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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright 2015 6WIND S.A.
 * Copyright 2015 Mellanox Technologies, Ltd
 */

#include <stddef.h>
#include <inttypes.h>
#include <unistd.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <errno.h>
#include <dirent.h>
#include <net/if.h>
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <linux/ethtool.h>
#include <linux/sockios.h>
#include <fcntl.h>
#include <stdalign.h>
#include <sys/un.h>
#include <time.h>

#include <rte_ethdev_driver.h>
#include <rte_bus_pci.h>
#include <rte_mbuf.h>
#include <rte_common.h>
#include <rte_interrupts.h>
#include <rte_malloc.h>
#include <rte_string_fns.h>
#include <rte_rwlock.h>
#include <rte_cycles.h>

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

#include "mlx5.h"
#include "mlx5_rxtx.h"
#include "mlx5_utils.h"

/* Supported speed values found in /usr/include/linux/ethtool.h */
#ifndef HAVE_SUPPORTED_40000baseKR4_Full
#define SUPPORTED_40000baseKR4_Full (1 << 23)
#endif
#ifndef HAVE_SUPPORTED_40000baseCR4_Full
#define SUPPORTED_40000baseCR4_Full (1 << 24)
#endif
#ifndef HAVE_SUPPORTED_40000baseSR4_Full
#define SUPPORTED_40000baseSR4_Full (1 << 25)
#endif
#ifndef HAVE_SUPPORTED_40000baseLR4_Full
#define SUPPORTED_40000baseLR4_Full (1 << 26)
#endif
#ifndef HAVE_SUPPORTED_56000baseKR4_Full
#define SUPPORTED_56000baseKR4_Full (1 << 27)
#endif
#ifndef HAVE_SUPPORTED_56000baseCR4_Full
#define SUPPORTED_56000baseCR4_Full (1 << 28)
#endif
#ifndef HAVE_SUPPORTED_56000baseSR4_Full
#define SUPPORTED_56000baseSR4_Full (1 << 29)
#endif
#ifndef HAVE_SUPPORTED_56000baseLR4_Full
#define SUPPORTED_56000baseLR4_Full (1 << 30)
#endif

/* Add defines in case the running kernel is not the same as user headers. */
#ifndef ETHTOOL_GLINKSETTINGS
struct ethtool_link_settings {
	uint32_t cmd;
	uint32_t speed;
	uint8_t duplex;
	uint8_t port;
	uint8_t phy_address;
	uint8_t autoneg;
	uint8_t mdio_support;
	uint8_t eth_to_mdix;
	uint8_t eth_tp_mdix_ctrl;
	int8_t link_mode_masks_nwords;
	uint32_t reserved[8];
	uint32_t link_mode_masks[];
};

/* The kernel values can be found in /include/uapi/linux/ethtool.h */
#define ETHTOOL_GLINKSETTINGS 0x0000004c
#define ETHTOOL_LINK_MODE_1000baseT_Full_BIT 5
#define ETHTOOL_LINK_MODE_Autoneg_BIT 6
#define ETHTOOL_LINK_MODE_1000baseKX_Full_BIT 17
#define ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT 18
#define ETHTOOL_LINK_MODE_10000baseKR_Full_BIT 19
#define ETHTOOL_LINK_MODE_10000baseR_FEC_BIT 20
#define ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT 21
#define ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT 22
#define ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT 23
#define ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT 24
#define ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT 25
#define ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT 26
#define ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT 27
#define ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT 28
#define ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT 29
#define ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT 30
#endif
#ifndef HAVE_ETHTOOL_LINK_MODE_25G
#define ETHTOOL_LINK_MODE_25000baseCR_Full_BIT 31
#define ETHTOOL_LINK_MODE_25000baseKR_Full_BIT 32
#define ETHTOOL_LINK_MODE_25000baseSR_Full_BIT 33
#endif
#ifndef HAVE_ETHTOOL_LINK_MODE_50G
#define ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT 34
#define ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT 35
#endif
#ifndef HAVE_ETHTOOL_LINK_MODE_100G
#define ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT 36
#define ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT 37
#define ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT 38
#define ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT 39
#endif
#ifndef HAVE_ETHTOOL_LINK_MODE_200G
#define ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT 62
#define ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT 63
#define ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT 0 /* 64 - 64 */
#define ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT 1 /* 65 - 64 */
#define ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT 2 /* 66 - 64 */
#endif


/**
 * Get interface name from private structure.
 *
 * This is a port representor-aware version of mlx5_get_ifname_sysfs().
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[out] ifname
 *   Interface name output buffer.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE])
{
	struct mlx5_priv *priv = dev->data->dev_private;
	unsigned int ifindex;

	MLX5_ASSERT(priv);
	MLX5_ASSERT(priv->sh);
	if (priv->bond_ifindex > 0) {
		memcpy(ifname, priv->bond_name, IF_NAMESIZE);
		return 0;
	}
	ifindex = mlx5_ifindex(dev);
	if (!ifindex) {
		if (!priv->representor)
			return mlx5_get_ifname_sysfs(priv->sh->ibdev_path,
						     *ifname);
		rte_errno = ENXIO;
		return -rte_errno;
	}
	if (if_indextoname(ifindex, &(*ifname)[0]))
		return 0;
	rte_errno = errno;
	return -rte_errno;
}

