Free Electrons

Embedded Linux Experts

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
/*
 * Copyright (c) 2007 Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 */

#include <linux/etherdevice.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/hash.h>
#include <net/ip.h>
#include <net/busy_poll.h>

#include <linux/mlx4/driver.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/cq.h>

#include "mlx4_en.h"
#include "en_port.h"

int mlx4_en_setup_tc(struct net_device *dev, u8 up)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	int i;
	unsigned int offset = 0;

	if (up && up != MLX4_EN_NUM_UP)
		return -EINVAL;

	netdev_set_num_tc(dev, up);

	/* Partition Tx queues evenly amongst UP's */
	for (i = 0; i < up; i++) {
		netdev_set_tc_queue(dev, i, priv->num_tx_rings_p_up, offset);
		offset += priv->num_tx_rings_p_up;
	}

	return 0;
}

#ifdef CONFIG_NET_RX_BUSY_POLL
/* must be called with local_bh_disable()d */
static int mlx4_en_low_latency_recv(struct napi_struct *napi)
{
	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
	struct net_device *dev = cq->dev;
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
	int done;

	if (!priv->port_up)
		return LL_FLUSH_FAILED;

	if (!mlx4_en_cq_lock_poll(cq))
		return LL_FLUSH_BUSY;

	done = mlx4_en_process_rx_cq(dev, cq, 4);
	if (likely(done))
		rx_ring->cleaned += done;
	else
		rx_ring->misses++;

	mlx4_en_cq_unlock_poll(cq);

	return done;
}
#endif	/* CONFIG_NET_RX_BUSY_POLL */

#ifdef CONFIG_RFS_ACCEL

struct mlx4_en_filter {
	struct list_head next;
	struct work_struct work;

	u8     ip_proto;
	__be32 src_ip;
	__be32 dst_ip;
	__be16 src_port;
	__be16 dst_port;

	int rxq_index;
	struct mlx4_en_priv *priv;
	u32 flow_id;			/* RFS infrastructure id */
	int id;				/* mlx4_en driver id */
	u64 reg_id;			/* Flow steering API id */
	u8 activated;			/* Used to prevent expiry before filter
					 * is attached
					 */
	struct hlist_node filter_chain;
};

static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv);

static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
{
	switch (ip_proto) {
	case IPPROTO_UDP:
		return MLX4_NET_TRANS_RULE_ID_UDP;
	case IPPROTO_TCP:
		return MLX4_NET_TRANS_RULE_ID_TCP;
	default:
		return -EPROTONOSUPPORT;
	}
};

static void mlx4_en_filter_work(struct work_struct *work)
{
	struct mlx4_en_filter *filter = container_of(work,
						     struct mlx4_en_filter,
						     work);
	struct mlx4_en_priv *priv = filter->priv;
	struct mlx4_spec_list spec_tcp_udp = {
		.id = mlx4_ip_proto_to_trans_rule_id(filter->ip_proto),
		{
			.tcp_udp = {
				.dst_port = filter->dst_port,
				.dst_port_msk = (__force __be16)-1,
				.src_port = filter->src_port,
				.src_port_msk = (__force __be16)-1,
			},
		},
	};
	struct mlx4_spec_list spec_ip = {
		.id = MLX4_NET_TRANS_RULE_ID_IPV4,
		{
			.ipv4 = {
				.dst_ip = filter->dst_ip,
				.dst_ip_msk = (__force __be32)-1,
				.src_ip = filter->src_ip,
				.src_ip_msk = (__force __be32)-1,
			},
		},
	};
	struct mlx4_spec_list spec_eth = {
		.id = MLX4_NET_TRANS_RULE_ID_ETH,
	};
	struct mlx4_net_trans_rule rule = {
		.list = LIST_HEAD_INIT(rule.list),
		.queue_mode = MLX4_NET_TRANS_Q_LIFO,
		.exclusive = 1,
		.allow_loopback = 1,
		.promisc_mode = MLX4_FS_REGULAR,
		.port = priv->port,
		.priority = MLX4_DOMAIN_RFS,
	};
	int rc;
	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);

	if (spec_tcp_udp.id < 0) {
		en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
			filter->ip_proto);
		goto ignore;
	}
	list_add_tail(&spec_eth.list, &rule.list);
	list_add_tail(&spec_ip.list, &rule.list);
	list_add_tail(&spec_tcp_udp.list, &rule.list);

	rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
	memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
	memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);

	filter->activated = 0;

	if (filter->reg_id) {
		rc = mlx4_flow_detach(priv->mdev->dev, filter->reg_id);
		if (rc && rc != -ENOENT)
			en_err(priv, "Error detaching flow. rc = %d\n", rc);
	}

	rc = mlx4_flow_attach(priv->mdev->dev, &rule, &filter->reg_id);
	if (rc)
		en_err(priv, "Error attaching flow. err = %d\n", rc);

ignore:
	mlx4_en_filter_rfs_expire(priv);

	filter->activated = 1;
}

static inline struct hlist_head *
filter_hash_bucket(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
		   __be16 src_port, __be16 dst_port)
{
	unsigned long l;
	int bucket_idx;

	l = (__force unsigned long)src_port |
	    ((__force unsigned long)dst_port << 2);
	l ^= (__force unsigned long)(src_ip ^ dst_ip);

	bucket_idx = hash_long(l, MLX4_EN_FILTER_HASH_SHIFT);

	return &priv->filter_hash[bucket_idx];
}

static struct mlx4_en_filter *
mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
		     __be32 dst_ip, u8 ip_proto, __be16 src_port,
		     __be16 dst_port, u32 flow_id)
{
	struct mlx4_en_filter *filter = NULL;

	filter = kzalloc(sizeof(struct mlx4_en_filter), GFP_ATOMIC);
	if (!filter)
		return NULL;

	filter->priv = priv;
	filter->rxq_index = rxq_index;
	INIT_WORK(&filter->work, mlx4_en_filter_work);

	filter->src_ip = src_ip;
	filter->dst_ip = dst_ip;
	filter->ip_proto = ip_proto;
	filter->src_port = src_port;
	filter->dst_port = dst_port;

	filter->flow_id = flow_id;

	filter->id = priv->last_filter_id++ % RPS_NO_FILTER;

	list_add_tail(&filter->next, &priv->filters);
	hlist_add_head(&filter->filter_chain,
		       filter_hash_bucket(priv, src_ip, dst_ip, src_port,
					  dst_port));

	return filter;
}

static void mlx4_en_filter_free(struct mlx4_en_filter *filter)
{
	struct mlx4_en_priv *priv = filter->priv;
	int rc;

	list_del(&filter->next);

	rc = mlx4_flow_detach(priv->mdev->dev, filter->reg_id);
	if (rc && rc != -ENOENT)
		en_err(priv, "Error detaching flow. rc = %d\n", rc);

	kfree(filter);
}

static inline struct mlx4_en_filter *
mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
		    u8 ip_proto, __be16 src_port, __be16 dst_port)
{
	struct mlx4_en_filter *filter;
	struct mlx4_en_filter *ret = NULL;

	hlist_for_each_entry(filter,
			     filter_hash_bucket(priv, src_ip, dst_ip,
						src_port, dst_port),
			     filter_chain) {
		if (filter->src_ip == src_ip &&
		    filter->dst_ip == dst_ip &&
		    filter->ip_proto == ip_proto &&
		    filter->src_port == src_port &&
		    filter->dst_port == dst_port) {
			ret = filter;
			break;
		}
	}

	return ret;
}

static int
mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
		   u16 rxq_index, u32 flow_id)
{
	struct mlx4_en_priv *priv = netdev_priv(net_dev);
	struct mlx4_en_filter *filter;
	const struct iphdr *ip;
	const __be16 *ports;
	u8 ip_proto;
	__be32 src_ip;
	__be32 dst_ip;
	__be16 src_port;
	__be16 dst_port;
	int nhoff = skb_network_offset(skb);
	int ret = 0;

	if (skb->protocol != htons(ETH_P_IP))
		return -EPROTONOSUPPORT;

	ip = (const struct iphdr *)(skb->data + nhoff);
	if (ip_is_fragment(ip))
		return -EPROTONOSUPPORT;

	if ((ip->protocol != IPPROTO_TCP) && (ip->protocol != IPPROTO_UDP))
		return -EPROTONOSUPPORT;
	ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);

	ip_proto = ip->protocol;
	src_ip = ip->saddr;
	dst_ip = ip->daddr;
	src_port = ports[0];
	dst_port = ports[1];

	spin_lock_bh(&priv->filters_lock);
	filter = mlx4_en_filter_find(priv, src_ip, dst_ip, ip_proto,
				     src_port, dst_port);
	if (filter) {
		if (filter->rxq_index == rxq_index)
			goto out;

