summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4/main.c
blob: 2cc3c626c3fea732d0862ff5f0ce520d442a6205 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2006, 2007 Cisco Systems, Inc. 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/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/io-mapping.h>
#include <linux/delay.h>
#include <linux/kmod.h>

#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>

#include "mlx4.h"
#include "fw.h"
#include "icm.h"

MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("Mellanox ConnectX HCA low-level driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);

struct workqueue_struct *mlx4_wq;

#ifdef CONFIG_MLX4_DEBUG

int mlx4_debug_level = 0;
module_param_named(debug_level, mlx4_debug_level, int, 0644);
MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0");

#endif /* CONFIG_MLX4_DEBUG */

#ifdef CONFIG_PCI_MSI

static int msi_x = 1;
module_param(msi_x, int, 0444);
MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");

#else /* CONFIG_PCI_MSI */

#define msi_x (0)

#endif /* CONFIG_PCI_MSI */

static uint8_t num_vfs[3] = {0, 0, 0};
static int num_vfs_argc;
module_param_array(num_vfs, byte , &num_vfs_argc, 0444);
MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0\n"
			  "num_vfs=port1,port2,port1+2");

static uint8_t probe_vf[3] = {0, 0, 0};
static int probe_vfs_argc;
module_param_array(probe_vf, byte, &probe_vfs_argc, 0444);
MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)\n"
			   "probe_vf=port1,port2,port1+2");

int mlx4_log_num_mgm_entry_size = MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
module_param_named(log_num_mgm_entry_size,
			mlx4_log_num_mgm_entry_size, int, 0444);
MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
					 " of qp per mcg, for example:"
					 " 10 gives 248.range: 7 <="
					 " log_num_mgm_entry_size <= 12."
					 " To activate device managed"
					 " flow steering when available, set to -1");

static bool enable_64b_cqe_eqe = true;
module_param(enable_64b_cqe_eqe, bool, 0444);
MODULE_PARM_DESC(enable_64b_cqe_eqe,
		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");

#define PF_CONTEXT_BEHAVIOUR_MASK	(MLX4_FUNC_CAP_64B_EQE_CQE | \
					 MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
					 MLX4_FUNC_CAP_DMFS_A0_STATIC)

#define RESET_PERSIST_MASK_FLAGS	(MLX4_FLAG_SRIOV)

static char mlx4_version[] =
	DRV_NAME ": Mellanox ConnectX core driver v"
	DRV_VERSION " (" DRV_RELDATE ")\n";

static struct mlx4_profile default_profile = {
	.num_qp		= 1 << 18,
	.num_srq	= 1 << 16,
	.rdmarc_per_qp	= 1 << 4,
	.num_cq		= 1 << 16,
	.num_mcg	= 1 << 13,
	.num_mpt	= 1 << 19,
	.num_mtt	= 1 << 20, /* It is really num mtt segements */
};

static struct mlx4_profile low_mem_profile = {
	.num_qp		= 1 << 17,
	.num_srq	= 1 << 6,
	.rdmarc_per_qp	= 1 << 4,
	.num_cq		= 1 << 8,
	.num_mcg	= 1 << 8,
	.num_mpt	= 1 << 9,
	.num_mtt	= 1 << 7,
};

static int log_num_mac = 7;
module_param_named(log_num_mac, log_num_mac, int, 0444);
MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");

static int log_num_vlan;
module_param_named(log_num_vlan, log_num_vlan, int, 0444);
MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
/* Log2 max number of VLANs per ETH port (0-7) */
#define MLX4_LOG_NUM_VLANS 7
#define MLX4_MIN_LOG_NUM_VLANS 0
#define MLX4_MIN_LOG_NUM_MAC 1

static bool use_prio;
module_param_named(use_prio, use_prio, bool, 0444);
MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");

int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");

static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
static int arr_argc = 2;
module_param_array(port_type_array, int, &arr_argc, 0444);
MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
				"1 for IB, 2 for Ethernet");

struct mlx4_port_config {
	struct list_head list;
	enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
	struct pci_dev *pdev;
};

static atomic_t pf_loading = ATOMIC_INIT(0);

static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
					      struct mlx4_dev_cap *dev_cap)
{
	/* The reserved_uars is calculated by system page size unit.
	 * Therefore, adjustment is added when the uar page size is less
	 * than the system page size
	 */
	dev->caps.reserved_uars	=
		max_t(int,
		      mlx4_get_num_reserved_uar(dev),
		      dev_cap->reserved_uars /
			(1 << (PAGE_SHIFT - dev->uar_page_shift)));
}

int mlx4_check_port_params(struct mlx4_dev *dev,
			   enum mlx4_port_type *port_type)
{
	int i;

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) {
		for (i = 0; i < dev->caps.num_ports - 1; i++) {
			if (port_type[i] != port_type[i + 1]) {
				mlx4_err(dev, "Only same port types supported on this HCA, aborting\n");
				return -EINVAL;
			}
		}
	}

	for (i = 0; i < dev->caps.num_ports; i++) {
		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
			mlx4_err(dev, "Requested port type for port %d is not supported on this HCA\n",
				 i + 1);
			return -EINVAL;
		}
	}
	return 0;
}

static void mlx4_set_port_mask(struct mlx4_dev *dev)
{
	int i;

	for (i = 1; i <= dev->caps.num_ports; ++i)
		dev->caps.port_mask[i] = dev->caps.port_type[i];
}

enum {
	MLX4_QUERY_FUNC_NUM_SYS_EQS = 1 << 0,
};

static int mlx4_query_func(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
	int err = 0;
	struct mlx4_func func;

	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) {
		err = mlx4_QUERY_FUNC(dev, &func, 0);
		if (err) {
			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
			return err;
		}
		dev_cap->max_eqs = func.max_eq;
		dev_cap->reserved_eqs = func.rsvd_eqs;
		dev_cap->reserved_uars = func.rsvd_uars;
		err |= MLX4_QUERY_FUNC_NUM_SYS_EQS;
	}
	return err;
}

static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev)
{
	struct mlx4_caps *dev_cap = &dev->caps;

	/* FW not supporting or cancelled by user */
	if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_EQE_STRIDE) ||
	    !(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_CQE_STRIDE))
		return;

	/* Must have 64B CQE_EQE enabled by FW to use bigger stride
	 * When FW has NCSI it may decide not to report 64B CQE/EQEs
	 */
	if (!(dev_cap->flags & MLX4_DEV_CAP_FLAG_64B_EQE) ||
	    !(dev_cap->flags & MLX4_DEV_CAP_FLAG_64B_CQE)) {
		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
		return;
	}

	if (cache_line_size() == 128 || cache_line_size() == 256) {
		mlx4_dbg(dev, "Enabling CQE stride cacheLine supported\n");
		/* Changing the real data inside CQE size to 32B */
		dev_cap->flags &= ~MLX4_DEV_CAP_FLAG_64B_CQE;
		dev_cap->flags &= ~MLX4_DEV_CAP_FLAG_64B_EQE;

		if (mlx4_is_master(dev))
			dev_cap->function_caps |= MLX4_FUNC_CAP_EQE_CQE_STRIDE;
	} else {
		if (cache_line_size() != 32  && cache_line_size() != 64)
			mlx4_dbg(dev, "Disabling CQE stride, cacheLine size unsupported\n");
		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
	}
}

static int _mlx4_dev_port(struct mlx4_dev *dev, int port,
			  struct mlx4_port_cap *port_cap)
{
	dev->caps.vl_cap[port]	    = port_cap->max_vl;
	dev->caps.ib_mtu_cap[port]	    = port_cap->ib_mtu;
	dev->phys_caps.gid_phys_table_len[port]  = port_cap->max_gids;
	dev->phys_caps.pkey_phys_table_len[port] = port_cap->max_pkeys;
	/* set gid and pkey table operating lengths by default
	 * to non-sriov values
	 */
	dev->caps.gid_table_len[port]  = port_cap->max_gids;
	dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
	dev->caps.port_width_cap[port] = port_cap->max_port_width;
	dev->caps.eth_mtu_cap[port]    = port_cap->eth_mtu;
	dev->caps.def_mac[port]        = port_cap->def_mac;
	dev->caps.supported_type[port] = port_cap->supported_port_types;
	dev->caps.suggested_type[port] = port_cap->suggested_type;
	dev->caps.default_sense[port] = port_cap->default_sense;
	dev->caps.trans_type[port]	    = port_cap->trans_type;
	dev->caps.vendor_oui[port]     = port_cap->vendor_oui;
	dev->caps.wavelength[port]     = port_cap->wavelength;
	dev->caps.trans_code[port]     = port_cap->trans_code;

	return 0;
}

static int mlx4_dev_port(struct mlx4_dev *dev, int port,
			 struct mlx4_port_cap *port_cap)
{
	int err = 0;

	err = mlx4_QUERY_PORT(dev, port, port_cap);

	if (err)
		mlx4_err(dev, "QUERY_PORT command failed.\n");

	return err;
}

static inline void mlx4_enable_ignore_fcs(struct mlx4_dev *dev)
{
	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_IGNORE_FCS))
		return;

	if (mlx4_is_mfunc(dev)) {
		mlx4_dbg(dev, "SRIOV mode - Disabling Ignore FCS");
		dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_IGNORE_FCS;
		return;
	}

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)) {
		mlx4_dbg(dev,
			 "Keep FCS is not supported - Disabling Ignore FCS");
		dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_IGNORE_FCS;
		return;
	}
}

#define MLX4_A0_STEERING_TABLE_SIZE	256
static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
	int err;
	int i;

	err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
	if (err) {
		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
		return err;
	}
	mlx4_dev_cap_dump(dev, dev_cap);

	if (dev_cap->min_page_sz > PAGE_SIZE) {
		mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n",
			 dev_cap->min_page_sz, PAGE_SIZE);
		return -ENODEV;
	}
	if (dev_cap->num_ports > MLX4_MAX_PORTS) {
		mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n",
			 dev_cap->num_ports, MLX4_MAX_PORTS);
		return -ENODEV;
	}

	if (dev_cap->uar_size > pci_resource_len(dev->persist->pdev, 2)) {
		mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
			 dev_cap->uar_size,
			 (unsigned long long)
			 pci_resource_len(dev->persist->pdev, 2));
		return -ENODEV;
	}

	dev->caps.num_ports	     = dev_cap->num_ports;
	dev->caps.num_sys_eqs = dev_cap->num_sys_eqs;
	dev->phys_caps.num_phys_eqs = dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS ?
				      dev->caps.num_sys_eqs :
				      MLX4_MAX_EQ_NUM;
	for (i = 1; i <= dev->caps.num_ports; ++i) {
		err = _mlx4_dev_port(dev, i, dev_cap->port_cap + i);
		if (err) {
			mlx4_err(dev, "QUERY_PORT command failed, aborting\n");
			return err;
		}
	}

	dev->caps.uar_page_size	     = PAGE_SIZE;
	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
	dev->caps.bf_reg_size	     = dev_cap->bf_reg_size;
	dev->caps.bf_regs_per_page   = dev_cap->bf_regs_per_page;
	dev->caps.max_sq_sg	     = dev_cap->max_sq_sg;
	dev->caps.max_rq_sg	     = dev_cap->max_rq_sg;
	dev->caps.max_wqes	     = dev_cap->max_qp_sz;
	dev->caps.max_qp_init_rdma   = dev_cap->max_requester_per_qp;
	dev->caps.max_srq_wqes	     = dev_cap->max_srq_sz;
	dev->caps.max_srq_sge	     = dev_cap->max_rq_sg - 1;
	dev->caps.reserved_srqs	     = dev_cap->reserved_srqs;
	dev->caps.max_sq_desc_sz     = dev_cap->max_sq_desc_sz;
	dev->caps.max_rq_desc_sz     = dev_cap->max_rq_desc_sz;
	/*
	 * Subtract 1 from the limit because we need to allocate a
	 * spare CQE so the HCA HW can tell the difference between an
	 * empty CQ and a full CQ.
	 */
	dev->caps.max_cqes	     = dev_cap->max_cq_sz - 1;
	dev->caps.reserved_cqs	     = dev_cap->reserved_cqs;
	dev->caps.reserved_eqs	     = dev_cap->reserved_eqs;
	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;

	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
					dev_cap->reserved_xrcds : 0;
	dev->caps.max_xrcds          = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
					dev_cap->max_xrcds : 0;
	dev->caps.mtt_entry_sz       = dev_cap->mtt_entry_sz;

	dev->caps.max_msg_sz         = dev_cap->max_msg_sz;
	dev->caps.page_size_cap	     = ~(u32) (dev_cap->min_page_sz - 1);
	dev->caps.flags		     = dev_cap->flags;
	dev->caps.flags2	     = dev_cap->flags2;
	dev->caps.bmme_flags	     = dev_cap->bmme_flags;
	dev->caps.reserved_lkey	     = dev_cap->reserved_lkey;
	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;

	/* Save uar page shift */
	if (!mlx4_is_slave(dev)) {
		/* Virtual PCI function needs to determine UAR page size from
		 * firmware. Only master PCI function can set the uar page size
		 */
		dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
		mlx4_set_num_reserved_uars(dev, dev_cap);
	}

	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
		struct mlx4_init_hca_param hca_param;

		memset(&hca_param, 0, sizeof(hca_param));
		err = mlx4_QUERY_HCA(dev, &hca_param);
		/* Turn off PHV_EN flag in case phv_check_en is set.
		 * phv_check_en is a HW check that parse the packet and verify
		 * phv bit was reported correctly in the wqe. To allow QinQ
		 * PHV_EN flag should be set and phv_check_en must be cleared
		 * otherwise QinQ packets will be drop by the HW.
		 */
		if (err || hca_param.phv_check_en)
			dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_PHV_EN;
	}

	/* Sense port always allowed on supported devices for ConnectX-1 and -2 */
	if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT)
		dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
	/* Don't do sense port on multifunction devices (for now at least) */
	if (mlx4_is_mfunc(dev))
		dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;

	if (mlx4_low_memory_profile()) {
		dev->caps.log_num_macs  = MLX4_MIN_LOG_NUM_MAC;
		dev->caps.log_num_vlans = MLX4_MIN_LOG_NUM_VLANS;
	} else {
		dev->caps.log_num_macs  = log_num_mac;
		dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
	}

	for (i = 1; i <= dev->caps.num_ports; ++i) {
		dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
		if (dev->caps.supported_type[i]) {
			/* if only ETH is supported - assign ETH */
			if (dev->caps.supported_type[i] == MLX4_PORT_TYPE_ETH)
				dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
			/* if only IB is supported, assign IB */
			else if (dev->caps.supported_type[i] ==
				 MLX4_PORT_TYPE_IB)
				dev->caps.port_type[i] = MLX4_PORT_TYPE_IB;
			else {
				/* if IB and ETH are supported, we set the port
				 * type according to user selection of port type;
				 * if user selected none, take the FW hint */
				if (port_type_array[i - 1] == MLX4_PORT_TYPE_NONE)
					dev->caps.port_type[i] = dev->caps.suggested_type[i] ?
						MLX4_PORT_TYPE_ETH : MLX4_PORT_TYPE_IB;
				else
					dev->caps.port_type[i] = port_type_array[i - 1];
			}
		}
		/*
		 * Link sensing is allowed on the port if 3 conditions are true:
		 * 1. Both protocols are supported on the port.
		 * 2. Different types are supported on the port
		 * 3. FW declared that it supports link sensing
		 */
		mlx4_priv(dev)->sense.sense_allowed[i] =
			((dev->caps.supported_type[i] == MLX4_PORT_TYPE_AUTO) &&
			 (dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
			 (dev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT));