/**
 * Perform ifreq ioctl() on associated Ethernet device.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param req
 *   Request number to pass to ioctl().
 * @param[out] ifr
 *   Interface request structure output buffer.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr)
{
	int sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
	int ret = 0;

	if (sock == -1) {
		rte_errno = errno;
		return -rte_errno;
	}
	ret = mlx5_get_ifname(dev, &ifr->ifr_name);
	if (ret)
		goto error;
	ret = ioctl(sock, req, ifr);
	if (ret == -1) {
		rte_errno = errno;
		goto error;
	}
	close(sock);
	return 0;
error:
	close(sock);
	return -rte_errno;
}

/**
 * Get device MTU.
 *
 * @param dev
 *   Pointer to Ethernet device.
 * @param[out] mtu
 *   MTU value output buffer.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu)
{
	struct ifreq request;
	int ret = mlx5_ifreq(dev, SIOCGIFMTU, &request);

	if (ret)
		return ret;
	*mtu = request.ifr_mtu;
	return 0;
}

/**
 * Set device MTU.
 *
 * @param dev
 *   Pointer to Ethernet device.
 * @param mtu
 *   MTU value to set.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
{
	struct ifreq request = { .ifr_mtu = mtu, };

	return mlx5_ifreq(dev, SIOCSIFMTU, &request);
}

/**
 * Set device flags.
 *
 * @param dev
 *   Pointer to Ethernet device.
 * @param keep
 *   Bitmask for flags that must remain untouched.
 * @param flags
 *   Bitmask for flags to modify.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_set_flags(struct rte_eth_dev *dev, unsigned int keep, unsigned int flags)
{
	struct ifreq request;
	int ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &request);

	if (ret)
		return ret;
	request.ifr_flags &= keep;
	request.ifr_flags |= flags & ~keep;
	return mlx5_ifreq(dev, SIOCSIFFLAGS, &request);
}

/**
 * Get device current raw clock counter
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] time
 *   Current raw clock counter of the device.
 *
 * @return
 *   0 if the clock has correctly been read
 *   The value of errno in case of error
 */
int
mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	struct ibv_context *ctx = priv->sh->ctx;
	struct ibv_values_ex values;
	int err = 0;

	values.comp_mask = IBV_VALUES_MASK_RAW_CLOCK;
	err = mlx5_glue->query_rt_values_ex(ctx, &values);
	if (err != 0) {
		DRV_LOG(WARNING, "Could not query the clock !");
		return err;
	}
	*clock = values.raw_clock.tv_nsec;
	return 0;
}

/**
 * Retrieve the master device for representor in the same switch domain.
 *
 * @param dev
 *   Pointer to representor Ethernet device structure.
 *
 * @return
 *   Master device structure  on success, NULL otherwise.
 */
static struct rte_eth_dev *
mlx5_find_master_dev(struct rte_eth_dev *dev)
{
	struct mlx5_priv *priv;
	uint16_t port_id;
	uint16_t domain_id;

	priv = dev->data->dev_private;
	domain_id = priv->domain_id;
	MLX5_ASSERT(priv->representor);
	MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
		struct mlx5_priv *opriv =
			rte_eth_devices[port_id].data->dev_private;
		if (opriv &&
		    opriv->master &&
		    opriv->domain_id == domain_id &&
		    opriv->sh == priv->sh)
			return &rte_eth_devices[port_id];
	}
	return NULL;
}

/**
 * DPDK callback to retrieve physical link information.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] link
 *   Storage for current link status.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_link_update_unlocked_gset(struct rte_eth_dev *dev,
			       struct rte_eth_link *link)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	struct ethtool_cmd edata = {
		.cmd = ETHTOOL_GSET /* Deprecated since Linux v4.5. */
	};
	struct ifreq ifr;
	struct rte_eth_link dev_link;
	int link_speed = 0;
	int ret;

	ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
	if (ret) {
		DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	dev_link = (struct rte_eth_link) {
		.link_status = ((ifr.ifr_flags & IFF_UP) &&
				(ifr.ifr_flags & IFF_RUNNING)),
	};
	ifr = (struct ifreq) {
		.ifr_data = (void *)&edata,
	};
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		if (ret == -ENOTSUP && priv->representor) {
			struct rte_eth_dev *master;

			/*
			 * For representors we can try to inherit link
			 * settings from the master device. Actually
			 * link settings do not make a lot of sense
			 * for representors due to missing physical
			 * link. The old kernel drivers supported
			 * emulated settings query for representors,
			 * the new ones do not, so we have to add
			 * this code for compatibility issues.
			 */
			master = mlx5_find_master_dev(dev);
			if (master) {
				ifr = (struct ifreq) {
					.ifr_data = (void *)&edata,
				};
				ret = mlx5_ifreq(master, SIOCETHTOOL, &ifr);
			}
		}
		if (ret) {
			DRV_LOG(WARNING,
				"port %u ioctl(SIOCETHTOOL,"
				" ETHTOOL_GSET) failed: %s",
				dev->data->port_id, strerror(rte_errno));
			return ret;
		}
	}
	link_speed = ethtool_cmd_speed(&edata);
	if (link_speed == -1)
		dev_link.link_speed = ETH_SPEED_NUM_UNKNOWN;
	else
		dev_link.link_speed = link_speed;
	priv->link_speed_capa = 0;
	if (edata.supported & SUPPORTED_Autoneg)
		priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
	if (edata.supported & (SUPPORTED_1000baseT_Full |
			       SUPPORTED_1000baseKX_Full))
		priv->link_speed_capa |= ETH_LINK_SPEED_1G;
	if (edata.supported & SUPPORTED_10000baseKR_Full)
		priv->link_speed_capa |= ETH_LINK_SPEED_10G;
	if (edata.supported & (SUPPORTED_40000baseKR4_Full |
			       SUPPORTED_40000baseCR4_Full |
			       SUPPORTED_40000baseSR4_Full |
			       SUPPORTED_40000baseLR4_Full))
		priv->link_speed_capa |= ETH_LINK_SPEED_40G;
	dev_link.link_duplex = ((edata.duplex == DUPLEX_HALF) ?
				ETH_LINK_HALF_DUPLEX : ETH_LINK_FULL_DUPLEX);
	dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
			ETH_LINK_SPEED_FIXED);
	*link = dev_link;
	return 0;
}