		filter->rxq_index = rxq_index;
	} else {
		filter = mlx4_en_filter_alloc(priv, rxq_index,
					      src_ip, dst_ip, ip_proto,
					      src_port, dst_port, flow_id);
		if (!filter) {
			ret = -ENOMEM;
			goto err;
		}
	}

	queue_work(priv->mdev->workqueue, &filter->work);

out:
	ret = filter->id;
err:
	spin_unlock_bh(&priv->filters_lock);

	return ret;
}

void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv)
{
	struct mlx4_en_filter *filter, *tmp;
	LIST_HEAD(del_list);

	spin_lock_bh(&priv->filters_lock);
	list_for_each_entry_safe(filter, tmp, &priv->filters, next) {
		list_move(&filter->next, &del_list);
		hlist_del(&filter->filter_chain);
	}
	spin_unlock_bh(&priv->filters_lock);

	list_for_each_entry_safe(filter, tmp, &del_list, next) {
		cancel_work_sync(&filter->work);
		mlx4_en_filter_free(filter);
	}
}

static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv)
{
	struct mlx4_en_filter *filter = NULL, *tmp, *last_filter = NULL;
	LIST_HEAD(del_list);
	int i = 0;

	spin_lock_bh(&priv->filters_lock);
	list_for_each_entry_safe(filter, tmp, &priv->filters, next) {
		if (i > MLX4_EN_FILTER_EXPIRY_QUOTA)
			break;

		if (filter->activated &&
		    !work_pending(&filter->work) &&
		    rps_may_expire_flow(priv->dev,
					filter->rxq_index, filter->flow_id,
					filter->id)) {
			list_move(&filter->next, &del_list);
			hlist_del(&filter->filter_chain);
		} else
			last_filter = filter;

		i++;
	}

	if (last_filter && (&last_filter->next != priv->filters.next))
		list_move(&priv->filters, &last_filter->next);

	spin_unlock_bh(&priv->filters_lock);

	list_for_each_entry_safe(filter, tmp, &del_list, next)
		mlx4_en_filter_free(filter);
}
#endif

static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
				   __be16 proto, u16 vid)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;
	int idx;

	en_dbg(HW, priv, "adding VLAN:%d\n", vid);

	set_bit(vid, priv->active_vlans);

	/* Add VID to port VLAN filter */
	mutex_lock(&mdev->state_lock);
	if (mdev->device_up && priv->port_up) {
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
		if (err)
			en_err(priv, "Failed configuring VLAN filter\n");
	}
	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
		en_dbg(HW, priv, "failed adding vlan %d\n", vid);
	mutex_unlock(&mdev->state_lock);

	return 0;
}

static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
				    __be16 proto, u16 vid)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;

	en_dbg(HW, priv, "Killing VID:%d\n", vid);

	clear_bit(vid, priv->active_vlans);

	/* Remove VID from port VLAN filter */
	mutex_lock(&mdev->state_lock);
	mlx4_unregister_vlan(mdev->dev, priv->port, vid);

	if (mdev->device_up && priv->port_up) {
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
		if (err)
			en_err(priv, "Failed configuring VLAN filter\n");
	}
	mutex_unlock(&mdev->state_lock);

	return 0;
}

static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
{
	int i;
	for (i = ETH_ALEN - 1; i >= 0; --i) {
		dst_mac[i] = src_mac & 0xff;
		src_mac >>= 8;
	}
	memset(&dst_mac[ETH_ALEN], 0, 2);
}


static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *addr,
				    int qpn, u64 *reg_id)
{
	int err;
	struct mlx4_spec_list spec_eth_outer = { {NULL} };
	struct mlx4_spec_list spec_vxlan     = { {NULL} };
	struct mlx4_spec_list spec_eth_inner = { {NULL} };

	struct mlx4_net_trans_rule rule = {
		.queue_mode = MLX4_NET_TRANS_Q_FIFO,
		.exclusive = 0,
		.allow_loopback = 1,
		.promisc_mode = MLX4_FS_REGULAR,
		.priority = MLX4_DOMAIN_NIC,
	};

	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);

	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
		return 0; /* do nothing */

	rule.port = priv->port;
	rule.qpn = qpn;
	INIT_LIST_HEAD(&rule.list);

	spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH;
	memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN);
	memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN);

	spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN;    /* any vxlan header */
	spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH;	 /* any inner eth header */

	list_add_tail(&spec_eth_outer.list, &rule.list);
	list_add_tail(&spec_vxlan.list,     &rule.list);
	list_add_tail(&spec_eth_inner.list, &rule.list);

	err = mlx4_flow_attach(priv->mdev->dev, &rule, reg_id);
	if (err) {
		en_err(priv, "failed to add vxlan steering rule, err %d\n", err);
		return err;
	}
	en_dbg(DRV, priv, "added vxlan steering rule, mac %pM reg_id %llx\n", addr, *reg_id);
	return 0;
}


static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
				unsigned char *mac, int *qpn, u64 *reg_id)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int err;

	switch (dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_B0: {
		struct mlx4_qp qp;
		u8 gid[16] = {0};

		qp.qpn = *qpn;
		memcpy(&gid[10], mac, ETH_ALEN);
		gid[5] = priv->port;

		err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
		break;
	}
	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
		struct mlx4_spec_list spec_eth = { {NULL} };
		__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);

		struct mlx4_net_trans_rule rule = {
			.queue_mode = MLX4_NET_TRANS_Q_FIFO,
			.exclusive = 0,
			.allow_loopback = 1,
			.promisc_mode = MLX4_FS_REGULAR,
			.priority = MLX4_DOMAIN_NIC,
		};

		rule.port = priv->port;
		rule.qpn = *qpn;
		INIT_LIST_HEAD(&rule.list);

		spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
		memcpy(spec_eth.eth.dst_mac, mac, ETH_ALEN);
		memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
		list_add_tail(&spec_eth.list, &rule.list);

		err = mlx4_flow_attach(dev, &rule, reg_id);
		break;
	}
	default:
		return -EINVAL;
	}
	if (err)
		en_warn(priv, "Failed Attaching Unicast\n");

	return err;
}

static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv,
				     unsigned char *mac, int qpn, u64 reg_id)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;

	switch (dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_B0: {
		struct mlx4_qp qp;
		u8 gid[16] = {0};

		qp.qpn = qpn;
		memcpy(&gid[10], mac, ETH_ALEN);
		gid[5] = priv->port;

		mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
		break;
	}
	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
		mlx4_flow_detach(dev, reg_id);
		break;
	}
	default:
		en_err(priv, "Invalid steering mode.\n");
	}
}

static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	struct mlx4_mac_entry *entry;
	int index = 0;
	int err = 0;
	u64 reg_id;
	int *qpn = &priv->base_qpn;
	u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);

	en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
	       priv->dev->dev_addr);
	index = mlx4_register_mac(dev, priv->port, mac);
	if (index < 0) {
		err = index;
		en_err(priv, "Failed adding MAC: %pM\n",
		       priv->dev->dev_addr);
		return err;
	}

	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
		int base_qpn = mlx4_get_base_qpn(dev, priv->port);
		*qpn = base_qpn + index;
		return 0;
	}

	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
	if (err) {
		en_err(priv, "Failed to reserve qp for mac registration\n");
		goto qp_err;
	}

	err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, &reg_id);
	if (err)
		goto steer_err;

	err = mlx4_en_tunnel_steer_add(priv, priv->dev->dev_addr, *qpn,
				       &priv->tunnel_reg_id);
	if (err)
		goto tunnel_err;

	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
	if (!entry) {
		err = -ENOMEM;
		goto alloc_err;
	}
	memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac));
	entry->reg_id = reg_id;

	hlist_add_head_rcu(&entry->hlist,
			   &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]);

	return 0;

alloc_err:
	if (priv->tunnel_reg_id)
		mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
tunnel_err:
	mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);

steer_err:
	mlx4_qp_release_range(dev, *qpn, 1);

qp_err:
	mlx4_unregister_mac(dev, priv->port, mac);
	return err;
}

static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int qpn = priv->base_qpn;
	u64 mac;

	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
		mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
		en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
		       priv->dev->dev_addr);
		mlx4_unregister_mac(dev, priv->port, mac);
	} else {
		struct mlx4_mac_entry *entry;
		struct hlist_node *tmp;
		struct hlist_head *bucket;
		unsigned int i;

		for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
			bucket = &priv->mac_hash[i];
			hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
				mac = mlx4_en_mac_to_u64(entry->mac);
				en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
				       entry->mac);
				mlx4_en_uc_steer_release(priv, entry->mac,
							 qpn, entry->reg_id);

				mlx4_unregister_mac(dev, priv->port, mac);
				hlist_del_rcu(&entry->hlist);
				kfree_rcu(entry, rcu);
			}
		}

		if (priv->tunnel_reg_id) {
			mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
			priv->tunnel_reg_id = 0;
		}

		en_dbg(DRV, priv, "Releasing qp: port %d, qpn %d\n",
		       priv->port, qpn);
		mlx4_qp_release_range(dev, qpn, 1);
		priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;
	}
}

static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
			       unsigned char *new_mac, unsigned char *prev_mac)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int err = 0;
	u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac);

