DPDK logo

Elixir Cross Referencer

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright 2015 6WIND S.A.
 * Copyright 2020 Mellanox Technologies, Ltd
 */

#include <stddef.h>
#include <unistd.h>
#include <string.h>
#include <stdint.h>
#include <stdlib.h>
#include <errno.h>
#include <net/if.h>
#include <linux/rtnetlink.h>
#include <linux/sockios.h>
#include <linux/ethtool.h>
#include <fcntl.h>

#include <rte_malloc.h>
#include <rte_ethdev_driver.h>
#include <rte_ethdev_pci.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
#include <rte_common.h>
#include <rte_kvargs.h>
#include <rte_rwlock.h>
#include <rte_spinlock.h>
#include <rte_string_fns.h>
#include <rte_alarm.h>
#include <rte_eal_paging.h>

#include <mlx5_glue.h>
#include <mlx5_devx_cmds.h>
#include <mlx5_common.h>
#include <mlx5_common_mp.h>
#include <mlx5_common_mr.h>
#include <mlx5_malloc.h>

#include "mlx5_defs.h"
#include "mlx5.h"
#include "mlx5_common_os.h"
#include "mlx5_utils.h"
#include "mlx5_rxtx.h"
#include "mlx5_autoconf.h"
#include "mlx5_mr.h"
#include "mlx5_flow.h"
#include "rte_pmd_mlx5.h"
#include "mlx5_verbs.h"

#define MLX5_TAGS_HLIST_ARRAY_SIZE 8192

#ifndef HAVE_IBV_MLX5_MOD_MPW
#define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2)
#define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3)
#endif

#ifndef HAVE_IBV_MLX5_MOD_CQE_128B_COMP
#define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4)
#endif

static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data";

/* Spinlock for mlx5_shared_data allocation. */
static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER;

/* Process local data for secondary processes. */
static struct mlx5_local_data mlx5_local_data;

/**
 * Set the completion channel file descriptor interrupt as non-blocking.
 *
 * @param[in] rxq_obj
 *   Pointer to RQ channel object, which includes the channel fd
 *
 * @param[out] fd
 *   The file descriptor (representing the intetrrupt) used in this channel.
 *
 * @return
 *   0 on successfully setting the fd to non-blocking, non-zero otherwise.
 */
int
mlx5_os_set_nonblock_channel_fd(int fd)
{
	int flags;

	flags = fcntl(fd, F_GETFL);
	return fcntl(fd, F_SETFL, flags | O_NONBLOCK);
}

/**
 * Get mlx5 device attributes. The glue function query_device_ex() is called
 * with out parameter of type 'struct ibv_device_attr_ex *'. Then fill in mlx5
 * device attributes from the glue out parameter.
 *
 * @param dev
 *   Pointer to ibv context.
 *
 * @param device_attr
 *   Pointer to mlx5 device attributes.
 *
 * @return
 *   0 on success, non zero error number otherwise
 */
int
mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr)
{
	int err;
	struct ibv_device_attr_ex attr_ex;
	memset(device_attr, 0, sizeof(*device_attr));
	err = mlx5_glue->query_device_ex(ctx, NULL, &attr_ex);
	if (err)
		return err;

	device_attr->device_cap_flags_ex = attr_ex.device_cap_flags_ex;
	device_attr->max_qp_wr = attr_ex.orig_attr.max_qp_wr;
	device_attr->max_sge = attr_ex.orig_attr.max_sge;
	device_attr->max_cq = attr_ex.orig_attr.max_cq;
	device_attr->max_qp = attr_ex.orig_attr.max_qp;
	device_attr->raw_packet_caps = attr_ex.raw_packet_caps;
	device_attr->max_rwq_indirection_table_size =
		attr_ex.rss_caps.max_rwq_indirection_table_size;
	device_attr->max_tso = attr_ex.tso_caps.max_tso;
	device_attr->tso_supported_qpts = attr_ex.tso_caps.supported_qpts;

	struct mlx5dv_context dv_attr = { .comp_mask = 0 };
	err = mlx5_glue->dv_query_device(ctx, &dv_attr);
	if (err)
		return err;

	device_attr->flags = dv_attr.flags;
	device_attr->comp_mask = dv_attr.comp_mask;
#ifdef HAVE_IBV_MLX5_MOD_SWP
	device_attr->sw_parsing_offloads =
		dv_attr.sw_parsing_caps.sw_parsing_offloads;
#endif
	device_attr->min_single_stride_log_num_of_bytes =
		dv_attr.striding_rq_caps.min_single_stride_log_num_of_bytes;
	device_attr->max_single_stride_log_num_of_bytes =
		dv_attr.striding_rq_caps.max_single_stride_log_num_of_bytes;
	device_attr->min_single_wqe_log_num_of_strides =
		dv_attr.striding_rq_caps.min_single_wqe_log_num_of_strides;
	device_attr->max_single_wqe_log_num_of_strides =
		dv_attr.striding_rq_caps.max_single_wqe_log_num_of_strides;
	device_attr->stride_supported_qpts =
		dv_attr.striding_rq_caps.supported_qpts;
#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
	device_attr->tunnel_offloads_caps = dv_attr.tunnel_offloads_caps;
#endif

	return err;
}

/**
 * Verbs callback to allocate a memory. This function should allocate the space
 * according to the size provided residing inside a huge page.
 * Please note that all allocation must respect the alignment from libmlx5
 * (i.e. currently rte_mem_page_size()).
 *
 * @param[in] size
 *   The size in bytes of the memory to allocate.
 * @param[in] data
 *   A pointer to the callback data.
 *
 * @return
 *   Allocated buffer, NULL otherwise and rte_errno is set.
 */
static void *
mlx5_alloc_verbs_buf(size_t size, void *data)
{
	struct mlx5_priv *priv = data;
	void *ret;
	unsigned int socket = SOCKET_ID_ANY;
	size_t alignment = rte_mem_page_size();
	if (alignment == (size_t)-1) {
		DRV_LOG(ERR, "Failed to get mem page size");
		rte_errno = ENOMEM;
		return NULL;
	}

	if (priv->verbs_alloc_ctx.type == MLX5_VERBS_ALLOC_TYPE_TX_QUEUE) {
		const struct mlx5_txq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;

		socket = ctrl->socket;
	} else if (priv->verbs_alloc_ctx.type ==
		   MLX5_VERBS_ALLOC_TYPE_RX_QUEUE) {
		const struct mlx5_rxq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;

		socket = ctrl->socket;
	}
	MLX5_ASSERT(data != NULL);
	ret = mlx5_malloc(0, size, alignment, socket);
	if (!ret && size)
		rte_errno = ENOMEM;
	return ret;
}

/**
 * Verbs callback to free a memory.
 *
 * @param[in] ptr
 *   A pointer to the memory to free.
 * @param[in] data
 *   A pointer to the callback data.
 */
static void
mlx5_free_verbs_buf(void *ptr, void *data __rte_unused)
{
	MLX5_ASSERT(data != NULL);
	mlx5_free(ptr);
}

/**
 * Initialize DR related data within private structure.
 * Routine checks the reference counter and does actual
 * resources creation/initialization only if counter is zero.
 *
 * @param[in] priv
 *   Pointer to the private device data structure.
 *
 * @return
 *   Zero on success, positive error code otherwise.
 */
static int
mlx5_alloc_shared_dr(struct mlx5_priv *priv)
{
	struct mlx5_dev_ctx_shared *sh = priv->sh;
	char s[MLX5_HLIST_NAMESIZE];
	int err = 0;

	if (!sh->flow_tbls)
		err = mlx5_alloc_table_hash_list(priv);
	else
		DRV_LOG(DEBUG, "sh->flow_tbls[%p] already created, reuse\n",
			(void *)sh->flow_tbls);
	if (err)
		return err;
	/* Create tags hash list table. */
	snprintf(s, sizeof(s), "%s_tags", sh->ibdev_name);
	sh->tag_table = mlx5_hlist_create(s, MLX5_TAGS_HLIST_ARRAY_SIZE);
	if (!sh->tag_table) {
		DRV_LOG(ERR, "tags with hash creation failed.");
		err = ENOMEM;
		goto error;
	}
#ifdef HAVE_MLX5DV_DR
	void *domain;

	if (sh->dv_refcnt) {
		/* Shared DV/DR structures is already initialized. */
		sh->dv_refcnt++;
		priv->dr_shared = 1;
		return 0;
	}
	/* Reference counter is zero, we should initialize structures. */
	domain = mlx5_glue->dr_create_domain(sh->ctx,
					     MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
	if (!domain) {
		DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed");
		err = errno;
		goto error;
	}
	sh->rx_domain = domain;
	domain = mlx5_glue->dr_create_domain(sh->ctx,
					     MLX5DV_DR_DOMAIN_TYPE_NIC_TX);
	if (!domain) {
		DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed");
		err = errno;
		goto error;
	}
	pthread_mutex_init(&sh->dv_mutex, NULL);
	sh->tx_domain = domain;
#ifdef HAVE_MLX5DV_DR_ESWITCH
	if (priv->config.dv_esw_en) {
		domain  = mlx5_glue->dr_create_domain
			(sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB);
		if (!domain) {
			DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed");
			err = errno;
			goto error;
		}
		sh->fdb_domain = domain;
		sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
	}
#endif
	if (priv->config.reclaim_mode == MLX5_RCM_AGGR) {
		mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1);
		mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1);
		if (sh->fdb_domain)
			mlx5_glue->dr_reclaim_domain_memory(sh->fdb_domain, 1);
	}
	sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan();
#endif /* HAVE_MLX5DV_DR */
	sh->dv_refcnt++;
	priv->dr_shared = 1;
	return 0;
error:
	/* Rollback the created objects. */
	if (sh->rx_domain) {
		mlx5_glue->dr_destroy_domain(sh->rx_domain);
		sh->rx_domain = NULL;
	}
	if (sh->tx_domain) {
		mlx5_glue->dr_destroy_domain(sh->tx_domain);
		sh->tx_domain = NULL;
	}
	if (sh->fdb_domain) {
		mlx5_glue->dr_destroy_domain(sh->fdb_domain);
		sh->fdb_domain = NULL;
	}
	if (sh->esw_drop_action) {
		mlx5_glue->destroy_flow_action(sh->esw_drop_action);
		sh->esw_drop_action = NULL;
	}
	if (sh->pop_vlan_action) {
		mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
		sh->pop_vlan_action = NULL;
	}
	if (sh->tag_table) {
		/* tags should be destroyed with flow before. */
		mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
		sh->tag_table = NULL;
	}
	mlx5_free_table_hash_list(priv);
	return err;
}

