aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
blob: 053560da63477df6d6804fd5f4c8a3dc19ba551d (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
/*
 * Copyright (c) 2003-2008 Chelsio, 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/moduleparam.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_vlan.h>
#include <linux/mdio.h>
#include <linux/sockios.h>
#include <linux/workqueue.h>
#include <linux/proc_fs.h>
#include <linux/rtnetlink.h>
#include <linux/firmware.h>
#include <linux/log2.h>
#include <linux/stringify.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <asm/uaccess.h>

#include "common.h"
#include "cxgb3_ioctl.h"
#include "regs.h"
#include "cxgb3_offload.h"
#include "version.h"

#include "cxgb3_ctl_defs.h"
#include "t3_cpl.h"
#include "firmware_exports.h"

enum {
	MAX_TXQ_ENTRIES = 16384,
	MAX_CTRL_TXQ_ENTRIES = 1024,
	MAX_RSPQ_ENTRIES = 16384,
	MAX_RX_BUFFERS = 16384,
	MAX_RX_JUMBO_BUFFERS = 16384,
	MIN_TXQ_ENTRIES = 4,
	MIN_CTRL_TXQ_ENTRIES = 4,
	MIN_RSPQ_ENTRIES = 32,
	MIN_FL_ENTRIES = 32
};

#define PORT_MASK ((1 << MAX_NPORTS) - 1)

#define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)

#define EEPROM_MAGIC 0x38E2F10C

#define CH_DEVICE(devid, idx) \
	{ PCI_VENDOR_ID_CHELSIO, devid, PCI_ANY_ID, PCI_ANY_ID, 0, 0, idx }

static DEFINE_PCI_DEVICE_TABLE(cxgb3_pci_tbl) = {
	CH_DEVICE(0x20, 0),	/* PE9000 */
	CH_DEVICE(0x21, 1),	/* T302E */
	CH_DEVICE(0x22, 2),	/* T310E */
	CH_DEVICE(0x23, 3),	/* T320X */
	CH_DEVICE(0x24, 1),	/* T302X */
	CH_DEVICE(0x25, 3),	/* T320E */
	CH_DEVICE(0x26, 2),	/* T310X */
	CH_DEVICE(0x30, 2),	/* T3B10 */
	CH_DEVICE(0x31, 3),	/* T3B20 */
	CH_DEVICE(0x32, 1),	/* T3B02 */
	CH_DEVICE(0x35, 6),	/* T3C20-derived T3C10 */
	CH_DEVICE(0x36, 3),	/* S320E-CR */
	CH_DEVICE(0x37, 7),	/* N320E-G2 */
	{0,}
};

MODULE_DESCRIPTION(DRV_DESC);
MODULE_AUTHOR("Chelsio Communications");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, cxgb3_pci_tbl);

static int dflt_msg_enable = DFLT_MSG_ENABLE;

module_param(dflt_msg_enable, int, 0644);
MODULE_PARM_DESC(dflt_msg_enable, "Chelsio T3 default message enable bitmap");

/*
 * The driver uses the best interrupt scheme available on a platform in the
 * order MSI-X, MSI, legacy pin interrupts.  This parameter determines which
 * of these schemes the driver may consider as follows:
 *
 * msi = 2: choose from among all three options
 * msi = 1: only consider MSI and pin interrupts
 * msi = 0: force pin interrupts
 */
static int msi = 2;

module_param(msi, int, 0644);
MODULE_PARM_DESC(msi, "whether to use MSI or MSI-X");

/*
 * The driver enables offload as a default.
 * To disable it, use ofld_disable = 1.
 */

static int ofld_disable = 0;

module_param(ofld_disable, int, 0644);
MODULE_PARM_DESC(ofld_disable, "whether to enable offload at init time or not");

/*
 * We have work elements that we need to cancel when an interface is taken
 * down.  Normally the work elements would be executed by keventd but that
 * can deadlock because of linkwatch.  If our close method takes the rtnl
 * lock and linkwatch is ahead of our work elements in keventd, linkwatch
 * will block keventd as it needs the rtnl lock, and we'll deadlock waiting
 * for our work to complete.  Get our own work queue to solve this.
 */
struct workqueue_struct *cxgb3_wq;

/**
 *	link_report - show link status and link speed/duplex
 *	@p: the port whose settings are to be reported
 *
 *	Shows the link status, speed, and duplex of a port.
 */
static void link_report(struct net_device *dev)
{
	if (!netif_carrier_ok(dev))
		printk(KERN_INFO "%s: link down\n", dev->name);
	else {
		const char *s = "10Mbps";
		const struct port_info *p = netdev_priv(dev);

		switch (p->link_config.speed) {
		case SPEED_10000:
			s = "10Gbps";
			break;
		case SPEED_1000:
			s = "1000Mbps";
			break;
		case SPEED_100:
			s = "100Mbps";
			break;
		}

		printk(KERN_INFO "%s: link up, %s, %s-duplex\n", dev->name, s,
		       p->link_config.duplex == DUPLEX_FULL ? "full" : "half");
	}
}

static void enable_tx_fifo_drain(struct adapter *adapter,
				 struct port_info *pi)
{
	t3_set_reg_field(adapter, A_XGM_TXFIFO_CFG + pi->mac.offset, 0,
			 F_ENDROPPKT);
	t3_write_reg(adapter, A_XGM_RX_CTRL + pi->mac.offset, 0);
	t3_write_reg(adapter, A_XGM_TX_CTRL + pi->mac.offset, F_TXEN);
	t3_write_reg(adapter, A_XGM_RX_CTRL + pi->mac.offset, F_RXEN);
}

static void disable_tx_fifo_drain(struct adapter *adapter,
				  struct port_info *pi)
{
	t3_set_reg_field(adapter, A_XGM_TXFIFO_CFG + pi->mac.offset,
			 F_ENDROPPKT, 0);
}

void t3_os_link_fault(struct adapter *adap, int port_id, int state)
{
	struct net_device *dev = adap->port[port_id];
	struct port_info *pi = netdev_priv(dev);

	if (state == netif_carrier_ok(dev))
		return;

	if (state) {
		struct cmac *mac = &pi->mac;

		netif_carrier_on(dev);

		disable_tx_fifo_drain(adap, pi);

		/* Clear local faults */
		t3_xgm_intr_disable(adap, pi->port_id);
		t3_read_reg(adap, A_XGM_INT_STATUS +
				    pi->mac.offset);
		t3_write_reg(adap,
			     A_XGM_INT_CAUSE + pi->mac.offset,
			     F_XGM_INT);

		t3_set_reg_field(adap,
				 A_XGM_INT_ENABLE +
				 pi->mac.offset,
				 F_XGM_INT, F_XGM_INT);
		t3_xgm_intr_enable(adap, pi->port_id);

		t3_mac_enable(mac, MAC_DIRECTION_TX);
	} else {
		netif_carrier_off(dev);

		/* Flush TX FIFO */
		enable_tx_fifo_drain(adap, pi);
	}
	link_report(dev);
}

/**
 *	t3_os_link_changed - handle link status changes
 *	@adapter: the adapter associated with the link change
 *	@port_id: the port index whose limk status has changed
 *	@link_stat: the new status of the link
 *	@speed: the new speed setting
 *	@duplex: the new duplex setting
 *	@pause: the new flow-control setting
 *
 *	This is the OS-dependent handler for link status changes.  The OS
 *	neutral handler takes care of most of the processing for these events,
 *	then calls this handler for any OS-specific processing.
 */
void t3_os_link_changed(struct adapter *adapter, int port_id, int link_stat,
			int speed, int duplex, int pause)
{
	struct net_device *dev = adapter->port[port_id];
	struct port_info *pi = netdev_priv(dev);
	struct cmac *mac = &pi->mac;