		/*
		 * If "default_sense" bit is set, we move the port to "AUTO" mode
		 * and perform sense_port FW command to try and set the correct
		 * port type from beginning
		 */
		if (mlx4_priv(dev)->sense.sense_allowed[i] && dev->caps.default_sense[i]) {
			enum mlx4_port_type sensed_port = MLX4_PORT_TYPE_NONE;
			dev->caps.possible_type[i] = MLX4_PORT_TYPE_AUTO;
			mlx4_SENSE_PORT(dev, i, &sensed_port);
			if (sensed_port != MLX4_PORT_TYPE_NONE)
				dev->caps.port_type[i] = sensed_port;
		} else {
			dev->caps.possible_type[i] = dev->caps.port_type[i];
		}

		if (dev->caps.log_num_macs > dev_cap->port_cap[i].log_max_macs) {
			dev->caps.log_num_macs = dev_cap->port_cap[i].log_max_macs;
			mlx4_warn(dev, "Requested number of MACs is too much for port %d, reducing to %d\n",
				  i, 1 << dev->caps.log_num_macs);
		}
		if (dev->caps.log_num_vlans > dev_cap->port_cap[i].log_max_vlans) {
			dev->caps.log_num_vlans = dev_cap->port_cap[i].log_max_vlans;
			mlx4_warn(dev, "Requested number of VLANs is too much for port %d, reducing to %d\n",
				  i, 1 << dev->caps.log_num_vlans);
		}
	}

	if (mlx4_is_master(dev) && (dev->caps.num_ports == 2) &&
	    (port_type_array[0] == MLX4_PORT_TYPE_IB) &&
	    (port_type_array[1] == MLX4_PORT_TYPE_ETH)) {
		mlx4_warn(dev,
			  "Granular QoS per VF not supported with IB/Eth configuration\n");
		dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_QOS_VPP;
	}

	dev->caps.max_counters = dev_cap->max_counters;

	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
		(1 << dev->caps.log_num_macs) *
		(1 << dev->caps.log_num_vlans) *
		dev->caps.num_ports;
	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;

	if (dev_cap->dmfs_high_rate_qpn_base > 0 &&
	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN)
		dev->caps.dmfs_high_rate_qpn_base = dev_cap->dmfs_high_rate_qpn_base;
	else
		dev->caps.dmfs_high_rate_qpn_base =
			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];

	if (dev_cap->dmfs_high_rate_qpn_range > 0 &&
	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
		dev->caps.dmfs_high_rate_qpn_range = dev_cap->dmfs_high_rate_qpn_range;
		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DEFAULT;
		dev->caps.flags2 |= MLX4_DEV_CAP_FLAG2_FS_A0;
	} else {
		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_NOT_SUPPORTED;
		dev->caps.dmfs_high_rate_qpn_base =
			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
		dev->caps.dmfs_high_rate_qpn_range = MLX4_A0_STEERING_TABLE_SIZE;
	}

	dev->caps.rl_caps = dev_cap->rl_caps;

	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] =
		dev->caps.dmfs_high_rate_qpn_range;

	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH];

	dev->caps.sqp_demux = (mlx4_is_master(dev)) ? MLX4_MAX_NUM_SLAVES : 0;

	if (!enable_64b_cqe_eqe && !mlx4_is_slave(dev)) {
		if (dev_cap->flags &
		    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) {
			mlx4_warn(dev, "64B EQEs/CQEs supported by the device but not enabled\n");
			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_CQE;
			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_EQE;
		}

		if (dev_cap->flags2 &
		    (MLX4_DEV_CAP_FLAG2_CQE_STRIDE |
		     MLX4_DEV_CAP_FLAG2_EQE_STRIDE)) {
			mlx4_warn(dev, "Disabling EQE/CQE stride per user request\n");
			dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
			dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
		}
	}

	if ((dev->caps.flags &
	    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) &&
	    mlx4_is_master(dev))
		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;

	if (!mlx4_is_slave(dev)) {
		mlx4_enable_cqe_eqe_stride(dev);
		dev->caps.alloc_res_qp_mask =
			(dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0) |
			MLX4_RESERVE_A0_QP;

		if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) &&
		    dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) {
			mlx4_warn(dev, "Old device ETS support detected\n");
			mlx4_warn(dev, "Consider upgrading device FW.\n");
			dev->caps.flags2 |= MLX4_DEV_CAP_FLAG2_ETS_CFG;
		}

	} else {
		dev->caps.alloc_res_qp_mask = 0;
	}

	mlx4_enable_ignore_fcs(dev);

	return 0;
}

static int mlx4_get_pcie_dev_link_caps(struct mlx4_dev *dev,
				       enum pci_bus_speed *speed,
				       enum pcie_link_width *width)
{
	u32 lnkcap1, lnkcap2;
	int err1, err2;

#define  PCIE_MLW_CAP_SHIFT 4	/* start of MLW mask in link capabilities */

	*speed = PCI_SPEED_UNKNOWN;
	*width = PCIE_LNK_WIDTH_UNKNOWN;

	err1 = pcie_capability_read_dword(dev->persist->pdev, PCI_EXP_LNKCAP,
					  &lnkcap1);
	err2 = pcie_capability_read_dword(dev->persist->pdev, PCI_EXP_LNKCAP2,
					  &lnkcap2);
	if (!err2 && lnkcap2) { /* PCIe r3.0-compliant */
		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
			*speed = PCIE_SPEED_8_0GT;
		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
			*speed = PCIE_SPEED_5_0GT;
		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
			*speed = PCIE_SPEED_2_5GT;
	}
	if (!err1) {
		*width = (lnkcap1 & PCI_EXP_LNKCAP_MLW) >> PCIE_MLW_CAP_SHIFT;
		if (!lnkcap2) { /* pre-r3.0 */
			if (lnkcap1 & PCI_EXP_LNKCAP_SLS_5_0GB)
				*speed = PCIE_SPEED_5_0GT;
			else if (lnkcap1 & PCI_EXP_LNKCAP_SLS_2_5GB)
				*speed = PCIE_SPEED_2_5GT;
		}
	}

	if (*speed == PCI_SPEED_UNKNOWN || *width == PCIE_LNK_WIDTH_UNKNOWN) {
		return err1 ? err1 :
			err2 ? err2 : -EINVAL;
	}
	return 0;
}

static void mlx4_check_pcie_caps(struct mlx4_dev *dev)
{
	enum pcie_link_width width, width_cap;
	enum pci_bus_speed speed, speed_cap;
	int err;

#define PCIE_SPEED_STR(speed) \
	(speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : \
	 speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : \
	 speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : \
	 "Unknown")

	err = mlx4_get_pcie_dev_link_caps(dev, &speed_cap, &width_cap);
	if (err) {
		mlx4_warn(dev,
			  "Unable to determine PCIe device BW capabilities\n");
		return;
	}

	err = pcie_get_minimum_link(dev->persist->pdev, &speed, &width);
	if (err || speed == PCI_SPEED_UNKNOWN ||
	    width == PCIE_LNK_WIDTH_UNKNOWN) {
		mlx4_warn(dev,
			  "Unable to determine PCI device chain minimum BW\n");
		return;
	}

	if (width != width_cap || speed != speed_cap)
		mlx4_warn(dev,
			  "PCIe BW is different than device's capability\n");

	mlx4_info(dev, "PCIe link speed is %s, device supports %s\n",
		  PCIE_SPEED_STR(speed), PCIE_SPEED_STR(speed_cap));
	mlx4_info(dev, "PCIe link width is x%d, device supports x%d\n",
		  width, width_cap);
	return;
}

/*The function checks if there are live vf, return the num of them*/
static int mlx4_how_many_lives_vf(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_slave_state *s_state;
	int i;
	int ret = 0;

	for (i = 1/*the ppf is 0*/; i < dev->num_slaves; ++i) {
		s_state = &priv->mfunc.master.slave_state[i];
		if (s_state->active && s_state->last_cmd !=
		    MLX4_COMM_CMD_RESET) {
			mlx4_warn(dev, "%s: slave: %d is still active\n",
				  __func__, i);
			ret++;
		}
	}
	return ret;
}

int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey)
{
	u32 qk = MLX4_RESERVED_QKEY_BASE;

	if (qpn >= dev->phys_caps.base_tunnel_sqpn + 8 * MLX4_MFUNC_MAX ||
	    qpn < dev->phys_caps.base_proxy_sqpn)
		return -EINVAL;

	if (qpn >= dev->phys_caps.base_tunnel_sqpn)
		/* tunnel qp */
		qk += qpn - dev->phys_caps.base_tunnel_sqpn;
	else
		qk += qpn - dev->phys_caps.base_proxy_sqpn;
	*qkey = qk;
	return 0;
}
EXPORT_SYMBOL(mlx4_get_parav_qkey);

void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val)
{
	struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev);

	if (!mlx4_is_master(dev))
		return;

	priv->virt2phys_pkey[slave][port - 1][i] = val;
}
EXPORT_SYMBOL(mlx4_sync_pkey_table);

void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid)
{
	struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev);

	if (!mlx4_is_master(dev))
		return;

	priv->slave_node_guids[slave] = guid;
}
EXPORT_SYMBOL(mlx4_put_slave_node_guid);

__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave)
{
	struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev);

	if (!mlx4_is_master(dev))
		return 0;

	return priv->slave_node_guids[slave];
}
EXPORT_SYMBOL(mlx4_get_slave_node_guid);

int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_slave_state *s_slave;

	if (!mlx4_is_master(dev))
		return 0;

	s_slave = &priv->mfunc.master.slave_state[slave];
	return !!s_slave->active;
}
EXPORT_SYMBOL(mlx4_is_slave_active);

static void slave_adjust_steering_mode(struct mlx4_dev *dev,
				       struct mlx4_dev_cap *dev_cap,
				       struct mlx4_init_hca_param *hca_param)
{
	dev->caps.steering_mode = hca_param->steering_mode;
	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
		dev->caps.fs_log_max_ucast_qp_range_size =
			dev_cap->fs_log_max_ucast_qp_range_size;
	} else
		dev->caps.num_qp_per_mgm =
			4 * ((1 << hca_param->log_mc_entry_sz)/16 - 2);

	mlx4_dbg(dev, "Steering mode is: %s\n",
		 mlx4_steering_mode_str(dev->caps.steering_mode));
}

static int mlx4_slave_cap(struct mlx4_dev *dev)
{
	int			   err;
	u32			   page_size;
	struct mlx4_dev_cap	   dev_cap;
	struct mlx4_func_cap	   func_cap;
	struct mlx4_init_hca_param hca_param;
	u8			   i;

	memset(&hca_param, 0, sizeof(hca_param));
	err = mlx4_QUERY_HCA(dev, &hca_param);
	if (err) {
		mlx4_err(dev, "QUERY_HCA command failed, aborting\n");
		return err;
	}

	/* fail if the hca has an unknown global capability
	 * at this time global_caps should be always zeroed
	 */
	if (hca_param.global_caps) {
		mlx4_err(dev, "Unknown hca global capabilities\n");
		return -ENOSYS;
	}

	mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;

	dev->caps.hca_core_clock = hca_param.hca_core_clock;

	memset(&dev_cap, 0, sizeof(dev_cap));
	dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp;
	err = mlx4_dev_cap(dev, &dev_cap);
	if (err) {
		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
		return err;
	}

	err = mlx4_QUERY_FW(dev);
	if (err)
		mlx4_err(dev, "QUERY_FW command failed: could not get FW version\n");

	page_size = ~dev->caps.page_size_cap + 1;
	mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
	if (page_size > PAGE_SIZE) {
		mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n",
			 page_size, PAGE_SIZE);
		return -ENODEV;
	}

	/* Set uar_page_shift for VF */
	dev->uar_page_shift = hca_param.uar_page_sz + 12;

	/* Make sure the master uar page size is valid */
	if (dev->uar_page_shift > PAGE_SHIFT) {
		mlx4_err(dev,
			 "Invalid configuration: uar page size is larger than system page size\n");
		return  -ENODEV;
	}

	/* Set reserved_uars based on the uar_page_shift */
	mlx4_set_num_reserved_uars(dev, &dev_cap);

	/* Although uar page size in FW differs from system page size,
	 * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core)
	 * still works with assumption that uar page size == system page size
	 */
	dev->caps.uar_page_size = PAGE_SIZE;

	memset(&func_cap, 0, sizeof(func_cap));
	err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap);
	if (err) {
		mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d)\n",
			 err);
		return err;
	}

	if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
	    PF_CONTEXT_BEHAVIOUR_MASK) {
		mlx4_err(dev, "Unknown pf context behaviour %x known flags %x\n",
			 func_cap.pf_context_behaviour, PF_CONTEXT_BEHAVIOUR_MASK);
		return -ENOSYS;
	}

	dev->caps.num_ports		= func_cap.num_ports;
	dev->quotas.qp			= func_cap.qp_quota;
	dev->quotas.srq			= func_cap.srq_quota;
	dev->quotas.cq			= func_cap.cq_quota;
	dev->quotas.mpt			= func_cap.mpt_quota;
	dev->quotas.mtt			= func_cap.mtt_quota;
	dev->caps.num_qps		= 1 << hca_param.log_num_qps;
	dev->caps.num_srqs		= 1 << hca_param.log_num_srqs;
	dev->caps.num_cqs		= 1 << hca_param.log_num_cqs;
	dev->caps.num_mpts		= 1 << hca_param.log_mpt_sz;
	dev->caps.num_eqs		= func_cap.max_eq;
	dev->caps.reserved_eqs		= func_cap.reserved_eq;
	dev->caps.reserved_lkey		= func_cap.reserved_lkey;
	dev->caps.num_pds               = MLX4_NUM_PDS;
	dev->caps.num_mgms              = 0;
	dev->caps.num_amgms             = 0;

	if (dev->caps.num_ports > MLX4_MAX_PORTS) {
		mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n",
			 dev->caps.num_ports, MLX4_MAX_PORTS);
		return -ENODEV;
	}

	mlx4_replace_zero_macs(dev);

	dev->caps.qp0_qkey = kcalloc(dev->caps.num_ports, sizeof(u32), GFP_KERNEL);
	dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
	dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
	dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
	dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);

	if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy ||
	    !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy ||
	    !dev->caps.qp0_qkey) {
		err = -ENOMEM;
		goto err_mem;
	}

	for (i = 1; i <= dev->caps.num_ports; ++i) {
		err = mlx4_QUERY_FUNC_CAP(dev, i, &func_cap);
		if (err) {
			mlx4_err(dev, "QUERY_FUNC_CAP port command failed for port %d, aborting (%d)\n",
				 i, err);
			goto err_mem;
		}
		dev->caps.qp0_qkey[i - 1] = func_cap.qp0_qkey;
		dev->caps.qp0_tunnel[i - 1] = func_cap.qp0_tunnel_qpn;
		dev->caps.qp0_proxy[i - 1] = func_cap.qp0_proxy_qpn;
		dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn;
		dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn;
		dev->caps.port_mask[i] = dev->caps.port_type[i];
		dev->caps.phys_port_id[i] = func_cap.phys_port_id;
		err = mlx4_get_slave_pkey_gid_tbl_len(dev, i,
						      &dev->caps.gid_table_len[i],
						      &dev->caps.pkey_table_len[i]);
		if (err)
			goto err_mem;
	}

	if (dev->caps.uar_page_size * (dev->caps.num_uars -
				       dev->caps.reserved_uars) >
				       pci_resource_len(dev->persist->pdev,
							2)) {
		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
			 dev->caps.uar_page_size * dev->caps.num_uars,
			 (unsigned long long)
			 pci_resource_len(dev->persist->pdev, 2));
		err = -ENOMEM;
		goto err_mem;
	}