	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
		struct hlist_head *bucket;
		unsigned int mac_hash;
		struct mlx4_mac_entry *entry;
		struct hlist_node *tmp;
		u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac);

		bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
		hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
			if (ether_addr_equal_64bits(entry->mac, prev_mac)) {
				mlx4_en_uc_steer_release(priv, entry->mac,
							 qpn, entry->reg_id);
				mlx4_unregister_mac(dev, priv->port,
						    prev_mac_u64);
				hlist_del_rcu(&entry->hlist);
				synchronize_rcu();
				memcpy(entry->mac, new_mac, ETH_ALEN);
				entry->reg_id = 0;
				mac_hash = new_mac[MLX4_EN_MAC_HASH_IDX];
				hlist_add_head_rcu(&entry->hlist,
						   &priv->mac_hash[mac_hash]);
				mlx4_register_mac(dev, priv->port, new_mac_u64);
				err = mlx4_en_uc_steer_add(priv, new_mac,
							   &qpn,
							   &entry->reg_id);
				if (err)
					return err;
				if (priv->tunnel_reg_id) {
					mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
					priv->tunnel_reg_id = 0;
				}
				err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn,
							       &priv->tunnel_reg_id);
				return err;
			}
		}
		return -EINVAL;
	}

	return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
}

u64 mlx4_en_mac_to_u64(u8 *addr)
{
	u64 mac = 0;
	int i;

	for (i = 0; i < ETH_ALEN; i++) {
		mac <<= 8;
		mac |= addr[i];
	}
	return mac;
}

static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
{
	int err = 0;

	if (priv->port_up) {
		/* Remove old MAC and insert the new one */
		err = mlx4_en_replace_mac(priv, priv->base_qpn,
					  priv->dev->dev_addr, priv->prev_mac);
		if (err)
			en_err(priv, "Failed changing HW MAC address\n");
		memcpy(priv->prev_mac, priv->dev->dev_addr,
		       sizeof(priv->prev_mac));
	} else
		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");

	return err;
}

static int mlx4_en_set_mac(struct net_device *dev, void *addr)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct sockaddr *saddr = addr;
	int err;

	if (!is_valid_ether_addr(saddr->sa_data))
		return -EADDRNOTAVAIL;

	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);

	mutex_lock(&mdev->state_lock);
	err = mlx4_en_do_set_mac(priv);
	mutex_unlock(&mdev->state_lock);

	return err;
}

static void mlx4_en_clear_list(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_mc_list *tmp, *mc_to_del;

	list_for_each_entry_safe(mc_to_del, tmp, &priv->mc_list, list) {
		list_del(&mc_to_del->list);
		kfree(mc_to_del);
	}
}

static void mlx4_en_cache_mclist(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct netdev_hw_addr *ha;
	struct mlx4_en_mc_list *tmp;

	mlx4_en_clear_list(dev);
	netdev_for_each_mc_addr(ha, dev) {
		tmp = kzalloc(sizeof(struct mlx4_en_mc_list), GFP_ATOMIC);
		if (!tmp) {
			mlx4_en_clear_list(dev);
			return;
		}
		memcpy(tmp->addr, ha->addr, ETH_ALEN);
		list_add_tail(&tmp->list, &priv->mc_list);
	}
}

static void update_mclist_flags(struct mlx4_en_priv *priv,
				struct list_head *dst,
				struct list_head *src)
{
	struct mlx4_en_mc_list *dst_tmp, *src_tmp, *new_mc;
	bool found;

	/* Find all the entries that should be removed from dst,
	 * These are the entries that are not found in src
	 */
	list_for_each_entry(dst_tmp, dst, list) {
		found = false;
		list_for_each_entry(src_tmp, src, list) {
			if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) {
				found = true;
				break;
			}
		}
		if (!found)
			dst_tmp->action = MCLIST_REM;
	}

	/* Add entries that exist in src but not in dst
	 * mark them as need to add
	 */
	list_for_each_entry(src_tmp, src, list) {
		found = false;
		list_for_each_entry(dst_tmp, dst, list) {
			if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) {
				dst_tmp->action = MCLIST_NONE;
				found = true;
				break;
			}
		}
		if (!found) {
			new_mc = kmemdup(src_tmp,
					 sizeof(struct mlx4_en_mc_list),
					 GFP_KERNEL);
			if (!new_mc)
				return;

			new_mc->action = MCLIST_ADD;
			list_add_tail(&new_mc->list, dst);
		}
	}
}

static void mlx4_en_set_rx_mode(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);

	if (!priv->port_up)
		return;

	queue_work(priv->mdev->workqueue, &priv->rx_mode_task);
}

static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv,
				     struct mlx4_en_dev *mdev)
{
	int err = 0;

	if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
		if (netif_msg_rx_status(priv))
			en_warn(priv, "Entering promiscuous mode\n");
		priv->flags |= MLX4_EN_FLAG_PROMISC;

		/* Enable promiscouos mode */
		switch (mdev->dev->caps.steering_mode) {
		case MLX4_STEERING_MODE_DEVICE_MANAGED:
			err = mlx4_flow_steer_promisc_add(mdev->dev,
							  priv->port,
							  priv->base_qpn,
							  MLX4_FS_ALL_DEFAULT);
			if (err)
				en_err(priv, "Failed enabling promiscuous mode\n");
			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
			break;

		case MLX4_STEERING_MODE_B0:
			err = mlx4_unicast_promisc_add(mdev->dev,
						       priv->base_qpn,
						       priv->port);
			if (err)
				en_err(priv, "Failed enabling unicast promiscuous mode\n");

			/* Add the default qp number as multicast
			 * promisc
			 */
			if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
				err = mlx4_multicast_promisc_add(mdev->dev,
								 priv->base_qpn,
								 priv->port);
				if (err)
					en_err(priv, "Failed enabling multicast promiscuous mode\n");
				priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
			}
			break;

		case MLX4_STEERING_MODE_A0:
			err = mlx4_SET_PORT_qpn_calc(mdev->dev,
						     priv->port,
						     priv->base_qpn,
						     1);
			if (err)
				en_err(priv, "Failed enabling promiscuous mode\n");
			break;
		}

		/* Disable port multicast filter (unconditionally) */
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
			en_err(priv, "Failed disabling multicast filter\n");

		/* Disable port VLAN filter */
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
		if (err)
			en_err(priv, "Failed disabling VLAN filter\n");
	}
}

static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv,
				       struct mlx4_en_dev *mdev)
{
	int err = 0;

	if (netif_msg_rx_status(priv))
		en_warn(priv, "Leaving promiscuous mode\n");
	priv->flags &= ~MLX4_EN_FLAG_PROMISC;

	/* Disable promiscouos mode */
	switch (mdev->dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_DEVICE_MANAGED:
		err = mlx4_flow_steer_promisc_remove(mdev->dev,
						     priv->port,
						     MLX4_FS_ALL_DEFAULT);
		if (err)
			en_err(priv, "Failed disabling promiscuous mode\n");
		priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		break;

	case MLX4_STEERING_MODE_B0:
		err = mlx4_unicast_promisc_remove(mdev->dev,
						  priv->base_qpn,
						  priv->port);
		if (err)
			en_err(priv, "Failed disabling unicast promiscuous mode\n");
		/* Disable Multicast promisc */
		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
			err = mlx4_multicast_promisc_remove(mdev->dev,
							    priv->base_qpn,
							    priv->port);
			if (err)
				en_err(priv, "Failed disabling multicast promiscuous mode\n");
			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		}
		break;

	case MLX4_STEERING_MODE_A0:
		err = mlx4_SET_PORT_qpn_calc(mdev->dev,
					     priv->port,
					     priv->base_qpn, 0);
		if (err)
			en_err(priv, "Failed disabling promiscuous mode\n");
		break;
	}

	/* Enable port VLAN filter */
	err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
	if (err)
		en_err(priv, "Failed enabling VLAN filter\n");
}

static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
				 struct net_device *dev,
				 struct mlx4_en_dev *mdev)
{
	struct mlx4_en_mc_list *mclist, *tmp;
	u64 mcast_addr = 0;
	u8 mc_list[16] = {0};
	int err = 0;

	/* Enable/disable the multicast filter according to IFF_ALLMULTI */
	if (dev->flags & IFF_ALLMULTI) {
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
			en_err(priv, "Failed disabling multicast filter\n");