	/* Skip changes from disabled ports. */
	if (!netif_running(dev))
		return;

	if (link_stat != netif_carrier_ok(dev)) {
		if (link_stat) {
			disable_tx_fifo_drain(adapter, pi);

			t3_mac_enable(mac, MAC_DIRECTION_RX);

			/* Clear local faults */
			t3_xgm_intr_disable(adapter, pi->port_id);
			t3_read_reg(adapter, A_XGM_INT_STATUS +
				    pi->mac.offset);
			t3_write_reg(adapter,
				     A_XGM_INT_CAUSE + pi->mac.offset,
				     F_XGM_INT);

			t3_set_reg_field(adapter,
					 A_XGM_INT_ENABLE + pi->mac.offset,
					 F_XGM_INT, F_XGM_INT);
			t3_xgm_intr_enable(adapter, pi->port_id);

			netif_carrier_on(dev);
		} else {
			netif_carrier_off(dev);

			t3_xgm_intr_disable(adapter, pi->port_id);
			t3_read_reg(adapter, A_XGM_INT_STATUS + pi->mac.offset);
			t3_set_reg_field(adapter,
					 A_XGM_INT_ENABLE + pi->mac.offset,
					 F_XGM_INT, 0);

			if (is_10G(adapter))
				pi->phy.ops->power_down(&pi->phy, 1);

			t3_read_reg(adapter, A_XGM_INT_STATUS + pi->mac.offset);
			t3_mac_disable(mac, MAC_DIRECTION_RX);
			t3_link_start(&pi->phy, mac, &pi->link_config);

			/* Flush TX FIFO */
			enable_tx_fifo_drain(adapter, pi);
		}

		link_report(dev);
	}
}

/**
 *	t3_os_phymod_changed - handle PHY module changes
 *	@phy: the PHY reporting the module change
 *	@mod_type: new module type
 *
 *	This is the OS-dependent handler for PHY module changes.  It is
 *	invoked when a PHY module is removed or inserted for any OS-specific
 *	processing.
 */
void t3_os_phymod_changed(struct adapter *adap, int port_id)
{
	static const char *mod_str[] = {
		NULL, "SR", "LR", "LRM", "TWINAX", "TWINAX", "unknown"
	};

	const struct net_device *dev = adap->port[port_id];
	const struct port_info *pi = netdev_priv(dev);

	if (pi->phy.modtype == phy_modtype_none)
		printk(KERN_INFO "%s: PHY module unplugged\n", dev->name);
	else
		printk(KERN_INFO "%s: %s PHY module inserted\n", dev->name,
		       mod_str[pi->phy.modtype]);
}

static void cxgb_set_rxmode(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);

	t3_mac_set_rx_mode(&pi->mac, dev);
}

/**
 *	link_start - enable a port
 *	@dev: the device to enable
 *
 *	Performs the MAC and PHY actions needed to enable a port.
 */
static void link_start(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct cmac *mac = &pi->mac;

	t3_mac_reset(mac);
	t3_mac_set_num_ucast(mac, MAX_MAC_IDX);
	t3_mac_set_mtu(mac, dev->mtu);
	t3_mac_set_address(mac, LAN_MAC_IDX, dev->dev_addr);
	t3_mac_set_address(mac, SAN_MAC_IDX, pi->iscsic.mac_addr);
	t3_mac_set_rx_mode(mac, dev);
	t3_link_start(&pi->phy, mac, &pi->link_config);
	t3_mac_enable(mac, MAC_DIRECTION_RX | MAC_DIRECTION_TX);
}

static inline void cxgb_disable_msi(struct adapter *adapter)
{
	if (adapter->flags & USING_MSIX) {
		pci_disable_msix(adapter->pdev);
		adapter->flags &= ~USING_MSIX;
	} else if (adapter->flags & USING_MSI) {
		pci_disable_msi(adapter->pdev);
		adapter->flags &= ~USING_MSI;
	}
}

/*
 * Interrupt handler for asynchronous events used with MSI-X.
 */
static irqreturn_t t3_async_intr_handler(int irq, void *cookie)
{
	t3_slow_intr_handler(cookie);
	return IRQ_HANDLED;
}

/*
 * Name the MSI-X interrupts.
 */
static void name_msix_vecs(struct adapter *adap)
{
	int i, j, msi_idx = 1, n = sizeof(adap->msix_info[0].desc) - 1;

	snprintf(adap->msix_info[0].desc, n, "%s", adap->name);
	adap->msix_info[0].desc[n] = 0;

	for_each_port(adap, j) {
		struct net_device *d = adap->port[j];
		const struct port_info *pi = netdev_priv(d);

		for (i = 0; i < pi->nqsets; i++, msi_idx++) {
			snprintf(adap->msix_info[msi_idx].desc, n,
				 "%s-%d", d->name, pi->first_qset + i);
			adap->msix_info[msi_idx].desc[n] = 0;
		}
	}
}

static int request_msix_data_irqs(struct adapter *adap)
{
	int i, j, err, qidx = 0;

	for_each_port(adap, i) {
		int nqsets = adap2pinfo(adap, i)->nqsets;

		for (j = 0; j < nqsets; ++j) {
			err = request_irq(adap->msix_info[qidx + 1].vec,
					  t3_intr_handler(adap,
							  adap->sge.qs[qidx].
							  rspq.polling), 0,
					  adap->msix_info[qidx + 1].desc,
					  &adap->sge.qs[qidx]);
			if (err) {
				while (--qidx >= 0)
					free_irq(adap->msix_info[qidx + 1].vec,
						 &adap->sge.qs[qidx]);
				return err;
			}
			qidx++;
		}
	}
	return 0;
}

static void free_irq_resources(struct adapter *adapter)
{
	if (adapter->flags & USING_MSIX) {
		int i, n = 0;

		free_irq(adapter->msix_info[0].vec, adapter);
		for_each_port(adapter, i)
			n += adap2pinfo(adapter, i)->nqsets;

		for (i = 0; i < n; ++i)
			free_irq(adapter->msix_info[i + 1].vec,
				 &adapter->sge.qs[i]);
	} else
		free_irq(adapter->pdev->irq, adapter);
}

static int await_mgmt_replies(struct adapter *adap, unsigned long init_cnt,
			      unsigned long n)
{
	int attempts = 10;

	while (adap->sge.qs[0].rspq.offload_pkts < init_cnt + n) {
		if (!--attempts)
			return -ETIMEDOUT;
		msleep(10);
	}
	return 0;
}

static int init_tp_parity(struct adapter *adap)
{
	int i;
	struct sk_buff *skb;
	struct cpl_set_tcb_field *greq;
	unsigned long cnt = adap->sge.qs[0].rspq.offload_pkts;

	t3_tp_set_offload_mode(adap, 1);

	for (i = 0; i < 16; i++) {
		struct cpl_smt_write_req *req;

		skb = alloc_skb(sizeof(*req), GFP_KERNEL);
		if (!skb)
			skb = adap->nofail_skb;
		if (!skb)
			goto alloc_skb_fail;

		req = (struct cpl_smt_write_req *)__skb_put(skb, sizeof(*req));
		memset(req, 0, sizeof(*req));
		req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
		OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SMT_WRITE_REQ, i));
		req->mtu_idx = NMTUS - 1;
		req->iff = i;
		t3_mgmt_tx(adap, skb);
		if (skb == adap->nofail_skb) {
			await_mgmt_replies(adap, cnt, i + 1);
			adap->nofail_skb = alloc_skb(sizeof(*greq), GFP_KERNEL);
			if (!adap->nofail_skb)
				goto alloc_skb_fail;
		}
	}