/**
 * Retrieve physical link information (unlocked version using new ioctl).
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] link
 *   Storage for current link status.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
static int
mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev,
			     struct rte_eth_link *link)

{
	struct mlx5_priv *priv = dev->data->dev_private;
	struct ethtool_link_settings gcmd = { .cmd = ETHTOOL_GLINKSETTINGS };
	struct ifreq ifr;
	struct rte_eth_link dev_link;
	struct rte_eth_dev *master = NULL;
	uint64_t sc;
	int ret;

	ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
	if (ret) {
		DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	dev_link = (struct rte_eth_link) {
		.link_status = ((ifr.ifr_flags & IFF_UP) &&
				(ifr.ifr_flags & IFF_RUNNING)),
	};
	ifr = (struct ifreq) {
		.ifr_data = (void *)&gcmd,
	};
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		if (ret == -ENOTSUP && priv->representor) {
			/*
			 * For representors we can try to inherit link
			 * settings from the master device. Actually
			 * link settings do not make a lot of sense
			 * for representors due to missing physical
			 * link. The old kernel drivers supported
			 * emulated settings query for representors,
			 * the new ones do not, so we have to add
			 * this code for compatibility issues.
			 */
			master = mlx5_find_master_dev(dev);
			if (master) {
				ifr = (struct ifreq) {
					.ifr_data = (void *)&gcmd,
				};
				ret = mlx5_ifreq(master, SIOCETHTOOL, &ifr);
			}
		}
		if (ret) {
			DRV_LOG(DEBUG,
				"port %u ioctl(SIOCETHTOOL,"
				" ETHTOOL_GLINKSETTINGS) failed: %s",
				dev->data->port_id, strerror(rte_errno));
			return ret;
		}
	}
	gcmd.link_mode_masks_nwords = -gcmd.link_mode_masks_nwords;

	alignas(struct ethtool_link_settings)
	uint8_t data[offsetof(struct ethtool_link_settings, link_mode_masks) +
		     sizeof(uint32_t) * gcmd.link_mode_masks_nwords * 3];
	struct ethtool_link_settings *ecmd = (void *)data;

	*ecmd = gcmd;
	ifr.ifr_data = (void *)ecmd;
	ret = mlx5_ifreq(master ? master : dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(DEBUG,
			"port %u ioctl(SIOCETHTOOL,"
			"ETHTOOL_GLINKSETTINGS) failed: %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	dev_link.link_speed = (ecmd->speed == UINT32_MAX) ?
				ETH_SPEED_NUM_UNKNOWN : ecmd->speed;
	sc = ecmd->link_mode_masks[0] |
		((uint64_t)ecmd->link_mode_masks[1] << 32);
	priv->link_speed_capa = 0;
	if (sc & MLX5_BITSHIFT(ETHTOOL_LINK_MODE_Autoneg_BIT))
		priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_1000baseT_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_1G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_10G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_20G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_40G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_56G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_25G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_50G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_100G;
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_200G;

	sc = ecmd->link_mode_masks[2] |
		((uint64_t)ecmd->link_mode_masks[3] << 32);
	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT) |
		  MLX5_BITSHIFT
		       (ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT) |
		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT)))
		priv->link_speed_capa |= ETH_LINK_SPEED_200G;
	dev_link.link_duplex = ((ecmd->duplex == DUPLEX_HALF) ?
				ETH_LINK_HALF_DUPLEX : ETH_LINK_FULL_DUPLEX);
	dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
				  ETH_LINK_SPEED_FIXED);
	*link = dev_link;
	return 0;
}

/**
 * DPDK callback to retrieve physical link information.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param wait_to_complete
 *   Wait for request completion.
 *
 * @return
 *   0 if link status was not updated, positive if it was, a negative errno
 *   value otherwise and rte_errno is set.
 */
int
mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
{
	int ret;
	struct rte_eth_link dev_link;
	time_t start_time = time(NULL);
	int retry = MLX5_GET_LINK_STATUS_RETRY_COUNT;

	do {
		ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
		if (ret == -ENOTSUP)
			ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
		if (ret == 0)
			break;
		/* Handle wait to complete situation. */
		if ((wait_to_complete || retry) && ret == -EAGAIN) {
			if (abs((int)difftime(time(NULL), start_time)) <
			    MLX5_LINK_STATUS_TIMEOUT) {
				usleep(0);
				continue;
			} else {
				rte_errno = EBUSY;
				return -rte_errno;
			}
		} else if (ret < 0) {
			return ret;
		}
	} while (wait_to_complete || retry-- > 0);
	ret = !!memcmp(&dev->data->dev_link, &dev_link,
		       sizeof(struct rte_eth_link));
	dev->data->dev_link = dev_link;
	return ret;
}