	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_EQE_ENABLED) {
		dev->caps.eqe_size   = 64;
		dev->caps.eqe_factor = 1;
	} else {
		dev->caps.eqe_size   = 32;
		dev->caps.eqe_factor = 0;
	}

	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_CQE_ENABLED) {
		dev->caps.cqe_size   = 64;
		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
	} else {
		dev->caps.cqe_size   = 32;
	}

	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_EQE_STRIDE_ENABLED) {
		dev->caps.eqe_size = hca_param.eqe_size;
		dev->caps.eqe_factor = 0;
	}

	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_CQE_STRIDE_ENABLED) {
		dev->caps.cqe_size = hca_param.cqe_size;
		/* User still need to know when CQE > 32B */
		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
	}

	dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
	mlx4_warn(dev, "Timestamping is not supported in slave mode\n");

	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
	mlx4_dbg(dev, "RSS support for IP fragments is %s\n",
		 hca_param.rss_ip_frags ? "on" : "off");

	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP &&
	    dev->caps.bf_reg_size)
		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP;

	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_A0_RES_QP)
		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_A0_QP;

	return 0;

err_mem:
	kfree(dev->caps.qp0_qkey);
	kfree(dev->caps.qp0_tunnel);
	kfree(dev->caps.qp0_proxy);
	kfree(dev->caps.qp1_tunnel);
	kfree(dev->caps.qp1_proxy);
	dev->caps.qp0_qkey = NULL;
	dev->caps.qp0_tunnel = NULL;
	dev->caps.qp0_proxy = NULL;
	dev->caps.qp1_tunnel = NULL;
	dev->caps.qp1_proxy = NULL;

	return err;
}

static void mlx4_request_modules(struct mlx4_dev *dev)
{
	int port;
	int has_ib_port = false;
	int has_eth_port = false;
#define EN_DRV_NAME	"mlx4_en"
#define IB_DRV_NAME	"mlx4_ib"

	for (port = 1; port <= dev->caps.num_ports; port++) {
		if (dev->caps.port_type[port] == MLX4_PORT_TYPE_IB)
			has_ib_port = true;
		else if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
			has_eth_port = true;
	}

	if (has_eth_port)
		request_module_nowait(EN_DRV_NAME);
	if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
		request_module_nowait(IB_DRV_NAME);
}

/*
 * Change the port configuration of the device.
 * Every user of this function must hold the port mutex.
 */
int mlx4_change_port_types(struct mlx4_dev *dev,
			   enum mlx4_port_type *port_types)
{
	int err = 0;
	int change = 0;
	int port;

	for (port = 0; port <  dev->caps.num_ports; port++) {
		/* Change the port type only if the new type is different
		 * from the current, and not set to Auto */
		if (port_types[port] != dev->caps.port_type[port + 1])
			change = 1;
	}
	if (change) {
		mlx4_unregister_device(dev);
		for (port = 1; port <= dev->caps.num_ports; port++) {
			mlx4_CLOSE_PORT(dev, port);
			dev->caps.port_type[port] = port_types[port - 1];
			err = mlx4_SET_PORT(dev, port, -1);
			if (err) {
				mlx4_err(dev, "Failed to set port %d, aborting\n",
					 port);
				goto out;
			}
		}
		mlx4_set_port_mask(dev);
		err = mlx4_register_device(dev);
		if (err) {
			mlx4_err(dev, "Failed to register device\n");
			goto out;
		}
		mlx4_request_modules(dev);
	}

out:
	return err;
}

static ssize_t show_port_type(struct device *dev,
			      struct device_attribute *attr,
			      char *buf)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_attr);
	struct mlx4_dev *mdev = info->dev;
	char type[8];

	sprintf(type, "%s",
		(mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_IB) ?
		"ib" : "eth");
	if (mdev->caps.possible_type[info->port] == MLX4_PORT_TYPE_AUTO)
		sprintf(buf, "auto (%s)\n", type);
	else
		sprintf(buf, "%s\n", type);

	return strlen(buf);
}

static ssize_t set_port_type(struct device *dev,
			     struct device_attribute *attr,
			     const char *buf, size_t count)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_attr);
	struct mlx4_dev *mdev = info->dev;
	struct mlx4_priv *priv = mlx4_priv(mdev);
	enum mlx4_port_type types[MLX4_MAX_PORTS];
	enum mlx4_port_type new_types[MLX4_MAX_PORTS];
	static DEFINE_MUTEX(set_port_type_mutex);
	int i;
	int err = 0;

	mutex_lock(&set_port_type_mutex);

	if (!strcmp(buf, "ib\n"))
		info->tmp_type = MLX4_PORT_TYPE_IB;
	else if (!strcmp(buf, "eth\n"))
		info->tmp_type = MLX4_PORT_TYPE_ETH;
	else if (!strcmp(buf, "auto\n"))
		info->tmp_type = MLX4_PORT_TYPE_AUTO;
	else {
		mlx4_err(mdev, "%s is not supported port type\n", buf);
		err = -EINVAL;
		goto err_out;
	}

	mlx4_stop_sense(mdev);
	mutex_lock(&priv->port_mutex);
	/* Possible type is always the one that was delivered */
	mdev->caps.possible_type[info->port] = info->tmp_type;

	for (i = 0; i < mdev->caps.num_ports; i++) {
		types[i] = priv->port[i+1].tmp_type ? priv->port[i+1].tmp_type :
					mdev->caps.possible_type[i+1];
		if (types[i] == MLX4_PORT_TYPE_AUTO)
			types[i] = mdev->caps.port_type[i+1];
	}

	if (!(mdev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
	    !(mdev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT)) {
		for (i = 1; i <= mdev->caps.num_ports; i++) {
			if (mdev->caps.possible_type[i] == MLX4_PORT_TYPE_AUTO) {
				mdev->caps.possible_type[i] = mdev->caps.port_type[i];
				err = -EINVAL;
			}
		}
	}
	if (err) {
		mlx4_err(mdev, "Auto sensing is not supported on this HCA. Set only 'eth' or 'ib' for both ports (should be the same)\n");
		goto out;
	}

	mlx4_do_sense_ports(mdev, new_types, types);

	err = mlx4_check_port_params(mdev, new_types);
	if (err)
		goto out;

	/* We are about to apply the changes after the configuration
	 * was verified, no need to remember the temporary types
	 * any more */
	for (i = 0; i < mdev->caps.num_ports; i++)
		priv->port[i + 1].tmp_type = 0;

	err = mlx4_change_port_types(mdev, new_types);

out:
	mlx4_start_sense(mdev);
	mutex_unlock(&priv->port_mutex);
err_out:
	mutex_unlock(&set_port_type_mutex);

	return err ? err : count;
}

enum ibta_mtu {
	IB_MTU_256  = 1,
	IB_MTU_512  = 2,
	IB_MTU_1024 = 3,
	IB_MTU_2048 = 4,
	IB_MTU_4096 = 5
};

static inline int int_to_ibta_mtu(int mtu)
{
	switch (mtu) {
	case 256:  return IB_MTU_256;
	case 512:  return IB_MTU_512;
	case 1024: return IB_MTU_1024;
	case 2048: return IB_MTU_2048;
	case 4096: return IB_MTU_4096;
	default: return -1;
	}
}

static inline int ibta_mtu_to_int(enum ibta_mtu mtu)
{
	switch (mtu) {
	case IB_MTU_256:  return  256;
	case IB_MTU_512:  return  512;
	case IB_MTU_1024: return 1024;
	case IB_MTU_2048: return 2048;
	case IB_MTU_4096: return 4096;
	default: return -1;
	}
}

static ssize_t show_port_ib_mtu(struct device *dev,
			     struct device_attribute *attr,
			     char *buf)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_mtu_attr);
	struct mlx4_dev *mdev = info->dev;

	if (mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_ETH)
		mlx4_warn(mdev, "port level mtu is only used for IB ports\n");

	sprintf(buf, "%d\n",
			ibta_mtu_to_int(mdev->caps.port_ib_mtu[info->port]));
	return strlen(buf);
}

static ssize_t set_port_ib_mtu(struct device *dev,
			     struct device_attribute *attr,
			     const char *buf, size_t count)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_mtu_attr);
	struct mlx4_dev *mdev = info->dev;
	struct mlx4_priv *priv = mlx4_priv(mdev);
	int err, port, mtu, ibta_mtu = -1;

	if (mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_ETH) {
		mlx4_warn(mdev, "port level mtu is only used for IB ports\n");
		return -EINVAL;
	}

	err = kstrtoint(buf, 0, &mtu);
	if (!err)
		ibta_mtu = int_to_ibta_mtu(mtu);

	if (err || ibta_mtu < 0) {
		mlx4_err(mdev, "%s is invalid IBTA mtu\n", buf);
		return -EINVAL;
	}

	mdev->caps.port_ib_mtu[info->port] = ibta_mtu;

	mlx4_stop_sense(mdev);
	mutex_lock(&priv->port_mutex);
	mlx4_unregister_device(mdev);
	for (port = 1; port <= mdev->caps.num_ports; port++) {
		mlx4_CLOSE_PORT(mdev, port);
		err = mlx4_SET_PORT(mdev, port, -1);
		if (err) {
			mlx4_err(mdev, "Failed to set port %d, aborting\n",
				 port);
			goto err_set_port;
		}
	}
	err = mlx4_register_device(mdev);
err_set_port:
	mutex_unlock(&priv->port_mutex);
	mlx4_start_sense(mdev);
	return err ? err : count;
}

/* bond for multi-function device */
#define MAX_MF_BOND_ALLOWED_SLAVES 63
static int mlx4_mf_bond(struct mlx4_dev *dev)
{
	int err = 0;
	struct mlx4_slaves_pport slaves_port1;
	struct mlx4_slaves_pport slaves_port2;
	DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX);

	slaves_port1 = mlx4_phys_to_slaves_pport(dev, 1);
	slaves_port2 = mlx4_phys_to_slaves_pport(dev, 2);
	bitmap_and(slaves_port_1_2,
		   slaves_port1.slaves, slaves_port2.slaves,
		   dev->persist->num_vfs + 1);

	/* only single port vfs are allowed */
	if (bitmap_weight(slaves_port_1_2, dev->persist->num_vfs + 1) > 1) {
		mlx4_warn(dev, "HA mode unsupported for dual ported VFs\n");
		return -EINVAL;
	}

	/* limit on maximum allowed VFs */
	if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
	    bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) >
	    MAX_MF_BOND_ALLOWED_SLAVES)
		return -EINVAL;

	if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) {
		mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n");
		return -EINVAL;
	}

	err = mlx4_bond_mac_table(dev);
	if (err)
		return err;
	err = mlx4_bond_vlan_table(dev);
	if (err)
		goto err1;
	err = mlx4_bond_fs_rules(dev);
	if (err)
		goto err2;

	return 0;
err2:
	(void)mlx4_unbond_vlan_table(dev);
err1:
	(void)mlx4_unbond_mac_table(dev);
	return err;
}

static int mlx4_mf_unbond(struct mlx4_dev *dev)
{
	int ret, ret1;

	ret = mlx4_unbond_fs_rules(dev);
	if (ret)
		mlx4_warn(dev, "multifunction unbond for flow rules failedi (%d)\n", ret);
	ret1 = mlx4_unbond_mac_table(dev);
	if (ret1) {
		mlx4_warn(dev, "multifunction unbond for MAC table failed (%d)\n", ret1);
		ret = ret1;
	}
	ret1 = mlx4_unbond_vlan_table(dev);
	if (ret1) {
		mlx4_warn(dev, "multifunction unbond for VLAN table failed (%d)\n", ret1);
		ret = ret1;
	}
	return ret;
}

int mlx4_bond(struct mlx4_dev *dev)
{
	int ret = 0;
	struct mlx4_priv *priv = mlx4_priv(dev);

	mutex_lock(&priv->bond_mutex);

	if (!mlx4_is_bonded(dev)) {
		ret = mlx4_do_bond(dev, true);
		if (ret)
			mlx4_err(dev, "Failed to bond device: %d\n", ret);
		if (!ret && mlx4_is_master(dev)) {
			ret = mlx4_mf_bond(dev);
			if (ret) {
				mlx4_err(dev, "bond for multifunction failed\n");
				mlx4_do_bond(dev, false);
			}
		}
	}

	mutex_unlock(&priv->bond_mutex);
	if (!ret)
		mlx4_dbg(dev, "Device is bonded\n");

	return ret;
}
EXPORT_SYMBOL_GPL(mlx4_bond);

int mlx4_unbond(struct mlx4_dev *dev)
{
	int ret = 0;
	struct mlx4_priv *priv = mlx4_priv(dev);

	mutex_lock(&priv->bond_mutex);

	if (mlx4_is_bonded(dev)) {
		int ret2 = 0;

		ret = mlx4_do_bond(dev, false);
		if (ret)
			mlx4_err(dev, "Failed to unbond device: %d\n", ret);
		if (mlx4_is_master(dev))
			ret2 = mlx4_mf_unbond(dev);
		if (ret2) {
			mlx4_warn(dev, "Failed to unbond device for multifunction (%d)\n", ret2);
			ret = ret2;
		}
	}

	mutex_unlock(&priv->bond_mutex);
	if (!ret)
		mlx4_dbg(dev, "Device is unbonded\n");

	return ret;
}
EXPORT_SYMBOL_GPL(mlx4_unbond);


int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
{
	u8 port1 = v2p->port1;
	u8 port2 = v2p->port2;
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;

	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
		return -ENOTSUPP;

	mutex_lock(&priv->bond_mutex);