	for (i = 0; i < 2048; i++) {
		struct cpl_l2t_write_req *req;

		skb = alloc_skb(sizeof(*req), GFP_KERNEL);
		if (!skb)
			skb = adap->nofail_skb;
		if (!skb)
			goto alloc_skb_fail;

		req = (struct cpl_l2t_write_req *)__skb_put(skb, sizeof(*req));
		memset(req, 0, sizeof(*req));
		req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
		OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_L2T_WRITE_REQ, i));
		req->params = htonl(V_L2T_W_IDX(i));
		t3_mgmt_tx(adap, skb);
		if (skb == adap->nofail_skb) {
			await_mgmt_replies(adap, cnt, 16 + i + 1);
			adap->nofail_skb = alloc_skb(sizeof(*greq), GFP_KERNEL);
			if (!adap->nofail_skb)
				goto alloc_skb_fail;
		}
	}

	for (i = 0; i < 2048; i++) {
		struct cpl_rte_write_req *req;

		skb = alloc_skb(sizeof(*req), GFP_KERNEL);
		if (!skb)
			skb = adap->nofail_skb;
		if (!skb)
			goto alloc_skb_fail;

		req = (struct cpl_rte_write_req *)__skb_put(skb, sizeof(*req));
		memset(req, 0, sizeof(*req));
		req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
		OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_RTE_WRITE_REQ, i));
		req->l2t_idx = htonl(V_L2T_W_IDX(i));
		t3_mgmt_tx(adap, skb);
		if (skb == adap->nofail_skb) {
			await_mgmt_replies(adap, cnt, 16 + 2048 + i + 1);
			adap->nofail_skb = alloc_skb(sizeof(*greq), GFP_KERNEL);
			if (!adap->nofail_skb)
				goto alloc_skb_fail;
		}
	}

	skb = alloc_skb(sizeof(*greq), GFP_KERNEL);
	if (!skb)
		skb = adap->nofail_skb;
	if (!skb)
		goto alloc_skb_fail;

	greq = (struct cpl_set_tcb_field *)__skb_put(skb, sizeof(*greq));
	memset(greq, 0, sizeof(*greq));
	greq->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
	OPCODE_TID(greq) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, 0));
	greq->mask = cpu_to_be64(1);
	t3_mgmt_tx(adap, skb);

	i = await_mgmt_replies(adap, cnt, 16 + 2048 + 2048 + 1);
	if (skb == adap->nofail_skb) {
		i = await_mgmt_replies(adap, cnt, 16 + 2048 + 2048 + 1);
		adap->nofail_skb = alloc_skb(sizeof(*greq), GFP_KERNEL);
	}

	t3_tp_set_offload_mode(adap, 0);
	return i;

alloc_skb_fail:
	t3_tp_set_offload_mode(adap, 0);
	return -ENOMEM;
}

/**
 *	setup_rss - configure RSS
 *	@adap: the adapter
 *
 *	Sets up RSS to distribute packets to multiple receive queues.  We
 *	configure the RSS CPU lookup table to distribute to the number of HW
 *	receive queues, and the response queue lookup table to narrow that
 *	down to the response queues actually configured for each port.
 *	We always configure the RSS mapping for two ports since the mapping
 *	table has plenty of entries.
 */
static void setup_rss(struct adapter *adap)
{
	int i;
	unsigned int nq0 = adap2pinfo(adap, 0)->nqsets;
	unsigned int nq1 = adap->port[1] ? adap2pinfo(adap, 1)->nqsets : 1;
	u8 cpus[SGE_QSETS + 1];
	u16 rspq_map[RSS_TABLE_SIZE];

	for (i = 0; i < SGE_QSETS; ++i)
		cpus[i] = i;
	cpus[SGE_QSETS] = 0xff;	/* terminator */

	for (i = 0; i < RSS_TABLE_SIZE / 2; ++i) {
		rspq_map[i] = i % nq0;
		rspq_map[i + RSS_TABLE_SIZE / 2] = (i % nq1) + nq0;
	}

	t3_config_rss(adap, F_RQFEEDBACKENABLE | F_TNLLKPEN | F_TNLMAPEN |
		      F_TNLPRTEN | F_TNL2TUPEN | F_TNL4TUPEN |
		      V_RRCPLCPUSIZE(6) | F_HASHTOEPLITZ, cpus, rspq_map);
}

static void ring_dbs(struct adapter *adap)
{
	int i, j;

	for (i = 0; i < SGE_QSETS; i++) {
		struct sge_qset *qs = &adap->sge.qs[i];

		if (qs->adap)
			for (j = 0; j < SGE_TXQ_PER_SET; j++)
				t3_write_reg(adap, A_SG_KDOORBELL, F_SELEGRCNTX | V_EGRCNTX(qs->txq[j].cntxt_id));
	}
}

static void init_napi(struct adapter *adap)
{
	int i;

	for (i = 0; i < SGE_QSETS; i++) {
		struct sge_qset *qs = &adap->sge.qs[i];

		if (qs->adap)
			netif_napi_add(qs->netdev, &qs->napi, qs->napi.poll,
				       64);
	}

	/*
	 * netif_napi_add() can be called only once per napi_struct because it
	 * adds each new napi_struct to a list.  Be careful not to call it a
	 * second time, e.g., during EEH recovery, by making a note of it.
	 */
	adap->flags |= NAPI_INIT;
}

/*
 * Wait until all NAPI handlers are descheduled.  This includes the handlers of
 * both netdevices representing interfaces and the dummy ones for the extra
 * queues.
 */
static void quiesce_rx(struct adapter *adap)
{
	int i;

	for (i = 0; i < SGE_QSETS; i++)
		if (adap->sge.qs[i].adap)
			napi_disable(&adap->sge.qs[i].napi);
}

static void enable_all_napi(struct adapter *adap)
{
	int i;
	for (i = 0; i < SGE_QSETS; i++)
		if (adap->sge.qs[i].adap)
			napi_enable(&adap->sge.qs[i].napi);
}

/**
 *	setup_sge_qsets - configure SGE Tx/Rx/response queues
 *	@adap: the adapter
 *
 *	Determines how many sets of SGE queues to use and initializes them.
 *	We support multiple queue sets per port if we have MSI-X, otherwise
 *	just one queue set per port.
 */
static int setup_sge_qsets(struct adapter *adap)
{
	int i, j, err, irq_idx = 0, qset_idx = 0;
	unsigned int ntxq = SGE_TXQ_PER_SET;

	if (adap->params.rev > 0 && !(adap->flags & USING_MSI))
		irq_idx = -1;

	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];
		struct port_info *pi = netdev_priv(dev);

		pi->qs = &adap->sge.qs[pi->first_qset];
		for (j = 0; j < pi->nqsets; ++j, ++qset_idx) {
			err = t3_sge_alloc_qset(adap, qset_idx, 1,
				(adap->flags & USING_MSIX) ? qset_idx + 1 :
							     irq_idx,
				&adap->params.sge.qset[qset_idx], ntxq, dev,
				netdev_get_tx_queue(dev, j));
			if (err) {
				t3_free_sge_resources(adap);
				return err;
			}
		}
	}

	return 0;
}

static ssize_t attr_show(struct device *d, char *buf,
			 ssize_t(*format) (struct net_device *, char *))
{
	ssize_t len;

	/* Synchronize with ioctls that may shut down the device */
	rtnl_lock();
	len = (*format) (to_net_dev(d), buf);
	rtnl_unlock();
	return len;
}

static ssize_t attr_store(struct device *d,
			  const char *buf, size_t len,
			  ssize_t(*set) (struct net_device *, unsigned int),
			  unsigned int min_val, unsigned int max_val)
{
	char *endp;
	ssize_t ret;
	unsigned int val;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	val = simple_strtoul(buf, &endp, 0);
	if (endp == buf || val < min_val || val > max_val)
		return -EINVAL;

	rtnl_lock();
	ret = (*set) (to_net_dev(d), val);
	if (!ret)
		ret = len;
	rtnl_unlock();
	return ret;
}