/**
 * Destroy DR related data within private structure.
 *
 * @param[in] priv
 *   Pointer to the private device data structure.
 */
void
mlx5_os_free_shared_dr(struct mlx5_priv *priv)
{
	struct mlx5_dev_ctx_shared *sh;

	if (!priv->dr_shared)
		return;
	priv->dr_shared = 0;
	sh = priv->sh;
	MLX5_ASSERT(sh);
#ifdef HAVE_MLX5DV_DR
	MLX5_ASSERT(sh->dv_refcnt);
	if (sh->dv_refcnt && --sh->dv_refcnt)
		return;
	if (sh->rx_domain) {
		mlx5_glue->dr_destroy_domain(sh->rx_domain);
		sh->rx_domain = NULL;
	}
	if (sh->tx_domain) {
		mlx5_glue->dr_destroy_domain(sh->tx_domain);
		sh->tx_domain = NULL;
	}
#ifdef HAVE_MLX5DV_DR_ESWITCH
	if (sh->fdb_domain) {
		mlx5_glue->dr_destroy_domain(sh->fdb_domain);
		sh->fdb_domain = NULL;
	}
	if (sh->esw_drop_action) {
		mlx5_glue->destroy_flow_action(sh->esw_drop_action);
		sh->esw_drop_action = NULL;
	}
#endif
	if (sh->pop_vlan_action) {
		mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
		sh->pop_vlan_action = NULL;
	}
	pthread_mutex_destroy(&sh->dv_mutex);
#endif /* HAVE_MLX5DV_DR */
	if (sh->tag_table) {
		/* tags should be destroyed with flow before. */
		mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
		sh->tag_table = NULL;
	}
	mlx5_free_table_hash_list(priv);
}

/**
 * Initialize shared data between primary and secondary process.
 *
 * A memzone is reserved by primary process and secondary processes attach to
 * the memzone.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_init_shared_data(void)
{
	const struct rte_memzone *mz;
	int ret = 0;

	rte_spinlock_lock(&mlx5_shared_data_lock);
	if (mlx5_shared_data == NULL) {
		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
			/* Allocate shared memory. */
			mz = rte_memzone_reserve(MZ_MLX5_PMD_SHARED_DATA,
						 sizeof(*mlx5_shared_data),
						 SOCKET_ID_ANY, 0);
			if (mz == NULL) {
				DRV_LOG(ERR,
					"Cannot allocate mlx5 shared data");
				ret = -rte_errno;
				goto error;
			}
			mlx5_shared_data = mz->addr;
			memset(mlx5_shared_data, 0, sizeof(*mlx5_shared_data));
			rte_spinlock_init(&mlx5_shared_data->lock);
		} else {
			/* Lookup allocated shared memory. */
			mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA);
			if (mz == NULL) {
				DRV_LOG(ERR,
					"Cannot attach mlx5 shared data");
				ret = -rte_errno;
				goto error;
			}
			mlx5_shared_data = mz->addr;
			memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
		}
	}
error:
	rte_spinlock_unlock(&mlx5_shared_data_lock);
	return ret;
}

/**
 * PMD global initialization.
 *
 * Independent from individual device, this function initializes global
 * per-PMD data structures distinguishing primary and secondary processes.
 * Hence, each initialization is called once per a process.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_init_once(void)
{
	struct mlx5_shared_data *sd;
	struct mlx5_local_data *ld = &mlx5_local_data;
	int ret = 0;

	if (mlx5_init_shared_data())
		return -rte_errno;
	sd = mlx5_shared_data;
	MLX5_ASSERT(sd);
	rte_spinlock_lock(&sd->lock);
	switch (rte_eal_process_type()) {
	case RTE_PROC_PRIMARY:
		if (sd->init_done)
			break;
		LIST_INIT(&sd->mem_event_cb_list);
		rte_rwlock_init(&sd->mem_event_rwlock);
		rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
						mlx5_mr_mem_event_cb, NULL);
		ret = mlx5_mp_init_primary(MLX5_MP_NAME,
					   mlx5_mp_os_primary_handle);
		if (ret)
			goto out;
		sd->init_done = true;
		break;
	case RTE_PROC_SECONDARY:
		if (ld->init_done)
			break;
		ret = mlx5_mp_init_secondary(MLX5_MP_NAME,
					     mlx5_mp_os_secondary_handle);
		if (ret)
			goto out;
		++sd->secondary_cnt;
		ld->init_done = true;
		break;
	default:
		break;
	}
out:
	rte_spinlock_unlock(&sd->lock);
	return ret;
}

/**
 * Spawn an Ethernet device from Verbs information.
 *
 * @param dpdk_dev
 *   Backing DPDK device.
 * @param spawn
 *   Verbs device parameters (name, port, switch_info) to spawn.
 * @param config
 *   Device configuration parameters.
 *
 * @return
 *   A valid Ethernet device object on success, NULL otherwise and rte_errno
 *   is set. The following errors are defined:
 *
 *   EBUSY: device is not supposed to be spawned.
 *   EEXIST: device is already spawned
 */
static struct rte_eth_dev *
mlx5_dev_spawn(struct rte_device *dpdk_dev,
	       struct mlx5_dev_spawn_data *spawn,
	       struct mlx5_dev_config *config)
{
	const struct mlx5_switch_info *switch_info = &spawn->info;
	struct mlx5_dev_ctx_shared *sh = NULL;
	struct ibv_port_attr port_attr;
	struct mlx5dv_context dv_attr = { .comp_mask = 0 };
	struct rte_eth_dev *eth_dev = NULL;
	struct mlx5_priv *priv = NULL;
	int err = 0;
	unsigned int hw_padding = 0;
	unsigned int mps;
	unsigned int cqe_comp;
	unsigned int cqe_pad = 0;
	unsigned int tunnel_en = 0;
	unsigned int mpls_en = 0;
	unsigned int swp = 0;
	unsigned int mprq = 0;
	unsigned int mprq_min_stride_size_n = 0;
	unsigned int mprq_max_stride_size_n = 0;
	unsigned int mprq_min_stride_num_n = 0;
	unsigned int mprq_max_stride_num_n = 0;
	struct rte_ether_addr mac;
	char name[RTE_ETH_NAME_MAX_LEN];
	int own_domain_id = 0;
	uint16_t port_id;
	unsigned int i;
#ifdef HAVE_MLX5DV_DR_DEVX_PORT
	struct mlx5dv_devx_port devx_port = { .comp_mask = 0 };
#endif

	/* Determine if this port representor is supposed to be spawned. */
	if (switch_info->representor && dpdk_dev->devargs) {
		struct rte_eth_devargs eth_da;

		err = rte_eth_devargs_parse(dpdk_dev->devargs->args, &eth_da);
		if (err) {
			rte_errno = -err;
			DRV_LOG(ERR, "failed to process device arguments: %s",
				strerror(rte_errno));
			return NULL;
		}
		for (i = 0; i < eth_da.nb_representor_ports; ++i)
			if (eth_da.representor_ports[i] ==
			    (uint16_t)switch_info->port_name)
				break;
		if (i == eth_da.nb_representor_ports) {
			rte_errno = EBUSY;
			return NULL;
		}
	}
	/* Build device name. */
	if (spawn->pf_bond <  0) {
		/* Single device. */
		if (!switch_info->representor)
			strlcpy(name, dpdk_dev->name, sizeof(name));
		else
			snprintf(name, sizeof(name), "%s_representor_%u",
				 dpdk_dev->name, switch_info->port_name);
	} else {
		/* Bonding device. */
		if (!switch_info->representor)
			snprintf(name, sizeof(name), "%s_%s",
				 dpdk_dev->name,
				 mlx5_os_get_dev_device_name(spawn->phys_dev));
		else
			snprintf(name, sizeof(name), "%s_%s_representor_%u",
				 dpdk_dev->name,
				 mlx5_os_get_dev_device_name(spawn->phys_dev),
				 switch_info->port_name);
	}
	/* check if the device is already spawned */
	if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
		rte_errno = EEXIST;
		return NULL;
	}
	DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
		struct mlx5_mp_id mp_id;

		eth_dev = rte_eth_dev_attach_secondary(name);
		if (eth_dev == NULL) {
			DRV_LOG(ERR, "can not attach rte ethdev");
			rte_errno = ENOMEM;
			return NULL;
		}
		eth_dev->device = dpdk_dev;
		eth_dev->dev_ops = &mlx5_os_dev_sec_ops;
		err = mlx5_proc_priv_init(eth_dev);
		if (err)
			return NULL;
		mp_id.port_id = eth_dev->data->port_id;
		strlcpy(mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
		/* Receive command fd from primary process */
		err = mlx5_mp_req_verbs_cmd_fd(&mp_id);
		if (err < 0)
			goto err_secondary;
		/* Remap UAR for Tx queues. */
		err = mlx5_tx_uar_init_secondary(eth_dev, err);
		if (err)
			goto err_secondary;
		/*
		 * Ethdev pointer is still required as input since
		 * the primary device is not accessible from the
		 * secondary process.
		 */
		eth_dev->rx_pkt_burst = mlx5_select_rx_function(eth_dev);
		eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
		return eth_dev;
err_secondary:
		mlx5_dev_close(eth_dev);
		return NULL;
	}
	/*
	 * Some parameters ("tx_db_nc" in particularly) are needed in
	 * advance to create dv/verbs device context. We proceed the
	 * devargs here to get ones, and later proceed devargs again
	 * to override some hardware settings.
	 */
	err = mlx5_args(config, dpdk_dev->devargs);
	if (err) {
		err = rte_errno;
		DRV_LOG(ERR, "failed to process device arguments: %s",
			strerror(rte_errno));
		goto error;
	}
	mlx5_malloc_mem_select(config->sys_mem_en);
	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
	if (!sh)
		return NULL;
	config->devx = sh->devx;
#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
	config->dest_tir = 1;
#endif
#ifdef HAVE_IBV_MLX5_MOD_SWP
	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
#endif
	/*
	 * Multi-packet send is supported by ConnectX-4 Lx PF as well
	 * as all ConnectX-5 devices.
	 */
#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS;
#endif
#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ;
#endif
	mlx5_glue->dv_query_device(sh->ctx, &dv_attr);
	if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
		if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
			DRV_LOG(DEBUG, "enhanced MPW is supported");
			mps = MLX5_MPW_ENHANCED;
		} else {
			DRV_LOG(DEBUG, "MPW is supported");
			mps = MLX5_MPW;
		}
	} else {
		DRV_LOG(DEBUG, "MPW isn't supported");
		mps = MLX5_MPW_DISABLED;
	}
#ifdef HAVE_IBV_MLX5_MOD_SWP
	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP)
		swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
	DRV_LOG(DEBUG, "SWP support: %u", swp);
#endif
	config->swp = !!swp;
#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) {
		struct mlx5dv_striding_rq_caps mprq_caps =
			dv_attr.striding_rq_caps;

