	 * The backward sequence of rta_types to pass in order to get
	 *  to the counters.
	 */
	uint16_t rta_type[] = { TCA_STATS_BASIC, TCA_ACT_STATS,
				TCA_FLOWER_ACT, TCA_OPTIONS };
	struct flow_tcf_stats_basic *sb_data = data;
	union {
		const struct nlmsghdr *c;
		struct nlmsghdr *nc;
	} tnlh = { .c = nlh };

	if (!flow_tcf_nl_filter_parse_and_get(tnlh.nc, rta_type,
					      RTE_DIM(rta_type) - 1,
					      (void *)&sb_data->counters))
		sb_data->valid = true;
	return MNL_CB_OK;
}

/**
 * Query a TC flower rule for its statistics via netlink.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[in] flow
 *   Pointer to the sub flow.
 * @param[out] data
 *   data retrieved by the query.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
flow_tcf_query_count(struct rte_eth_dev *dev,
			  struct rte_flow *flow,
			  void *data,
			  struct rte_flow_error *error)
{
	struct flow_tcf_stats_basic sb_data;
	struct rte_flow_query_count *qc = data;
	struct priv *priv = dev->data->dev_private;
	struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
	struct mnl_socket *nl = ctx->nl;
	struct mlx5_flow *dev_flow;
	struct nlmsghdr *nlh;
	uint32_t seq = priv->tcf_context->seq++;
	ssize_t ret;
	assert(qc);

	memset(&sb_data, 0, sizeof(sb_data));
	dev_flow = LIST_FIRST(&flow->dev_flows);
	/* E-Switch flow can't be expanded. */
	assert(!LIST_NEXT(dev_flow, next));
	if (!dev_flow->flow->counter)
		goto notsup_exit;
	nlh = dev_flow->tcf.nlh;
	nlh->nlmsg_type = RTM_GETTFILTER;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ECHO;
	nlh->nlmsg_seq = seq;
	if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) == -1)
		goto error_exit;
	do {
		ret = mnl_socket_recvfrom(nl, ctx->buf, ctx->buf_size);
		if (ret <= 0)
			break;
		ret = mnl_cb_run(ctx->buf, ret, seq,
				 mnl_socket_get_portid(nl),
				 flow_tcf_nl_message_get_stats_basic,
				 (void *)&sb_data);
	} while (ret > 0);
	/* Return the delta from last reset. */
	if (sb_data.valid) {
		/* Return the delta from last reset. */
		qc->hits_set = 1;
		qc->bytes_set = 1;
		qc->hits = sb_data.counters.packets - flow->counter->hits;
		qc->bytes = sb_data.counters.bytes - flow->counter->bytes;
		if (qc->reset) {
			flow->counter->hits = sb_data.counters.packets;
			flow->counter->bytes = sb_data.counters.bytes;
		}
		return 0;
	}
	return rte_flow_error_set(error, EINVAL,
				  RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
				  NULL,
				  "flow does not have counter");
error_exit:
	return rte_flow_error_set
			(error, errno, RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
			 NULL, "netlink: failed to read flow rule counters");
notsup_exit:
	return rte_flow_error_set
			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
			 NULL, "counters are not available.");
}

/**
 * Query a flow.
 *
 * @see rte_flow_query()
 * @see rte_flow_ops
 */
static int
flow_tcf_query(struct rte_eth_dev *dev,
	       struct rte_flow *flow,
	       const struct rte_flow_action *actions,
	       void *data,
	       struct rte_flow_error *error)
{
	int ret = -EINVAL;

	for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
		switch (actions->type) {
		case RTE_FLOW_ACTION_TYPE_VOID:
			break;
		case RTE_FLOW_ACTION_TYPE_COUNT:
			ret = flow_tcf_query_count(dev, flow, data, error);
			break;
		default:
			return rte_flow_error_set(error, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  actions,
						  "action not supported");
		}
	}
	return ret;
}

const struct mlx5_flow_driver_ops mlx5_flow_tcf_drv_ops = {
	.validate = flow_tcf_validate,
	.prepare = flow_tcf_prepare,
	.translate = flow_tcf_translate,
	.apply = flow_tcf_apply,
	.remove = flow_tcf_remove,
	.destroy = flow_tcf_destroy,
	.query = flow_tcf_query,
};