#define CXGB3_SHOW(name, val_expr) \
static ssize_t format_##name(struct net_device *dev, char *buf) \
{ \
	struct port_info *pi = netdev_priv(dev); \
	struct adapter *adap = pi->adapter; \
	return sprintf(buf, "%u\n", val_expr); \
} \
static ssize_t show_##name(struct device *d, struct device_attribute *attr, \
			   char *buf) \
{ \
	return attr_show(d, buf, format_##name); \
}

static ssize_t set_nfilters(struct net_device *dev, unsigned int val)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adap = pi->adapter;
	int min_tids = is_offload(adap) ? MC5_MIN_TIDS : 0;

	if (adap->flags & FULL_INIT_DONE)
		return -EBUSY;
	if (val && adap->params.rev == 0)
		return -EINVAL;
	if (val > t3_mc5_size(&adap->mc5) - adap->params.mc5.nservers -
	    min_tids)
		return -EINVAL;
	adap->params.mc5.nfilters = val;
	return 0;
}

static ssize_t store_nfilters(struct device *d, struct device_attribute *attr,
			      const char *buf, size_t len)
{
	return attr_store(d, buf, len, set_nfilters, 0, ~0);
}

static ssize_t set_nservers(struct net_device *dev, unsigned int val)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adap = pi->adapter;

	if (adap->flags & FULL_INIT_DONE)
		return -EBUSY;
	if (val > t3_mc5_size(&adap->mc5) - adap->params.mc5.nfilters -
	    MC5_MIN_TIDS)
		return -EINVAL;
	adap->params.mc5.nservers = val;
	return 0;
}

static ssize_t store_nservers(struct device *d, struct device_attribute *attr,
			      const char *buf, size_t len)
{
	return attr_store(d, buf, len, set_nservers, 0, ~0);
}

#define CXGB3_ATTR_R(name, val_expr) \
CXGB3_SHOW(name, val_expr) \
static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)

#define CXGB3_ATTR_RW(name, val_expr, store_method) \
CXGB3_SHOW(name, val_expr) \
static DEVICE_ATTR(name, S_IRUGO | S_IWUSR, show_##name, store_method)

CXGB3_ATTR_R(cam_size, t3_mc5_size(&adap->mc5));
CXGB3_ATTR_RW(nfilters, adap->params.mc5.nfilters, store_nfilters);
CXGB3_ATTR_RW(nservers, adap->params.mc5.nservers, store_nservers);

static struct attribute *cxgb3_attrs[] = {
	&dev_attr_cam_size.attr,
	&dev_attr_nfilters.attr,
	&dev_attr_nservers.attr,
	NULL
};

static struct attribute_group cxgb3_attr_group = {.attrs = cxgb3_attrs };

static ssize_t tm_attr_show(struct device *d,
			    char *buf, int sched)
{
	struct port_info *pi = netdev_priv(to_net_dev(d));
	struct adapter *adap = pi->adapter;
	unsigned int v, addr, bpt, cpt;
	ssize_t len;

	addr = A_TP_TX_MOD_Q1_Q0_RATE_LIMIT - sched / 2;
	rtnl_lock();
	t3_write_reg(adap, A_TP_TM_PIO_ADDR, addr);
	v = t3_read_reg(adap, A_TP_TM_PIO_DATA);
	if (sched & 1)
		v >>= 16;
	bpt = (v >> 8) & 0xff;
	cpt = v & 0xff;
	if (!cpt)
		len = sprintf(buf, "disabled\n");
	else {
		v = (adap->params.vpd.cclk * 1000) / cpt;
		len = sprintf(buf, "%u Kbps\n", (v * bpt) / 125);
	}
	rtnl_unlock();
	return len;
}

static ssize_t tm_attr_store(struct device *d,
			     const char *buf, size_t len, int sched)
{
	struct port_info *pi = netdev_priv(to_net_dev(d));
	struct adapter *adap = pi->adapter;
	unsigned int val;
	char *endp;
	ssize_t ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	val = simple_strtoul(buf, &endp, 0);
	if (endp == buf || val > 10000000)
		return -EINVAL;

	rtnl_lock();
	ret = t3_config_sched(adap, val, sched);
	if (!ret)
		ret = len;
	rtnl_unlock();
	return ret;
}

#define TM_ATTR(name, sched) \
static ssize_t show_##name(struct device *d, struct device_attribute *attr, \
			   char *buf) \
{ \
	return tm_attr_show(d, buf, sched); \
} \
static ssize_t store_##name(struct device *d, struct device_attribute *attr, \
			    const char *buf, size_t len) \
{ \
	return tm_attr_store(d, buf, len, sched); \
} \
static DEVICE_ATTR(name, S_IRUGO | S_IWUSR, show_##name, store_##name)

TM_ATTR(sched0, 0);
TM_ATTR(sched1, 1);
TM_ATTR(sched2, 2);
TM_ATTR(sched3, 3);
TM_ATTR(sched4, 4);
TM_ATTR(sched5, 5);
TM_ATTR(sched6, 6);
TM_ATTR(sched7, 7);

static struct attribute *offload_attrs[] = {
	&dev_attr_sched0.attr,
	&dev_attr_sched1.attr,
	&dev_attr_sched2.attr,
	&dev_attr_sched3.attr,
	&dev_attr_sched4.attr,
	&dev_attr_sched5.attr,
	&dev_attr_sched6.attr,
	&dev_attr_sched7.attr,
	NULL
};

static struct attribute_group offload_attr_group = {.attrs = offload_attrs };

/*
 * Sends an sk_buff to an offload queue driver
 * after dealing with any active network taps.
 */
static inline int offload_tx(struct t3cdev *tdev, struct sk_buff *skb)
{
	int ret;

	local_bh_disable();
	ret = t3_offload_tx(tdev, skb);
	local_bh_enable();
	return ret;
}

static int write_smt_entry(struct adapter *adapter, int idx)
{
	struct cpl_smt_write_req *req;
	struct port_info *pi = netdev_priv(adapter->port[idx]);
	struct sk_buff *skb = alloc_skb(sizeof(*req), GFP_KERNEL);

	if (!skb)
		return -ENOMEM;

	req = (struct cpl_smt_write_req *)__skb_put(skb, sizeof(*req));
	req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SMT_WRITE_REQ, idx));
	req->mtu_idx = NMTUS - 1;	/* should be 0 but there's a T3 bug */
	req->iff = idx;
	memcpy(req->src_mac0, adapter->port[idx]->dev_addr, ETH_ALEN);
	memcpy(req->src_mac1, pi->iscsic.mac_addr, ETH_ALEN);
	skb->priority = 1;
	offload_tx(&adapter->tdev, skb);
	return 0;
}

static int init_smt(struct adapter *adapter)
{
	int i;

	for_each_port(adapter, i)
	    write_smt_entry(adapter, i);
	return 0;
}

static void init_port_mtus(struct adapter *adapter)
{
	unsigned int mtus = adapter->port[0]->mtu;

	if (adapter->port[1])
		mtus |= adapter->port[1]->mtu << 16;
	t3_write_reg(adapter, A_TP_MTU_PORT_TABLE, mtus);
}

static int send_pktsched_cmd(struct adapter *adap, int sched, int qidx, int lo,
			      int hi, int port)
{
	struct sk_buff *skb;
	struct mngt_pktsched_wr *req;
	int ret;