		/* Add the default qp number as multicast promisc */
		if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
			switch (mdev->dev->caps.steering_mode) {
			case MLX4_STEERING_MODE_DEVICE_MANAGED:
				err = mlx4_flow_steer_promisc_add(mdev->dev,
								  priv->port,
								  priv->base_qpn,
								  MLX4_FS_MC_DEFAULT);
				break;

			case MLX4_STEERING_MODE_B0:
				err = mlx4_multicast_promisc_add(mdev->dev,
								 priv->base_qpn,
								 priv->port);
				break;

			case MLX4_STEERING_MODE_A0:
				break;
			}
			if (err)
				en_err(priv, "Failed entering multicast promisc mode\n");
			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
		}
	} else {
		/* Disable Multicast promisc */
		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
			switch (mdev->dev->caps.steering_mode) {
			case MLX4_STEERING_MODE_DEVICE_MANAGED:
				err = mlx4_flow_steer_promisc_remove(mdev->dev,
								     priv->port,
								     MLX4_FS_MC_DEFAULT);
				break;

			case MLX4_STEERING_MODE_B0:
				err = mlx4_multicast_promisc_remove(mdev->dev,
								    priv->base_qpn,
								    priv->port);
				break;

			case MLX4_STEERING_MODE_A0:
				break;
			}
			if (err)
				en_err(priv, "Failed disabling multicast promiscuous mode\n");
			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		}

		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
			en_err(priv, "Failed disabling multicast filter\n");

		/* Flush mcast filter and init it with broadcast address */
		mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, ETH_BCAST,
				    1, MLX4_MCAST_CONFIG);

		/* Update multicast list - we cache all addresses so they won't
		 * change while HW is updated holding the command semaphor */
		netif_addr_lock_bh(dev);
		mlx4_en_cache_mclist(dev);
		netif_addr_unlock_bh(dev);
		list_for_each_entry(mclist, &priv->mc_list, list) {
			mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
			mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
					    mcast_addr, 0, MLX4_MCAST_CONFIG);
		}
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_ENABLE);
		if (err)
			en_err(priv, "Failed enabling multicast filter\n");

		update_mclist_flags(priv, &priv->curr_list, &priv->mc_list);
		list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
			if (mclist->action == MCLIST_REM) {
				/* detach this address and delete from list */
				memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
				mc_list[5] = priv->port;
				err = mlx4_multicast_detach(mdev->dev,
							    &priv->rss_map.indir_qp,
							    mc_list,
							    MLX4_PROT_ETH,
							    mclist->reg_id);
				if (err)
					en_err(priv, "Fail to detach multicast address\n");

				if (mclist->tunnel_reg_id) {
					err = mlx4_flow_detach(priv->mdev->dev, mclist->tunnel_reg_id);
					if (err)
						en_err(priv, "Failed to detach multicast address\n");
				}

				/* remove from list */
				list_del(&mclist->list);
				kfree(mclist);
			} else if (mclist->action == MCLIST_ADD) {
				/* attach the address */
				memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
				/* needed for B0 steering support */
				mc_list[5] = priv->port;
				err = mlx4_multicast_attach(mdev->dev,
							    &priv->rss_map.indir_qp,
							    mc_list,
							    priv->port, 0,
							    MLX4_PROT_ETH,
							    &mclist->reg_id);
				if (err)
					en_err(priv, "Fail to attach multicast address\n");

				err = mlx4_en_tunnel_steer_add(priv, &mc_list[10], priv->base_qpn,
							       &mclist->tunnel_reg_id);
				if (err)
					en_err(priv, "Failed to attach multicast address\n");
			}
		}
	}
}

static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
				 struct net_device *dev,
				 struct mlx4_en_dev *mdev)
{
	struct netdev_hw_addr *ha;
	struct mlx4_mac_entry *entry;
	struct hlist_node *tmp;
	bool found;
	u64 mac;
	int err = 0;
	struct hlist_head *bucket;
	unsigned int i;
	int removed = 0;
	u32 prev_flags;

	/* Note that we do not need to protect our mac_hash traversal with rcu,
	 * since all modification code is protected by mdev->state_lock
	 */

	/* find what to remove */
	for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
		bucket = &priv->mac_hash[i];
		hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
			found = false;
			netdev_for_each_uc_addr(ha, dev) {
				if (ether_addr_equal_64bits(entry->mac,
							    ha->addr)) {
					found = true;
					break;
				}
			}

			/* MAC address of the port is not in uc list */
			if (ether_addr_equal_64bits(entry->mac, dev->dev_addr))
				found = true;

			if (!found) {
				mac = mlx4_en_mac_to_u64(entry->mac);
				mlx4_en_uc_steer_release(priv, entry->mac,
							 priv->base_qpn,
							 entry->reg_id);
				mlx4_unregister_mac(mdev->dev, priv->port, mac);

				hlist_del_rcu(&entry->hlist);
				kfree_rcu(entry, rcu);
				en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n",
				       entry->mac, priv->port);
				++removed;
			}
		}
	}

	/* if we didn't remove anything, there is no use in trying to add
	 * again once we are in a forced promisc mode state
	 */
	if ((priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) && 0 == removed)
		return;

	prev_flags = priv->flags;
	priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;

	/* find what to add */
	netdev_for_each_uc_addr(ha, dev) {
		found = false;
		bucket = &priv->mac_hash[ha->addr[MLX4_EN_MAC_HASH_IDX]];
		hlist_for_each_entry(entry, bucket, hlist) {
			if (ether_addr_equal_64bits(entry->mac, ha->addr)) {
				found = true;
				break;
			}
		}

		if (!found) {
			entry = kmalloc(sizeof(*entry), GFP_KERNEL);
			if (!entry) {
				en_err(priv, "Failed adding MAC %pM on port:%d (out of memory)\n",
				       ha->addr, priv->port);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			}
			mac = mlx4_en_mac_to_u64(ha->addr);
			memcpy(entry->mac, ha->addr, ETH_ALEN);
			err = mlx4_register_mac(mdev->dev, priv->port, mac);
			if (err < 0) {
				en_err(priv, "Failed registering MAC %pM on port %d: %d\n",
				       ha->addr, priv->port, err);
				kfree(entry);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			}
			err = mlx4_en_uc_steer_add(priv, ha->addr,
						   &priv->base_qpn,
						   &entry->reg_id);
			if (err) {
				en_err(priv, "Failed adding MAC %pM on port %d: %d\n",
				       ha->addr, priv->port, err);
				mlx4_unregister_mac(mdev->dev, priv->port, mac);
				kfree(entry);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			} else {
				unsigned int mac_hash;
				en_dbg(DRV, priv, "Added MAC %pM on port:%d\n",
				       ha->addr, priv->port);
				mac_hash = ha->addr[MLX4_EN_MAC_HASH_IDX];
				bucket = &priv->mac_hash[mac_hash];
				hlist_add_head_rcu(&entry->hlist, bucket);
			}
		}
	}

	if (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) {
		en_warn(priv, "Forcing promiscuous mode on port:%d\n",
			priv->port);
	} else if (prev_flags & MLX4_EN_FLAG_FORCE_PROMISC) {
		en_warn(priv, "Stop forcing promiscuous mode on port:%d\n",
			priv->port);
	}
}

static void mlx4_en_do_set_rx_mode(struct work_struct *work)
{
	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
						 rx_mode_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct net_device *dev = priv->dev;

	mutex_lock(&mdev->state_lock);
	if (!mdev->device_up) {
		en_dbg(HW, priv, "Card is not up, ignoring rx mode change.\n");
		goto out;
	}
	if (!priv->port_up) {
		en_dbg(HW, priv, "Port is down, ignoring rx mode change.\n");
		goto out;
	}

	if (!netif_carrier_ok(dev)) {
		if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
			if (priv->port_state.link_state) {
				priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
				netif_carrier_on(dev);
				en_dbg(LINK, priv, "Link Up\n");
			}
		}
	}

	if (dev->priv_flags & IFF_UNICAST_FLT)
		mlx4_en_do_uc_filter(priv, dev, mdev);

	/* Promsicuous mode: disable all filters */
	if ((dev->flags & IFF_PROMISC) ||
	    (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC)) {
		mlx4_en_set_promisc_mode(priv, mdev);
		goto out;
	}

	/* Not in promiscuous mode */
	if (priv->flags & MLX4_EN_FLAG_PROMISC)
		mlx4_en_clear_promisc_mode(priv, mdev);

	mlx4_en_do_multicast(priv, dev, mdev);
out:
	mutex_unlock(&mdev->state_lock);
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void mlx4_en_netpoll(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_cq *cq;
	int i;