	/* zero means keep current mapping for this port */
	if (port1 == 0)
		port1 = priv->v2p.port1;
	if (port2 == 0)
		port2 = priv->v2p.port2;

	if ((port1 < 1) || (port1 > MLX4_MAX_PORTS) ||
	    (port2 < 1) || (port2 > MLX4_MAX_PORTS) ||
	    (port1 == 2 && port2 == 1)) {
		/* besides boundary checks cross mapping makes
		 * no sense and therefore not allowed */
		err = -EINVAL;
	} else if ((port1 == priv->v2p.port1) &&
		 (port2 == priv->v2p.port2)) {
		err = 0;
	} else {
		err = mlx4_virt2phy_port_map(dev, port1, port2);
		if (!err) {
			mlx4_dbg(dev, "port map changed: [%d][%d]\n",
				 port1, port2);
			priv->v2p.port1 = port1;
			priv->v2p.port2 = port2;
		} else {
			mlx4_err(dev, "Failed to change port mape: %d\n", err);
		}
	}

	mutex_unlock(&priv->bond_mutex);
	return err;
}
EXPORT_SYMBOL_GPL(mlx4_port_map_set);

static int mlx4_load_fw(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;

	priv->fw.fw_icm = mlx4_alloc_icm(dev, priv->fw.fw_pages,
					 GFP_HIGHUSER | __GFP_NOWARN, 0);
	if (!priv->fw.fw_icm) {
		mlx4_err(dev, "Couldn't allocate FW area, aborting\n");
		return -ENOMEM;
	}

	err = mlx4_MAP_FA(dev, priv->fw.fw_icm);
	if (err) {
		mlx4_err(dev, "MAP_FA command failed, aborting\n");
		goto err_free;
	}

	err = mlx4_RUN_FW(dev);
	if (err) {
		mlx4_err(dev, "RUN_FW command failed, aborting\n");
		goto err_unmap_fa;
	}

	return 0;

err_unmap_fa:
	mlx4_UNMAP_FA(dev);

err_free:
	mlx4_free_icm(dev, priv->fw.fw_icm, 0);
	return err;
}

static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
				int cmpt_entry_sz)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;
	int num_eqs;

	err = mlx4_init_icm_table(dev, &priv->qp_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_QP *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err)
		goto err;

	err = mlx4_init_icm_table(dev, &priv->srq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_SRQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_srqs,
				  dev->caps.reserved_srqs, 0, 0);
	if (err)
		goto err_qp;

	err = mlx4_init_icm_table(dev, &priv->cq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_CQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_cqs,
				  dev->caps.reserved_cqs, 0, 0);
	if (err)
		goto err_srq;

	num_eqs = dev->phys_caps.num_phys_eqs;
	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_EQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, num_eqs, num_eqs, 0, 0);
	if (err)
		goto err_cq;

	return 0;

err_cq:
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);

err_srq:
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);

err_qp:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

err:
	return err;
}

static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
			 struct mlx4_init_hca_param *init_hca, u64 icm_size)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	u64 aux_pages;
	int num_eqs;
	int err;

	err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages);
	if (err) {
		mlx4_err(dev, "SET_ICM_SIZE command failed, aborting\n");
		return err;
	}

	mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory\n",
		 (unsigned long long) icm_size >> 10,
		 (unsigned long long) aux_pages << 2);

	priv->fw.aux_icm = mlx4_alloc_icm(dev, aux_pages,
					  GFP_HIGHUSER | __GFP_NOWARN, 0);
	if (!priv->fw.aux_icm) {
		mlx4_err(dev, "Couldn't allocate aux memory, aborting\n");
		return -ENOMEM;
	}

	err = mlx4_MAP_ICM_AUX(dev, priv->fw.aux_icm);
	if (err) {
		mlx4_err(dev, "MAP_ICM_AUX command failed, aborting\n");
		goto err_free_aux;
	}

	err = mlx4_init_cmpt_table(dev, init_hca->cmpt_base, dev_cap->cmpt_entry_sz);
	if (err) {
		mlx4_err(dev, "Failed to map cMPT context memory, aborting\n");
		goto err_unmap_aux;
	}


	num_eqs = dev->phys_caps.num_phys_eqs;
	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
				  num_eqs, num_eqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map EQ context memory, aborting\n");
		goto err_unmap_cmpt;
	}

	/*
	 * Reserved MTT entries must be aligned up to a cacheline
	 * boundary, since the FW will write to them, while the driver
	 * writes to all other MTT entries. (The variable
	 * dev->caps.mtt_entry_sz below is really the MTT segment
	 * size, not the raw entry size)
	 */
	dev->caps.reserved_mtts =
		ALIGN(dev->caps.reserved_mtts * dev->caps.mtt_entry_sz,
		      dma_get_cache_alignment()) / dev->caps.mtt_entry_sz;

	err = mlx4_init_icm_table(dev, &priv->mr_table.mtt_table,
				  init_hca->mtt_base,
				  dev->caps.mtt_entry_sz,
				  dev->caps.num_mtts,
				  dev->caps.reserved_mtts, 1, 0);
	if (err) {
		mlx4_err(dev, "Failed to map MTT context memory, aborting\n");
		goto err_unmap_eq;
	}

	err = mlx4_init_icm_table(dev, &priv->mr_table.dmpt_table,
				  init_hca->dmpt_base,
				  dev_cap->dmpt_entry_sz,
				  dev->caps.num_mpts,
				  dev->caps.reserved_mrws, 1, 1);
	if (err) {
		mlx4_err(dev, "Failed to map dMPT context memory, aborting\n");
		goto err_unmap_mtt;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.qp_table,
				  init_hca->qpc_base,
				  dev_cap->qpc_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map QP context memory, aborting\n");
		goto err_unmap_dmpt;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.auxc_table,
				  init_hca->auxc_base,
				  dev_cap->aux_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map AUXC context memory, aborting\n");
		goto err_unmap_qp;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.altc_table,
				  init_hca->altc_base,
				  dev_cap->altc_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map ALTC context memory, aborting\n");
		goto err_unmap_auxc;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.rdmarc_table,
				  init_hca->rdmarc_base,
				  dev_cap->rdmarc_entry_sz << priv->qp_table.rdmarc_shift,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map RDMARC context memory, aborting\n");
		goto err_unmap_altc;
	}

	err = mlx4_init_icm_table(dev, &priv->cq_table.table,
				  init_hca->cqc_base,
				  dev_cap->cqc_entry_sz,
				  dev->caps.num_cqs,
				  dev->caps.reserved_cqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map CQ context memory, aborting\n");
		goto err_unmap_rdmarc;
	}

	err = mlx4_init_icm_table(dev, &priv->srq_table.table,
				  init_hca->srqc_base,
				  dev_cap->srq_entry_sz,
				  dev->caps.num_srqs,
				  dev->caps.reserved_srqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map SRQ context memory, aborting\n");
		goto err_unmap_cq;
	}

	/*
	 * For flow steering device managed mode it is required to use
	 * mlx4_init_icm_table. For B0 steering mode it's not strictly
	 * required, but for simplicity just map the whole multicast
	 * group table now.  The table isn't very big and it's a lot
	 * easier than trying to track ref counts.
	 */
	err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
				  init_hca->mc_base,
				  mlx4_get_mgm_entry_size(dev),
				  dev->caps.num_mgms + dev->caps.num_amgms,
				  dev->caps.num_mgms + dev->caps.num_amgms,
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map MCG context memory, aborting\n");
		goto err_unmap_srq;
	}

	return 0;

err_unmap_srq:
	mlx4_cleanup_icm_table(dev, &priv->srq_table.table);

err_unmap_cq:
	mlx4_cleanup_icm_table(dev, &priv->cq_table.table);

err_unmap_rdmarc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.rdmarc_table);

err_unmap_altc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.altc_table);

err_unmap_auxc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.auxc_table);

err_unmap_qp:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.qp_table);

err_unmap_dmpt:
	mlx4_cleanup_icm_table(dev, &priv->mr_table.dmpt_table);

err_unmap_mtt:
	mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table);

err_unmap_eq:
	mlx4_cleanup_icm_table(dev, &priv->eq_table.table);

err_unmap_cmpt:
	mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

err_unmap_aux:
	mlx4_UNMAP_ICM_AUX(dev);

err_free_aux:
	mlx4_free_icm(dev, priv->fw.aux_icm, 0);

	return err;
}

static void mlx4_free_icms(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	mlx4_cleanup_icm_table(dev, &priv->mcg_table.table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.rdmarc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.altc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.auxc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.qp_table);
	mlx4_cleanup_icm_table(dev, &priv->mr_table.dmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table);
	mlx4_cleanup_icm_table(dev, &priv->eq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

	mlx4_UNMAP_ICM_AUX(dev);
	mlx4_free_icm(dev, priv->fw.aux_icm, 0);
}

static void mlx4_slave_exit(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	mutex_lock(&priv->cmd.slave_cmd_mutex);
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_CMD_NA_OP,
			  MLX4_COMM_TIME))
		mlx4_warn(dev, "Failed to close slave function\n");
	mutex_unlock(&priv->cmd.slave_cmd_mutex);
}

static int map_bf_area(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	resource_size_t bf_start;
	resource_size_t bf_len;
	int err = 0;

	if (!dev->caps.bf_reg_size)
		return -ENXIO;

	bf_start = pci_resource_start(dev->persist->pdev, 2) +
			(dev->caps.num_uars << PAGE_SHIFT);
	bf_len = pci_resource_len(dev->persist->pdev, 2) -
			(dev->caps.num_uars << PAGE_SHIFT);
	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
	if (!priv->bf_mapping)
		err = -ENOMEM;

	return err;
}

static void unmap_bf_area(struct mlx4_dev *dev)
{
	if (mlx4_priv(dev)->bf_mapping)
		io_mapping_free(mlx4_priv(dev)->bf_mapping);
}

cycle_t mlx4_read_clock(struct mlx4_dev *dev)
{
	u32 clockhi, clocklo, clockhi1;
	cycle_t cycles;
	int i;
	struct mlx4_priv *priv = mlx4_priv(dev);

	for (i = 0; i < 10; i++) {
		clockhi = swab32(readl(priv->clock_mapping));
		clocklo = swab32(readl(priv->clock_mapping + 4));
		clockhi1 = swab32(readl(priv->clock_mapping));
		if (clockhi == clockhi1)
			break;
	}

	cycles = (u64) clockhi << 32 | (u64) clocklo;

	return cycles;
}
EXPORT_SYMBOL_GPL(mlx4_read_clock);


static int map_internal_clock(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	priv->clock_mapping =
		ioremap(pci_resource_start(dev->persist->pdev,
					   priv->fw.clock_bar) +
			priv->fw.clock_offset, MLX4_CLOCK_SIZE);

	if (!priv->clock_mapping)
		return -ENOMEM;

	return 0;
}

int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
				   struct mlx4_clock_params *params)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	if (mlx4_is_slave(dev))
		return -ENOTSUPP;

	if (!params)
		return -EINVAL;

	params->bar = priv->fw.clock_bar;
	params->offset = priv->fw.clock_offset;
	params->size = MLX4_CLOCK_SIZE;

	return 0;
}
EXPORT_SYMBOL_GPL(mlx4_get_internal_clock_params);

static void unmap_internal_clock(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	if (priv->clock_mapping)
		iounmap(priv->clock_mapping);
}

static void mlx4_close_hca(struct mlx4_dev *dev)
{
	unmap_internal_clock(dev);
	unmap_bf_area(dev);
	if (mlx4_is_slave(dev))
		mlx4_slave_exit(dev);
	else {
		mlx4_CLOSE_HCA(dev, 0);
		mlx4_free_icms(dev);
	}
}

static void mlx4_close_fw(struct mlx4_dev *dev)
{
	if (!mlx4_is_slave(dev)) {
		mlx4_UNMAP_FA(dev);
		mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
	}
}

static int mlx4_comm_check_offline(struct mlx4_dev *dev)
{
#define COMM_CHAN_OFFLINE_OFFSET 0x09

	u32 comm_flags;
	u32 offline_bit;
	unsigned long end;
	struct mlx4_priv *priv = mlx4_priv(dev);

	end = msecs_to_jiffies(MLX4_COMM_OFFLINE_TIME_OUT) + jiffies;
	while (time_before(jiffies, end)) {
		comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
					  MLX4_COMM_CHAN_FLAGS));
		offline_bit = (comm_flags &
			       (u32)(1 << COMM_CHAN_OFFLINE_OFFSET));
		if (!offline_bit)
			return 0;
		/* There are cases as part of AER/Reset flow that PF needs
		 * around 100 msec to load. We therefore sleep for 100 msec
		 * to allow other tasks to make use of that CPU during this
		 * time interval.
		 */
		msleep(100);
	}
	mlx4_err(dev, "Communication channel is offline.\n");
	return -EIO;
}

static void mlx4_reset_vf_support(struct mlx4_dev *dev)
{
#define COMM_CHAN_RST_OFFSET 0x1e

	struct mlx4_priv *priv = mlx4_priv(dev);
	u32 comm_rst;
	u32 comm_caps;

	comm_caps = swab32(readl((__iomem char *)priv->mfunc.comm +
				 MLX4_COMM_CHAN_CAPS));
	comm_rst = (comm_caps & (u32)(1 << COMM_CHAN_RST_OFFSET));

	if (comm_rst)
		dev->caps.vf_caps |= MLX4_VF_CAP_FLAG_RESET;
}

static int mlx4_init_slave(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	u64 dma = (u64) priv->mfunc.vhcr_dma;
	int ret_from_reset = 0;
	u32 slave_read;
	u32 cmd_channel_ver;

	if (atomic_read(&pf_loading)) {
		mlx4_warn(dev, "PF is not ready - Deferring probe\n");
		return -EPROBE_DEFER;
	}

	mutex_lock(&priv->cmd.slave_cmd_mutex);
	priv->cmd.max_cmds = 1;
	if (mlx4_comm_check_offline(dev)) {
		mlx4_err(dev, "PF is not responsive, skipping initialization\n");
		goto err_offline;
	}

	mlx4_reset_vf_support(dev);
	mlx4_warn(dev, "Sending reset\n");
	ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0,
				       MLX4_COMM_CMD_NA_OP, MLX4_COMM_TIME);
	/* if we are in the middle of flr the slave will try
	 * NUM_OF_RESET_RETRIES times before leaving.*/
	if (ret_from_reset) {
		if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) {
			mlx4_warn(dev, "slave is currently in the middle of FLR - Deferring probe\n");
			mutex_unlock(&priv->cmd.slave_cmd_mutex);
			return -EPROBE_DEFER;
		} else
			goto err;
	}

	/* check the driver version - the slave I/F revision
	 * must match the master's */
	slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
	cmd_channel_ver = mlx4_comm_get_version();

	if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) !=
		MLX4_COMM_GET_IF_REV(slave_read)) {
		mlx4_err(dev, "slave driver version is not supported by the master\n");
		goto err;
	}

	mlx4_warn(dev, "Sending vhcr0\n");
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR0, dma >> 48,
			     MLX4_COMM_CMD_NA_OP, MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR1, dma >> 32,
			     MLX4_COMM_CMD_NA_OP, MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR2, dma >> 16,
			     MLX4_COMM_CMD_NA_OP, MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_EN, dma,
			  MLX4_COMM_CMD_NA_OP, MLX4_COMM_TIME))
		goto err;

	mutex_unlock(&priv->cmd.slave_cmd_mutex);
	return 0;

err:
	mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_CMD_NA_OP, 0);
err_offline:
	mutex_unlock(&priv->cmd.slave_cmd_mutex);
	return -EIO;
}

static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
{
	int i;

	for (i = 1; i <= dev->caps.num_ports; i++) {
		if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH)
			dev->caps.gid_table_len[i] =
				mlx4_get_slave_num_gids(dev, 0, i);
		else
			dev->caps.gid_table_len[i] = 1;
		dev->caps.pkey_table_len[i] =
			dev->phys_caps.pkey_phys_table_len[i] - 1;
	}
}

static int choose_log_fs_mgm_entry_size(int qp_per_entry)
{
	int i = MLX4_MIN_MGM_LOG_ENTRY_SIZE;

	for (i = MLX4_MIN_MGM_LOG_ENTRY_SIZE; i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE;
	      i++) {
		if (qp_per_entry <= 4 * ((1 << i) / 16 - 2))
			break;
	}