		DRV_LOG(DEBUG, "\tmin_single_stride_log_num_of_bytes: %d",
			mprq_caps.min_single_stride_log_num_of_bytes);
		DRV_LOG(DEBUG, "\tmax_single_stride_log_num_of_bytes: %d",
			mprq_caps.max_single_stride_log_num_of_bytes);
		DRV_LOG(DEBUG, "\tmin_single_wqe_log_num_of_strides: %d",
			mprq_caps.min_single_wqe_log_num_of_strides);
		DRV_LOG(DEBUG, "\tmax_single_wqe_log_num_of_strides: %d",
			mprq_caps.max_single_wqe_log_num_of_strides);
		DRV_LOG(DEBUG, "\tsupported_qpts: %d",
			mprq_caps.supported_qpts);
		DRV_LOG(DEBUG, "device supports Multi-Packet RQ");
		mprq = 1;
		mprq_min_stride_size_n =
			mprq_caps.min_single_stride_log_num_of_bytes;
		mprq_max_stride_size_n =
			mprq_caps.max_single_stride_log_num_of_bytes;
		mprq_min_stride_num_n =
			mprq_caps.min_single_wqe_log_num_of_strides;
		mprq_max_stride_num_n =
			mprq_caps.max_single_wqe_log_num_of_strides;
	}
#endif
	if (RTE_CACHE_LINE_SIZE == 128 &&
	    !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP))
		cqe_comp = 0;
	else
		cqe_comp = 1;
	config->cqe_comp = cqe_comp;
#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD
	/* Whether device supports 128B Rx CQE padding. */
	cqe_pad = RTE_CACHE_LINE_SIZE == 128 &&
		  (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_PAD);
#endif
#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
		tunnel_en = ((dv_attr.tunnel_offloads_caps &
			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN) &&
			     (dv_attr.tunnel_offloads_caps &
			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE) &&
			     (dv_attr.tunnel_offloads_caps &
			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE));
	}
	DRV_LOG(DEBUG, "tunnel offloading is %ssupported",
		tunnel_en ? "" : "not ");
#else
	DRV_LOG(WARNING,
		"tunnel offloading disabled due to old OFED/rdma-core version");
#endif
	config->tunnel_en = tunnel_en;
#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
	mpls_en = ((dv_attr.tunnel_offloads_caps &
		    MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) &&
		   (dv_attr.tunnel_offloads_caps &
		    MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_UDP));
	DRV_LOG(DEBUG, "MPLS over GRE/UDP tunnel offloading is %ssupported",
		mpls_en ? "" : "not ");
#else
	DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to"
		" old OFED/rdma-core version or firmware configuration");
#endif
	config->mpls_en = mpls_en;
	/* Check port status. */
	err = mlx5_glue->query_port(sh->ctx, spawn->phys_port, &port_attr);
	if (err) {
		DRV_LOG(ERR, "port query failed: %s", strerror(err));
		goto error;
	}
	if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
		DRV_LOG(ERR, "port is not configured in Ethernet mode");
		err = EINVAL;
		goto error;
	}
	if (port_attr.state != IBV_PORT_ACTIVE)
		DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)",
			mlx5_glue->port_state_str(port_attr.state),
			port_attr.state);
	/* Allocate private eth device data. */
	priv = mlx5_malloc(MLX5_MEM_ZERO | MLX5_MEM_RTE,
			   sizeof(*priv),
			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
	if (priv == NULL) {
		DRV_LOG(ERR, "priv allocation failure");
		err = ENOMEM;
		goto error;
	}
	priv->sh = sh;
	priv->dev_port = spawn->phys_port;
	priv->pci_dev = spawn->pci_dev;
	priv->mtu = RTE_ETHER_MTU;
	priv->mp_id.port_id = port_id;
	strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
	/* Some internal functions rely on Netlink sockets, open them now. */
	priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
	priv->nl_socket_route =	mlx5_nl_init(NETLINK_ROUTE);
	priv->representor = !!switch_info->representor;
	priv->master = !!switch_info->master;
	priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
	priv->vport_meta_tag = 0;
	priv->vport_meta_mask = 0;
	priv->pf_bond = spawn->pf_bond;
#ifdef HAVE_MLX5DV_DR_DEVX_PORT
	/*
	 * The DevX port query API is implemented. E-Switch may use
	 * either vport or reg_c[0] metadata register to match on
	 * vport index. The engaged part of metadata register is
	 * defined by mask.
	 */
	if (switch_info->representor || switch_info->master) {
		devx_port.comp_mask = MLX5DV_DEVX_PORT_VPORT |
				      MLX5DV_DEVX_PORT_MATCH_REG_C_0;
		err = mlx5_glue->devx_port_query(sh->ctx, spawn->phys_port,
						 &devx_port);
		if (err) {
			DRV_LOG(WARNING,
				"can't query devx port %d on device %s",
				spawn->phys_port,
				mlx5_os_get_dev_device_name(spawn->phys_dev));
			devx_port.comp_mask = 0;
		}
	}
	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_MATCH_REG_C_0) {
		priv->vport_meta_tag = devx_port.reg_c_0.value;
		priv->vport_meta_mask = devx_port.reg_c_0.mask;
		if (!priv->vport_meta_mask) {
			DRV_LOG(ERR, "vport zero mask for port %d"
				     " on bonding device %s",
				     spawn->phys_port,
				     mlx5_os_get_dev_device_name
							(spawn->phys_dev));
			err = ENOTSUP;
			goto error;
		}
		if (priv->vport_meta_tag & ~priv->vport_meta_mask) {
			DRV_LOG(ERR, "invalid vport tag for port %d"
				     " on bonding device %s",
				     spawn->phys_port,
				     mlx5_os_get_dev_device_name
							(spawn->phys_dev));
			err = ENOTSUP;
			goto error;
		}
	}
	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) {
		priv->vport_id = devx_port.vport_num;
	} else if (spawn->pf_bond >= 0) {
		DRV_LOG(ERR, "can't deduce vport index for port %d"
			     " on bonding device %s",
			     spawn->phys_port,
			     mlx5_os_get_dev_device_name(spawn->phys_dev));
		err = ENOTSUP;
		goto error;
	} else {
		/* Suppose vport index in compatible way. */
		priv->vport_id = switch_info->representor ?
				 switch_info->port_name + 1 : -1;
	}
#else
	/*
	 * Kernel/rdma_core support single E-Switch per PF configurations
	 * only and vport_id field contains the vport index for
	 * associated VF, which is deduced from representor port name.
	 * For example, let's have the IB device port 10, it has
	 * attached network device eth0, which has port name attribute
	 * pf0vf2, we can deduce the VF number as 2, and set vport index
	 * as 3 (2+1). This assigning schema should be changed if the
	 * multiple E-Switch instances per PF configurations or/and PCI
	 * subfunctions are added.
	 */
	priv->vport_id = switch_info->representor ?
			 switch_info->port_name + 1 : -1;
#endif
	/* representor_id field keeps the unmodified VF index. */
	priv->representor_id = switch_info->representor ?
			       switch_info->port_name : -1;
	/*
	 * Look for sibling devices in order to reuse their switch domain
	 * if any, otherwise allocate one.
	 */
	MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
		const struct mlx5_priv *opriv =
			rte_eth_devices[port_id].data->dev_private;