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		skb = adap->nofail_skb;
	if (!skb)
		return -ENOMEM;

	req = (struct mngt_pktsched_wr *)skb_put(skb, sizeof(*req));
	req->wr_hi = htonl(V_WR_OP(FW_WROPCODE_MNGT));
	req->mngt_opcode = FW_MNGTOPCODE_PKTSCHED_SET;
	req->sched = sched;
	req->idx = qidx;
	req->min = lo;
	req->max = hi;
	req->binding = port;
	ret = t3_mgmt_tx(adap, skb);
	if (skb == adap->nofail_skb) {
		adap->nofail_skb = alloc_skb(sizeof(struct cpl_set_tcb_field),
					     GFP_KERNEL);
		if (!adap->nofail_skb)
			ret = -ENOMEM;
	}

	return ret;
}

static int bind_qsets(struct adapter *adap)
{
	int i, j, err = 0;

	for_each_port(adap, i) {
		const struct port_info *pi = adap2pinfo(adap, i);

		for (j = 0; j < pi->nqsets; ++j) {
			int ret = send_pktsched_cmd(adap, 1,
						    pi->first_qset + j, -1,
						    -1, i);
			if (ret)
				err = ret;
		}
	}

	return err;
}

#define FW_VERSION __stringify(FW_VERSION_MAJOR) "."			\
	__stringify(FW_VERSION_MINOR) "." __stringify(FW_VERSION_MICRO)
#define FW_FNAME "cxgb3/t3fw-" FW_VERSION ".bin"
#define TPSRAM_VERSION __stringify(TP_VERSION_MAJOR) "."		\
	__stringify(TP_VERSION_MINOR) "." __stringify(TP_VERSION_MICRO)
#define TPSRAM_NAME "cxgb3/t3%c_psram-" TPSRAM_VERSION ".bin"
#define AEL2005_OPT_EDC_NAME "cxgb3/ael2005_opt_edc.bin"
#define AEL2005_TWX_EDC_NAME "cxgb3/ael2005_twx_edc.bin"
#define AEL2020_TWX_EDC_NAME "cxgb3/ael2020_twx_edc.bin"
MODULE_FIRMWARE(FW_FNAME);
MODULE_FIRMWARE("cxgb3/t3b_psram-" TPSRAM_VERSION ".bin");
MODULE_FIRMWARE("cxgb3/t3c_psram-" TPSRAM_VERSION ".bin");
MODULE_FIRMWARE(AEL2005_OPT_EDC_NAME);
MODULE_FIRMWARE(AEL2005_TWX_EDC_NAME);
MODULE_FIRMWARE(AEL2020_TWX_EDC_NAME);

static inline const char *get_edc_fw_name(int edc_idx)
{
	const char *fw_name = NULL;

	switch (edc_idx) {
	case EDC_OPT_AEL2005:
		fw_name = AEL2005_OPT_EDC_NAME;
		break;
	case EDC_TWX_AEL2005:
		fw_name = AEL2005_TWX_EDC_NAME;
		break;
	case EDC_TWX_AEL2020:
		fw_name = AEL2020_TWX_EDC_NAME;
		break;
	}
	return fw_name;
}

int t3_get_edc_fw(struct cphy *phy, int edc_idx, int size)
{
	struct adapter *adapter = phy->adapter;
	const struct firmware *fw;
	char buf[64];
	u32 csum;
	const __be32 *p;
	u16 *cache = phy->phy_cache;
	int i, ret;

	snprintf(buf, sizeof(buf), get_edc_fw_name(edc_idx));

	ret = request_firmware(&fw, buf, &adapter->pdev->dev);
	if (ret < 0) {
		dev_err(&adapter->pdev->dev,
			"could not upgrade firmware: unable to load %s\n",
			buf);
		return ret;
	}

	/* check size, take checksum in account */
	if (fw->size > size + 4) {
		CH_ERR(adapter, "firmware image too large %u, expected %d\n",
		       (unsigned int)fw->size, size + 4);
		ret = -EINVAL;
	}

	/* compute checksum */
	p = (const __be32 *)fw->data;
	for (csum = 0, i = 0; i < fw->size / sizeof(csum); i++)
		csum += ntohl(p[i]);

	if (csum != 0xffffffff) {
		CH_ERR(adapter, "corrupted firmware image, checksum %u\n",
		       csum);
		ret = -EINVAL;
	}

	for (i = 0; i < size / 4 ; i++) {
		*cache++ = (be32_to_cpu(p[i]) & 0xffff0000) >> 16;
		*cache++ = be32_to_cpu(p[i]) & 0xffff;
	}

	release_firmware(fw);

	return ret;
}

static int upgrade_fw(struct adapter *adap)
{
	int ret;
	const struct firmware *fw;
	struct device *dev = &adap->pdev->dev;

	ret = request_firmware(&fw, FW_FNAME, dev);
	if (ret < 0) {
		dev_err(dev, "could not upgrade firmware: unable to load %s\n",
			FW_FNAME);
		return ret;
	}
	ret = t3_load_fw(adap, fw->data, fw->size);
	release_firmware(fw);

	if (ret == 0)
		dev_info(dev, "successful upgrade to firmware %d.%d.%d\n",
			 FW_VERSION_MAJOR, FW_VERSION_MINOR, FW_VERSION_MICRO);
	else
		dev_err(dev, "failed to upgrade to firmware %d.%d.%d\n",
			FW_VERSION_MAJOR, FW_VERSION_MINOR, FW_VERSION_MICRO);

	return ret;
}

static inline char t3rev2char(struct adapter *adapter)
{
	char rev = 0;

	switch(adapter->params.rev) {
	case T3_REV_B:
	case T3_REV_B2:
		rev = 'b';
		break;
	case T3_REV_C:
		rev = 'c';
		break;
	}
	return rev;
}

static int update_tpsram(struct adapter *adap)
{
	const struct firmware *tpsram;
	char buf[64];
	struct device *dev = &adap->pdev->dev;
	int ret;
	char rev;

	rev = t3rev2char(adap);
	if (!rev)
		return 0;

	snprintf(buf, sizeof(buf), TPSRAM_NAME, rev);

	ret = request_firmware(&tpsram, buf, dev);
	if (ret < 0) {
		dev_err(dev, "could not load TP SRAM: unable to load %s\n",
			buf);
		return ret;
	}

	ret = t3_check_tpsram(adap, tpsram->data, tpsram->size);
	if (ret)
		goto release_tpsram;

	ret = t3_set_proto_sram(adap, tpsram->data);
	if (ret == 0)
		dev_info(dev,
			 "successful update of protocol engine "
			 "to %d.%d.%d\n",
			 TP_VERSION_MAJOR, TP_VERSION_MINOR, TP_VERSION_MICRO);
	else
		dev_err(dev, "failed to update of protocol engine %d.%d.%d\n",
			TP_VERSION_MAJOR, TP_VERSION_MINOR, TP_VERSION_MICRO);
	if (ret)
		dev_err(dev, "loading protocol SRAM failed\n");

release_tpsram:
	release_firmware(tpsram);

	return ret;
}

/**
 *	cxgb_up - enable the adapter
 *	@adapter: adapter being enabled
 *
 *	Called when the first port is enabled, this function performs the
 *	actions necessary to make an adapter operational, such as completing
 *	the initialization of HW modules, and enabling interrupts.
 *
 *	Must be called with the rtnl lock held.
 */
static int cxgb_up(struct adapter *adap)
{
	int err;

	if (!(adap->flags & FULL_INIT_DONE)) {
		err = t3_check_fw_version(adap);
		if (err == -EINVAL) {
			err = upgrade_fw(adap);
			CH_WARN(adap, "FW upgrade to %d.%d.%d %s\n",
				FW_VERSION_MAJOR, FW_VERSION_MINOR,
				FW_VERSION_MICRO, err ? "failed" : "succeeded");
		}

		err = t3_check_tpsram_version(adap);
		if (err == -EINVAL) {
			err = update_tpsram(adap);
			CH_WARN(adap, "TP upgrade to %d.%d.%d %s\n",
				TP_VERSION_MAJOR, TP_VERSION_MINOR,
				TP_VERSION_MICRO, err ? "failed" : "succeeded");
		}