	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
}

static const char *dmfs_high_rate_steering_mode_str(int dmfs_high_steer_mode)
{
	switch (dmfs_high_steer_mode) {
	case MLX4_STEERING_DMFS_A0_DEFAULT:
		return "default performance";

	case MLX4_STEERING_DMFS_A0_DYNAMIC:
		return "dynamic hybrid mode";

	case MLX4_STEERING_DMFS_A0_STATIC:
		return "performance optimized for limited rule configuration (static)";

	case MLX4_STEERING_DMFS_A0_DISABLE:
		return "disabled performance optimized steering";

	case MLX4_STEERING_DMFS_A0_NOT_SUPPORTED:
		return "performance optimized steering not supported";

	default:
		return "Unrecognized mode";
	}
}

#define MLX4_DMFS_A0_STEERING			(1UL << 2)

static void choose_steering_mode(struct mlx4_dev *dev,
				 struct mlx4_dev_cap *dev_cap)
{
	if (mlx4_log_num_mgm_entry_size <= 0) {
		if ((-mlx4_log_num_mgm_entry_size) & MLX4_DMFS_A0_STEERING) {
			if (dev->caps.dmfs_high_steer_mode ==
			    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
				mlx4_err(dev, "DMFS high rate mode not supported\n");
			else
				dev->caps.dmfs_high_steer_mode =
					MLX4_STEERING_DMFS_A0_STATIC;
		}
	}

	if (mlx4_log_num_mgm_entry_size <= 0 &&
	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
	    (!mlx4_is_mfunc(dev) ||
	     (dev_cap->fs_max_num_qp_per_entry >=
	     (dev->persist->num_vfs + 1))) &&
	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
		dev->oper_log_mgm_entry_size =
			choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry);
		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
		dev->caps.fs_log_max_ucast_qp_range_size =
			dev_cap->fs_log_max_ucast_qp_range_size;
	} else {
		if (dev->caps.dmfs_high_steer_mode !=
		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
			dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DISABLE;
		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
		else {
			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;

			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags set to use B0 steering - falling back to A0 steering mode\n");
		}
		dev->oper_log_mgm_entry_size =
			mlx4_log_num_mgm_entry_size > 0 ?
			mlx4_log_num_mgm_entry_size :
			MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
	}
	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, modparam log_num_mgm_entry_size = %d\n",
		 mlx4_steering_mode_str(dev->caps.steering_mode),
		 dev->oper_log_mgm_entry_size,
		 mlx4_log_num_mgm_entry_size);
}

static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
				       struct mlx4_dev_cap *dev_cap)
{
	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED &&
	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN;
	else
		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE;

	mlx4_dbg(dev, "Tunneling offload mode is: %s\n",  (dev->caps.tunnel_offload_mode
		 == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none");
}

static int mlx4_validate_optimized_steering(struct mlx4_dev *dev)
{
	int i;
	struct mlx4_port_cap port_cap;

	if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
		return -EINVAL;

	for (i = 1; i <= dev->caps.num_ports; i++) {
		if (mlx4_dev_port(dev, i, &port_cap)) {
			mlx4_err(dev,
				 "QUERY_DEV_CAP command failed, can't veify DMFS high rate steering.\n");
		} else if ((dev->caps.dmfs_high_steer_mode !=
			    MLX4_STEERING_DMFS_A0_DEFAULT) &&
			   (port_cap.dmfs_optimized_state ==
			    !!(dev->caps.dmfs_high_steer_mode ==
			    MLX4_STEERING_DMFS_A0_DISABLE))) {
			mlx4_err(dev,
				 "DMFS high rate steer mode differ, driver requested %s but %s in FW.\n",
				 dmfs_high_rate_steering_mode_str(
					dev->caps.dmfs_high_steer_mode),
				 (port_cap.dmfs_optimized_state ?
					"enabled" : "disabled"));
		}
	}

	return 0;
}

static int mlx4_init_fw(struct mlx4_dev *dev)
{
	struct mlx4_mod_stat_cfg   mlx4_cfg;
	int err = 0;

	if (!mlx4_is_slave(dev)) {
		err = mlx4_QUERY_FW(dev);
		if (err) {
			if (err == -EACCES)
				mlx4_info(dev, "non-primary physical function, skipping\n");
			else
				mlx4_err(dev, "QUERY_FW command failed, aborting\n");
			return err;
		}

		err = mlx4_load_fw(dev);
		if (err) {
			mlx4_err(dev, "Failed to start FW, aborting\n");
			return err;
		}

		mlx4_cfg.log_pg_sz_m = 1;
		mlx4_cfg.log_pg_sz = 0;
		err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
		if (err)
			mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");
	}

	return err;
}

static int mlx4_init_hca(struct mlx4_dev *dev)
{
	struct mlx4_priv	  *priv = mlx4_priv(dev);
	struct mlx4_adapter	   adapter;
	struct mlx4_dev_cap	   dev_cap;
	struct mlx4_profile	   profile;
	struct mlx4_init_hca_param init_hca;
	u64 icm_size;
	struct mlx4_config_dev_params params;
	int err;

	if (!mlx4_is_slave(dev)) {
		err = mlx4_dev_cap(dev, &dev_cap);
		if (err) {
			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
			return err;
		}

		choose_steering_mode(dev, &dev_cap);
		choose_tunnel_offload_mode(dev, &dev_cap);

		if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC &&
		    mlx4_is_master(dev))
			dev->caps.function_caps |= MLX4_FUNC_CAP_DMFS_A0_STATIC;

		err = mlx4_get_phys_port_id(dev);
		if (err)
			mlx4_err(dev, "Fail to get physical port id\n");

		if (mlx4_is_master(dev))
			mlx4_parav_master_pf_caps(dev);

		if (mlx4_low_memory_profile()) {
			mlx4_info(dev, "Running from within kdump kernel. Using low memory profile\n");
			profile = low_mem_profile;
		} else {
			profile = default_profile;
		}
		if (dev->caps.steering_mode ==
		    MLX4_STEERING_MODE_DEVICE_MANAGED)
			profile.num_mcg = MLX4_FS_NUM_MCG;

		icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
					     &init_hca);
		if ((long long) icm_size < 0) {
			err = icm_size;
			return err;
		}

		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;

		/* Always set UAR page size 4KB, set log_uar_sz accordingly */
		init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
				      PAGE_SHIFT -
				      DEFAULT_UAR_PAGE_SHIFT;
		init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;

		init_hca.mw_enabled = 0;
		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
		    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
			init_hca.mw_enabled = INIT_HCA_TPT_MW_ENABLE;

		err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
		if (err)
			return err;

		err = mlx4_INIT_HCA(dev, &init_hca);
		if (err) {
			mlx4_err(dev, "INIT_HCA command failed, aborting\n");
			goto err_free_icm;
		}

		if (dev_cap.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) {
			err = mlx4_query_func(dev, &dev_cap);
			if (err < 0) {
				mlx4_err(dev, "QUERY_FUNC command failed, aborting.\n");
				goto err_close;
			} else if (err & MLX4_QUERY_FUNC_NUM_SYS_EQS) {
				dev->caps.num_eqs = dev_cap.max_eqs;
				dev->caps.reserved_eqs = dev_cap.reserved_eqs;
				dev->caps.reserved_uars = dev_cap.reserved_uars;
			}
		}

		/*
		 * If TS is supported by FW
		 * read HCA frequency by QUERY_HCA command
		 */
		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) {
			memset(&init_hca, 0, sizeof(init_hca));
			err = mlx4_QUERY_HCA(dev, &init_hca);
			if (err) {
				mlx4_err(dev, "QUERY_HCA command failed, disable timestamp\n");
				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
			} else {
				dev->caps.hca_core_clock =
					init_hca.hca_core_clock;
			}

			/* In case we got HCA frequency 0 - disable timestamping
			 * to avoid dividing by zero
			 */
			if (!dev->caps.hca_core_clock) {
				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
				mlx4_err(dev,
					 "HCA frequency is 0 - timestamping is not supported\n");
			} else if (map_internal_clock(dev)) {
				/*
				 * Map internal clock,
				 * in case of failure disable timestamping
				 */
				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
				mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n");
			}
		}

		if (dev->caps.dmfs_high_steer_mode !=
		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED) {
			if (mlx4_validate_optimized_steering(dev))
				mlx4_warn(dev, "Optimized steering validation failed\n");

			if (dev->caps.dmfs_high_steer_mode ==
			    MLX4_STEERING_DMFS_A0_DISABLE) {
				dev->caps.dmfs_high_rate_qpn_base =
					dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
				dev->caps.dmfs_high_rate_qpn_range =
					MLX4_A0_STEERING_TABLE_SIZE;
			}

			mlx4_dbg(dev, "DMFS high rate steer mode is: %s\n",
				 dmfs_high_rate_steering_mode_str(
					dev->caps.dmfs_high_steer_mode));
		}
	} else {
		err = mlx4_init_slave(dev);
		if (err) {
			if (err != -EPROBE_DEFER)
				mlx4_err(dev, "Failed to initialize slave\n");
			return err;
		}

		err = mlx4_slave_cap(dev);
		if (err) {
			mlx4_err(dev, "Failed to obtain slave caps\n");
			goto err_close;
		}
	}

	if (map_bf_area(dev))
		mlx4_dbg(dev, "Failed to map blue flame area\n");

	/*Only the master set the ports, all the rest got it from it.*/
	if (!mlx4_is_slave(dev))
		mlx4_set_port_mask(dev);

	err = mlx4_QUERY_ADAPTER(dev, &adapter);
	if (err) {
		mlx4_err(dev, "QUERY_ADAPTER command failed, aborting\n");
		goto unmap_bf;
	}

	/* Query CONFIG_DEV parameters */
	err = mlx4_config_dev_retrieval(dev, &params);
	if (err && err != -ENOTSUPP) {
		mlx4_err(dev, "Failed to query CONFIG_DEV parameters\n");
	} else if (!err) {
		dev->caps.rx_checksum_flags_port[1] = params.rx_csum_flags_port_1;
		dev->caps.rx_checksum_flags_port[2] = params.rx_csum_flags_port_2;
	}
	priv->eq_table.inta_pin = adapter.inta_pin;
	memcpy(dev->board_id, adapter.board_id, sizeof dev->board_id);

	return 0;

unmap_bf:
	unmap_internal_clock(dev);
	unmap_bf_area(dev);

	if (mlx4_is_slave(dev)) {
		kfree(dev->caps.qp0_qkey);
		kfree(dev->caps.qp0_tunnel);
		kfree(dev->caps.qp0_proxy);
		kfree(dev->caps.qp1_tunnel);
		kfree(dev->caps.qp1_proxy);
	}

err_close:
	if (mlx4_is_slave(dev))
		mlx4_slave_exit(dev);
	else
		mlx4_CLOSE_HCA(dev, 0);

err_free_icm:
	if (!mlx4_is_slave(dev))
		mlx4_free_icms(dev);

	return err;
}

static int mlx4_init_counters_table(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int nent_pow2;

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return -ENOENT;

	if (!dev->caps.max_counters)
		return -ENOSPC;

	nent_pow2 = roundup_pow_of_two(dev->caps.max_counters);
	/* reserve last counter index for sink counter */
	return mlx4_bitmap_init(&priv->counters_bitmap, nent_pow2,
				nent_pow2 - 1, 0,
				nent_pow2 - dev->caps.max_counters + 1);
}

static void mlx4_cleanup_counters_table(struct mlx4_dev *dev)
{
	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return;

	if (!dev->caps.max_counters)
		return;

	mlx4_bitmap_cleanup(&mlx4_priv(dev)->counters_bitmap);
}

static void mlx4_cleanup_default_counters(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int port;

	for (port = 0; port < dev->caps.num_ports; port++)
		if (priv->def_counter[port] != -1)
			mlx4_counter_free(dev,  priv->def_counter[port]);
}

static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int port, err = 0;
	u32 idx;

	for (port = 0; port < dev->caps.num_ports; port++)
		priv->def_counter[port] = -1;

	for (port = 0; port < dev->caps.num_ports; port++) {
		err = mlx4_counter_alloc(dev, &idx);

		if (!err || err == -ENOSPC) {
			priv->def_counter[port] = idx;
		} else if (err == -ENOENT) {
			err = 0;
			continue;
		} else if (mlx4_is_slave(dev) && err == -EINVAL) {
			priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
			mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
				  MLX4_SINK_COUNTER_INDEX(dev));
			err = 0;
		} else {
			mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
				 __func__, port + 1, err);
			mlx4_cleanup_default_counters(dev);
			return err;
		}

		mlx4_dbg(dev, "%s: default counter index %d for port %d\n",
			 __func__, priv->def_counter[port], port + 1);
	}

	return err;
}

int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return -ENOENT;

	*idx = mlx4_bitmap_alloc(&priv->counters_bitmap);
	if (*idx == -1) {
		*idx = MLX4_SINK_COUNTER_INDEX(dev);
		return -ENOSPC;
	}

	return 0;
}

int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
{
	u64 out_param;
	int err;

	if (mlx4_is_mfunc(dev)) {
		err = mlx4_cmd_imm(dev, 0, &out_param, RES_COUNTER,
				   RES_OP_RESERVE, MLX4_CMD_ALLOC_RES,
				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
		if (!err)
			*idx = get_param_l(&out_param);

		return err;
	}
	return __mlx4_counter_alloc(dev, idx);
}
EXPORT_SYMBOL_GPL(mlx4_counter_alloc);

static int __mlx4_clear_if_stat(struct mlx4_dev *dev,
				u8 counter_index)
{
	struct mlx4_cmd_mailbox *if_stat_mailbox;
	int err;
	u32 if_stat_in_mod = (counter_index & 0xff) | MLX4_QUERY_IF_STAT_RESET;

	if_stat_mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(if_stat_mailbox))
		return PTR_ERR(if_stat_mailbox);

	err = mlx4_cmd_box(dev, 0, if_stat_mailbox->dma, if_stat_in_mod, 0,
			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
			   MLX4_CMD_NATIVE);

	mlx4_free_cmd_mailbox(dev, if_stat_mailbox);
	return err;
}

void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
{
	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return;

	if (idx == MLX4_SINK_COUNTER_INDEX(dev))
		return;

	__mlx4_clear_if_stat(dev, idx);

	mlx4_bitmap_free(&mlx4_priv(dev)->counters_bitmap, idx, MLX4_USE_RR);
	return;
}

void mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
{
	u64 in_param = 0;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&in_param, idx);
		mlx4_cmd(dev, in_param, RES_COUNTER, RES_OP_RESERVE,
			 MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
			 MLX4_CMD_WRAPPED);
		return;
	}
	__mlx4_counter_free(dev, idx);
}
EXPORT_SYMBOL_GPL(mlx4_counter_free);

int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	return priv->def_counter[port - 1];
}
EXPORT_SYMBOL_GPL(mlx4_get_default_counter_index);

void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
}
EXPORT_SYMBOL_GPL(mlx4_set_admin_guid);