/**
 * DPDK callback to get flow control status.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] fc_conf
 *   Flow control output buffer.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_dev_get_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
{
	struct ifreq ifr;
	struct ethtool_pauseparam ethpause = {
		.cmd = ETHTOOL_GPAUSEPARAM
	};
	int ret;

	ifr.ifr_data = (void *)&ethpause;
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING,
			"port %u ioctl(SIOCETHTOOL, ETHTOOL_GPAUSEPARAM) failed:"
			" %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	fc_conf->autoneg = ethpause.autoneg;
	if (ethpause.rx_pause && ethpause.tx_pause)
		fc_conf->mode = RTE_FC_FULL;
	else if (ethpause.rx_pause)
		fc_conf->mode = RTE_FC_RX_PAUSE;
	else if (ethpause.tx_pause)
		fc_conf->mode = RTE_FC_TX_PAUSE;
	else
		fc_conf->mode = RTE_FC_NONE;
	return 0;
}

/**
 * DPDK callback to modify flow control parameters.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[in] fc_conf
 *   Flow control parameters.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_dev_set_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
{
	struct ifreq ifr;
	struct ethtool_pauseparam ethpause = {
		.cmd = ETHTOOL_SPAUSEPARAM
	};
	int ret;

	ifr.ifr_data = (void *)&ethpause;
	ethpause.autoneg = fc_conf->autoneg;
	if (((fc_conf->mode & RTE_FC_FULL) == RTE_FC_FULL) ||
	    (fc_conf->mode & RTE_FC_RX_PAUSE))
		ethpause.rx_pause = 1;
	else
		ethpause.rx_pause = 0;

	if (((fc_conf->mode & RTE_FC_FULL) == RTE_FC_FULL) ||
	    (fc_conf->mode & RTE_FC_TX_PAUSE))
		ethpause.tx_pause = 1;
	else
		ethpause.tx_pause = 0;
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING,
			"port %u ioctl(SIOCETHTOOL, ETHTOOL_SPAUSEPARAM)"
			" failed: %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	return 0;
}

/**
 * Handle asynchronous removal event for entire multiport device.
 *
 * @param sh
 *   Infiniband device shared context.
 */
static void
mlx5_dev_interrupt_device_fatal(struct mlx5_dev_ctx_shared *sh)
{
	uint32_t i;

	for (i = 0; i < sh->max_port; ++i) {
		struct rte_eth_dev *dev;

		if (sh->port[i].ih_port_id >= RTE_MAX_ETHPORTS) {
			/*
			 * Or not existing port either no
			 * handler installed for this port.
			 */
			continue;
		}
		dev = &rte_eth_devices[sh->port[i].ih_port_id];
		MLX5_ASSERT(dev);
		if (dev->data->dev_conf.intr_conf.rmv)
			rte_eth_dev_callback_process
				(dev, RTE_ETH_EVENT_INTR_RMV, NULL);
	}
}

/**
 * Handle shared asynchronous events the NIC (removal event
 * and link status change). Supports multiport IB device.
 *
 * @param cb_arg
 *   Callback argument.
 */
void
mlx5_dev_interrupt_handler(void *cb_arg)
{
	struct mlx5_dev_ctx_shared *sh = cb_arg;
	struct ibv_async_event event;

	/* Read all message from the IB device and acknowledge them. */
	for (;;) {
		struct rte_eth_dev *dev;
		uint32_t tmp;

		if (mlx5_glue->get_async_event(sh->ctx, &event))
			break;
		/* Retrieve and check IB port index. */
		tmp = (uint32_t)event.element.port_num;
		if (!tmp && event.event_type == IBV_EVENT_DEVICE_FATAL) {
			/*
			 * The DEVICE_FATAL event is called once for
			 * entire device without port specifying.
			 * We should notify all existing ports.
			 */
			mlx5_glue->ack_async_event(&event);
			mlx5_dev_interrupt_device_fatal(sh);
			continue;
		}
		MLX5_ASSERT(tmp && (tmp <= sh->max_port));
		if (!tmp) {
			/* Unsupported device level event. */
			mlx5_glue->ack_async_event(&event);
			DRV_LOG(DEBUG,
				"unsupported common event (type %d)",
				event.event_type);
			continue;
		}
		if (tmp > sh->max_port) {
			/* Invalid IB port index. */
			mlx5_glue->ack_async_event(&event);
			DRV_LOG(DEBUG,
				"cannot handle an event (type %d)"
				"due to invalid IB port index (%u)",
				event.event_type, tmp);
			continue;
		}
		if (sh->port[tmp - 1].ih_port_id >= RTE_MAX_ETHPORTS) {
			/* No handler installed. */
			mlx5_glue->ack_async_event(&event);
			DRV_LOG(DEBUG,
				"cannot handle an event (type %d)"
				"due to no handler installed for port %u",
				event.event_type, tmp);
			continue;
		}
		/* Retrieve ethernet device descriptor. */
		tmp = sh->port[tmp - 1].ih_port_id;
		dev = &rte_eth_devices[tmp];
		MLX5_ASSERT(dev);
		if ((event.event_type == IBV_EVENT_PORT_ACTIVE ||
		     event.event_type == IBV_EVENT_PORT_ERR) &&
			dev->data->dev_conf.intr_conf.lsc) {
			mlx5_glue->ack_async_event(&event);
			if (mlx5_link_update(dev, 0) == -EAGAIN) {
				usleep(0);
				continue;
			}
			rte_eth_dev_callback_process
				(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
			continue;
		}
		DRV_LOG(DEBUG,
			"port %u cannot handle an unknown event (type %d)",
			dev->data->port_id, event.event_type);
		mlx5_glue->ack_async_event(&event);
	}
}