		/*
		 * Clear interrupts now to catch errors if t3_init_hw fails.
		 * We clear them again later as initialization may trigger
		 * conditions that can interrupt.
		 */
		t3_intr_clear(adap);

		err = t3_init_hw(adap, 0);
		if (err)
			goto out;

		t3_set_reg_field(adap, A_TP_PARA_REG5, 0, F_RXDDPOFFINIT);
		t3_write_reg(adap, A_ULPRX_TDDP_PSZ, V_HPZ0(PAGE_SHIFT - 12));

		err = setup_sge_qsets(adap);
		if (err)
			goto out;

		setup_rss(adap);
		if (!(adap->flags & NAPI_INIT))
			init_napi(adap);

		t3_start_sge_timers(adap);
		adap->flags |= FULL_INIT_DONE;
	}

	t3_intr_clear(adap);

	if (adap->flags & USING_MSIX) {
		name_msix_vecs(adap);
		err = request_irq(adap->msix_info[0].vec,
				  t3_async_intr_handler, 0,
				  adap->msix_info[0].desc, adap);
		if (err)
			goto irq_err;

		err = request_msix_data_irqs(adap);
		if (err) {
			free_irq(adap->msix_info[0].vec, adap);
			goto irq_err;
		}
	} else if ((err = request_irq(adap->pdev->irq,
				      t3_intr_handler(adap,
						      adap->sge.qs[0].rspq.
						      polling),
				      (adap->flags & USING_MSI) ?
				       0 : IRQF_SHARED,
				      adap->name, adap)))
		goto irq_err;

	enable_all_napi(adap);
	t3_sge_start(adap);
	t3_intr_enable(adap);

	if (adap->params.rev >= T3_REV_C && !(adap->flags & TP_PARITY_INIT) &&
	    is_offload(adap) && init_tp_parity(adap) == 0)
		adap->flags |= TP_PARITY_INIT;

	if (adap->flags & TP_PARITY_INIT) {
		t3_write_reg(adap, A_TP_INT_CAUSE,
			     F_CMCACHEPERR | F_ARPLUTPERR);
		t3_write_reg(adap, A_TP_INT_ENABLE, 0x7fbfffff);
	}

	if (!(adap->flags & QUEUES_BOUND)) {
		int ret = bind_qsets(adap);

		if (ret < 0) {
			CH_ERR(adap, "failed to bind qsets, err %d\n", ret);
			t3_intr_disable(adap);
			free_irq_resources(adap);
			err = ret;
			goto out;
		}
		adap->flags |= QUEUES_BOUND;
	}

out:
	return err;
irq_err:
	CH_ERR(adap, "request_irq failed, err %d\n", err);
	goto out;
}

/*
 * Release resources when all the ports and offloading have been stopped.
 */
static void cxgb_down(struct adapter *adapter, int on_wq)
{
	t3_sge_stop(adapter);
	spin_lock_irq(&adapter->work_lock);	/* sync with PHY intr task */
	t3_intr_disable(adapter);
	spin_unlock_irq(&adapter->work_lock);

	free_irq_resources(adapter);
	quiesce_rx(adapter);
	t3_sge_stop(adapter);
	if (!on_wq)
		flush_workqueue(cxgb3_wq);/* wait for external IRQ handler */
}

static void schedule_chk_task(struct adapter *adap)
{
	unsigned int timeo;

	timeo = adap->params.linkpoll_period ?
	    (HZ * adap->params.linkpoll_period) / 10 :
	    adap->params.stats_update_period * HZ;
	if (timeo)
		queue_delayed_work(cxgb3_wq, &adap->adap_check_task, timeo);
}

static int offload_open(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct t3cdev *tdev = dev2t3cdev(dev);
	int adap_up = adapter->open_device_map & PORT_MASK;
	int err;

	if (test_and_set_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map))
		return 0;

	if (!adap_up && (err = cxgb_up(adapter)) < 0)
		goto out;

	t3_tp_set_offload_mode(adapter, 1);
	tdev->lldev = adapter->port[0];
	err = cxgb3_offload_activate(adapter);
	if (err)
		goto out;

	init_port_mtus(adapter);
	t3_load_mtus(adapter, adapter->params.mtus, adapter->params.a_wnd,
		     adapter->params.b_wnd,
		     adapter->params.rev == 0 ?
		     adapter->port[0]->mtu : 0xffff);
	init_smt(adapter);

	if (sysfs_create_group(&tdev->lldev->dev.kobj, &offload_attr_group))
		dev_dbg(&dev->dev, "cannot create sysfs group\n");

	/* Call back all registered clients */
	cxgb3_add_clients(tdev);

out:
	/* restore them in case the offload module has changed them */
	if (err) {
		t3_tp_set_offload_mode(adapter, 0);
		clear_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map);
		cxgb3_set_dummy_ops(tdev);
	}
	return err;
}

static int offload_close(struct t3cdev *tdev)
{
	struct adapter *adapter = tdev2adap(tdev);
	struct t3c_data *td = T3C_DATA(tdev);

	if (!test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map))
		return 0;

	/* Call back all registered clients */
	cxgb3_remove_clients(tdev);

	sysfs_remove_group(&tdev->lldev->dev.kobj, &offload_attr_group);

	/* Flush work scheduled while releasing TIDs */
	flush_work_sync(&td->tid_release_task);

	tdev->lldev = NULL;
	cxgb3_set_dummy_ops(tdev);
	t3_tp_set_offload_mode(adapter, 0);
	clear_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map);

	if (!adapter->open_device_map)
		cxgb_down(adapter, 0);

	cxgb3_offload_deactivate(adapter);
	return 0;
}

static int cxgb_open(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	int other_ports = adapter->open_device_map & PORT_MASK;
	int err;

	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0)
		return err;

	set_bit(pi->port_id, &adapter->open_device_map);
	if (is_offload(adapter) && !ofld_disable) {
		err = offload_open(dev);
		if (err)
			printk(KERN_WARNING
			       "Could not initialize offload capabilities\n");
	}

	netif_set_real_num_tx_queues(dev, pi->nqsets);
	err = netif_set_real_num_rx_queues(dev, pi->nqsets);
	if (err)
		return err;
	link_start(dev);
	t3_port_intr_enable(adapter, pi->port_id);
	netif_tx_start_all_queues(dev);
	if (!other_ports)
		schedule_chk_task(adapter);

	cxgb3_event_notify(&adapter->tdev, OFFLOAD_PORT_UP, pi->port_id);
	return 0;
}

static int __cxgb_close(struct net_device *dev, int on_wq)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	
	if (!adapter->open_device_map)
		return 0;