	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = priv->rx_cq[i];
		napi_schedule(&cq->napi);
	}
}
#endif

static void mlx4_en_tx_timeout(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int i;

	if (netif_msg_timer(priv))
		en_warn(priv, "Tx timeout called on port:%d\n", priv->port);

	for (i = 0; i < priv->tx_ring_num; i++) {
		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
			continue;
		en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
			i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
			priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
	}

	priv->port_stats.tx_timeout++;
	en_dbg(DRV, priv, "Scheduling watchdog\n");
	queue_work(mdev->workqueue, &priv->watchdog_task);
}


static struct net_device_stats *mlx4_en_get_stats(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);

	spin_lock_bh(&priv->stats_lock);
	memcpy(&priv->ret_stats, &priv->stats, sizeof(priv->stats));
	spin_unlock_bh(&priv->stats_lock);

	return &priv->ret_stats;
}

static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
{
	struct mlx4_en_cq *cq;
	int i;

	/* If we haven't received a specific coalescing setting
	 * (module param), we set the moderation parameters as follows:
	 * - moder_cnt is set to the number of mtu sized packets to
	 *   satisfy our coalescing target.
	 * - moder_time is set to a fixed value.
	 */
	priv->rx_frames = MLX4_EN_RX_COAL_TARGET;
	priv->rx_usecs = MLX4_EN_RX_COAL_TIME;
	priv->tx_frames = MLX4_EN_TX_COAL_PKTS;
	priv->tx_usecs = MLX4_EN_TX_COAL_TIME;
	en_dbg(INTR, priv, "Default coalesing params for mtu:%d - rx_frames:%d rx_usecs:%d\n",
	       priv->dev->mtu, priv->rx_frames, priv->rx_usecs);

	/* Setup cq moderation params */
	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = priv->rx_cq[i];
		cq->moder_cnt = priv->rx_frames;
		cq->moder_time = priv->rx_usecs;
		priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
		priv->last_moder_packets[i] = 0;
		priv->last_moder_bytes[i] = 0;
	}

	for (i = 0; i < priv->tx_ring_num; i++) {
		cq = priv->tx_cq[i];
		cq->moder_cnt = priv->tx_frames;
		cq->moder_time = priv->tx_usecs;
	}

	/* Reset auto-moderation params */
	priv->pkt_rate_low = MLX4_EN_RX_RATE_LOW;
	priv->rx_usecs_low = MLX4_EN_RX_COAL_TIME_LOW;
	priv->pkt_rate_high = MLX4_EN_RX_RATE_HIGH;
	priv->rx_usecs_high = MLX4_EN_RX_COAL_TIME_HIGH;
	priv->sample_interval = MLX4_EN_SAMPLE_INTERVAL;
	priv->adaptive_rx_coal = 1;
	priv->last_moder_jiffies = 0;
	priv->last_moder_tx_packets = 0;
}

static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
{
	unsigned long period = (unsigned long) (jiffies - priv->last_moder_jiffies);
	struct mlx4_en_cq *cq;
	unsigned long packets;
	unsigned long rate;
	unsigned long avg_pkt_size;
	unsigned long rx_packets;
	unsigned long rx_bytes;
	unsigned long rx_pkt_diff;
	int moder_time;
	int ring, err;

	if (!priv->adaptive_rx_coal || period < priv->sample_interval * HZ)
		return;

	for (ring = 0; ring < priv->rx_ring_num; ring++) {
		spin_lock_bh(&priv->stats_lock);
		rx_packets = priv->rx_ring[ring]->packets;
		rx_bytes = priv->rx_ring[ring]->bytes;
		spin_unlock_bh(&priv->stats_lock);

		rx_pkt_diff = ((unsigned long) (rx_packets -
				priv->last_moder_packets[ring]));
		packets = rx_pkt_diff;
		rate = packets * HZ / period;
		avg_pkt_size = packets ? ((unsigned long) (rx_bytes -
				priv->last_moder_bytes[ring])) / packets : 0;

		/* Apply auto-moderation only when packet rate
		 * exceeds a rate that it matters */
		if (rate > (MLX4_EN_RX_RATE_THRESH / priv->rx_ring_num) &&
		    avg_pkt_size > MLX4_EN_AVG_PKT_SMALL) {
			if (rate < priv->pkt_rate_low)
				moder_time = priv->rx_usecs_low;
			else if (rate > priv->pkt_rate_high)
				moder_time = priv->rx_usecs_high;
			else
				moder_time = (rate - priv->pkt_rate_low) *
					(priv->rx_usecs_high - priv->rx_usecs_low) /
					(priv->pkt_rate_high - priv->pkt_rate_low) +
					priv->rx_usecs_low;
		} else {
			moder_time = priv->rx_usecs_low;
		}

		if (moder_time != priv->last_moder_time[ring]) {
			priv->last_moder_time[ring] = moder_time;
			cq = priv->rx_cq[ring];
			cq->moder_time = moder_time;
			cq->moder_cnt = priv->rx_frames;
			err = mlx4_en_set_cq_moder(priv, cq);
			if (err)
				en_err(priv, "Failed modifying moderation for cq:%d\n",
				       ring);
		}
		priv->last_moder_packets[ring] = rx_packets;
		priv->last_moder_bytes[ring] = rx_bytes;
	}

	priv->last_moder_jiffies = jiffies;
}

static void mlx4_en_do_get_stats(struct work_struct *work)
{
	struct delayed_work *delay = to_delayed_work(work);
	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
						 stats_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;

	mutex_lock(&mdev->state_lock);
	if (mdev->device_up) {
		if (priv->port_up) {
			err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0);
			if (err)
				en_dbg(HW, priv, "Could not update stats\n");

			mlx4_en_auto_moderation(priv);
		}

		queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
	}
	if (mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port]) {
		mlx4_en_do_set_mac(priv);
		mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port] = 0;
	}
	mutex_unlock(&mdev->state_lock);
}

/* mlx4_en_service_task - Run service task for tasks that needed to be done
 * periodically
 */
static void mlx4_en_service_task(struct work_struct *work)
{
	struct delayed_work *delay = to_delayed_work(work);
	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
						 service_task);
	struct mlx4_en_dev *mdev = priv->mdev;

	mutex_lock(&mdev->state_lock);
	if (mdev->device_up) {
		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
			mlx4_en_ptp_overflow_check(mdev);

		queue_delayed_work(mdev->workqueue, &priv->service_task,
				   SERVICE_TASK_DELAY);
	}
	mutex_unlock(&mdev->state_lock);
}

static void mlx4_en_linkstate(struct work_struct *work)
{
	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
						 linkstate_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	int linkstate = priv->link_state;

	mutex_lock(&mdev->state_lock);
	/* If observable port state changed set carrier state and
	 * report to system log */
	if (priv->last_link_state != linkstate) {
		if (linkstate == MLX4_DEV_EVENT_PORT_DOWN) {
			en_info(priv, "Link Down\n");
			netif_carrier_off(priv->dev);
		} else {
			en_info(priv, "Link Up\n");
			netif_carrier_on(priv->dev);
		}
	}
	priv->last_link_state = linkstate;
	mutex_unlock(&mdev->state_lock);
}


int mlx4_en_start_port(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_en_cq *cq;
	struct mlx4_en_tx_ring *tx_ring;
	int rx_index = 0;
	int tx_index = 0;
	int err = 0;
	int i;
	int j;
	u8 mc_list[16] = {0};

	if (priv->port_up) {
		en_dbg(DRV, priv, "start port called while port already up\n");
		return 0;
	}

	INIT_LIST_HEAD(&priv->mc_list);
	INIT_LIST_HEAD(&priv->curr_list);
	INIT_LIST_HEAD(&priv->ethtool_list);
	memset(&priv->ethtool_rules[0], 0,
	       sizeof(struct ethtool_flow_id) * MAX_NUM_OF_FS_RULES);

	/* Calculate Rx buf size */
	dev->mtu = min(dev->mtu, priv->max_mtu);
	mlx4_en_calc_rx_buf(dev);
	en_dbg(DRV, priv, "Rx buf size:%d\n", priv->rx_skb_size);

	/* Configure rx cq's and rings */
	err = mlx4_en_activate_rx_rings(priv);
	if (err) {
		en_err(priv, "Failed to activate RX rings\n");
		return err;
	}
	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = priv->rx_cq[i];

		mlx4_en_cq_init_lock(cq);

		err = mlx4_en_activate_cq(priv, cq, i);
		if (err) {
			en_err(priv, "Failed activating Rx CQ\n");
			goto cq_err;
		}
		for (j = 0; j < cq->size; j++)
			cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK;
		err = mlx4_en_set_cq_moder(priv, cq);
		if (err) {
			en_err(priv, "Failed setting cq moderation parameters");
			mlx4_en_deactivate_cq(priv, cq);
			goto cq_err;
		}
		mlx4_en_arm_cq(priv, cq);
		priv->rx_ring[i]->cqn = cq->mcq.cqn;
		++rx_index;
	}