/*
 * Unregister callback handler safely. The handler may be active
 * while we are trying to unregister it, in this case code -EAGAIN
 * is returned by rte_intr_callback_unregister(). This routine checks
 * the return code and tries to unregister handler again.
 *
 * @param handle
 *   interrupt handle
 * @param cb_fn
 *   pointer to callback routine
 * @cb_arg
 *   opaque callback parameter
 */
void
mlx5_intr_callback_unregister(const struct rte_intr_handle *handle,
			      rte_intr_callback_fn cb_fn, void *cb_arg)
{
	/*
	 * Try to reduce timeout management overhead by not calling
	 * the timer related routines on the first iteration. If the
	 * unregistering succeeds on first call there will be no
	 * timer calls at all.
	 */
	uint64_t twait = 0;
	uint64_t start = 0;

	do {
		int ret;

		ret = rte_intr_callback_unregister(handle, cb_fn, cb_arg);
		if (ret >= 0)
			return;
		if (ret != -EAGAIN) {
			DRV_LOG(INFO, "failed to unregister interrupt"
				      " handler (error: %d)", ret);
			MLX5_ASSERT(false);
			return;
		}
		if (twait) {
			struct timespec onems;

			/* Wait one millisecond and try again. */
			onems.tv_sec = 0;
			onems.tv_nsec = NS_PER_S / MS_PER_S;
			nanosleep(&onems, 0);
			/* Check whether one second elapsed. */
			if ((rte_get_timer_cycles() - start) <= twait)
				continue;
		} else {
			/*
			 * We get the amount of timer ticks for one second.
			 * If this amount elapsed it means we spent one
			 * second in waiting. This branch is executed once
			 * on first iteration.
			 */
			twait = rte_get_timer_hz();
			MLX5_ASSERT(twait);
		}
		/*
		 * Timeout elapsed, show message (once a second) and retry.
		 * We have no other acceptable option here, if we ignore
		 * the unregistering return code the handler will not
		 * be unregistered, fd will be closed and we may get the
		 * crush. Hanging and messaging in the loop seems not to be
		 * the worst choice.
		 */
		DRV_LOG(INFO, "Retrying to unregister interrupt handler");
		start = rte_get_timer_cycles();
	} while (true);
}

/**
 * Handle DEVX interrupts from the NIC.
 * This function is probably called from the DPDK host thread.
 *
 * @param cb_arg
 *   Callback argument.
 */
void
mlx5_dev_interrupt_handler_devx(void *cb_arg)
{
#ifndef HAVE_IBV_DEVX_ASYNC
	(void)cb_arg;
	return;
#else
	struct mlx5_dev_ctx_shared *sh = cb_arg;
	union {
		struct mlx5dv_devx_async_cmd_hdr cmd_resp;
		uint8_t buf[MLX5_ST_SZ_BYTES(query_flow_counter_out) +
			    MLX5_ST_SZ_BYTES(traffic_counter) +
			    sizeof(struct mlx5dv_devx_async_cmd_hdr)];
	} out;
	uint8_t *buf = out.buf + sizeof(out.cmd_resp);

	while (!mlx5_glue->devx_get_async_cmd_comp(sh->devx_comp,
						   &out.cmd_resp,
						   sizeof(out.buf)))
		mlx5_flow_async_pool_query_handle
			(sh, (uint64_t)out.cmd_resp.wr_id,
			 mlx5_devx_get_out_command_status(buf));
#endif /* HAVE_IBV_DEVX_ASYNC */
}

/**
 * DPDK callback to bring the link DOWN.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_set_link_down(struct rte_eth_dev *dev)
{
	return mlx5_set_flags(dev, ~IFF_UP, ~IFF_UP);
}

/**
 * DPDK callback to bring the link UP.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_set_link_up(struct rte_eth_dev *dev)
{
	return mlx5_set_flags(dev, ~IFF_UP, IFF_UP);
}

/**
 * Check if mlx5 device was removed.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 *
 * @return
 *   1 when device is removed, otherwise 0.
 */
int
mlx5_is_removed(struct rte_eth_dev *dev)
{
	struct ibv_device_attr device_attr;
	struct mlx5_priv *priv = dev->data->dev_private;

	if (mlx5_glue->query_device(priv->sh->ctx, &device_attr) == EIO)
		return 1;
	return 0;
}