	/* Stop link fault interrupts */
	t3_xgm_intr_disable(adapter, pi->port_id);
	t3_read_reg(adapter, A_XGM_INT_STATUS + pi->mac.offset);

	t3_port_intr_disable(adapter, pi->port_id);
	netif_tx_stop_all_queues(dev);
	pi->phy.ops->power_down(&pi->phy, 1);
	netif_carrier_off(dev);
	t3_mac_disable(&pi->mac, MAC_DIRECTION_TX | MAC_DIRECTION_RX);

	spin_lock_irq(&adapter->work_lock);	/* sync with update task */
	clear_bit(pi->port_id, &adapter->open_device_map);
	spin_unlock_irq(&adapter->work_lock);

	if (!(adapter->open_device_map & PORT_MASK))
		cancel_delayed_work_sync(&adapter->adap_check_task);

	if (!adapter->open_device_map)
		cxgb_down(adapter, on_wq);

	cxgb3_event_notify(&adapter->tdev, OFFLOAD_PORT_DOWN, pi->port_id);
	return 0;
}

static int cxgb_close(struct net_device *dev)
{
	return __cxgb_close(dev, 0);
}

static struct net_device_stats *cxgb_get_stats(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct net_device_stats *ns = &pi->netstats;
	const struct mac_stats *pstats;

	spin_lock(&adapter->stats_lock);
	pstats = t3_mac_update_stats(&pi->mac);
	spin_unlock(&adapter->stats_lock);

	ns->tx_bytes = pstats->tx_octets;
	ns->tx_packets = pstats->tx_frames;
	ns->rx_bytes = pstats->rx_octets;
	ns->rx_packets = pstats->rx_frames;
	ns->multicast = pstats->rx_mcast_frames;

	ns->tx_errors = pstats->tx_underrun;
	ns->rx_errors = pstats->rx_symbol_errs + pstats->rx_fcs_errs +
	    pstats->rx_too_long + pstats->rx_jabber + pstats->rx_short +
	    pstats->rx_fifo_ovfl;

	/* detailed rx_errors */
	ns->rx_length_errors = pstats->rx_jabber + pstats->rx_too_long;
	ns->rx_over_errors = 0;
	ns->rx_crc_errors = pstats->rx_fcs_errs;
	ns->rx_frame_errors = pstats->rx_symbol_errs;
	ns->rx_fifo_errors = pstats->rx_fifo_ovfl;
	ns->rx_missed_errors = pstats->rx_cong_drops;

	/* detailed tx_errors */
	ns->tx_aborted_errors = 0;
	ns->tx_carrier_errors = 0;
	ns->tx_fifo_errors = pstats->tx_underrun;
	ns->tx_heartbeat_errors = 0;
	ns->tx_window_errors = 0;
	return ns;
}

static u32 get_msglevel(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	return adapter->msg_enable;
}

static void set_msglevel(struct net_device *dev, u32 val)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	adapter->msg_enable = val;
}

static char stats_strings[][ETH_GSTRING_LEN] = {
	"TxOctetsOK         ",
	"TxFramesOK         ",
	"TxMulticastFramesOK",
	"TxBroadcastFramesOK",
	"TxPauseFrames      ",
	"TxUnderrun         ",
	"TxExtUnderrun      ",

	"TxFrames64         ",
	"TxFrames65To127    ",
	"TxFrames128To255   ",
	"TxFrames256To511   ",
	"TxFrames512To1023  ",
	"TxFrames1024To1518 ",
	"TxFrames1519ToMax  ",

	"RxOctetsOK         ",
	"RxFramesOK         ",
	"RxMulticastFramesOK",
	"RxBroadcastFramesOK",
	"RxPauseFrames      ",
	"RxFCSErrors        ",
	"RxSymbolErrors     ",
	"RxShortErrors      ",
	"RxJabberErrors     ",
	"RxLengthErrors     ",
	"RxFIFOoverflow     ",

	"RxFrames64         ",
	"RxFrames65To127    ",
	"RxFrames128To255   ",
	"RxFrames256To511   ",
	"RxFrames512To1023  ",
	"RxFrames1024To1518 ",
	"RxFrames1519ToMax  ",

	"PhyFIFOErrors      ",
	"TSO                ",
	"VLANextractions    ",
	"VLANinsertions     ",
	"TxCsumOffload      ",
	"RxCsumGood         ",
	"LroAggregated      ",
	"LroFlushed         ",
	"LroNoDesc          ",
	"RxDrops            ",

	"CheckTXEnToggled   ",
	"CheckResets        ",

	"LinkFaults         ",
};

static int get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(stats_strings);
	default:
		return -EOPNOTSUPP;
	}
}

#define T3_REGMAP_SIZE (3 * 1024)

static int get_regs_len(struct net_device *dev)
{
	return T3_REGMAP_SIZE;
}

static int get_eeprom_len(struct net_device *dev)
{
	return EEPROMSIZE;
}

static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	u32 fw_vers = 0;
	u32 tp_vers = 0;

	spin_lock(&adapter->stats_lock);
	t3_get_fw_version(adapter, &fw_vers);
	t3_get_tp_version(adapter, &tp_vers);
	spin_unlock(&adapter->stats_lock);

	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
	strlcpy(info->bus_info, pci_name(adapter->pdev),
		sizeof(info->bus_info));
	if (!fw_vers)
		strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
	else {
		snprintf(info->fw_version, sizeof(info->fw_version),
			 "%s %u.%u.%u TP %u.%u.%u",
			 G_FW_VERSION_TYPE(fw_vers) ? "T" : "N",
			 G_FW_VERSION_MAJOR(fw_vers),
			 G_FW_VERSION_MINOR(fw_vers),
			 G_FW_VERSION_MICRO(fw_vers),
			 G_TP_VERSION_MAJOR(tp_vers),
			 G_TP_VERSION_MINOR(tp_vers),
			 G_TP_VERSION_MICRO(tp_vers));
	}
}

static void get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
	if (stringset == ETH_SS_STATS)
		memcpy(data, stats_strings, sizeof(stats_strings));
}

static unsigned long collect_sge_port_stats(struct adapter *adapter,
					    struct port_info *p, int idx)
{
	int i;
	unsigned long tot = 0;

	for (i = p->first_qset; i < p->first_qset + p->nqsets; ++i)
		tot += adapter->sge.qs[i].port_stats[idx];
	return tot;
}

static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
		      u64 *data)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	const struct mac_stats *s;

	spin_lock(&adapter->stats_lock);
	s = t3_mac_update_stats(&pi->mac);
	spin_unlock(&adapter->stats_lock);

	*data++ = s->tx_octets;
	*data++ = s->tx_frames;
	*data++ = s->tx_mcast_frames;
	*data++ = s->tx_bcast_frames;
	*data++ = s->tx_pause;
	*data++ = s->tx_underrun;
	*data++ = s->tx_fifo_urun;

	*data++ = s->tx_frames_64;
	*data++ = s->tx_frames_65_127;
	*data++ = s->tx_frames_128_255;
	*data++ = s->tx_frames_256_511;
	*data++ = s->tx_frames_512_1023;
	*data++ = s->tx_frames_1024_1518;
	*data++ = s->tx_frames_1519_max;

	*data++ = s->rx_octets;
	*data++ = s->rx_frames;
	*data++ = s->rx_mcast_frames;
	*data++ = s->rx_bcast_frames;
	*data++ = s->rx_pause;
	*data++ = s->rx_fcs_errs;
	*data++ = s->rx_symbol_errs;
	*data++ = s->rx_short;
	*data++ = s->rx_jabber;
	*data++ = s->rx_too_long;
	*data++ = s->rx_fifo_ovfl;

	*data++ = s->rx_frames_64;
	*data++ = s->rx_frames_65_127;
	*data++ = s->rx_frames_128_255;
	*data++ = s->rx_frames_256_511;
	*data++ = s->rx_frames_512_1023;
	*data++ = s->rx_frames_1024_1518;
	*data++ = s->rx_frames_1519_max;

	*data++ = pi->phy.fifo_errors;

	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_TSO);
	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_VLANEX);
	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_VLANINS);
	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_TX_CSUM);
	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_RX_CSUM_GOOD);
	*data++ = 0;
	*data++ = 0;
	*data++ = 0;
	*data++ = s->rx_cong_drops;