		if (!opriv ||
		    opriv->sh != priv->sh ||
			opriv->domain_id ==
			RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
			continue;
		priv->domain_id = opriv->domain_id;
		break;
	}
	if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
		err = rte_eth_switch_domain_alloc(&priv->domain_id);
		if (err) {
			err = rte_errno;
			DRV_LOG(ERR, "unable to allocate switch domain: %s",
				strerror(rte_errno));
			goto error;
		}
		own_domain_id = 1;
	}
	/* Override some values set by hardware configuration. */
	mlx5_args(config, dpdk_dev->devargs);
	err = mlx5_dev_check_sibling_config(priv, config);
	if (err)
		goto error;
	config->hw_csum = !!(sh->device_attr.device_cap_flags_ex &
			    IBV_DEVICE_RAW_IP_CSUM);
	DRV_LOG(DEBUG, "checksum offloading is %ssupported",
		(config->hw_csum ? "" : "not "));
#if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \
	!defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
	DRV_LOG(DEBUG, "counters are not supported");
#endif
#if !defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_MLX5DV_DR)
	if (config->dv_flow_en) {
		DRV_LOG(WARNING, "DV flow is not supported");
		config->dv_flow_en = 0;
	}
#endif
	config->ind_table_max_size =
		sh->device_attr.max_rwq_indirection_table_size;
	/*
	 * Remove this check once DPDK supports larger/variable
	 * indirection tables.
	 */
	if (config->ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
		config->ind_table_max_size = ETH_RSS_RETA_SIZE_512;
	DRV_LOG(DEBUG, "maximum Rx indirection table size is %u",
		config->ind_table_max_size);
	config->hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
				  IBV_RAW_PACKET_CAP_CVLAN_STRIPPING);
	DRV_LOG(DEBUG, "VLAN stripping is %ssupported",
		(config->hw_vlan_strip ? "" : "not "));
	config->hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
				 IBV_RAW_PACKET_CAP_SCATTER_FCS);
#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
	hw_padding = !!sh->device_attr.rx_pad_end_addr_align;
#elif defined(HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING)
	hw_padding = !!(sh->device_attr.device_cap_flags_ex &
			IBV_DEVICE_PCI_WRITE_END_PADDING);
#endif
	if (config->hw_padding && !hw_padding) {
		DRV_LOG(DEBUG, "Rx end alignment padding isn't supported");
		config->hw_padding = 0;
	} else if (config->hw_padding) {
		DRV_LOG(DEBUG, "Rx end alignment padding is enabled");
	}
	config->tso = (sh->device_attr.max_tso > 0 &&
		      (sh->device_attr.tso_supported_qpts &
		       (1 << IBV_QPT_RAW_PACKET)));
	if (config->tso)
		config->tso_max_payload_sz = sh->device_attr.max_tso;
	/*
	 * MPW is disabled by default, while the Enhanced MPW is enabled
	 * by default.
	 */
	if (config->mps == MLX5_ARG_UNSET)
		config->mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED :
							  MLX5_MPW_DISABLED;
	else
		config->mps = config->mps ? mps : MLX5_MPW_DISABLED;
	DRV_LOG(INFO, "%sMPS is %s",
		config->mps == MLX5_MPW_ENHANCED ? "enhanced " :
		config->mps == MLX5_MPW ? "legacy " : "",
		config->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
	if (config->cqe_comp && !cqe_comp) {
		DRV_LOG(WARNING, "Rx CQE compression isn't supported");
		config->cqe_comp = 0;
	}
	if (config->cqe_pad && !cqe_pad) {
		DRV_LOG(WARNING, "Rx CQE padding isn't supported");
		config->cqe_pad = 0;
	} else if (config->cqe_pad) {
		DRV_LOG(INFO, "Rx CQE padding is enabled");
	}
	if (config->devx) {
		priv->counter_fallback = 0;
		err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
		if (err) {
			err = -err;
			goto error;
		}
		if (!config->hca_attr.flow_counters_dump)
			priv->counter_fallback = 1;
#ifndef HAVE_IBV_DEVX_ASYNC
		priv->counter_fallback = 1;
#endif
		if (priv->counter_fallback)
			DRV_LOG(INFO, "Use fall-back DV counter management");
		/* Check for LRO support. */
		if (config->dest_tir && config->hca_attr.lro_cap &&
		    config->dv_flow_en) {
			/* TBD check tunnel lro caps. */
			config->lro.supported = config->hca_attr.lro_cap;
			DRV_LOG(DEBUG, "Device supports LRO");
			/*
			 * If LRO timeout is not configured by application,
			 * use the minimal supported value.
			 */
			if (!config->lro.timeout)
				config->lro.timeout =
				config->hca_attr.lro_timer_supported_periods[0];
			DRV_LOG(DEBUG, "LRO session timeout set to %d usec",
				config->lro.timeout);
		}
#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER)
		if (config->hca_attr.qos.sup &&
		    config->hca_attr.qos.srtcm_sup &&
		    config->dv_flow_en) {
			uint8_t reg_c_mask =
				config->hca_attr.qos.flow_meter_reg_c_ids;
			/*
			 * Meter needs two REG_C's for color match and pre-sfx
			 * flow match. Here get the REG_C for color match.
			 * REG_C_0 and REG_C_1 is reserved for metadata feature.
			 */
			reg_c_mask &= 0xfc;
			if (__builtin_popcount(reg_c_mask) < 1) {
				priv->mtr_en = 0;
				DRV_LOG(WARNING, "No available register for"
					" meter.");
			} else {
				priv->mtr_color_reg = ffs(reg_c_mask) - 1 +
						      REG_C_0;
				priv->mtr_en = 1;
				priv->mtr_reg_share =
				      config->hca_attr.qos.flow_meter_reg_share;
				DRV_LOG(DEBUG, "The REG_C meter uses is %d",
					priv->mtr_color_reg);
			}
		}
#endif
	}
	if (config->tx_pp) {
		DRV_LOG(DEBUG, "Timestamp counter frequency %u kHz",
			config->hca_attr.dev_freq_khz);
		DRV_LOG(DEBUG, "Packet pacing is %ssupported",
			config->hca_attr.qos.packet_pacing ? "" : "not ");
		DRV_LOG(DEBUG, "Cross channel ops are %ssupported",
			config->hca_attr.cross_channel ? "" : "not ");
		DRV_LOG(DEBUG, "WQE index ignore is %ssupported",
			config->hca_attr.wqe_index_ignore ? "" : "not ");
		DRV_LOG(DEBUG, "Non-wire SQ feature is %ssupported",
			config->hca_attr.non_wire_sq ? "" : "not ");
		DRV_LOG(DEBUG, "Static WQE SQ feature is %ssupported (%d)",
			config->hca_attr.log_max_static_sq_wq ? "" : "not ",
			config->hca_attr.log_max_static_sq_wq);
		DRV_LOG(DEBUG, "WQE rate PP mode is %ssupported",
			config->hca_attr.qos.wqe_rate_pp ? "" : "not ");
		if (!config->devx) {
			DRV_LOG(ERR, "DevX is required for packet pacing");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.qos.packet_pacing) {
			DRV_LOG(ERR, "Packet pacing is not supported");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.cross_channel) {
			DRV_LOG(ERR, "Cross channel operations are"
				     " required for packet pacing");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.wqe_index_ignore) {
			DRV_LOG(ERR, "WQE index ignore feature is"
				     " required for packet pacing");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.non_wire_sq) {
			DRV_LOG(ERR, "Non-wire SQ feature is"
				     " required for packet pacing");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.log_max_static_sq_wq) {
			DRV_LOG(ERR, "Static WQE SQ feature is"
				     " required for packet pacing");
			err = ENODEV;
			goto error;
		}
		if (!config->hca_attr.qos.wqe_rate_pp) {
			DRV_LOG(ERR, "WQE rate mode is required"
				     " for packet pacing");
			err = ENODEV;
			goto error;
		}
#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET
		DRV_LOG(ERR, "DevX does not provide UAR offset,"
			     " can't create queues for packet pacing");
		err = ENODEV;
		goto error;
#endif
	}
	if (config->devx) {
		uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];

		err = config->hca_attr.access_register_user ?
			mlx5_devx_cmd_register_read
				(sh->ctx, MLX5_REGISTER_ID_MTUTC, 0,
				reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP;
		if (!err) {
			uint32_t ts_mode;

			/* MTUTC register is read successfully. */
			ts_mode = MLX5_GET(register_mtutc, reg,
					   time_stamp_mode);
			if (ts_mode == MLX5_MTUTC_TIMESTAMP_MODE_REAL_TIME)
				config->rt_timestamp = 1;
		} else {
			/* Kernel does not support register reading. */
			if (config->hca_attr.dev_freq_khz ==
						 (NS_PER_S / MS_PER_S))
				config->rt_timestamp = 1;
		}
	}
	/*
	 * If HW has bug working with tunnel packet decapsulation and
	 * scatter FCS, and decapsulation is needed, clear the hw_fcs_strip
	 * bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore.
	 */
	if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en)
		config->hw_fcs_strip = 0;
	DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
		(config->hw_fcs_strip ? "" : "not "));
	if (config->mprq.enabled && mprq) {
		if (config->mprq.stride_num_n &&
		    (config->mprq.stride_num_n > mprq_max_stride_num_n ||
		     config->mprq.stride_num_n < mprq_min_stride_num_n)) {
			config->mprq.stride_num_n =
				RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
						mprq_min_stride_num_n),
					mprq_max_stride_num_n);
			DRV_LOG(WARNING,
				"the number of strides"
				" for Multi-Packet RQ is out of range,"
				" setting default value (%u)",
				1 << config->mprq.stride_num_n);
		}
		if (config->mprq.stride_size_n &&
		    (config->mprq.stride_size_n > mprq_max_stride_size_n ||
		     config->mprq.stride_size_n < mprq_min_stride_size_n)) {
			config->mprq.stride_size_n =
				RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N,
						mprq_min_stride_size_n),
					mprq_max_stride_size_n);
			DRV_LOG(WARNING,
				"the size of a stride"
				" for Multi-Packet RQ is out of range,"
				" setting default value (%u)",
				1 << config->mprq.stride_size_n);
		}
		config->mprq.min_stride_size_n = mprq_min_stride_size_n;
		config->mprq.max_stride_size_n = mprq_max_stride_size_n;
	} else if (config->mprq.enabled && !mprq) {
		DRV_LOG(WARNING, "Multi-Packet RQ isn't supported");
		config->mprq.enabled = 0;
	}
	if (config->max_dump_files_num == 0)
		config->max_dump_files_num = 128;
	eth_dev = rte_eth_dev_allocate(name);
	if (eth_dev == NULL) {
		DRV_LOG(ERR, "can not allocate rte ethdev");
		err = ENOMEM;
		goto error;
	}
	/* Flag to call rte_eth_dev_release_port() in rte_eth_dev_close(). */
	eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
	if (priv->representor) {
		eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR;
		eth_dev->data->representor_id = priv->representor_id;
	}
	/*
	 * Store associated network device interface index. This index
	 * is permanent throughout the lifetime of device. So, we may store
	 * the ifindex here and use the cached value further.
	 */
	MLX5_ASSERT(spawn->ifindex);
	priv->if_index = spawn->ifindex;
	eth_dev->data->dev_private = priv;
	priv->dev_data = eth_dev->data;
	eth_dev->data->mac_addrs = priv->mac;
	eth_dev->device = dpdk_dev;
	/* Configure the first MAC address by default. */
	if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) {
		DRV_LOG(ERR,
			"port %u cannot get MAC address, is mlx5_en"
			" loaded? (errno: %s)",
			eth_dev->data->port_id, strerror(rte_errno));
		err = ENODEV;
		goto error;
	}
	DRV_LOG(INFO,
		"port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x",
		eth_dev->data->port_id,
		mac.addr_bytes[0], mac.addr_bytes[1],
		mac.addr_bytes[2], mac.addr_bytes[3],
		mac.addr_bytes[4], mac.addr_bytes[5]);
#ifdef RTE_LIBRTE_MLX5_DEBUG
	{
		char ifname[IF_NAMESIZE];