/**
 * Analyze gathered port parameters via sysfs to recognize master
 * and representor devices for E-Switch configuration.
 *
 * @param[in] device_dir
 *   flag of presence of "device" directory under port device key.
 * @param[inout] switch_info
 *   Port information, including port name as a number and port name
 *   type if recognized
 *
 * @return
 *   master and representor flags are set in switch_info according to
 *   recognized parameters (if any).
 */
static void
mlx5_sysfs_check_switch_info(bool device_dir,
			     struct mlx5_switch_info *switch_info)
{
	switch (switch_info->name_type) {
	case MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN:
		/*
		 * Name is not recognized, assume the master,
		 * check the device directory presence.
		 */
		switch_info->master = device_dir;
		break;
	case MLX5_PHYS_PORT_NAME_TYPE_NOTSET:
		/*
		 * Name is not set, this assumes the legacy naming
		 * schema for master, just check if there is
		 * a device directory.
		 */
		switch_info->master = device_dir;
		break;
	case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
		/* New uplink naming schema recognized. */
		switch_info->master = 1;
		break;
	case MLX5_PHYS_PORT_NAME_TYPE_LEGACY:
		/* Legacy representors naming schema. */
		switch_info->representor = !device_dir;
		break;
	case MLX5_PHYS_PORT_NAME_TYPE_PFHPF:
		/* Fallthrough */
	case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
		/* New representors naming schema. */
		switch_info->representor = 1;
		break;
	}
}

/**
 * Get switch information associated with network interface.
 *
 * @param ifindex
 *   Network interface index.
 * @param[out] info
 *   Switch information object, populated in case of success.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_sysfs_switch_info(unsigned int ifindex, struct mlx5_switch_info *info)
{
	char ifname[IF_NAMESIZE];
	char port_name[IF_NAMESIZE];
	FILE *file;
	struct mlx5_switch_info data = {
		.master = 0,
		.representor = 0,
		.name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET,
		.port_name = 0,
		.switch_id = 0,
	};
	DIR *dir;
	bool port_switch_id_set = false;
	bool device_dir = false;
	char c;
	int ret;

	if (!if_indextoname(ifindex, ifname)) {
		rte_errno = errno;
		return -rte_errno;
	}

	MKSTR(phys_port_name, "/sys/class/net/%s/phys_port_name",
	      ifname);
	MKSTR(phys_switch_id, "/sys/class/net/%s/phys_switch_id",
	      ifname);
	MKSTR(pci_device, "/sys/class/net/%s/device",
	      ifname);

	file = fopen(phys_port_name, "rb");
	if (file != NULL) {
		ret = fscanf(file, "%" RTE_STR(IF_NAMESIZE) "s", port_name);
		fclose(file);
		if (ret == 1)
			mlx5_translate_port_name(port_name, &data);
	}
	file = fopen(phys_switch_id, "rb");
	if (file == NULL) {
		rte_errno = errno;
		return -rte_errno;
	}
	port_switch_id_set =
		fscanf(file, "%" SCNx64 "%c", &data.switch_id, &c) == 2 &&
		c == '\n';
	fclose(file);
	dir = opendir(pci_device);
	if (dir != NULL) {
		closedir(dir);
		device_dir = true;
	}
	if (port_switch_id_set) {
		/* We have some E-Switch configuration. */
		mlx5_sysfs_check_switch_info(device_dir, &data);
	}
	*info = data;
	MLX5_ASSERT(!(data.master && data.representor));
	if (data.master && data.representor) {
		DRV_LOG(ERR, "ifindex %u device is recognized as master"
			     " and as representor", ifindex);
		rte_errno = ENODEV;
		return -rte_errno;
	}
	return 0;
}

/**
 * Get bond information associated with network interface.
 *
 * @param pf_ifindex
 *   Network interface index of bond slave interface
 * @param[out] ifindex
 *   Pointer to bond ifindex.
 * @param[out] ifname
 *   Pointer to bond ifname.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_sysfs_bond_info(unsigned int pf_ifindex, unsigned int *ifindex,
		     char *ifname)
{
	char name[IF_NAMESIZE];
	FILE *file;
	unsigned int index;
	int ret;

	if (!if_indextoname(pf_ifindex, name) || !strlen(name)) {
		rte_errno = errno;
		return -rte_errno;
	}
	MKSTR(bond_if, "/sys/class/net/%s/master/ifindex", name);
	/* read bond ifindex */
	file = fopen(bond_if, "rb");
	if (file == NULL) {
		rte_errno = errno;
		return -rte_errno;
	}
	ret = fscanf(file, "%u", &index);
	fclose(file);
	if (ret <= 0) {
		rte_errno = errno;
		return -rte_errno;
	}
	if (ifindex)
		*ifindex = index;

	/* read bond device name from symbol link */
	if (ifname) {
		if (!if_indextoname(index, ifname)) {
			rte_errno = errno;
			return -rte_errno;
		}
	}
	return 0;
}

/**
 * DPDK callback to retrieve plug-in module EEPROM information (type and size).
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] modinfo
 *   Storage for plug-in module EEPROM information.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_get_module_info(struct rte_eth_dev *dev,
		     struct rte_eth_dev_module_info *modinfo)
{
	struct ethtool_modinfo info = {
		.cmd = ETHTOOL_GMODULEINFO,
	};
	struct ifreq ifr = (struct ifreq) {
		.ifr_data = (void *)&info,
	};
	int ret = 0;

	if (!dev || !modinfo) {
		DRV_LOG(WARNING, "missing argument, cannot get module info");
		rte_errno = EINVAL;
		return -rte_errno;
	}
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
			dev->data->port_id, strerror(rte_errno));
		return ret;
	}
	modinfo->type = info.type;
	modinfo->eeprom_len = info.eeprom_len;
	return ret;
}