	/* Set qp number */
	en_dbg(DRV, priv, "Getting qp number for port %d\n", priv->port);
	err = mlx4_en_get_qp(priv);
	if (err) {
		en_err(priv, "Failed getting eth qp\n");
		goto cq_err;
	}
	mdev->mac_removed[priv->port] = 0;

	err = mlx4_en_config_rss_steer(priv);
	if (err) {
		en_err(priv, "Failed configuring rss steering\n");
		goto mac_err;
	}

	err = mlx4_en_create_drop_qp(priv);
	if (err)
		goto rss_err;

	/* Configure tx cq's and rings */
	for (i = 0; i < priv->tx_ring_num; i++) {
		/* Configure cq */
		cq = priv->tx_cq[i];
		err = mlx4_en_activate_cq(priv, cq, i);
		if (err) {
			en_err(priv, "Failed allocating Tx CQ\n");
			goto tx_err;
		}
		err = mlx4_en_set_cq_moder(priv, cq);
		if (err) {
			en_err(priv, "Failed setting cq moderation parameters");
			mlx4_en_deactivate_cq(priv, cq);
			goto tx_err;
		}
		en_dbg(DRV, priv, "Resetting index of collapsed CQ:%d to -1\n", i);
		cq->buf->wqe_index = cpu_to_be16(0xffff);

		/* Configure ring */
		tx_ring = priv->tx_ring[i];
		err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
			i / priv->num_tx_rings_p_up);
		if (err) {
			en_err(priv, "Failed allocating Tx ring\n");
			mlx4_en_deactivate_cq(priv, cq);
			goto tx_err;
		}
		tx_ring->tx_queue = netdev_get_tx_queue(dev, i);

		/* Arm CQ for TX completions */
		mlx4_en_arm_cq(priv, cq);

		/* Set initial ownership of all Tx TXBBs to SW (1) */
		for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
			*((u32 *) (tx_ring->buf + j)) = 0xffffffff;
		++tx_index;
	}

	/* Configure port */
	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
				    priv->rx_skb_size + ETH_FCS_LEN,
				    priv->prof->tx_pause,
				    priv->prof->tx_ppp,
				    priv->prof->rx_pause,
				    priv->prof->rx_ppp);
	if (err) {
		en_err(priv, "Failed setting port general configurations for port %d, with error %d\n",
		       priv->port, err);
		goto tx_err;
	}
	/* Set default qp number */
	err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port, priv->base_qpn, 0);
	if (err) {
		en_err(priv, "Failed setting default qp numbers\n");
		goto tx_err;
	}

	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
		if (err) {
			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
			       err);
			goto tx_err;
		}
	}

	/* Init port */
	en_dbg(HW, priv, "Initializing port\n");
	err = mlx4_INIT_PORT(mdev->dev, priv->port);
	if (err) {
		en_err(priv, "Failed Initializing port\n");
		goto tx_err;
	}

	/* Attach rx QP to bradcast address */
	memset(&mc_list[10], 0xff, ETH_ALEN);
	mc_list[5] = priv->port; /* needed for B0 steering support */
	if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
				  priv->port, 0, MLX4_PROT_ETH,
				  &priv->broadcast_id))
		mlx4_warn(mdev, "Failed Attaching Broadcast\n");

	/* Must redo promiscuous mode setup. */
	priv->flags &= ~(MLX4_EN_FLAG_PROMISC | MLX4_EN_FLAG_MC_PROMISC);

	/* Schedule multicast task to populate multicast list */
	queue_work(mdev->workqueue, &priv->rx_mode_task);

	mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);

	priv->port_up = true;
	netif_tx_start_all_queues(dev);
	netif_device_attach(dev);

	return 0;

tx_err:
	while (tx_index--) {
		mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
		mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
	}
	mlx4_en_destroy_drop_qp(priv);
rss_err:
	mlx4_en_release_rss_steer(priv);
mac_err:
	mlx4_en_put_qp(priv);
cq_err:
	while (rx_index--)
		mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
	for (i = 0; i < priv->rx_ring_num; i++)
		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);

	return err; /* need to close devices */
}


void mlx4_en_stop_port(struct net_device *dev, int detach)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_en_mc_list *mclist, *tmp;
	struct ethtool_flow_id *flow, *tmp_flow;
	int i;
	u8 mc_list[16] = {0};

	if (!priv->port_up) {
		en_dbg(DRV, priv, "stop port called while port already down\n");
		return;
	}

	/* close port*/
	mlx4_CLOSE_PORT(mdev->dev, priv->port);

	/* Synchronize with tx routine */
	netif_tx_lock_bh(dev);
	if (detach)
		netif_device_detach(dev);
	netif_tx_stop_all_queues(dev);
	netif_tx_unlock_bh(dev);

	netif_tx_disable(dev);

	/* Set port as not active */
	priv->port_up = false;

	/* Promsicuous mode */
	if (mdev->dev->caps.steering_mode ==
	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
		priv->flags &= ~(MLX4_EN_FLAG_PROMISC |
				 MLX4_EN_FLAG_MC_PROMISC);
		mlx4_flow_steer_promisc_remove(mdev->dev,
					       priv->port,
					       MLX4_FS_ALL_DEFAULT);
		mlx4_flow_steer_promisc_remove(mdev->dev,
					       priv->port,
					       MLX4_FS_MC_DEFAULT);
	} else if (priv->flags & MLX4_EN_FLAG_PROMISC) {
		priv->flags &= ~MLX4_EN_FLAG_PROMISC;

		/* Disable promiscouos mode */
		mlx4_unicast_promisc_remove(mdev->dev, priv->base_qpn,
					    priv->port);

		/* Disable Multicast promisc */
		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
			mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn,
						      priv->port);
			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		}
	}

	/* Detach All multicasts */
	memset(&mc_list[10], 0xff, ETH_ALEN);
	mc_list[5] = priv->port; /* needed for B0 steering support */
	mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
			      MLX4_PROT_ETH, priv->broadcast_id);
	list_for_each_entry(mclist, &priv->curr_list, list) {
		memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
		mc_list[5] = priv->port;
		mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
				      mc_list, MLX4_PROT_ETH, mclist->reg_id);
		if (mclist->tunnel_reg_id)
			mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);
	}
	mlx4_en_clear_list(dev);
	list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
		list_del(&mclist->list);
		kfree(mclist);
	}

	/* Flush multicast filter */
	mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);

	/* Remove flow steering rules for the port*/
	if (mdev->dev->caps.steering_mode ==
	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
		ASSERT_RTNL();
		list_for_each_entry_safe(flow, tmp_flow,
					 &priv->ethtool_list, list) {
			mlx4_flow_detach(mdev->dev, flow->id);
			list_del(&flow->list);
		}
	}

	mlx4_en_destroy_drop_qp(priv);

	/* Free TX Rings */
	for (i = 0; i < priv->tx_ring_num; i++) {
		mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
		mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
	}
	msleep(10);

	for (i = 0; i < priv->tx_ring_num; i++)
		mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);

	/* Free RSS qps */
	mlx4_en_release_rss_steer(priv);

	/* Unregister Mac address for the port */
	mlx4_en_put_qp(priv);
	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN))
		mdev->mac_removed[priv->port] = 1;

	/* Free RX Rings */
	for (i = 0; i < priv->rx_ring_num; i++) {
		struct mlx4_en_cq *cq = priv->rx_cq[i];

		local_bh_disable();
		while (!mlx4_en_cq_lock_napi(cq)) {
			pr_info("CQ %d locked\n", i);
			mdelay(1);
		}
		local_bh_enable();

		while (test_bit(NAPI_STATE_SCHED, &cq->napi.state))
			msleep(1);
		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
		mlx4_en_deactivate_cq(priv, cq);
	}
}

static void mlx4_en_restart(struct work_struct *work)
{
	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
						 watchdog_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct net_device *dev = priv->dev;

	en_dbg(DRV, priv, "Watchdog task called for port %d\n", priv->port);

	mutex_lock(&mdev->state_lock);
	if (priv->port_up) {
		mlx4_en_stop_port(dev, 1);
		if (mlx4_en_start_port(dev))
			en_err(priv, "Failed restarting port %d\n", priv->port);
	}
	mutex_unlock(&mdev->state_lock);
}

static void mlx4_en_clear_stats(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int i;

	if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
		en_dbg(HW, priv, "Failed dumping statistics\n");

	memset(&priv->stats, 0, sizeof(priv->stats));
	memset(&priv->pstats, 0, sizeof(priv->pstats));
	memset(&priv->pkstats, 0, sizeof(priv->pkstats));
	memset(&priv->port_stats, 0, sizeof(priv->port_stats));

	for (i = 0; i < priv->tx_ring_num; i++) {
		priv->tx_ring[i]->bytes = 0;
		priv->tx_ring[i]->packets = 0;
		priv->tx_ring[i]->tx_csum = 0;
	}
	for (i = 0; i < priv->rx_ring_num; i++) {
		priv->rx_ring[i]->bytes = 0;
		priv->rx_ring[i]->packets = 0;
		priv->rx_ring[i]->csum_ok = 0;
		priv->rx_ring[i]->csum_none = 0;
	}
}

static int mlx4_en_open(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err = 0;

	mutex_lock(&mdev->state_lock);

	if (!mdev->device_up) {
		en_err(priv, "Cannot open - device down/disabled\n");
		err = -EBUSY;
		goto out;
	}