		if (mlx5_get_ifname(eth_dev, &ifname) == 0)
			DRV_LOG(DEBUG, "port %u ifname is \"%s\"",
				eth_dev->data->port_id, ifname);
		else
			DRV_LOG(DEBUG, "port %u ifname is unknown",
				eth_dev->data->port_id);
	}
#endif
	/* Get actual MTU if possible. */
	err = mlx5_get_mtu(eth_dev, &priv->mtu);
	if (err) {
		err = rte_errno;
		goto error;
	}
	DRV_LOG(DEBUG, "port %u MTU is %u", eth_dev->data->port_id,
		priv->mtu);
	/* Initialize burst functions to prevent crashes before link-up. */
	eth_dev->rx_pkt_burst = removed_rx_burst;
	eth_dev->tx_pkt_burst = removed_tx_burst;
	eth_dev->dev_ops = &mlx5_os_dev_ops;
	/* Register MAC address. */
	claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
	if (config->vf && config->vf_nl_en)
		mlx5_nl_mac_addr_sync(priv->nl_socket_route,
				      mlx5_ifindex(eth_dev),
				      eth_dev->data->mac_addrs,
				      MLX5_MAX_MAC_ADDRESSES);
	priv->flows = 0;
	priv->ctrl_flows = 0;
	TAILQ_INIT(&priv->flow_meters);
	TAILQ_INIT(&priv->flow_meter_profiles);
	/* Hint libmlx5 to use PMD allocator for data plane resources */
	mlx5_glue->dv_set_context_attr(sh->ctx,
			MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
			(void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){
				.alloc = &mlx5_alloc_verbs_buf,
				.free = &mlx5_free_verbs_buf,
				.data = priv,
			}));
	/* Bring Ethernet device up. */
	DRV_LOG(DEBUG, "port %u forcing Ethernet interface up",
		eth_dev->data->port_id);
	mlx5_set_link_up(eth_dev);
	/*
	 * Even though the interrupt handler is not installed yet,
	 * interrupts will still trigger on the async_fd from
	 * Verbs context returned by ibv_open_device().
	 */
	mlx5_link_update(eth_dev, 0);
#ifdef HAVE_MLX5DV_DR_ESWITCH
	if (!(config->hca_attr.eswitch_manager && config->dv_flow_en &&
	      (switch_info->representor || switch_info->master)))
		config->dv_esw_en = 0;
#else
	config->dv_esw_en = 0;
#endif
	/* Detect minimal data bytes to inline. */
	mlx5_set_min_inline(spawn, config);
	/* Store device configuration on private structure. */
	priv->config = *config;
	/* Create context for virtual machine VLAN workaround. */
	priv->vmwa_context = mlx5_vlan_vmwa_init(eth_dev, spawn->ifindex);
	if (config->dv_flow_en) {
		err = mlx5_alloc_shared_dr(priv);
		if (err)
			goto error;
		/*
		 * RSS id is shared with meter flow id. Meter flow id can only
		 * use the 24 MSB of the register.
		 */
		priv->qrss_id_pool = mlx5_flow_id_pool_alloc(UINT32_MAX >>
				     MLX5_MTR_COLOR_BITS);
		if (!priv->qrss_id_pool) {
			DRV_LOG(ERR, "can't create flow id pool");
			err = ENOMEM;
			goto error;
		}
	}
	/* Supported Verbs flow priority number detection. */
	err = mlx5_flow_discover_priorities(eth_dev);
	if (err < 0) {
		err = -err;
		goto error;
	}
	priv->config.flow_prio = err;
	if (!priv->config.dv_esw_en &&
	    priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
		DRV_LOG(WARNING, "metadata mode %u is not supported "
				 "(no E-Switch)", priv->config.dv_xmeta_en);
		priv->config.dv_xmeta_en = MLX5_XMETA_MODE_LEGACY;
	}
	mlx5_set_metadata_mask(eth_dev);
	if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY &&
	    !priv->sh->dv_regc0_mask) {
		DRV_LOG(ERR, "metadata mode %u is not supported "
			     "(no metadata reg_c[0] is available)",
			     priv->config.dv_xmeta_en);
			err = ENOTSUP;
			goto error;
	}
	/*
	 * Allocate the buffer for flow creating, just once.
	 * The allocation must be done before any flow creating.
	 */
	mlx5_flow_alloc_intermediate(eth_dev);
	/* Query availability of metadata reg_c's. */
	err = mlx5_flow_discover_mreg_c(eth_dev);
	if (err < 0) {
		err = -err;
		goto error;
	}
	if (!mlx5_flow_ext_mreg_supported(eth_dev)) {
		DRV_LOG(DEBUG,
			"port %u extensive metadata register is not supported",
			eth_dev->data->port_id);
		if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
			DRV_LOG(ERR, "metadata mode %u is not supported "
				     "(no metadata registers available)",
				     priv->config.dv_xmeta_en);
			err = ENOTSUP;
			goto error;
		}
	}
	if (priv->config.dv_flow_en &&
	    priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY &&
	    mlx5_flow_ext_mreg_supported(eth_dev) &&
	    priv->sh->dv_regc0_mask) {
		priv->mreg_cp_tbl = mlx5_hlist_create(MLX5_FLOW_MREG_HNAME,
						      MLX5_FLOW_MREG_HTABLE_SZ);
		if (!priv->mreg_cp_tbl) {
			err = ENOMEM;
			goto error;
		}
	}
	return eth_dev;
error:
	if (priv) {
		if (priv->mreg_cp_tbl)
			mlx5_hlist_destroy(priv->mreg_cp_tbl, NULL, NULL);
		if (priv->sh)
			mlx5_os_free_shared_dr(priv);
		if (priv->nl_socket_route >= 0)
			close(priv->nl_socket_route);
		if (priv->nl_socket_rdma >= 0)
			close(priv->nl_socket_rdma);
		if (priv->vmwa_context)
			mlx5_vlan_vmwa_exit(priv->vmwa_context);
		if (priv->qrss_id_pool)
			mlx5_flow_id_pool_release(priv->qrss_id_pool);
		if (own_domain_id)
			claim_zero(rte_eth_switch_domain_free(priv->domain_id));
		mlx5_free(priv);
		if (eth_dev != NULL)
			eth_dev->data->dev_private = NULL;
	}
	if (eth_dev != NULL) {
		/* mac_addrs must not be freed alone because part of
		 * dev_private
		 **/
		eth_dev->data->mac_addrs = NULL;
		rte_eth_dev_release_port(eth_dev);
	}
	if (sh)
		mlx5_free_shared_dev_ctx(sh);
	MLX5_ASSERT(err > 0);
	rte_errno = err;
	return NULL;
}

/**
 * Comparison callback to sort device data.
 *
 * This is meant to be used with qsort().
 *
 * @param a[in]
 *   Pointer to pointer to first data object.
 * @param b[in]
 *   Pointer to pointer to second data object.
 *
 * @return
 *   0 if both objects are equal, less than 0 if the first argument is less
 *   than the second, greater than 0 otherwise.
 */
static int
mlx5_dev_spawn_data_cmp(const void *a, const void *b)
{
	const struct mlx5_switch_info *si_a =
		&((const struct mlx5_dev_spawn_data *)a)->info;
	const struct mlx5_switch_info *si_b =
		&((const struct mlx5_dev_spawn_data *)b)->info;
	int ret;

	/* Master device first. */
	ret = si_b->master - si_a->master;
	if (ret)
		return ret;
	/* Then representor devices. */
	ret = si_b->representor - si_a->representor;
	if (ret)
		return ret;
	/* Unidentified devices come last in no specific order. */
	if (!si_a->representor)
		return 0;
	/* Order representors by name. */
	return si_a->port_name - si_b->port_name;
}

/**
 * Match PCI information for possible slaves of bonding device.
 *
 * @param[in] ibv_dev
 *   Pointer to Infiniband device structure.
 * @param[in] pci_dev
 *   Pointer to PCI device structure to match PCI address.
 * @param[in] nl_rdma
 *   Netlink RDMA group socket handle.
 *
 * @return
 *   negative value if no bonding device found, otherwise
 *   positive index of slave PF in bonding.
 */
static int
mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev,
			   const struct rte_pci_device *pci_dev,
			   int nl_rdma)
{
	char ifname[IF_NAMESIZE + 1];
	unsigned int ifindex;
	unsigned int np, i;
	FILE *file = NULL;
	int pf = -1;

	/*
	 * Try to get master device name. If something goes
	 * wrong suppose the lack of kernel support and no
	 * bonding devices.
	 */
	if (nl_rdma < 0)
		return -1;
	if (!strstr(ibv_dev->name, "bond"))
		return -1;
	np = mlx5_nl_portnum(nl_rdma, ibv_dev->name);
	if (!np)
		return -1;
	/*
	 * The Master device might not be on the predefined
	 * port (not on port index 1, it is not garanted),
	 * we have to scan all Infiniband device port and
	 * find master.
	 */
	for (i = 1; i <= np; ++i) {
		/* Check whether Infiniband port is populated. */
		ifindex = mlx5_nl_ifindex(nl_rdma, ibv_dev->name, i);
		if (!ifindex)
			continue;
		if (!if_indextoname(ifindex, ifname))
			continue;
		/* Try to read bonding slave names from sysfs. */
		MKSTR(slaves,
		      "/sys/class/net/%s/master/bonding/slaves", ifname);
		file = fopen(slaves, "r");
		if (file)
			break;
	}
	if (!file)
		return -1;
	/* Use safe format to check maximal buffer length. */
	MLX5_ASSERT(atol(RTE_STR(IF_NAMESIZE)) == IF_NAMESIZE);
	while (fscanf(file, "%" RTE_STR(IF_NAMESIZE) "s", ifname) == 1) {
		char tmp_str[IF_NAMESIZE + 32];
		struct rte_pci_addr pci_addr;
		struct mlx5_switch_info	info;

		/* Process slave interface names in the loop. */
		snprintf(tmp_str, sizeof(tmp_str),
			 "/sys/class/net/%s", ifname);
		if (mlx5_dev_to_pci_addr(tmp_str, &pci_addr)) {
			DRV_LOG(WARNING, "can not get PCI address"
					 " for netdev \"%s\"", ifname);
			continue;
		}
		if (pci_dev->addr.domain != pci_addr.domain ||
		    pci_dev->addr.bus != pci_addr.bus ||
		    pci_dev->addr.devid != pci_addr.devid ||
		    pci_dev->addr.function != pci_addr.function)
			continue;
		/* Slave interface PCI address match found. */
		fclose(file);
		snprintf(tmp_str, sizeof(tmp_str),
			 "/sys/class/net/%s/phys_port_name", ifname);
		file = fopen(tmp_str, "rb");
		if (!file)
			break;
		info.name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET;
		if (fscanf(file, "%32s", tmp_str) == 1)
			mlx5_translate_port_name(tmp_str, &info);
		if (info.name_type == MLX5_PHYS_PORT_NAME_TYPE_LEGACY ||
		    info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK)
			pf = info.port_name;
		break;
	}
	if (file)
		fclose(file);
	return pf;
}

/**
 * DPDK callback to register a PCI device.
 *
 * This function spawns Ethernet devices out of a given PCI device.
 *
 * @param[in] pci_drv
 *   PCI driver structure (mlx5_driver).
 * @param[in] pci_dev
 *   PCI device information.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
		  struct rte_pci_device *pci_dev)
{
	struct ibv_device **ibv_list;
	/*
	 * Number of found IB Devices matching with requested PCI BDF.
	 * nd != 1 means there are multiple IB devices over the same
	 * PCI device and we have representors and master.
	 */
	unsigned int nd = 0;
	/*
	 * Number of found IB device Ports. nd = 1 and np = 1..n means
	 * we have the single multiport IB device, and there may be
	 * representors attached to some of found ports.
	 */
	unsigned int np = 0;
	/*
	 * Number of DPDK ethernet devices to Spawn - either over
	 * multiple IB devices or multiple ports of single IB device.
	 * Actually this is the number of iterations to spawn.
	 */
	unsigned int ns = 0;
	/*
	 * Bonding device
	 *   < 0 - no bonding device (single one)
	 *  >= 0 - bonding device (value is slave PF index)
	 */
	int bd = -1;
	struct mlx5_dev_spawn_data *list = NULL;
	struct mlx5_dev_config dev_config;
	unsigned int dev_config_vf;
	int ret;