/**
 * DPDK callback to retrieve plug-in module EEPROM data.
 *
 * @param dev
 *   Pointer to Ethernet device structure.
 * @param[out] info
 *   Storage for plug-in module EEPROM data.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
			   struct rte_dev_eeprom_info *info)
{
	struct ethtool_eeprom *eeprom;
	struct ifreq ifr;
	int ret = 0;

	if (!dev || !info) {
		DRV_LOG(WARNING, "missing argument, cannot get module eeprom");
		rte_errno = EINVAL;
		return -rte_errno;
	}
	eeprom = mlx5_malloc(MLX5_MEM_ZERO,
			     (sizeof(struct ethtool_eeprom) + info->length), 0,
			     SOCKET_ID_ANY);
	if (!eeprom) {
		DRV_LOG(WARNING, "port %u cannot allocate memory for "
			"eeprom data", dev->data->port_id);
		rte_errno = ENOMEM;
		return -rte_errno;
	}
	eeprom->cmd = ETHTOOL_GMODULEEEPROM;
	eeprom->offset = info->offset;
	eeprom->len = info->length;
	ifr = (struct ifreq) {
		.ifr_data = (void *)eeprom,
	};
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret)
		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
			dev->data->port_id, strerror(rte_errno));
	else
		rte_memcpy(info->data, eeprom->data, info->length);
	mlx5_free(eeprom);
	return ret;
}

/**
 * Read device counters table.
 *
 * @param dev
 *   Pointer to Ethernet device.
 * @param[out] stats
 *   Counters table output buffer.
 *
 * @return
 *   0 on success and stats is filled, negative errno value otherwise and
 *   rte_errno is set.
 */
int
mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
	unsigned int i;
	struct ifreq ifr;
	unsigned int stats_sz = xstats_ctrl->stats_n * sizeof(uint64_t);
	unsigned char et_stat_buf[sizeof(struct ethtool_stats) + stats_sz];
	struct ethtool_stats *et_stats = (struct ethtool_stats *)et_stat_buf;
	int ret;

	et_stats->cmd = ETHTOOL_GSTATS;
	et_stats->n_stats = xstats_ctrl->stats_n;
	ifr.ifr_data = (caddr_t)et_stats;
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING,
			"port %u unable to read statistic values from device",
			dev->data->port_id);
		return ret;
	}
	for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) {
		if (xstats_ctrl->info[i].dev) {
			ret = mlx5_os_read_dev_stat(priv,
					    xstats_ctrl->info[i].ctr_name,
					    &stats[i]);
			/* return last xstats counter if fail to read. */
			if (ret == 0)
				xstats_ctrl->xstats[i] = stats[i];
			else
				stats[i] = xstats_ctrl->xstats[i];
		} else {
			stats[i] = (uint64_t)
				et_stats->data[xstats_ctrl->dev_table_idx[i]];
		}
	}
	return 0;
}

/**
 * Query the number of statistics provided by ETHTOOL.
 *
 * @param dev
 *   Pointer to Ethernet device.
 *
 * @return
 *   Number of statistics on success, negative errno value otherwise and
 *   rte_errno is set.
 */
int
mlx5_os_get_stats_n(struct rte_eth_dev *dev)
{
	struct ethtool_drvinfo drvinfo;
	struct ifreq ifr;
	int ret;

	drvinfo.cmd = ETHTOOL_GDRVINFO;
	ifr.ifr_data = (caddr_t)&drvinfo;
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING, "port %u unable to query number of statistics",
			dev->data->port_id);
		return ret;
	}
	return drvinfo.n_stats;
}

static const struct mlx5_counter_ctrl mlx5_counters_init[] = {
	{
		.dpdk_name = "rx_unicast_bytes",
		.ctr_name = "rx_vport_unicast_bytes",
	},
	{
		.dpdk_name = "rx_multicast_bytes",
		.ctr_name = "rx_vport_multicast_bytes",
	},
	{
		.dpdk_name = "rx_broadcast_bytes",
		.ctr_name = "rx_vport_broadcast_bytes",
	},
	{
		.dpdk_name = "rx_unicast_packets",
		.ctr_name = "rx_vport_unicast_packets",
	},
	{
		.dpdk_name = "rx_multicast_packets",
		.ctr_name = "rx_vport_multicast_packets",
	},
	{
		.dpdk_name = "rx_broadcast_packets",
		.ctr_name = "rx_vport_broadcast_packets",
	},
	{
		.dpdk_name = "tx_unicast_bytes",
		.ctr_name = "tx_vport_unicast_bytes",
	},
	{
		.dpdk_name = "tx_multicast_bytes",
		.ctr_name = "tx_vport_multicast_bytes",
	},
	{
		.dpdk_name = "tx_broadcast_bytes",
		.ctr_name = "tx_vport_broadcast_bytes",
	},
	{
		.dpdk_name = "tx_unicast_packets",
		.ctr_name = "tx_vport_unicast_packets",
	},
	{
		.dpdk_name = "tx_multicast_packets",
		.ctr_name = "tx_vport_multicast_packets",
	},
	{
		.dpdk_name = "tx_broadcast_packets",
		.ctr_name = "tx_vport_broadcast_packets",
	},
	{
		.dpdk_name = "rx_wqe_errors",
		.ctr_name = "rx_wqe_err",
	},
	{
		.dpdk_name = "rx_phy_crc_errors",
		.ctr_name = "rx_crc_errors_phy",
	},
	{
		.dpdk_name = "rx_phy_in_range_len_errors",
		.ctr_name = "rx_in_range_len_errors_phy",
	},
	{
		.dpdk_name = "rx_phy_symbol_errors",
		.ctr_name = "rx_symbol_err_phy",
	},
	{
		.dpdk_name = "tx_phy_errors",
		.ctr_name = "tx_errors_phy",
	},
	{
		.dpdk_name = "rx_out_of_buffer",
		.ctr_name = "out_of_buffer",
		.dev = 1,
	},
	{
		.dpdk_name = "tx_phy_packets",
		.ctr_name = "tx_packets_phy",
	},
	{
		.dpdk_name = "rx_phy_packets",
		.ctr_name = "rx_packets_phy",
	},
	{
		.dpdk_name = "tx_phy_discard_packets",
		.ctr_name = "tx_discards_phy",
	},
	{
		.dpdk_name = "rx_phy_discard_packets",
		.ctr_name = "rx_discards_phy",
	},
	{
		.dpdk_name = "tx_phy_bytes",
		.ctr_name = "tx_bytes_phy",
	},
	{
		.dpdk_name = "rx_phy_bytes",
		.ctr_name = "rx_bytes_phy",
	},
	/* Representor only */
	{
		.dpdk_name = "rx_vport_packets",
		.ctr_name = "vport_rx_packets",
	},
	{
		.dpdk_name = "rx_vport_bytes",
		.ctr_name = "vport_rx_bytes",
	},
	{
		.dpdk_name = "tx_vport_packets",
		.ctr_name = "vport_tx_packets",
	},
	{
		.dpdk_name = "tx_vport_bytes",
		.ctr_name = "vport_tx_bytes",
	},
};