	/* Reset HW statistics and SW counters */
	mlx4_en_clear_stats(dev);

	err = mlx4_en_start_port(dev);
	if (err)
		en_err(priv, "Failed starting port:%d\n", priv->port);

out:
	mutex_unlock(&mdev->state_lock);
	return err;
}


static int mlx4_en_close(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;

	en_dbg(IFDOWN, priv, "Close port called\n");

	mutex_lock(&mdev->state_lock);

	mlx4_en_stop_port(dev, 0);
	netif_carrier_off(dev);

	mutex_unlock(&mdev->state_lock);
	return 0;
}

void mlx4_en_free_resources(struct mlx4_en_priv *priv)
{
	int i;

#ifdef CONFIG_RFS_ACCEL
	free_irq_cpu_rmap(priv->dev->rx_cpu_rmap);
	priv->dev->rx_cpu_rmap = NULL;
#endif

	for (i = 0; i < priv->tx_ring_num; i++) {
		if (priv->tx_ring && priv->tx_ring[i])
			mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
		if (priv->tx_cq && priv->tx_cq[i])
			mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
	}

	for (i = 0; i < priv->rx_ring_num; i++) {
		if (priv->rx_ring[i])
			mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
				priv->prof->rx_ring_size, priv->stride);
		if (priv->rx_cq[i])
			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
	}

	if (priv->base_tx_qpn) {
		mlx4_qp_release_range(priv->mdev->dev, priv->base_tx_qpn, priv->tx_ring_num);
		priv->base_tx_qpn = 0;
	}
}

int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
{
	struct mlx4_en_port_profile *prof = priv->prof;
	int i;
	int err;
	int node;

	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
	if (err) {
		en_err(priv, "failed reserving range for TX rings\n");
		return err;
	}

	/* Create tx Rings */
	for (i = 0; i < priv->tx_ring_num; i++) {
		node = cpu_to_node(i % num_online_cpus());
		if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
				      prof->tx_ring_size, i, TX, node))
			goto err;

		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
					   priv->base_tx_qpn + i,
					   prof->tx_ring_size, TXBB_SIZE,
					   node, i))
			goto err;
	}

	/* Create rx Rings */
	for (i = 0; i < priv->rx_ring_num; i++) {
		node = cpu_to_node(i % num_online_cpus());
		if (mlx4_en_create_cq(priv, &priv->rx_cq[i],
				      prof->rx_ring_size, i, RX, node))
			goto err;

		if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
					   prof->rx_ring_size, priv->stride,
					   node))
			goto err;
	}

#ifdef CONFIG_RFS_ACCEL
	if (priv->mdev->dev->caps.comp_pool) {
		priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool);
		if (!priv->dev->rx_cpu_rmap)
			goto err;
	}
#endif

	return 0;

err:
	en_err(priv, "Failed to allocate NIC resources\n");
	for (i = 0; i < priv->rx_ring_num; i++) {
		if (priv->rx_ring[i])
			mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
						prof->rx_ring_size,
						priv->stride);
		if (priv->rx_cq[i])
			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
	}
	for (i = 0; i < priv->tx_ring_num; i++) {
		if (priv->tx_ring[i])
			mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
		if (priv->tx_cq[i])
			mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
	}
	return -ENOMEM;
}


void mlx4_en_destroy_netdev(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;

	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);

	/* Unregister device - this will close the port if it was up */
	if (priv->registered)
		unregister_netdev(dev);

	if (priv->allocated)
		mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE);

	cancel_delayed_work(&priv->stats_task);
	cancel_delayed_work(&priv->service_task);
	/* flush any pending task for this netdev */
	flush_workqueue(mdev->workqueue);

	/* Detach the netdev so tasks would not attempt to access it */
	mutex_lock(&mdev->state_lock);
	mdev->pndev[priv->port] = NULL;
	mutex_unlock(&mdev->state_lock);

	mlx4_en_free_resources(priv);

	kfree(priv->tx_ring);
	kfree(priv->tx_cq);

	free_netdev(dev);
}

static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err = 0;

	en_dbg(DRV, priv, "Change MTU called - current:%d new:%d\n",
		 dev->mtu, new_mtu);

	if ((new_mtu < MLX4_EN_MIN_MTU) || (new_mtu > priv->max_mtu)) {
		en_err(priv, "Bad MTU size:%d.\n", new_mtu);
		return -EPERM;
	}
	dev->mtu = new_mtu;

	if (netif_running(dev)) {
		mutex_lock(&mdev->state_lock);
		if (!mdev->device_up) {
			/* NIC is probably restarting - let watchdog task reset
			 * the port */
			en_dbg(DRV, priv, "Change MTU called with card down!?\n");
		} else {
			mlx4_en_stop_port(dev, 1);
			err = mlx4_en_start_port(dev);
			if (err) {
				en_err(priv, "Failed restarting port:%d\n",
					 priv->port);
				queue_work(mdev->workqueue, &priv->watchdog_task);
			}
		}
		mutex_unlock(&mdev->state_lock);
	}
	return 0;
}

static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct hwtstamp_config config;

	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
		return -EFAULT;

	/* reserved for future extensions */
	if (config.flags)
		return -EINVAL;

	/* device doesn't support time stamping */
	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS))
		return -EINVAL;

	/* TX HW timestamp */
	switch (config.tx_type) {
	case HWTSTAMP_TX_OFF:
	case HWTSTAMP_TX_ON:
		break;
	default:
		return -ERANGE;
	}

	/* RX HW timestamp */
	switch (config.rx_filter) {
	case HWTSTAMP_FILTER_NONE:
		break;
	case HWTSTAMP_FILTER_ALL:
	case HWTSTAMP_FILTER_SOME:
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
		config.rx_filter = HWTSTAMP_FILTER_ALL;
		break;
	default:
		return -ERANGE;
	}

	if (mlx4_en_timestamp_config(dev, config.tx_type, config.rx_filter)) {
		config.tx_type = HWTSTAMP_TX_OFF;
		config.rx_filter = HWTSTAMP_FILTER_NONE;
	}

	return copy_to_user(ifr->ifr_data, &config,
			    sizeof(config)) ? -EFAULT : 0;
}

static int mlx4_en_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);

	return copy_to_user(ifr->ifr_data, &priv->hwtstamp_config,
			    sizeof(priv->hwtstamp_config)) ? -EFAULT : 0;
}

static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	switch (cmd) {
	case SIOCSHWTSTAMP:
		return mlx4_en_hwtstamp_set(dev, ifr);
	case SIOCGHWTSTAMP:
		return mlx4_en_hwtstamp_get(dev, ifr);
	default:
		return -EOPNOTSUPP;
	}
}

static int mlx4_en_set_features(struct net_device *netdev,
		netdev_features_t features)
{
	struct mlx4_en_priv *priv = netdev_priv(netdev);

	if (features & NETIF_F_LOOPBACK)
		priv->ctrl_flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
	else
		priv->ctrl_flags &=
			cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);

	mlx4_en_update_loopback_state(netdev, features);

	return 0;

}

static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
{
	struct mlx4_en_priv *en_priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = en_priv->mdev;
	u64 mac_u64 = mlx4_en_mac_to_u64(mac);

	if (!is_valid_ether_addr(mac))
		return -EINVAL;