__be64 mlx4_get_admin_guid(struct mlx4_dev *dev, int entry, int port)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	return priv->mfunc.master.vf_admin[entry].vport[port].guid;
}
EXPORT_SYMBOL_GPL(mlx4_get_admin_guid);

void mlx4_set_random_admin_guid(struct mlx4_dev *dev, int entry, int port)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	__be64 guid;

	/* hw GUID */
	if (entry == 0)
		return;

	get_random_bytes((char *)&guid, sizeof(guid));
	guid &= ~(cpu_to_be64(1ULL << 56));
	guid |= cpu_to_be64(1ULL << 57);
	priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
}

static int mlx4_setup_hca(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;
	int port;
	__be32 ib_port_default_caps;

	err = mlx4_init_uar_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize user access region table, aborting\n");
		 return err;
	}

	err = mlx4_uar_alloc(dev, &priv->driver_uar);
	if (err) {
		mlx4_err(dev, "Failed to allocate driver access region, aborting\n");
		goto err_uar_table_free;
	}

	priv->kar = ioremap((phys_addr_t) priv->driver_uar.pfn << PAGE_SHIFT, PAGE_SIZE);
	if (!priv->kar) {
		mlx4_err(dev, "Couldn't map kernel access region, aborting\n");
		err = -ENOMEM;
		goto err_uar_free;
	}

	err = mlx4_init_pd_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize protection domain table, aborting\n");
		goto err_kar_unmap;
	}

	err = mlx4_init_xrcd_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize reliable connection domain table, aborting\n");
		goto err_pd_table_free;
	}

	err = mlx4_init_mr_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize memory region table, aborting\n");
		goto err_xrcd_table_free;
	}

	if (!mlx4_is_slave(dev)) {
		err = mlx4_init_mcg_table(dev);
		if (err) {
			mlx4_err(dev, "Failed to initialize multicast group table, aborting\n");
			goto err_mr_table_free;
		}
		err = mlx4_config_mad_demux(dev);
		if (err) {
			mlx4_err(dev, "Failed in config_mad_demux, aborting\n");
			goto err_mcg_table_free;
		}
	}

	err = mlx4_init_eq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize event queue table, aborting\n");
		goto err_mcg_table_free;
	}

	err = mlx4_cmd_use_events(dev);
	if (err) {
		mlx4_err(dev, "Failed to switch to event-driven firmware commands, aborting\n");
		goto err_eq_table_free;
	}

	err = mlx4_NOP(dev);
	if (err) {
		if (dev->flags & MLX4_FLAG_MSI_X) {
			mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n",
				  priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
			mlx4_warn(dev, "Trying again without MSI-X\n");
		} else {
			mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n",
				 priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
			mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n");
		}

		goto err_cmd_poll;
	}

	mlx4_dbg(dev, "NOP command IRQ test passed\n");

	err = mlx4_init_cq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize completion queue table, aborting\n");
		goto err_cmd_poll;
	}

	err = mlx4_init_srq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize shared receive queue table, aborting\n");
		goto err_cq_table_free;
	}

	err = mlx4_init_qp_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize queue pair table, aborting\n");
		goto err_srq_table_free;
	}

	if (!mlx4_is_slave(dev)) {
		err = mlx4_init_counters_table(dev);
		if (err && err != -ENOENT) {
			mlx4_err(dev, "Failed to initialize counters table, aborting\n");
			goto err_qp_table_free;
		}
	}

	err = mlx4_allocate_default_counters(dev);
	if (err) {
		mlx4_err(dev, "Failed to allocate default counters, aborting\n");
		goto err_counters_table_free;
	}

	if (!mlx4_is_slave(dev)) {
		for (port = 1; port <= dev->caps.num_ports; port++) {
			ib_port_default_caps = 0;
			err = mlx4_get_port_ib_caps(dev, port,
						    &ib_port_default_caps);
			if (err)
				mlx4_warn(dev, "failed to get port %d default ib capabilities (%d). Continuing with caps = 0\n",
					  port, err);
			dev->caps.ib_port_def_cap[port] = ib_port_default_caps;

			/* initialize per-slave default ib port capabilities */
			if (mlx4_is_master(dev)) {
				int i;
				for (i = 0; i < dev->num_slaves; i++) {
					if (i == mlx4_master_func_num(dev))
						continue;
					priv->mfunc.master.slave_state[i].ib_cap_mask[port] =
						ib_port_default_caps;
				}
			}

			if (mlx4_is_mfunc(dev))
				dev->caps.port_ib_mtu[port] = IB_MTU_2048;
			else
				dev->caps.port_ib_mtu[port] = IB_MTU_4096;

			err = mlx4_SET_PORT(dev, port, mlx4_is_master(dev) ?
					    dev->caps.pkey_table_len[port] : -1);
			if (err) {
				mlx4_err(dev, "Failed to set port %d, aborting\n",
					 port);
				goto err_default_countes_free;
			}
		}
	}

	return 0;

err_default_countes_free:
	mlx4_cleanup_default_counters(dev);

err_counters_table_free:
	if (!mlx4_is_slave(dev))
		mlx4_cleanup_counters_table(dev);

err_qp_table_free:
	mlx4_cleanup_qp_table(dev);

err_srq_table_free:
	mlx4_cleanup_srq_table(dev);

err_cq_table_free:
	mlx4_cleanup_cq_table(dev);

err_cmd_poll:
	mlx4_cmd_use_polling(dev);

err_eq_table_free:
	mlx4_cleanup_eq_table(dev);

err_mcg_table_free:
	if (!mlx4_is_slave(dev))
		mlx4_cleanup_mcg_table(dev);

err_mr_table_free:
	mlx4_cleanup_mr_table(dev);

err_xrcd_table_free:
	mlx4_cleanup_xrcd_table(dev);

err_pd_table_free:
	mlx4_cleanup_pd_table(dev);

err_kar_unmap:
	iounmap(priv->kar);

err_uar_free:
	mlx4_uar_free(dev, &priv->driver_uar);

err_uar_table_free:
	mlx4_cleanup_uar_table(dev);
	return err;
}

static int mlx4_init_affinity_hint(struct mlx4_dev *dev, int port, int eqn)
{
	int requested_cpu = 0;
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_eq *eq;
	int off = 0;
	int i;

	if (eqn > dev->caps.num_comp_vectors)
		return -EINVAL;

	for (i = 1; i < port; i++)
		off += mlx4_get_eqs_per_port(dev, i);

	requested_cpu = eqn - off - !!(eqn > MLX4_EQ_ASYNC);

	/* Meaning EQs are shared, and this call comes from the second port */
	if (requested_cpu < 0)
		return 0;

	eq = &priv->eq_table.eq[eqn];

	if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL))
		return -ENOMEM;

	cpumask_set_cpu(requested_cpu, eq->affinity_mask);

	return 0;
}

static void mlx4_enable_msi_x(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct msix_entry *entries;
	int i;
	int port = 0;

	if (msi_x) {
		int nreq = dev->caps.num_ports * num_online_cpus() + 1;

		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
			     nreq);
		if (nreq > MAX_MSIX)
			nreq = MAX_MSIX;

		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
		if (!entries)
			goto no_msi;

		for (i = 0; i < nreq; ++i)
			entries[i].entry = i;

		nreq = pci_enable_msix_range(dev->persist->pdev, entries, 2,
					     nreq);

		if (nreq < 0 || nreq < MLX4_EQ_ASYNC) {
			kfree(entries);
			goto no_msi;
		}
		/* 1 is reserved for events (asyncrounous EQ) */
		dev->caps.num_comp_vectors = nreq - 1;

		priv->eq_table.eq[MLX4_EQ_ASYNC].irq = entries[0].vector;
		bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
			    dev->caps.num_ports);

		for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
			if (i == MLX4_EQ_ASYNC)
				continue;

			priv->eq_table.eq[i].irq =
				entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;

			if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
				bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
					    dev->caps.num_ports);
				/* We don't set affinity hint when there
				 * aren't enough EQs
				 */
			} else {
				set_bit(port,
					priv->eq_table.eq[i].actv_ports.ports);
				if (mlx4_init_affinity_hint(dev, port + 1, i))
					mlx4_warn(dev, "Couldn't init hint cpumask for EQ %d\n",
						  i);
			}
			/* We divide the Eqs evenly between the two ports.
			 * (dev->caps.num_comp_vectors / dev->caps.num_ports)
			 * refers to the number of Eqs per port
			 * (i.e eqs_per_port). Theoretically, we would like to
			 * write something like (i + 1) % eqs_per_port == 0.
			 * However, since there's an asynchronous Eq, we have
			 * to skip over it by comparing this condition to
			 * !!((i + 1) > MLX4_EQ_ASYNC).
			 */
			if ((dev->caps.num_comp_vectors > dev->caps.num_ports) &&
			    ((i + 1) %
			     (dev->caps.num_comp_vectors / dev->caps.num_ports)) ==
			    !!((i + 1) > MLX4_EQ_ASYNC))
				/* If dev->caps.num_comp_vectors < dev->caps.num_ports,
				 * everything is shared anyway.
				 */
				port++;
		}

		dev->flags |= MLX4_FLAG_MSI_X;

		kfree(entries);
		return;
	}

no_msi:
	dev->caps.num_comp_vectors = 1;

	BUG_ON(MLX4_EQ_ASYNC >= 2);
	for (i = 0; i < 2; ++i) {
		priv->eq_table.eq[i].irq = dev->persist->pdev->irq;
		if (i != MLX4_EQ_ASYNC) {
			bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
				    dev->caps.num_ports);
		}
	}
}

static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
{
	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
	int err = 0;

	info->dev = dev;
	info->port = port;
	if (!mlx4_is_slave(dev)) {
		mlx4_init_mac_table(dev, &info->mac_table);
		mlx4_init_vlan_table(dev, &info->vlan_table);
		mlx4_init_roce_gid_table(dev, &info->gid_table);
		info->base_qpn = mlx4_get_base_qpn(dev, port);
	}

	sprintf(info->dev_name, "mlx4_port%d", port);
	info->port_attr.attr.name = info->dev_name;
	if (mlx4_is_mfunc(dev))
		info->port_attr.attr.mode = S_IRUGO;
	else {
		info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
		info->port_attr.store     = set_port_type;
	}
	info->port_attr.show      = show_port_type;
	sysfs_attr_init(&info->port_attr.attr);

	err = device_create_file(&dev->persist->pdev->dev, &info->port_attr);
	if (err) {
		mlx4_err(dev, "Failed to create file for port %d\n", port);
		info->port = -1;
	}

	sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
	info->port_mtu_attr.attr.name = info->dev_mtu_name;
	if (mlx4_is_mfunc(dev))
		info->port_mtu_attr.attr.mode = S_IRUGO;
	else {
		info->port_mtu_attr.attr.mode = S_IRUGO | S_IWUSR;
		info->port_mtu_attr.store     = set_port_ib_mtu;
	}
	info->port_mtu_attr.show      = show_port_ib_mtu;
	sysfs_attr_init(&info->port_mtu_attr.attr);

	err = device_create_file(&dev->persist->pdev->dev,
				 &info->port_mtu_attr);
	if (err) {
		mlx4_err(dev, "Failed to create mtu file for port %d\n", port);
		device_remove_file(&info->dev->persist->pdev->dev,
				   &info->port_attr);
		info->port = -1;
	}

	return err;
}

static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
{
	if (info->port < 0)
		return;

	device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr);
	device_remove_file(&info->dev->persist->pdev->dev,
			   &info->port_mtu_attr);
#ifdef CONFIG_RFS_ACCEL
	free_irq_cpu_rmap(info->rmap);
	info->rmap = NULL;
#endif
}

static int mlx4_init_steering(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int num_entries = dev->caps.num_ports;
	int i, j;

	priv->steer = kzalloc(sizeof(struct mlx4_steer) * num_entries, GFP_KERNEL);
	if (!priv->steer)
		return -ENOMEM;

	for (i = 0; i < num_entries; i++)
		for (j = 0; j < MLX4_NUM_STEERS; j++) {
			INIT_LIST_HEAD(&priv->steer[i].promisc_qps[j]);
			INIT_LIST_HEAD(&priv->steer[i].steer_entries[j]);
		}
	return 0;
}

static void mlx4_clear_steering(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_steer_index *entry, *tmp_entry;
	struct mlx4_promisc_qp *pqp, *tmp_pqp;
	int num_entries = dev->caps.num_ports;
	int i, j;

	for (i = 0; i < num_entries; i++) {
		for (j = 0; j < MLX4_NUM_STEERS; j++) {
			list_for_each_entry_safe(pqp, tmp_pqp,
						 &priv->steer[i].promisc_qps[j],
						 list) {
				list_del(&pqp->list);
				kfree(pqp);
			}
			list_for_each_entry_safe(entry, tmp_entry,
						 &priv->steer[i].steer_entries[j],
						 list) {
				list_del(&entry->list);
				list_for_each_entry_safe(pqp, tmp_pqp,
							 &entry->duplicates,
							 list) {
					list_del(&pqp->list);
					kfree(pqp);
				}
				kfree(entry);
			}
		}
	}
	kfree(priv->steer);
}

static int extended_func_num(struct pci_dev *pdev)
{
	return PCI_SLOT(pdev->devfn) * 8 + PCI_FUNC(pdev->devfn);
}

#define MLX4_OWNER_BASE	0x8069c
#define MLX4_OWNER_SIZE	4

static int mlx4_get_ownership(struct mlx4_dev *dev)
{
	void __iomem *owner;
	u32 ret;

	if (pci_channel_offline(dev->persist->pdev))
		return -EIO;

	owner = ioremap(pci_resource_start(dev->persist->pdev, 0) +
			MLX4_OWNER_BASE,
			MLX4_OWNER_SIZE);
	if (!owner) {
		mlx4_err(dev, "Failed to obtain ownership bit\n");
		return -ENOMEM;
	}

	ret = readl(owner);
	iounmap(owner);
	return (int) !!ret;
}

static void mlx4_free_ownership(struct mlx4_dev *dev)
{
	void __iomem *owner;

	if (pci_channel_offline(dev->persist->pdev))
		return;

	owner = ioremap(pci_resource_start(dev->persist->pdev, 0) +
			MLX4_OWNER_BASE,
			MLX4_OWNER_SIZE);
	if (!owner) {
		mlx4_err(dev, "Failed to obtain ownership bit\n");
		return;
	}
	writel(0, owner);
	msleep(1000);
	iounmap(owner);
}