	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
		mlx5_pmd_socket_init();
	ret = mlx5_init_once();
	if (ret) {
		DRV_LOG(ERR, "unable to init PMD global data: %s",
			strerror(rte_errno));
		return -rte_errno;
	}
	errno = 0;
	ibv_list = mlx5_glue->get_device_list(&ret);
	if (!ibv_list) {
		rte_errno = errno ? errno : ENOSYS;
		DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?");
		return -rte_errno;
	}
	/*
	 * First scan the list of all Infiniband devices to find
	 * matching ones, gathering into the list.
	 */
	struct ibv_device *ibv_match[ret + 1];
	int nl_route = mlx5_nl_init(NETLINK_ROUTE);
	int nl_rdma = mlx5_nl_init(NETLINK_RDMA);
	unsigned int i;

	while (ret-- > 0) {
		struct rte_pci_addr pci_addr;

		DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name);
		bd = mlx5_device_bond_pci_match
				(ibv_list[ret], pci_dev, nl_rdma);
		if (bd >= 0) {
			/*
			 * Bonding device detected. Only one match is allowed,
			 * the bonding is supported over multi-port IB device,
			 * there should be no matches on representor PCI
			 * functions or non VF LAG bonding devices with
			 * specified address.
			 */
			if (nd) {
				DRV_LOG(ERR,
					"multiple PCI match on bonding device"
					"\"%s\" found", ibv_list[ret]->name);
				rte_errno = ENOENT;
				ret = -rte_errno;
				goto exit;
			}
			DRV_LOG(INFO, "PCI information matches for"
				      " slave %d bonding device \"%s\"",
				      bd, ibv_list[ret]->name);
			ibv_match[nd++] = ibv_list[ret];
			break;
		}
		if (mlx5_dev_to_pci_addr
			(ibv_list[ret]->ibdev_path, &pci_addr))
			continue;
		if (pci_dev->addr.domain != pci_addr.domain ||
		    pci_dev->addr.bus != pci_addr.bus ||
		    pci_dev->addr.devid != pci_addr.devid ||
		    pci_dev->addr.function != pci_addr.function)
			continue;
		DRV_LOG(INFO, "PCI information matches for device \"%s\"",
			ibv_list[ret]->name);
		ibv_match[nd++] = ibv_list[ret];
	}
	ibv_match[nd] = NULL;
	if (!nd) {
		/* No device matches, just complain and bail out. */
		DRV_LOG(WARNING,
			"no Verbs device matches PCI device " PCI_PRI_FMT ","
			" are kernel drivers loaded?",
			pci_dev->addr.domain, pci_dev->addr.bus,
			pci_dev->addr.devid, pci_dev->addr.function);
		rte_errno = ENOENT;
		ret = -rte_errno;
		goto exit;
	}
	if (nd == 1) {
		/*
		 * Found single matching device may have multiple ports.
		 * Each port may be representor, we have to check the port
		 * number and check the representors existence.
		 */
		if (nl_rdma >= 0)
			np = mlx5_nl_portnum(nl_rdma, ibv_match[0]->name);
		if (!np)
			DRV_LOG(WARNING, "can not get IB device \"%s\""
					 " ports number", ibv_match[0]->name);
		if (bd >= 0 && !np) {
			DRV_LOG(ERR, "can not get ports"
				     " for bonding device");
			rte_errno = ENOENT;
			ret = -rte_errno;
			goto exit;
		}
	}
#ifndef HAVE_MLX5DV_DR_DEVX_PORT
	if (bd >= 0) {
		/*
		 * This may happen if there is VF LAG kernel support and
		 * application is compiled with older rdma_core library.
		 */
		DRV_LOG(ERR,
			"No kernel/verbs support for VF LAG bonding found.");
		rte_errno = ENOTSUP;
		ret = -rte_errno;
		goto exit;
	}
#endif
	/*
	 * Now we can determine the maximal
	 * amount of devices to be spawned.
	 */
	list = mlx5_malloc(MLX5_MEM_ZERO,
			   sizeof(struct mlx5_dev_spawn_data) *
			   (np ? np : nd),
			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
	if (!list) {
		DRV_LOG(ERR, "spawn data array allocation failure");
		rte_errno = ENOMEM;
		ret = -rte_errno;
		goto exit;
	}
	if (bd >= 0 || np > 1) {
		/*
		 * Single IB device with multiple ports found,
		 * it may be E-Switch master device and representors.
		 * We have to perform identification through the ports.
		 */
		MLX5_ASSERT(nl_rdma >= 0);
		MLX5_ASSERT(ns == 0);
		MLX5_ASSERT(nd == 1);
		MLX5_ASSERT(np);
		for (i = 1; i <= np; ++i) {
			list[ns].max_port = np;
			list[ns].phys_port = i;
			list[ns].phys_dev = ibv_match[0];
			list[ns].eth_dev = NULL;
			list[ns].pci_dev = pci_dev;
			list[ns].pf_bond = bd;
			list[ns].ifindex = mlx5_nl_ifindex
				(nl_rdma,
				mlx5_os_get_dev_device_name
						(list[ns].phys_dev), i);
			if (!list[ns].ifindex) {
				/*
				 * No network interface index found for the
				 * specified port, it means there is no
				 * representor on this port. It's OK,
				 * there can be disabled ports, for example
				 * if sriov_numvfs < sriov_totalvfs.
				 */
				continue;
			}
			ret = -1;
			if (nl_route >= 0)
				ret = mlx5_nl_switch_info
					       (nl_route,
						list[ns].ifindex,
						&list[ns].info);
			if (ret || (!list[ns].info.representor &&
				    !list[ns].info.master)) {
				/*
				 * We failed to recognize representors with
				 * Netlink, let's try to perform the task
				 * with sysfs.
				 */
				ret =  mlx5_sysfs_switch_info
						(list[ns].ifindex,
						 &list[ns].info);
			}
			if (!ret && bd >= 0) {
				switch (list[ns].info.name_type) {
				case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
					if (list[ns].info.port_name == bd)
						ns++;
					break;
				case MLX5_PHYS_PORT_NAME_TYPE_PFHPF:
					/* Fallthrough */
				case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
					if (list[ns].info.pf_num == bd)
						ns++;
					break;
				default:
					break;
				}
				continue;
			}
			if (!ret && (list[ns].info.representor ^
				     list[ns].info.master))
				ns++;
		}
		if (!ns) {
			DRV_LOG(ERR,
				"unable to recognize master/representors"
				" on the IB device with multiple ports");
			rte_errno = ENOENT;
			ret = -rte_errno;
			goto exit;
		}
	} else {
		/*
		 * The existence of several matching entries (nd > 1) means
		 * port representors have been instantiated. No existing Verbs
		 * call nor sysfs entries can tell them apart, this can only
		 * be done through Netlink calls assuming kernel drivers are
		 * recent enough to support them.
		 *
		 * In the event of identification failure through Netlink,
		 * try again through sysfs, then:
		 *
		 * 1. A single IB device matches (nd == 1) with single
		 *    port (np=0/1) and is not a representor, assume
		 *    no switch support.
		 *
		 * 2. Otherwise no safe assumptions can be made;
		 *    complain louder and bail out.
		 */
		for (i = 0; i != nd; ++i) {
			memset(&list[ns].info, 0, sizeof(list[ns].info));
			list[ns].max_port = 1;
			list[ns].phys_port = 1;
			list[ns].phys_dev = ibv_match[i];
			list[ns].eth_dev = NULL;
			list[ns].pci_dev = pci_dev;
			list[ns].pf_bond = -1;
			list[ns].ifindex = 0;
			if (nl_rdma >= 0)
				list[ns].ifindex = mlx5_nl_ifindex
				(nl_rdma,
				mlx5_os_get_dev_device_name
						(list[ns].phys_dev), 1);
			if (!list[ns].ifindex) {
				char ifname[IF_NAMESIZE];

				/*
				 * Netlink failed, it may happen with old
				 * ib_core kernel driver (before 4.16).
				 * We can assume there is old driver because
				 * here we are processing single ports IB
				 * devices. Let's try sysfs to retrieve
				 * the ifindex. The method works for
				 * master device only.
				 */
				if (nd > 1) {
					/*
					 * Multiple devices found, assume
					 * representors, can not distinguish
					 * master/representor and retrieve
					 * ifindex via sysfs.
					 */
					continue;
				}
				ret = mlx5_get_ifname_sysfs
					(ibv_match[i]->ibdev_path, ifname);
				if (!ret)
					list[ns].ifindex =
						if_nametoindex(ifname);
				if (!list[ns].ifindex) {
					/*
					 * No network interface index found
					 * for the specified device, it means
					 * there it is neither representor
					 * nor master.
					 */
					continue;
				}
			}
			ret = -1;
			if (nl_route >= 0)
				ret = mlx5_nl_switch_info
					       (nl_route,
						list[ns].ifindex,
						&list[ns].info);
			if (ret || (!list[ns].info.representor &&
				    !list[ns].info.master)) {
				/*
				 * We failed to recognize representors with
				 * Netlink, let's try to perform the task
				 * with sysfs.
				 */
				ret =  mlx5_sysfs_switch_info
						(list[ns].ifindex,
						 &list[ns].info);
			}
			if (!ret && (list[ns].info.representor ^
				     list[ns].info.master)) {
				ns++;
			} else if ((nd == 1) &&
				   !list[ns].info.representor &&
				   !list[ns].info.master) {
				/*
				 * Single IB device with
				 * one physical port and
				 * attached network device.
				 * May be SRIOV is not enabled
				 * or there is no representors.
				 */
				DRV_LOG(INFO, "no E-Switch support detected");
				ns++;
				break;
			}
		}
		if (!ns) {
			DRV_LOG(ERR,
				"unable to recognize master/representors"
				" on the multiple IB devices");
			rte_errno = ENOENT;
			ret = -rte_errno;
			goto exit;
		}
	}
	MLX5_ASSERT(ns);
	/*
	 * Sort list to probe devices in natural order for users convenience
	 * (i.e. master first, then representors from lowest to highest ID).
	 */
	qsort(list, ns, sizeof(*list), mlx5_dev_spawn_data_cmp);
	/* Device specific configuration. */
	switch (pci_dev->id.device_id) {
	case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF:
	case PCI_DEVICE_ID_MELLANOX_CONNECTX6DXVF:
		dev_config_vf = 1;
		break;
	default:
		dev_config_vf = 0;
		break;
	}
	for (i = 0; i != ns; ++i) {
		uint32_t restore;