static const unsigned int xstats_n = RTE_DIM(mlx5_counters_init);

/**
 * Init the structures to read device counters.
 *
 * @param dev
 *   Pointer to Ethernet device.
 */
void
mlx5_os_stats_init(struct rte_eth_dev *dev)
{
	struct mlx5_priv *priv = dev->data->dev_private;
	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
	struct mlx5_stats_ctrl *stats_ctrl = &priv->stats_ctrl;
	unsigned int i;
	unsigned int j;
	struct ifreq ifr;
	struct ethtool_gstrings *strings = NULL;
	unsigned int dev_stats_n;
	unsigned int str_sz;
	int ret;

	/* So that it won't aggregate for each init. */
	xstats_ctrl->mlx5_stats_n = 0;
	ret = mlx5_os_get_stats_n(dev);
	if (ret < 0) {
		DRV_LOG(WARNING, "port %u no extended statistics available",
			dev->data->port_id);
		return;
	}
	dev_stats_n = ret;
	/* Allocate memory to grab stat names and values. */
	str_sz = dev_stats_n * ETH_GSTRING_LEN;
	strings = (struct ethtool_gstrings *)
		  mlx5_malloc(0, str_sz + sizeof(struct ethtool_gstrings), 0,
			      SOCKET_ID_ANY);
	if (!strings) {
		DRV_LOG(WARNING, "port %u unable to allocate memory for xstats",
		     dev->data->port_id);
		return;
	}
	strings->cmd = ETHTOOL_GSTRINGS;
	strings->string_set = ETH_SS_STATS;
	strings->len = dev_stats_n;
	ifr.ifr_data = (caddr_t)strings;
	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
	if (ret) {
		DRV_LOG(WARNING, "port %u unable to get statistic names",
			dev->data->port_id);
		goto free;
	}
	for (i = 0; i != dev_stats_n; ++i) {
		const char *curr_string = (const char *)
			&strings->data[i * ETH_GSTRING_LEN];

		for (j = 0; j != xstats_n; ++j) {
			if (!strcmp(mlx5_counters_init[j].ctr_name,
				    curr_string)) {
				unsigned int idx = xstats_ctrl->mlx5_stats_n++;

				xstats_ctrl->dev_table_idx[idx] = i;
				xstats_ctrl->info[idx] = mlx5_counters_init[j];
				break;
			}
		}
	}
	/* Add dev counters. */
	for (i = 0; i != xstats_n; ++i) {
		if (mlx5_counters_init[i].dev) {
			unsigned int idx = xstats_ctrl->mlx5_stats_n++;

			xstats_ctrl->info[idx] = mlx5_counters_init[i];
			xstats_ctrl->hw_stats[idx] = 0;
		}
	}
	MLX5_ASSERT(xstats_ctrl->mlx5_stats_n <= MLX5_MAX_XSTATS);
	xstats_ctrl->stats_n = dev_stats_n;
	/* Copy to base at first time. */
	ret = mlx5_os_read_dev_counters(dev, xstats_ctrl->base);
	if (ret)
		DRV_LOG(ERR, "port %u cannot read device counters: %s",
			dev->data->port_id, strerror(rte_errno));
	mlx5_os_read_dev_stat(priv, "out_of_buffer", &stats_ctrl->imissed_base);
	stats_ctrl->imissed = 0;
free:
	mlx5_free(strings);
}

/**
 * Get MAC address by querying netdevice.
 *
 * @param[in] dev
 *   Pointer to Ethernet device.
 * @param[out] mac
 *   MAC address output buffer.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN])
{
	struct ifreq request;
	int ret;

	ret = mlx5_ifreq(dev, SIOCGIFHWADDR, &request);
	if (ret)
		return ret;
	memcpy(mac, request.ifr_hwaddr.sa_data, RTE_ETHER_ADDR_LEN);
	return 0;
}