#define SRIOV_VALID_STATE(flags) (!!((flags) & MLX4_FLAG_SRIOV)	==\
				  !!((flags) & MLX4_FLAG_MASTER))

static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
			     u8 total_vfs, int existing_vfs, int reset_flow)
{
	u64 dev_flags = dev->flags;
	int err = 0;
	int fw_enabled_sriov_vfs = min(pci_sriov_get_totalvfs(pdev),
					MLX4_MAX_NUM_VF);

	if (reset_flow) {
		dev->dev_vfs = kcalloc(total_vfs, sizeof(*dev->dev_vfs),
				       GFP_KERNEL);
		if (!dev->dev_vfs)
			goto free_mem;
		return dev_flags;
	}

	atomic_inc(&pf_loading);
	if (dev->flags &  MLX4_FLAG_SRIOV) {
		if (existing_vfs != total_vfs) {
			mlx4_err(dev, "SR-IOV was already enabled, but with num_vfs (%d) different than requested (%d)\n",
				 existing_vfs, total_vfs);
			total_vfs = existing_vfs;
		}
	}

	dev->dev_vfs = kzalloc(total_vfs * sizeof(*dev->dev_vfs), GFP_KERNEL);
	if (NULL == dev->dev_vfs) {
		mlx4_err(dev, "Failed to allocate memory for VFs\n");
		goto disable_sriov;
	}

	if (!(dev->flags &  MLX4_FLAG_SRIOV)) {
		if (total_vfs > fw_enabled_sriov_vfs) {
			mlx4_err(dev, "requested vfs (%d) > available vfs (%d). Continuing without SR_IOV\n",
				 total_vfs, fw_enabled_sriov_vfs);
			err = -ENOMEM;
			goto disable_sriov;
		}
		mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", total_vfs);
		err = pci_enable_sriov(pdev, total_vfs);
	}
	if (err) {
		mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d)\n",
			 err);
		goto disable_sriov;
	} else {
		mlx4_warn(dev, "Running in master mode\n");
		dev_flags |= MLX4_FLAG_SRIOV |
			MLX4_FLAG_MASTER;
		dev_flags &= ~MLX4_FLAG_SLAVE;
		dev->persist->num_vfs = total_vfs;
	}
	return dev_flags;

disable_sriov:
	atomic_dec(&pf_loading);
free_mem:
	dev->persist->num_vfs = 0;
	kfree(dev->dev_vfs);
        dev->dev_vfs = NULL;
	return dev_flags & ~MLX4_FLAG_MASTER;
}

enum {
	MLX4_DEV_CAP_CHECK_NUM_VFS_ABOVE_64 = -1,
};

static int mlx4_check_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
			      int *nvfs)
{
	int requested_vfs = nvfs[0] + nvfs[1] + nvfs[2];
	/* Checking for 64 VFs as a limitation of CX2 */
	if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_80_VFS) &&
	    requested_vfs >= 64) {
		mlx4_err(dev, "Requested %d VFs, but FW does not support more than 64\n",
			 requested_vfs);
		return MLX4_DEV_CAP_CHECK_NUM_VFS_ABOVE_64;
	}
	return 0;
}

static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
			 int total_vfs, int *nvfs, struct mlx4_priv *priv,
			 int reset_flow)
{
	struct mlx4_dev *dev;
	unsigned sum = 0;
	int err;
	int port;
	int i;
	struct mlx4_dev_cap *dev_cap = NULL;
	int existing_vfs = 0;

	dev = &priv->dev;

	INIT_LIST_HEAD(&priv->ctx_list);
	spin_lock_init(&priv->ctx_lock);

	mutex_init(&priv->port_mutex);
	mutex_init(&priv->bond_mutex);

	INIT_LIST_HEAD(&priv->pgdir_list);
	mutex_init(&priv->pgdir_mutex);

	INIT_LIST_HEAD(&priv->bf_list);
	mutex_init(&priv->bf_mutex);

	dev->rev_id = pdev->revision;
	dev->numa_node = dev_to_node(&pdev->dev);

	/* Detect if this device is a virtual function */
	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
		mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
		dev->flags |= MLX4_FLAG_SLAVE;
	} else {
		/* We reset the device and enable SRIOV only for physical
		 * devices.  Try to claim ownership on the device;
		 * if already taken, skip -- do not allow multiple PFs */
		err = mlx4_get_ownership(dev);
		if (err) {
			if (err < 0)
				return err;
			else {
				mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n");
				return -EINVAL;
			}
		}

		atomic_set(&priv->opreq_count, 0);
		INIT_WORK(&priv->opreq_task, mlx4_opreq_action);

		/*
		 * Now reset the HCA before we touch the PCI capabilities or
		 * attempt a firmware command, since a boot ROM may have left
		 * the HCA in an undefined state.
		 */
		err = mlx4_reset(dev);
		if (err) {
			mlx4_err(dev, "Failed to reset HCA, aborting\n");
			goto err_sriov;
		}

		if (total_vfs) {
			dev->flags = MLX4_FLAG_MASTER;
			existing_vfs = pci_num_vf(pdev);
			if (existing_vfs)
				dev->flags |= MLX4_FLAG_SRIOV;
			dev->persist->num_vfs = total_vfs;
		}
	}

	/* on load remove any previous indication of internal error,
	 * device is up.
	 */
	dev->persist->state = MLX4_DEVICE_STATE_UP;

slave_start:
	err = mlx4_cmd_init(dev);
	if (err) {
		mlx4_err(dev, "Failed to init command interface, aborting\n");
		goto err_sriov;
	}

	/* In slave functions, the communication channel must be initialized
	 * before posting commands. Also, init num_slaves before calling
	 * mlx4_init_hca */
	if (mlx4_is_mfunc(dev)) {
		if (mlx4_is_master(dev)) {
			dev->num_slaves = MLX4_MAX_NUM_SLAVES;

		} else {
			dev->num_slaves = 0;
			err = mlx4_multi_func_init(dev);
			if (err) {
				mlx4_err(dev, "Failed to init slave mfunc interface, aborting\n");
				goto err_cmd;
			}
		}
	}

	err = mlx4_init_fw(dev);
	if (err) {
		mlx4_err(dev, "Failed to init fw, aborting.\n");
		goto err_mfunc;
	}

	if (mlx4_is_master(dev)) {
		/* when we hit the goto slave_start below, dev_cap already initialized */
		if (!dev_cap) {
			dev_cap = kzalloc(sizeof(*dev_cap), GFP_KERNEL);

			if (!dev_cap) {
				err = -ENOMEM;
				goto err_fw;
			}

			err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
			if (err) {
				mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
				goto err_fw;
			}

			if (mlx4_check_dev_cap(dev, dev_cap, nvfs))
				goto err_fw;

			if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
				u64 dev_flags = mlx4_enable_sriov(dev, pdev,
								  total_vfs,
								  existing_vfs,
								  reset_flow);

				mlx4_close_fw(dev);
				mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
				dev->flags = dev_flags;
				if (!SRIOV_VALID_STATE(dev->flags)) {
					mlx4_err(dev, "Invalid SRIOV state\n");
					goto err_sriov;
				}
				err = mlx4_reset(dev);
				if (err) {
					mlx4_err(dev, "Failed to reset HCA, aborting.\n");
					goto err_sriov;
				}
				goto slave_start;
			}
		} else {
			/* Legacy mode FW requires SRIOV to be enabled before
			 * doing QUERY_DEV_CAP, since max_eq's value is different if
			 * SRIOV is enabled.
			 */
			memset(dev_cap, 0, sizeof(*dev_cap));
			err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
			if (err) {
				mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
				goto err_fw;
			}

			if (mlx4_check_dev_cap(dev, dev_cap, nvfs))
				goto err_fw;
		}
	}

	err = mlx4_init_hca(dev);
	if (err) {
		if (err == -EACCES) {
			/* Not primary Physical function
			 * Running in slave mode */
			mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
			/* We're not a PF */
			if (dev->flags & MLX4_FLAG_SRIOV) {
				if (!existing_vfs)
					pci_disable_sriov(pdev);
				if (mlx4_is_master(dev) && !reset_flow)
					atomic_dec(&pf_loading);
				dev->flags &= ~MLX4_FLAG_SRIOV;
			}
			if (!mlx4_is_slave(dev))
				mlx4_free_ownership(dev);
			dev->flags |= MLX4_FLAG_SLAVE;
			dev->flags &= ~MLX4_FLAG_MASTER;
			goto slave_start;
		} else
			goto err_fw;
	}

	if (mlx4_is_master(dev) && (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
		u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs,
						  existing_vfs, reset_flow);

		if ((dev->flags ^ dev_flags) & (MLX4_FLAG_MASTER | MLX4_FLAG_SLAVE)) {
			mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_VHCR);
			dev->flags = dev_flags;
			err = mlx4_cmd_init(dev);
			if (err) {
				/* Only VHCR is cleaned up, so could still
				 * send FW commands
				 */
				mlx4_err(dev, "Failed to init VHCR command interface, aborting\n");
				goto err_close;
			}
		} else {
			dev->flags = dev_flags;
		}

		if (!SRIOV_VALID_STATE(dev->flags)) {
			mlx4_err(dev, "Invalid SRIOV state\n");
			goto err_close;
		}
	}

	/* check if the device is functioning at its maximum possible speed.
	 * No return code for this call, just warn the user in case of PCI
	 * express device capabilities are under-satisfied by the bus.
	 */
	if (!mlx4_is_slave(dev))
		mlx4_check_pcie_caps(dev);

	/* In master functions, the communication channel must be initialized
	 * after obtaining its address from fw */
	if (mlx4_is_master(dev)) {
		if (dev->caps.num_ports < 2 &&
		    num_vfs_argc > 1) {
			err = -EINVAL;
			mlx4_err(dev,
				 "Error: Trying to configure VFs on port 2, but HCA has only %d physical ports\n",
				 dev->caps.num_ports);
			goto err_close;
		}
		memcpy(dev->persist->nvfs, nvfs, sizeof(dev->persist->nvfs));

		for (i = 0;
		     i < sizeof(dev->persist->nvfs)/
		     sizeof(dev->persist->nvfs[0]); i++) {
			unsigned j;

			for (j = 0; j < dev->persist->nvfs[i]; ++sum, ++j) {
				dev->dev_vfs[sum].min_port = i < 2 ? i + 1 : 1;
				dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
					dev->caps.num_ports;
			}
		}

		/* In master functions, the communication channel
		 * must be initialized after obtaining its address from fw
		 */
		err = mlx4_multi_func_init(dev);
		if (err) {
			mlx4_err(dev, "Failed to init master mfunc interface, aborting.\n");
			goto err_close;
		}
	}

	err = mlx4_alloc_eq_table(dev);
	if (err)
		goto err_master_mfunc;

	bitmap_zero(priv->msix_ctl.pool_bm, MAX_MSIX);
	mutex_init(&priv->msix_ctl.pool_lock);

	mlx4_enable_msi_x(dev);
	if ((mlx4_is_mfunc(dev)) &&
	    !(dev->flags & MLX4_FLAG_MSI_X)) {
		err = -ENOSYS;
		mlx4_err(dev, "INTx is not supported in multi-function mode, aborting\n");
		goto err_free_eq;
	}

	if (!mlx4_is_slave(dev)) {
		err = mlx4_init_steering(dev);
		if (err)
			goto err_disable_msix;
	}

	err = mlx4_setup_hca(dev);
	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X) &&
	    !mlx4_is_mfunc(dev)) {
		dev->flags &= ~MLX4_FLAG_MSI_X;
		dev->caps.num_comp_vectors = 1;
		pci_disable_msix(pdev);
		err = mlx4_setup_hca(dev);
	}

	if (err)
		goto err_steer;

	mlx4_init_quotas(dev);
	/* When PF resources are ready arm its comm channel to enable
	 * getting commands
	 */
	if (mlx4_is_master(dev)) {
		err = mlx4_ARM_COMM_CHANNEL(dev);
		if (err) {
			mlx4_err(dev, " Failed to arm comm channel eq: %x\n",
				 err);
			goto err_steer;
		}
	}

	for (port = 1; port <= dev->caps.num_ports; port++) {
		err = mlx4_init_port_info(dev, port);
		if (err)
			goto err_port;
	}

	priv->v2p.port1 = 1;
	priv->v2p.port2 = 2;

	err = mlx4_register_device(dev);
	if (err)
		goto err_port;

	mlx4_request_modules(dev);

	mlx4_sense_init(dev);
	mlx4_start_sense(dev);

	priv->removed = 0;

	if (mlx4_is_master(dev) && dev->persist->num_vfs && !reset_flow)
		atomic_dec(&pf_loading);

	kfree(dev_cap);
	return 0;

err_port:
	for (--port; port >= 1; --port)
		mlx4_cleanup_port_info(&priv->port[port]);

	mlx4_cleanup_default_counters(dev);
	if (!mlx4_is_slave(dev))
		mlx4_cleanup_counters_table(dev);
	mlx4_cleanup_qp_table(dev);
	mlx4_cleanup_srq_table(dev);
	mlx4_cleanup_cq_table(dev);
	mlx4_cmd_use_polling(dev);
	mlx4_cleanup_eq_table(dev);
	mlx4_cleanup_mcg_table(dev);
	mlx4_cleanup_mr_table(dev);
	mlx4_cleanup_xrcd_table(dev);
	mlx4_cleanup_pd_table(dev);
	mlx4_cleanup_uar_table(dev);

err_steer:
	if (!mlx4_is_slave(dev))
		mlx4_clear_steering(dev);

err_disable_msix:
	if (dev->flags & MLX4_FLAG_MSI_X)
		pci_disable_msix(pdev);

err_free_eq:
	mlx4_free_eq_table(dev);

err_master_mfunc:
	if (mlx4_is_master(dev)) {
		mlx4_free_resource_tracker(dev, RES_TR_FREE_STRUCTS_ONLY);
		mlx4_multi_func_cleanup(dev);
	}

	if (mlx4_is_slave(dev)) {
		kfree(dev->caps.qp0_qkey);
		kfree(dev->caps.qp0_tunnel);
		kfree(dev->caps.qp0_proxy);
		kfree(dev->caps.qp1_tunnel);
		kfree(dev->caps.qp1_proxy);
	}

err_close:
	mlx4_close_hca(dev);

err_fw:
	mlx4_close_fw(dev);

err_mfunc:
	if (mlx4_is_slave(dev))
		mlx4_multi_func_cleanup(dev);

err_cmd:
	mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);

err_sriov:
	if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs) {
		pci_disable_sriov(pdev);
		dev->flags &= ~MLX4_FLAG_SRIOV;
	}

	if (mlx4_is_master(dev) && dev->persist->num_vfs && !reset_flow)
		atomic_dec(&pf_loading);

	kfree(priv->dev.dev_vfs);

	if (!mlx4_is_slave(dev))
		mlx4_free_ownership(dev);

	kfree(dev_cap);
	return err;
}

static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
			   struct mlx4_priv *priv)
{
	int err;
	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
	int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0};
	const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = {
		{2, 0, 0}, {0, 1, 2}, {0, 1, 2} };
	unsigned total_vfs = 0;
	unsigned int i;

	pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));

	err = pci_enable_device(pdev);
	if (err) {
		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
		return err;
	}