		/* Default configuration. */
		memset(&dev_config, 0, sizeof(struct mlx5_dev_config));
		dev_config.vf = dev_config_vf;
		dev_config.mps = MLX5_ARG_UNSET;
		dev_config.dbnc = MLX5_ARG_UNSET;
		dev_config.rx_vec_en = 1;
		dev_config.txq_inline_max = MLX5_ARG_UNSET;
		dev_config.txq_inline_min = MLX5_ARG_UNSET;
		dev_config.txq_inline_mpw = MLX5_ARG_UNSET;
		dev_config.txqs_inline = MLX5_ARG_UNSET;
		dev_config.vf_nl_en = 1;
		dev_config.mr_ext_memseg_en = 1;
		dev_config.mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
		dev_config.mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
		dev_config.dv_esw_en = 1;
		dev_config.dv_flow_en = 1;
		dev_config.decap_en = 1;
		dev_config.log_hp_size = MLX5_ARG_UNSET;
		list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
						 &list[i],
						 &dev_config);
		if (!list[i].eth_dev) {
			if (rte_errno != EBUSY && rte_errno != EEXIST)
				break;
			/* Device is disabled or already spawned. Ignore it. */
			continue;
		}
		restore = list[i].eth_dev->data->dev_flags;
		rte_eth_copy_pci_info(list[i].eth_dev, pci_dev);
		/* Restore non-PCI flags cleared by the above call. */
		list[i].eth_dev->data->dev_flags |= restore;
		rte_eth_dev_probing_finish(list[i].eth_dev);
	}
	if (i != ns) {
		DRV_LOG(ERR,
			"probe of PCI device " PCI_PRI_FMT " aborted after"
			" encountering an error: %s",
			pci_dev->addr.domain, pci_dev->addr.bus,
			pci_dev->addr.devid, pci_dev->addr.function,
			strerror(rte_errno));
		ret = -rte_errno;
		/* Roll back. */
		while (i--) {
			if (!list[i].eth_dev)
				continue;
			mlx5_dev_close(list[i].eth_dev);
			/* mac_addrs must not be freed because in dev_private */
			list[i].eth_dev->data->mac_addrs = NULL;
			claim_zero(rte_eth_dev_release_port(list[i].eth_dev));
		}
		/* Restore original error. */
		rte_errno = -ret;
	} else {
		ret = 0;
	}
exit:
	/*
	 * Do the routine cleanup:
	 * - close opened Netlink sockets
	 * - free allocated spawn data array
	 * - free the Infiniband device list
	 */
	if (nl_rdma >= 0)
		close(nl_rdma);
	if (nl_route >= 0)
		close(nl_route);
	if (list)
		mlx5_free(list);
	MLX5_ASSERT(ibv_list);
	mlx5_glue->free_device_list(ibv_list);
	return ret;
}

static int
mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config)
{
	char *env;
	int value;

	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
	/* Get environment variable to store. */
	env = getenv(MLX5_SHUT_UP_BF);
	value = env ? !!strcmp(env, "0") : MLX5_ARG_UNSET;
	if (config->dbnc == MLX5_ARG_UNSET)
		setenv(MLX5_SHUT_UP_BF, MLX5_SHUT_UP_BF_DEFAULT, 1);
	else
		setenv(MLX5_SHUT_UP_BF,
		       config->dbnc == MLX5_TXDB_NCACHED ? "1" : "0", 1);
	return value;
}

static void
mlx5_restore_doorbell_mapping_env(int value)
{
	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
	/* Restore the original environment variable state. */
	if (value == MLX5_ARG_UNSET)
		unsetenv(MLX5_SHUT_UP_BF);
	else
		setenv(MLX5_SHUT_UP_BF, value ? "1" : "0", 1);
}

/**
 * Extract pdn of PD object using DV API.
 *
 * @param[in] pd
 *   Pointer to the verbs PD object.
 * @param[out] pdn
 *   Pointer to the PD object number variable.
 *
 * @return
 *   0 on success, error value otherwise.
 */
int
mlx5_os_get_pdn(void *pd, uint32_t *pdn)
{
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
	struct mlx5dv_obj obj;
	struct mlx5dv_pd pd_info;
	int ret = 0;

	obj.pd.in = pd;
	obj.pd.out = &pd_info;
	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD);
	if (ret) {
		DRV_LOG(DEBUG, "Fail to get PD object info");
		return ret;
	}
	*pdn = pd_info.pdn;
	return 0;
#else
	(void)pd;
	(void)pdn;
	return -ENOTSUP;
#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
}

/**
 * Function API to open IB device.
 *
 * This function calls the Linux glue APIs to open a device.
 *
 * @param[in] spawn
 *   Pointer to the IB device attributes (name, port, etc).
 * @param[out] config
 *   Pointer to device configuration structure.
 * @param[out] sh
 *   Pointer to shared context structure.
 *
 * @return
 *   0 on success, a positive error value otherwise.
 */
int
mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
		     const struct mlx5_dev_config *config,
		     struct mlx5_dev_ctx_shared *sh)
{
	int dbmap_env;
	int err = 0;

	sh->numa_node = spawn->pci_dev->device.numa_node;
	pthread_mutex_init(&sh->txpp.mutex, NULL);
	/*
	 * Configure environment variable "MLX5_BF_SHUT_UP"
	 * before the device creation. The rdma_core library
	 * checks the variable at device creation and
	 * stores the result internally.
	 */
	dbmap_env = mlx5_config_doorbell_mapping_env(config);
	/* Try to open IB device with DV first, then usual Verbs. */
	errno = 0;
	sh->ctx = mlx5_glue->dv_open_device(spawn->phys_dev);
	if (sh->ctx) {
		sh->devx = 1;
		DRV_LOG(DEBUG, "DevX is supported");
		/* The device is created, no need for environment. */
		mlx5_restore_doorbell_mapping_env(dbmap_env);
	} else {
		/* The environment variable is still configured. */
		sh->ctx = mlx5_glue->open_device(spawn->phys_dev);
		err = errno ? errno : ENODEV;
		/*
		 * The environment variable is not needed anymore,
		 * all device creation attempts are completed.
		 */
		mlx5_restore_doorbell_mapping_env(dbmap_env);
		if (!sh->ctx)
			return err;
		DRV_LOG(DEBUG, "DevX is NOT supported");
		err = 0;
	}
	return err;
}

/**
 * Install shared asynchronous device events handler.
 * This function is implemented to support event sharing
 * between multiple ports of single IB device.
 *
 * @param sh
 *   Pointer to mlx5_dev_ctx_shared object.
 */
void
mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh)
{
	int ret;
	int flags;

	sh->intr_handle.fd = -1;
	flags = fcntl(((struct ibv_context *)sh->ctx)->async_fd, F_GETFL);
	ret = fcntl(((struct ibv_context *)sh->ctx)->async_fd,
		    F_SETFL, flags | O_NONBLOCK);
	if (ret) {
		DRV_LOG(INFO, "failed to change file descriptor async event"
			" queue");
	} else {
		sh->intr_handle.fd = ((struct ibv_context *)sh->ctx)->async_fd;
		sh->intr_handle.type = RTE_INTR_HANDLE_EXT;
		if (rte_intr_callback_register(&sh->intr_handle,
					mlx5_dev_interrupt_handler, sh)) {
			DRV_LOG(INFO, "Fail to install the shared interrupt.");
			sh->intr_handle.fd = -1;
		}
	}
	if (sh->devx) {
#ifdef HAVE_IBV_DEVX_ASYNC
		sh->intr_handle_devx.fd = -1;
		sh->devx_comp =
			(void *)mlx5_glue->devx_create_cmd_comp(sh->ctx);
		struct mlx5dv_devx_cmd_comp *devx_comp = sh->devx_comp;
		if (!devx_comp) {
			DRV_LOG(INFO, "failed to allocate devx_comp.");
			return;
		}
		flags = fcntl(devx_comp->fd, F_GETFL);
		ret = fcntl(devx_comp->fd, F_SETFL, flags | O_NONBLOCK);
		if (ret) {
			DRV_LOG(INFO, "failed to change file descriptor"
				" devx comp");
			return;
		}
		sh->intr_handle_devx.fd = devx_comp->fd;
		sh->intr_handle_devx.type = RTE_INTR_HANDLE_EXT;
		if (rte_intr_callback_register(&sh->intr_handle_devx,
					mlx5_dev_interrupt_handler_devx, sh)) {
			DRV_LOG(INFO, "Fail to install the devx shared"
				" interrupt.");
			sh->intr_handle_devx.fd = -1;
		}
#endif /* HAVE_IBV_DEVX_ASYNC */
	}
}

/**
 * Uninstall shared asynchronous device events handler.
 * This function is implemented to support event sharing
 * between multiple ports of single IB device.
 *
 * @param dev
 *   Pointer to mlx5_dev_ctx_shared object.
 */
void
mlx5_os_dev_shared_handler_uninstall(struct mlx5_dev_ctx_shared *sh)
{
	if (sh->intr_handle.fd >= 0)
		mlx5_intr_callback_unregister(&sh->intr_handle,
					      mlx5_dev_interrupt_handler, sh);
#ifdef HAVE_IBV_DEVX_ASYNC
	if (sh->intr_handle_devx.fd >= 0)
		rte_intr_callback_unregister(&sh->intr_handle_devx,
				  mlx5_dev_interrupt_handler_devx, sh);
	if (sh->devx_comp)
		mlx5_glue->devx_destroy_cmd_comp(sh->devx_comp);
#endif
}

/**
 * Read statistics by a named counter.
 *
 * @param[in] priv
 *   Pointer to the private device data structure.
 * @param[in] ctr_name
 *   Pointer to the name of the statistic counter to read
 * @param[out] stat
 *   Pointer to read statistic value.
 * @return
 *   0 on success and stat is valud, 1 if failed to read the value
 *   rte_errno is set.
 *
 */
int
mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name,
		      uint64_t *stat)
{
	int fd;

	if (priv->sh) {
		MKSTR(path, "%s/ports/%d/hw_counters/%s",
		      priv->sh->ibdev_path,
		      priv->dev_port,
		      ctr_name);
		fd = open(path, O_RDONLY);
		/*
		 * in switchdev the file location is not per port
		 * but rather in <ibdev_path>/hw_counters/<file_name>.
		 */
		if (fd == -1) {
			MKSTR(path1, "%s/hw_counters/%s",
			      priv->sh->ibdev_path,
			      ctr_name);
			fd = open(path1, O_RDONLY);
		}
		if (fd != -1) {
			char buf[21] = {'\0'};
			ssize_t n = read(fd, buf, sizeof(buf));

			close(fd);
			if (n != -1) {
				*stat = strtoull(buf, NULL, 10);
				return 0;
			}
		}
	}
	*stat = 0;
	return 1;
}