/**
 * Create and configure a libmnl socket for Netlink flow rules.
 *
 * @return
 *   A valid libmnl socket object pointer on success, NULL otherwise and
 *   rte_errno is set.
 */
static struct mnl_socket *
flow_tcf_mnl_socket_create(void)
{
	struct mnl_socket *nl = mnl_socket_open(NETLINK_ROUTE);

	if (nl) {
		mnl_socket_setsockopt(nl, NETLINK_CAP_ACK, &(int){ 1 },
				      sizeof(int));
		if (!mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID))
			return nl;
	}
	rte_errno = errno;
	if (nl)
		mnl_socket_close(nl);
	return NULL;
}

/**
 * Destroy a libmnl socket.
 *
 * @param nl
 *   Libmnl socket of the @p NETLINK_ROUTE kind.
 */
static void
flow_tcf_mnl_socket_destroy(struct mnl_socket *nl)
{
	if (nl)
		mnl_socket_close(nl);
}

/**
 * Initialize ingress qdisc of a given network interface.
 *
 * @param ctx
 *   Pointer to tc-flower context to use.
 * @param ifindex
 *   Index of network interface to initialize.
 * @param[out] error
 *   Perform verbose error reporting if not NULL.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_flow_tcf_init(struct mlx5_flow_tcf_context *ctx,
		   unsigned int ifindex, struct rte_flow_error *error)
{
	struct nlmsghdr *nlh;
	struct tcmsg *tcm;
	alignas(struct nlmsghdr)
	uint8_t buf[mnl_nlmsg_size(sizeof(*tcm)) +
		    SZ_NLATTR_STRZ_OF("ingress") +
		    MNL_BUF_EXTRA_SPACE];

	/* Destroy existing ingress qdisc and everything attached to it. */
	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = RTM_DELQDISC;
	nlh->nlmsg_flags = NLM_F_REQUEST;
	tcm = mnl_nlmsg_put_extra_header(nlh, sizeof(*tcm));
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm_ifindex = ifindex;
	tcm->tcm_handle = TC_H_MAKE(TC_H_INGRESS, 0);
	tcm->tcm_parent = TC_H_INGRESS;
	assert(sizeof(buf) >= nlh->nlmsg_len);
	/* Ignore errors when qdisc is already absent. */
	if (flow_tcf_nl_ack(ctx, nlh, NULL, NULL) &&
	    rte_errno != EINVAL && rte_errno != ENOENT)
		return rte_flow_error_set(error, rte_errno,
					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
					  "netlink: failed to remove ingress"
					  " qdisc");
	/* Create fresh ingress qdisc. */
	nlh = mnl_nlmsg_put_header(buf);
	nlh->nlmsg_type = RTM_NEWQDISC;
	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
	tcm = mnl_nlmsg_put_extra_header(nlh, sizeof(*tcm));
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm_ifindex = ifindex;
	tcm->tcm_handle = TC_H_MAKE(TC_H_INGRESS, 0);
	tcm->tcm_parent = TC_H_INGRESS;
	mnl_attr_put_strz_check(nlh, sizeof(buf), TCA_KIND, "ingress");
	assert(sizeof(buf) >= nlh->nlmsg_len);
	if (flow_tcf_nl_ack(ctx, nlh, NULL, NULL))
		return rte_flow_error_set(error, rte_errno,
					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
					  "netlink: failed to create ingress"
					  " qdisc");
	return 0;
}

/**
 * Create libmnl context for Netlink flow rules.
 *
 * @return
 *   A valid libmnl socket object pointer on success, NULL otherwise and
 *   rte_errno is set.
 */
struct mlx5_flow_tcf_context *
mlx5_flow_tcf_context_create(void)
{
	struct mlx5_flow_tcf_context *ctx = rte_zmalloc(__func__,
							sizeof(*ctx),
							sizeof(uint32_t));
	if (!ctx)
		goto error;
	ctx->nl = flow_tcf_mnl_socket_create();
	if (!ctx->nl)
		goto error;
	ctx->buf_size = MNL_SOCKET_BUFFER_SIZE;
	ctx->buf = rte_zmalloc(__func__,
			       ctx->buf_size, sizeof(uint32_t));
	if (!ctx->buf)
		goto error;
	ctx->seq = random();
	return ctx;
error:
	mlx5_flow_tcf_context_destroy(ctx);
	return NULL;
}

/**
 * Destroy a libmnl context.
 *
 * @param ctx
 *   Libmnl socket of the @p NETLINK_ROUTE kind.
 */
void
mlx5_flow_tcf_context_destroy(struct mlx5_flow_tcf_context *ctx)
{
	if (!ctx)
		return;
	flow_tcf_mnl_socket_destroy(ctx->nl);
	rte_free(ctx->buf);
	rte_free(ctx);
}