	/* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS
	 * per port, we must limit the number of VFs to 63 (since their are
	 * 128 MACs)
	 */
	for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc;
	     total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) {
		nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i];
		if (nvfs[i] < 0) {
			dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n");
			err = -EINVAL;
			goto err_disable_pdev;
		}
	}
	for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc;
	     i++) {
		prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i];
		if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) {
			dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n");
			err = -EINVAL;
			goto err_disable_pdev;
		}
	}
	if (total_vfs > MLX4_MAX_NUM_VF) {
		dev_err(&pdev->dev,
			"Requested more VF's (%d) than allowed by hw (%d)\n",
			total_vfs, MLX4_MAX_NUM_VF);
		err = -EINVAL;
		goto err_disable_pdev;
	}

	for (i = 0; i < MLX4_MAX_PORTS; i++) {
		if (nvfs[i] + nvfs[2] > MLX4_MAX_NUM_VF_P_PORT) {
			dev_err(&pdev->dev,
				"Requested more VF's (%d) for port (%d) than allowed by driver (%d)\n",
				nvfs[i] + nvfs[2], i + 1,
				MLX4_MAX_NUM_VF_P_PORT);
			err = -EINVAL;
			goto err_disable_pdev;
		}
	}

	/* Check for BARs. */
	if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) &&
	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
		dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n",
			pci_dev_data, pci_resource_flags(pdev, 0));
		err = -ENODEV;
		goto err_disable_pdev;
	}
	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
		dev_err(&pdev->dev, "Missing UAR, aborting\n");
		err = -ENODEV;
		goto err_disable_pdev;
	}

	err = pci_request_regions(pdev, DRV_NAME);
	if (err) {
		dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n");
		goto err_disable_pdev;
	}

	pci_set_master(pdev);

	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
	if (err) {
		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
			goto err_release_regions;
		}
	}
	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
	if (err) {
		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n");
			goto err_release_regions;
		}
	}

	/* Allow large DMA segments, up to the firmware limit of 1 GB */
	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
	/* Detect if this device is a virtual function */
	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
		/* When acting as pf, we normally skip vfs unless explicitly
		 * requested to probe them.
		 */
		if (total_vfs) {
			unsigned vfs_offset = 0;

			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
			     vfs_offset + nvfs[i] < extended_func_num(pdev);
			     vfs_offset += nvfs[i], i++)
				;
			if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
				err = -ENODEV;
				goto err_release_regions;
			}
			if ((extended_func_num(pdev) - vfs_offset)
			    > prb_vf[i]) {
				dev_warn(&pdev->dev, "Skipping virtual function:%d\n",
					 extended_func_num(pdev));
				err = -ENODEV;
				goto err_release_regions;
			}
		}
	}

	err = mlx4_catas_init(&priv->dev);
	if (err)
		goto err_release_regions;

	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
	if (err)
		goto err_catas;

	return 0;

err_catas:
	mlx4_catas_end(&priv->dev);

err_release_regions:
	pci_release_regions(pdev);

err_disable_pdev:
	pci_disable_device(pdev);
	pci_set_drvdata(pdev, NULL);
	return err;
}

static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct mlx4_priv *priv;
	struct mlx4_dev *dev;
	int ret;

	printk_once(KERN_INFO "%s", mlx4_version);

	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (!priv)
		return -ENOMEM;

	dev       = &priv->dev;
	dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL);
	if (!dev->persist) {
		kfree(priv);
		return -ENOMEM;
	}
	dev->persist->pdev = pdev;
	dev->persist->dev = dev;
	pci_set_drvdata(pdev, dev->persist);
	priv->pci_dev_data = id->driver_data;
	mutex_init(&dev->persist->device_state_mutex);
	mutex_init(&dev->persist->interface_state_mutex);

	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
	if (ret) {
		kfree(dev->persist);
		kfree(priv);
	} else {
		pci_save_state(pdev);
	}

	return ret;
}

static void mlx4_clean_dev(struct mlx4_dev *dev)
{
	struct mlx4_dev_persistent *persist = dev->persist;
	struct mlx4_priv *priv = mlx4_priv(dev);
	unsigned long	flags = (dev->flags & RESET_PERSIST_MASK_FLAGS);

	memset(priv, 0, sizeof(*priv));
	priv->dev.persist = persist;
	priv->dev.flags = flags;
}

static void mlx4_unload_one(struct pci_dev *pdev)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
	struct mlx4_dev  *dev  = persist->dev;
	struct mlx4_priv *priv = mlx4_priv(dev);
	int               pci_dev_data;
	int p, i;

	if (priv->removed)
		return;

	/* saving current ports type for further use */
	for (i = 0; i < dev->caps.num_ports; i++) {
		dev->persist->curr_port_type[i] = dev->caps.port_type[i + 1];
		dev->persist->curr_port_poss_type[i] = dev->caps.
						       possible_type[i + 1];
	}

	pci_dev_data = priv->pci_dev_data;

	mlx4_stop_sense(dev);
	mlx4_unregister_device(dev);

	for (p = 1; p <= dev->caps.num_ports; p++) {
		mlx4_cleanup_port_info(&priv->port[p]);
		mlx4_CLOSE_PORT(dev, p);
	}

	if (mlx4_is_master(dev))
		mlx4_free_resource_tracker(dev,
					   RES_TR_FREE_SLAVES_ONLY);

	mlx4_cleanup_default_counters(dev);
	if (!mlx4_is_slave(dev))
		mlx4_cleanup_counters_table(dev);
	mlx4_cleanup_qp_table(dev);
	mlx4_cleanup_srq_table(dev);
	mlx4_cleanup_cq_table(dev);
	mlx4_cmd_use_polling(dev);
	mlx4_cleanup_eq_table(dev);
	mlx4_cleanup_mcg_table(dev);
	mlx4_cleanup_mr_table(dev);
	mlx4_cleanup_xrcd_table(dev);
	mlx4_cleanup_pd_table(dev);

	if (mlx4_is_master(dev))
		mlx4_free_resource_tracker(dev,
					   RES_TR_FREE_STRUCTS_ONLY);

	iounmap(priv->kar);
	mlx4_uar_free(dev, &priv->driver_uar);
	mlx4_cleanup_uar_table(dev);
	if (!mlx4_is_slave(dev))
		mlx4_clear_steering(dev);
	mlx4_free_eq_table(dev);
	if (mlx4_is_master(dev))
		mlx4_multi_func_cleanup(dev);
	mlx4_close_hca(dev);
	mlx4_close_fw(dev);
	if (mlx4_is_slave(dev))
		mlx4_multi_func_cleanup(dev);
	mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);

	if (dev->flags & MLX4_FLAG_MSI_X)
		pci_disable_msix(pdev);

	if (!mlx4_is_slave(dev))
		mlx4_free_ownership(dev);

	kfree(dev->caps.qp0_qkey);
	kfree(dev->caps.qp0_tunnel);
	kfree(dev->caps.qp0_proxy);
	kfree(dev->caps.qp1_tunnel);
	kfree(dev->caps.qp1_proxy);
	kfree(dev->dev_vfs);

	mlx4_clean_dev(dev);
	priv->pci_dev_data = pci_dev_data;
	priv->removed = 1;
}

static void mlx4_remove_one(struct pci_dev *pdev)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
	struct mlx4_dev  *dev  = persist->dev;
	struct mlx4_priv *priv = mlx4_priv(dev);
	int active_vfs = 0;

	mutex_lock(&persist->interface_state_mutex);
	persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
	mutex_unlock(&persist->interface_state_mutex);

	/* Disabling SR-IOV is not allowed while there are active vf's */
	if (mlx4_is_master(dev) && dev->flags & MLX4_FLAG_SRIOV) {
		active_vfs = mlx4_how_many_lives_vf(dev);
		if (active_vfs) {
			pr_warn("Removing PF when there are active VF's !!\n");
			pr_warn("Will not disable SR-IOV.\n");
		}
	}

	/* device marked to be under deletion running now without the lock
	 * letting other tasks to be terminated
	 */
	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
		mlx4_unload_one(pdev);
	else
		mlx4_info(dev, "%s: interface is down\n", __func__);
	mlx4_catas_end(dev);
	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
		mlx4_warn(dev, "Disabling SR-IOV\n");
		pci_disable_sriov(pdev);
	}

	pci_release_regions(pdev);
	pci_disable_device(pdev);
	kfree(dev->persist);
	kfree(priv);
	pci_set_drvdata(pdev, NULL);
}

static int restore_current_port_types(struct mlx4_dev *dev,
				      enum mlx4_port_type *types,
				      enum mlx4_port_type *poss_types)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err, i;

	mlx4_stop_sense(dev);

	mutex_lock(&priv->port_mutex);
	for (i = 0; i < dev->caps.num_ports; i++)
		dev->caps.possible_type[i + 1] = poss_types[i];
	err = mlx4_change_port_types(dev, types);
	mlx4_start_sense(dev);
	mutex_unlock(&priv->port_mutex);

	return err;
}

int mlx4_restart_one(struct pci_dev *pdev)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
	struct mlx4_dev	 *dev  = persist->dev;
	struct mlx4_priv *priv = mlx4_priv(dev);
	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
	int pci_dev_data, err, total_vfs;

	pci_dev_data = priv->pci_dev_data;
	total_vfs = dev->persist->num_vfs;
	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));

	mlx4_unload_one(pdev);
	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
	if (err) {
		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
			 __func__, pci_name(pdev), err);
		return err;
	}

	err = restore_current_port_types(dev, dev->persist->curr_port_type,
					 dev->persist->curr_port_poss_type);
	if (err)
		mlx4_err(dev, "could not restore original port types (%d)\n",
			 err);

	return err;
}

static const struct pci_device_id mlx4_pci_table[] = {
	/* MT25408 "Hermon" SDR */
	{ PCI_VDEVICE(MELLANOX, 0x6340), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" DDR */
	{ PCI_VDEVICE(MELLANOX, 0x634a), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" QDR */
	{ PCI_VDEVICE(MELLANOX, 0x6354), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" DDR PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x6732), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" QDR PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x673c), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" EN 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x6368), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25408 "Hermon" EN 10GigE PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x6750), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25458 ConnectX EN 10GBASE-T 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x6372), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x675a), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT26468 ConnectX EN 10GigE PCIe gen2*/
	{ PCI_VDEVICE(MELLANOX, 0x6764), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
	{ PCI_VDEVICE(MELLANOX, 0x6746), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT26478 ConnectX2 40GigE PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x676e), MLX4_PCI_DEV_FORCE_SENSE_PORT },
	/* MT25400 Family [ConnectX-2 Virtual Function] */
	{ PCI_VDEVICE(MELLANOX, 0x1002), MLX4_PCI_DEV_IS_VF },
	/* MT27500 Family [ConnectX-3] */
	{ PCI_VDEVICE(MELLANOX, 0x1003), 0 },
	/* MT27500 Family [ConnectX-3 Virtual Function] */
	{ PCI_VDEVICE(MELLANOX, 0x1004), MLX4_PCI_DEV_IS_VF },
	{ PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1008), 0 }, /* MT27521 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1009), 0 }, /* MT27530 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100a), 0 }, /* MT27531 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100b), 0 }, /* MT27540 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100c), 0 }, /* MT27541 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100d), 0 }, /* MT27550 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100e), 0 }, /* MT27551 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100f), 0 }, /* MT27560 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1010), 0 }, /* MT27561 Family */
	{ 0, }
};

MODULE_DEVICE_TABLE(pci, mlx4_pci_table);

static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
					      pci_channel_state_t state)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);

	mlx4_err(persist->dev, "mlx4_pci_err_detected was called\n");
	mlx4_enter_error_state(persist);

	mutex_lock(&persist->interface_state_mutex);
	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
		mlx4_unload_one(pdev);

	mutex_unlock(&persist->interface_state_mutex);
	if (state == pci_channel_io_perm_failure)
		return PCI_ERS_RESULT_DISCONNECT;

	pci_disable_device(pdev);
	return PCI_ERS_RESULT_NEED_RESET;
}

static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
	struct mlx4_dev	 *dev  = persist->dev;
	struct mlx4_priv *priv = mlx4_priv(dev);
	int               ret;
	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
	int total_vfs;

	mlx4_err(dev, "mlx4_pci_slot_reset was called\n");
	ret = pci_enable_device(pdev);
	if (ret) {
		mlx4_err(dev, "Can not re-enable device, ret=%d\n", ret);
		return PCI_ERS_RESULT_DISCONNECT;
	}

	pci_set_master(pdev);
	pci_restore_state(pdev);
	pci_save_state(pdev);

	total_vfs = dev->persist->num_vfs;
	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));

	mutex_lock(&persist->interface_state_mutex);
	if (!(persist->interface_state & MLX4_INTERFACE_STATE_UP)) {
		ret = mlx4_load_one(pdev, priv->pci_dev_data, total_vfs, nvfs,
				    priv, 1);
		if (ret) {
			mlx4_err(dev, "%s: mlx4_load_one failed, ret=%d\n",
				 __func__,  ret);
			goto end;
		}

		ret = restore_current_port_types(dev, dev->persist->
						 curr_port_type, dev->persist->
						 curr_port_poss_type);
		if (ret)
			mlx4_err(dev, "could not restore original port types (%d)\n", ret);
	}
end:
	mutex_unlock(&persist->interface_state_mutex);

	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
}

static void mlx4_shutdown(struct pci_dev *pdev)
{
	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);

	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
	mutex_lock(&persist->interface_state_mutex);
	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
		mlx4_unload_one(pdev);
	mutex_unlock(&persist->interface_state_mutex);
}

static const struct pci_error_handlers mlx4_err_handler = {
	.error_detected = mlx4_pci_err_detected,
	.slot_reset     = mlx4_pci_slot_reset,
};

static struct pci_driver mlx4_driver = {
	.name		= DRV_NAME,
	.id_table	= mlx4_pci_table,
	.probe		= mlx4_init_one,
	.shutdown	= mlx4_shutdown,
	.remove		= mlx4_remove_one,
	.err_handler    = &mlx4_err_handler,
};

static int __init mlx4_verify_params(void)
{
	if ((log_num_mac < 0) || (log_num_mac > 7)) {
		pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac);
		return -1;
	}

	if (log_num_vlan != 0)
		pr_warn("mlx4_core: log_num_vlan - obsolete module param, using %d\n",
			MLX4_LOG_NUM_VLANS);

	if (use_prio != 0)
		pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");

	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
		pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n",
			log_mtts_per_seg);
		return -1;
	}

	/* Check if module param for ports type has legal combination */
	if (port_type_array[0] == false && port_type_array[1] == true) {
		pr_warn("Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
		port_type_array[0] = true;
	}

	if (mlx4_log_num_mgm_entry_size < -7 ||
	    (mlx4_log_num_mgm_entry_size > 0 &&
	     (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
	      mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE))) {
		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-7..0 or %d..%d)\n",
			mlx4_log_num_mgm_entry_size,
			MLX4_MIN_MGM_LOG_ENTRY_SIZE,
			MLX4_MAX_MGM_LOG_ENTRY_SIZE);
		return -1;
	}

	return 0;
}

static int __init mlx4_init(void)
{
	int ret;

	if (mlx4_verify_params())
		return -EINVAL;


	mlx4_wq = create_singlethread_workqueue("mlx4");
	if (!mlx4_wq)
		return -ENOMEM;

	ret = pci_register_driver(&mlx4_driver);
	if (ret < 0)
		destroy_workqueue(mlx4_wq);
	return ret < 0 ? ret : 0;
}

static void __exit mlx4_cleanup(void)
{
	pci_unregister_driver(&mlx4_driver);
	destroy_workqueue(mlx4_wq);
}

module_init(mlx4_init);
module_exit(mlx4_cleanup);