/**
 * Set the reg_mr and dereg_mr call backs
 *
 * @param reg_mr_cb[out]
 *   Pointer to reg_mr func
 * @param dereg_mr_cb[out]
 *   Pointer to dereg_mr func
 *
 */
void
mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,
		      mlx5_dereg_mr_t *dereg_mr_cb)
{
	*reg_mr_cb = mlx5_verbs_ops.reg_mr;
	*dereg_mr_cb = mlx5_verbs_ops.dereg_mr;
}

/**
 * Remove a MAC address from device
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param index
 *   MAC address index.
 */
void
mlx5_os_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	const int vf = priv->config.vf;

	if (vf)
		mlx5_nl_mac_addr_remove(priv->nl_socket_route,
					mlx5_ifindex(dev), priv->mac_own,
					&dev->data->mac_addrs[index], index);
}

/**
 * Adds a MAC address to the device
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param mac_addr
 *   MAC address to register.
 * @param index
 *   MAC address index.
 *
 * @return
 *   0 on success, a negative errno value otherwise
 */
int
mlx5_os_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
		     uint32_t index)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	const int vf = priv->config.vf;
	int ret = 0;

	if (vf)
		ret = mlx5_nl_mac_addr_add(priv->nl_socket_route,
					   mlx5_ifindex(dev), priv->mac_own,
					   mac, index);
	return ret;
}

/**
 * Modify a VF MAC address
 *
 * @param priv
 *   Pointer to device private data.
 * @param mac_addr
 *   MAC address to modify into.
 * @param iface_idx
 *   Net device interface index
 * @param vf_index
 *   VF index
 *
 * @return
 *   0 on success, a negative errno value otherwise
 */
int
mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
			   unsigned int iface_idx,
			   struct rte_ether_addr *mac_addr,
			   int vf_index)
{
	return mlx5_nl_vf_mac_addr_modify
		(priv->nl_socket_route, iface_idx, mac_addr, vf_index);
}

/**
 * Set device promiscuous mode
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param enable
 *   0 - promiscuous is disabled, otherwise - enabled
 *
 * @return
 *   0 on success, a negative error value otherwise
 */
int
mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
{
	struct mlx5_priv *priv = dev->data->dev_private;

	return mlx5_nl_promisc(priv->nl_socket_route,
			       mlx5_ifindex(dev), !!enable);
}

/**
 * Set device promiscuous mode
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param enable
 *   0 - all multicase is disabled, otherwise - enabled
 *
 * @return
 *   0 on success, a negative error value otherwise
 */
int
mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
{
	struct mlx5_priv *priv = dev->data->dev_private;

	return mlx5_nl_allmulti(priv->nl_socket_route,
				mlx5_ifindex(dev), !!enable);
}

const struct eth_dev_ops mlx5_os_dev_ops = {
	.dev_configure = mlx5_dev_configure,
	.dev_start = mlx5_dev_start,
	.dev_stop = mlx5_dev_stop,
	.dev_set_link_down = mlx5_set_link_down,
	.dev_set_link_up = mlx5_set_link_up,
	.dev_close = mlx5_dev_close,
	.promiscuous_enable = mlx5_promiscuous_enable,
	.promiscuous_disable = mlx5_promiscuous_disable,
	.allmulticast_enable = mlx5_allmulticast_enable,
	.allmulticast_disable = mlx5_allmulticast_disable,
	.link_update = mlx5_link_update,
	.stats_get = mlx5_stats_get,
	.stats_reset = mlx5_stats_reset,
	.xstats_get = mlx5_xstats_get,
	.xstats_reset = mlx5_xstats_reset,
	.xstats_get_names = mlx5_xstats_get_names,
	.fw_version_get = mlx5_fw_version_get,
	.dev_infos_get = mlx5_dev_infos_get,
	.read_clock = mlx5_txpp_read_clock,
	.dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
	.vlan_filter_set = mlx5_vlan_filter_set,
	.rx_queue_setup = mlx5_rx_queue_setup,
	.rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
	.tx_queue_setup = mlx5_tx_queue_setup,
	.tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup,
	.rx_queue_release = mlx5_rx_queue_release,
	.tx_queue_release = mlx5_tx_queue_release,
	.rx_queue_start = mlx5_rx_queue_start,
	.rx_queue_stop = mlx5_rx_queue_stop,
	.tx_queue_start = mlx5_tx_queue_start,
	.tx_queue_stop = mlx5_tx_queue_stop,
	.flow_ctrl_get = mlx5_dev_get_flow_ctrl,
	.flow_ctrl_set = mlx5_dev_set_flow_ctrl,
	.mac_addr_remove = mlx5_mac_addr_remove,
	.mac_addr_add = mlx5_mac_addr_add,
	.mac_addr_set = mlx5_mac_addr_set,
	.set_mc_addr_list = mlx5_set_mc_addr_list,
	.mtu_set = mlx5_dev_set_mtu,
	.vlan_strip_queue_set = mlx5_vlan_strip_queue_set,
	.vlan_offload_set = mlx5_vlan_offload_set,
	.reta_update = mlx5_dev_rss_reta_update,
	.reta_query = mlx5_dev_rss_reta_query,
	.rss_hash_update = mlx5_rss_hash_update,
	.rss_hash_conf_get = mlx5_rss_hash_conf_get,
	.filter_ctrl = mlx5_dev_filter_ctrl,
	.rx_descriptor_status = mlx5_rx_descriptor_status,
	.tx_descriptor_status = mlx5_tx_descriptor_status,
	.rxq_info_get = mlx5_rxq_info_get,
	.txq_info_get = mlx5_txq_info_get,
	.rx_burst_mode_get = mlx5_rx_burst_mode_get,
	.tx_burst_mode_get = mlx5_tx_burst_mode_get,
	.rx_queue_count = mlx5_rx_queue_count,
	.rx_queue_intr_enable = mlx5_rx_intr_enable,
	.rx_queue_intr_disable = mlx5_rx_intr_disable,
	.is_removed = mlx5_is_removed,
	.udp_tunnel_port_add  = mlx5_udp_tunnel_port_add,
	.get_module_info = mlx5_get_module_info,
	.get_module_eeprom = mlx5_get_module_eeprom,
	.hairpin_cap_get = mlx5_hairpin_cap_get,
	.mtr_ops_get = mlx5_flow_meter_ops_get,
};

/* Available operations from secondary process. */
const struct eth_dev_ops mlx5_os_dev_sec_ops = {
	.stats_get = mlx5_stats_get,
	.stats_reset = mlx5_stats_reset,
	.xstats_get = mlx5_xstats_get,
	.xstats_reset = mlx5_xstats_reset,
	.xstats_get_names = mlx5_xstats_get_names,
	.fw_version_get = mlx5_fw_version_get,
	.dev_infos_get = mlx5_dev_infos_get,
	.read_clock = mlx5_txpp_read_clock,
	.rx_queue_start = mlx5_rx_queue_start,
	.rx_queue_stop = mlx5_rx_queue_stop,
	.tx_queue_start = mlx5_tx_queue_start,
	.tx_queue_stop = mlx5_tx_queue_stop,
	.rx_descriptor_status = mlx5_rx_descriptor_status,
	.tx_descriptor_status = mlx5_tx_descriptor_status,
	.rxq_info_get = mlx5_rxq_info_get,
	.txq_info_get = mlx5_txq_info_get,
	.rx_burst_mode_get = mlx5_rx_burst_mode_get,
	.tx_burst_mode_get = mlx5_tx_burst_mode_get,
	.get_module_info = mlx5_get_module_info,
	.get_module_eeprom = mlx5_get_module_eeprom,
};

/* Available operations in flow isolated mode. */
const struct eth_dev_ops mlx5_os_dev_ops_isolate = {
	.dev_configure = mlx5_dev_configure,
	.dev_start = mlx5_dev_start,
	.dev_stop = mlx5_dev_stop,
	.dev_set_link_down = mlx5_set_link_down,
	.dev_set_link_up = mlx5_set_link_up,
	.dev_close = mlx5_dev_close,
	.promiscuous_enable = mlx5_promiscuous_enable,
	.promiscuous_disable = mlx5_promiscuous_disable,
	.allmulticast_enable = mlx5_allmulticast_enable,
	.allmulticast_disable = mlx5_allmulticast_disable,
	.link_update = mlx5_link_update,
	.stats_get = mlx5_stats_get,
	.stats_reset = mlx5_stats_reset,
	.xstats_get = mlx5_xstats_get,
	.xstats_reset = mlx5_xstats_reset,
	.xstats_get_names = mlx5_xstats_get_names,
	.fw_version_get = mlx5_fw_version_get,
	.dev_infos_get = mlx5_dev_infos_get,
	.read_clock = mlx5_txpp_read_clock,
	.dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
	.vlan_filter_set = mlx5_vlan_filter_set,
	.rx_queue_setup = mlx5_rx_queue_setup,
	.rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
	.tx_queue_setup = mlx5_tx_queue_setup,
	.tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup,
	.rx_queue_release = mlx5_rx_queue_release,
	.tx_queue_release = mlx5_tx_queue_release,
	.rx_queue_start = mlx5_rx_queue_start,
	.rx_queue_stop = mlx5_rx_queue_stop,
	.tx_queue_start = mlx5_tx_queue_start,
	.tx_queue_stop = mlx5_tx_queue_stop,
	.flow_ctrl_get = mlx5_dev_get_flow_ctrl,
	.flow_ctrl_set = mlx5_dev_set_flow_ctrl,
	.mac_addr_remove = mlx5_mac_addr_remove,
	.mac_addr_add = mlx5_mac_addr_add,
	.mac_addr_set = mlx5_mac_addr_set,
	.set_mc_addr_list = mlx5_set_mc_addr_list,
	.mtu_set = mlx5_dev_set_mtu,
	.vlan_strip_queue_set = mlx5_vlan_strip_queue_set,
	.vlan_offload_set = mlx5_vlan_offload_set,
	.filter_ctrl = mlx5_dev_filter_ctrl,
	.rx_descriptor_status = mlx5_rx_descriptor_status,
	.tx_descriptor_status = mlx5_tx_descriptor_status,
	.rxq_info_get = mlx5_rxq_info_get,
	.txq_info_get = mlx5_txq_info_get,
	.rx_burst_mode_get = mlx5_rx_burst_mode_get,
	.tx_burst_mode_get = mlx5_tx_burst_mode_get,
	.rx_queue_intr_enable = mlx5_rx_intr_enable,
	.rx_queue_intr_disable = mlx5_rx_intr_disable,
	.is_removed = mlx5_is_removed,
	.get_module_info = mlx5_get_module_info,
	.get_module_eeprom = mlx5_get_module_eeprom,
	.hairpin_cap_get = mlx5_hairpin_cap_get,
	.mtr_ops_get = mlx5_flow_meter_ops_get,
};