	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
}

static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos)
{
	struct mlx4_en_priv *en_priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = en_priv->mdev;

	return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos);
}

static int mlx4_en_set_vf_spoofchk(struct net_device *dev, int vf, bool setting)
{
	struct mlx4_en_priv *en_priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = en_priv->mdev;

	return mlx4_set_vf_spoofchk(mdev->dev, en_priv->port, vf, setting);
}

static int mlx4_en_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf)
{
	struct mlx4_en_priv *en_priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = en_priv->mdev;

	return mlx4_get_vf_config(mdev->dev, en_priv->port, vf, ivf);
}

static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_state)
{
	struct mlx4_en_priv *en_priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = en_priv->mdev;

	return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state);
}

#define PORT_ID_BYTE_LEN 8
static int mlx4_en_get_phys_port_id(struct net_device *dev,
				    struct netdev_phys_port_id *ppid)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_dev *mdev = priv->mdev->dev;
	int i;
	u64 phys_port_id = mdev->caps.phys_port_id[priv->port];

	if (!phys_port_id)
		return -EOPNOTSUPP;

	ppid->id_len = sizeof(phys_port_id);
	for (i = PORT_ID_BYTE_LEN - 1; i >= 0; --i) {
		ppid->id[i] =  phys_port_id & 0xff;
		phys_port_id >>= 8;
	}
	return 0;
}

static const struct net_device_ops mlx4_netdev_ops = {
	.ndo_open		= mlx4_en_open,
	.ndo_stop		= mlx4_en_close,
	.ndo_start_xmit		= mlx4_en_xmit,
	.ndo_select_queue	= mlx4_en_select_queue,
	.ndo_get_stats		= mlx4_en_get_stats,
	.ndo_set_rx_mode	= mlx4_en_set_rx_mode,
	.ndo_set_mac_address	= mlx4_en_set_mac,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_change_mtu		= mlx4_en_change_mtu,
	.ndo_do_ioctl		= mlx4_en_ioctl,
	.ndo_tx_timeout		= mlx4_en_tx_timeout,
	.ndo_vlan_rx_add_vid	= mlx4_en_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid	= mlx4_en_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= mlx4_en_netpoll,
#endif
	.ndo_set_features	= mlx4_en_set_features,
	.ndo_setup_tc		= mlx4_en_setup_tc,
#ifdef CONFIG_RFS_ACCEL
	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
	.ndo_busy_poll		= mlx4_en_low_latency_recv,
#endif
	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
};

static const struct net_device_ops mlx4_netdev_ops_master = {
	.ndo_open		= mlx4_en_open,
	.ndo_stop		= mlx4_en_close,
	.ndo_start_xmit		= mlx4_en_xmit,
	.ndo_select_queue	= mlx4_en_select_queue,
	.ndo_get_stats		= mlx4_en_get_stats,
	.ndo_set_rx_mode	= mlx4_en_set_rx_mode,
	.ndo_set_mac_address	= mlx4_en_set_mac,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_change_mtu		= mlx4_en_change_mtu,
	.ndo_tx_timeout		= mlx4_en_tx_timeout,
	.ndo_vlan_rx_add_vid	= mlx4_en_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid	= mlx4_en_vlan_rx_kill_vid,
	.ndo_set_vf_mac		= mlx4_en_set_vf_mac,
	.ndo_set_vf_vlan	= mlx4_en_set_vf_vlan,
	.ndo_set_vf_spoofchk	= mlx4_en_set_vf_spoofchk,
	.ndo_set_vf_link_state	= mlx4_en_set_vf_link_state,
	.ndo_get_vf_config	= mlx4_en_get_vf_config,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= mlx4_en_netpoll,
#endif
	.ndo_set_features	= mlx4_en_set_features,
	.ndo_setup_tc		= mlx4_en_setup_tc,
#ifdef CONFIG_RFS_ACCEL
	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
#endif
	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
};

int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
			struct mlx4_en_port_profile *prof)
{
	struct net_device *dev;
	struct mlx4_en_priv *priv;
	int i;
	int err;
	u64 mac_u64;

	dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
				 MAX_TX_RINGS, MAX_RX_RINGS);
	if (dev == NULL)
		return -ENOMEM;

	netif_set_real_num_tx_queues(dev, prof->tx_ring_num);
	netif_set_real_num_rx_queues(dev, prof->rx_ring_num);

	SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev);
	dev->dev_id =  port - 1;

	/*
	 * Initialize driver private data
	 */

	priv = netdev_priv(dev);
	memset(priv, 0, sizeof(struct mlx4_en_priv));
	priv->dev = dev;
	priv->mdev = mdev;
	priv->ddev = &mdev->pdev->dev;
	priv->prof = prof;
	priv->port = port;
	priv->port_up = false;
	priv->flags = prof->flags;
	priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
			MLX4_WQE_CTRL_SOLICITED);
	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
	priv->tx_ring_num = prof->tx_ring_num;

	priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
				GFP_KERNEL);
	if (!priv->tx_ring) {
		err = -ENOMEM;
		goto out;
	}
	priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
			      GFP_KERNEL);
	if (!priv->tx_cq) {
		err = -ENOMEM;
		goto out;
	}
	priv->rx_ring_num = prof->rx_ring_num;
	priv->cqe_factor = (mdev->dev->caps.cqe_size == 64) ? 1 : 0;
	priv->mac_index = -1;
	priv->msg_enable = MLX4_EN_MSG_LEVEL;
	spin_lock_init(&priv->stats_lock);
	INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
	INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
#ifdef CONFIG_MLX4_EN_DCB
	if (!mlx4_is_slave(priv->mdev->dev)) {
		if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) {
			dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
		} else {
			en_info(priv, "enabling only PFC DCB ops\n");
			dev->dcbnl_ops = &mlx4_en_dcbnl_pfc_ops;
		}
	}
#endif

	for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i)
		INIT_HLIST_HEAD(&priv->mac_hash[i]);

	/* Query for default mac and max mtu */
	priv->max_mtu = mdev->dev->caps.eth_mtu_cap[priv->port];

	/* Set default MAC */
	dev->addr_len = ETH_ALEN;
	mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
	if (!is_valid_ether_addr(dev->dev_addr)) {
		if (mlx4_is_slave(priv->mdev->dev)) {
			eth_hw_addr_random(dev);
			en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr);
			mac_u64 = mlx4_en_mac_to_u64(dev->dev_addr);
			mdev->dev->caps.def_mac[priv->port] = mac_u64;
		} else {
			en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
			       priv->port, dev->dev_addr);
			err = -EINVAL;
			goto out;
		}
	}

	memcpy(priv->prev_mac, dev->dev_addr, sizeof(priv->prev_mac));

	priv->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
					  DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
	err = mlx4_en_alloc_resources(priv);
	if (err)
		goto out;

#ifdef CONFIG_RFS_ACCEL
	INIT_LIST_HEAD(&priv->filters);
	spin_lock_init(&priv->filters_lock);
#endif

	/* Initialize time stamping config */
	priv->hwtstamp_config.flags = 0;
	priv->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF;
	priv->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;

	/* Allocate page for receive rings */
	err = mlx4_alloc_hwq_res(mdev->dev, &priv->res,
				MLX4_EN_PAGE_SIZE, MLX4_EN_PAGE_SIZE);
	if (err) {
		en_err(priv, "Failed to allocate page for rx qps\n");
		goto out;
	}
	priv->allocated = 1;

	/*
	 * Initialize netdev entry points
	 */
	if (mlx4_is_master(priv->mdev->dev))
		dev->netdev_ops = &mlx4_netdev_ops_master;
	else
		dev->netdev_ops = &mlx4_netdev_ops;
	dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT;
	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);

	SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops);

	/*
	 * Set driver features
	 */
	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
	if (mdev->LSO_support)
		dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;

	dev->vlan_features = dev->hw_features;

	dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH;
	dev->features = dev->hw_features | NETIF_F_HIGHDMA |
			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
			NETIF_F_HW_VLAN_CTAG_FILTER;
	dev->hw_features |= NETIF_F_LOOPBACK;

	if (mdev->dev->caps.steering_mode ==
	    MLX4_STEERING_MODE_DEVICE_MANAGED)
		dev->hw_features |= NETIF_F_NTUPLE;

	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
		dev->priv_flags |= IFF_UNICAST_FLT;

	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
		dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
					NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
	}

	mdev->pndev[port] = dev;

	netif_carrier_off(dev);
	mlx4_en_set_default_moderation(priv);

	err = register_netdev(dev);
	if (err) {
		en_err(priv, "Netdev registration failed for port %d\n", port);
		goto out;
	}
	priv->registered = 1;

	en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
	en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);

	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);

	/* Configure port */
	mlx4_en_calc_rx_buf(dev);
	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
				    priv->rx_skb_size + ETH_FCS_LEN,
				    prof->tx_pause, prof->tx_ppp,
				    prof->rx_pause, prof->rx_ppp);
	if (err) {
		en_err(priv, "Failed setting port general configurations "
		       "for port %d, with error %d\n", priv->port, err);
		goto out;
	}

	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
		if (err) {
			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
			       err);
			goto out;
		}
	}

	/* Init port */
	en_warn(priv, "Initializing port\n");
	err = mlx4_INIT_PORT(mdev->dev, priv->port);
	if (err) {
		en_err(priv, "Failed Initializing port\n");
		goto out;
	}
	queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);

	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
		queue_delayed_work(mdev->workqueue, &priv->service_task,
				   SERVICE_TASK_DELAY);

	return 0;

out:
	mlx4_en_destroy_netdev(dev);
	return err;
}