	*data++ = s->num_toggled;
	*data++ = s->num_resets;

	*data++ = s->link_faults;
}

static inline void reg_block_dump(struct adapter *ap, void *buf,
				  unsigned int start, unsigned int end)
{
	u32 *p = buf + start;

	for (; start <= end; start += sizeof(u32))
		*p++ = t3_read_reg(ap, start);
}

static void get_regs(struct net_device *dev, struct ethtool_regs *regs,
		     void *buf)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *ap = pi->adapter;

	/*
	 * Version scheme:
	 * bits 0..9: chip version
	 * bits 10..15: chip revision
	 * bit 31: set for PCIe cards
	 */
	regs->version = 3 | (ap->params.rev << 10) | (is_pcie(ap) << 31);

	/*
	 * We skip the MAC statistics registers because they are clear-on-read.
	 * Also reading multi-register stats would need to synchronize with the
	 * periodic mac stats accumulation.  Hard to justify the complexity.
	 */
	memset(buf, 0, T3_REGMAP_SIZE);
	reg_block_dump(ap, buf, 0, A_SG_RSPQ_CREDIT_RETURN);
	reg_block_dump(ap, buf, A_SG_HI_DRB_HI_THRSH, A_ULPRX_PBL_ULIMIT);
	reg_block_dump(ap, buf, A_ULPTX_CONFIG, A_MPS_INT_CAUSE);
	reg_block_dump(ap, buf, A_CPL_SWITCH_CNTRL, A_CPL_MAP_TBL_DATA);
	reg_block_dump(ap, buf, A_SMB_GLOBAL_TIME_CFG, A_XGM_SERDES_STAT3);
	reg_block_dump(ap, buf, A_XGM_SERDES_STATUS0,
		       XGM_REG(A_XGM_SERDES_STAT3, 1));
	reg_block_dump(ap, buf, XGM_REG(A_XGM_SERDES_STATUS0, 1),
		       XGM_REG(A_XGM_RX_SPI4_SOP_EOP_CNT, 1));
}

static int restart_autoneg(struct net_device *dev)
{
	struct port_info *p = netdev_priv(dev);

	if (!netif_running(dev))
		return -EAGAIN;
	if (p->link_config.autoneg != AUTONEG_ENABLE)
		return -EINVAL;
	p->phy.ops->autoneg_restart(&p->phy);
	return 0;
}

static int set_phys_id(struct net_device *dev,
		       enum ethtool_phys_id_state state)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	switch (state) {
	case ETHTOOL_ID_ACTIVE:
		return 1;	/* cycle on/off once per second */

	case ETHTOOL_ID_OFF:
		t3_set_reg_field(adapter, A_T3DBG_GPIO_EN, F_GPIO0_OUT_VAL, 0);
		break;

	case ETHTOOL_ID_ON:
	case ETHTOOL_ID_INACTIVE:
		t3_set_reg_field(adapter, A_T3DBG_GPIO_EN, F_GPIO0_OUT_VAL,
			 F_GPIO0_OUT_VAL);
	}

	return 0;
}

static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
	struct port_info *p = netdev_priv(dev);

	cmd->supported = p->link_config.supported;
	cmd->advertising = p->link_config.advertising;

	if (netif_carrier_ok(dev)) {
		ethtool_cmd_speed_set(cmd, p->link_config.speed);
		cmd->duplex = p->link_config.duplex;
	} else {
		ethtool_cmd_speed_set(cmd, -1);
		cmd->duplex = -1;
	}

	cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE;
	cmd->phy_address = p->phy.mdio.prtad;
	cmd->transceiver = XCVR_EXTERNAL;
	cmd->autoneg = p->link_config.autoneg;
	cmd->maxtxpkt = 0;
	cmd->maxrxpkt = 0;
	return 0;
}

static int speed_duplex_to_caps(int speed, int duplex)
{
	int cap = 0;

	switch (speed) {
	case SPEED_10:
		if (duplex == DUPLEX_FULL)
			cap = SUPPORTED_10baseT_Full;
		else
			cap = SUPPORTED_10baseT_Half;
		break;
	case SPEED_100:
		if (duplex == DUPLEX_FULL)
			cap = SUPPORTED_100baseT_Full;
		else
			cap = SUPPORTED_100baseT_Half;
		break;
	case SPEED_1000:
		if (duplex == DUPLEX_FULL)
			cap = SUPPORTED_1000baseT_Full;
		else
			cap = SUPPORTED_1000baseT_Half;
		break;
	case SPEED_10000:
		if (duplex == DUPLEX_FULL)
			cap = SUPPORTED_10000baseT_Full;
	}
	return cap;
}

#define ADVERTISED_MASK (ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full | \
		      ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full | \
		      ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full | \
		      ADVERTISED_10000baseT_Full)

static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
	struct port_info *p = netdev_priv(dev);
	struct link_config *lc = &p->link_config;

	if (!(lc->supported & SUPPORTED_Autoneg)) {
		/*
		 * PHY offers a single speed/duplex.  See if that's what's
		 * being requested.
		 */
		if (cmd->autoneg == AUTONEG_DISABLE) {
			u32 speed = ethtool_cmd_speed(cmd);
			int cap = speed_duplex_to_caps(speed, cmd->duplex);
			if (lc->supported & cap)
				return 0;
		}
		return -EINVAL;
	}

	if (cmd->autoneg == AUTONEG_DISABLE) {
		u32 speed = ethtool_cmd_speed(cmd);
		int cap = speed_duplex_to_caps(speed, cmd->duplex);

		if (!(lc->supported & cap) || (speed == SPEED_1000))
			return -EINVAL;
		lc->requested_speed = speed;
		lc->requested_duplex = cmd->duplex;
		lc->advertising = 0;
	} else {
		cmd->advertising &= ADVERTISED_MASK;
		cmd->advertising &= lc->supported;
		if (!cmd->advertising)
			return -EINVAL;
		lc->requested_speed = SPEED_INVALID;
		lc->requested_duplex = DUPLEX_INVALID;
		lc->advertising = cmd->advertising | ADVERTISED_Autoneg;
	}
	lc->autoneg = cmd->autoneg;
	if (netif_running(dev))
		t3_link_start(&p->phy, &p->mac, lc);
	return 0;
}

static void get_pauseparam(struct net_device *dev,
			   struct ethtool_pauseparam *epause)
{
	struct port_info *p = netdev_priv(dev);

	epause->autoneg = (p->link_config.requested_fc & PAUSE_AUTONEG) != 0;
	epause->rx_pause = (p->link_config.fc & PAUSE_RX) != 0;
	epause->tx_pause = (p->link_config.fc & PAUSE_TX) != 0;
}

static int set_pauseparam(struct net_device *dev,
			  struct ethtool_pauseparam *epause)
{
	struct port_info *p = netdev_priv(dev);
	struct link_config *lc = &p->link_config;

	if (epause->autoneg == AUTONEG_DISABLE)
		lc->requested_fc = 0;
	else if (lc->supported & SUPPORTED_Autoneg)
		lc->requested_fc = PAUSE_AUTONEG;
	else
		return -EINVAL;

	if (epause->rx_pause)
		lc->requested_fc |= PAUSE_RX;
	if (epause->tx_pause)
		lc->requested_fc |= PAUSE_TX;
	if (lc->autoneg == AUTONEG_ENABLE) {
		if (netif_running(dev))
			t3_link_start(&p->phy, &p->mac, lc);
	} else {
		lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX);
		if (netif_running(dev))
			t3_mac_set_speed_duplex_fc(&p->mac, -1, -1, lc->fc);
	}
	return 0;
}

static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	const struct qset_params *q = &adapter->params.sge.qset[pi->first_qset];

	e->rx_max_pending = MAX_RX_BUFFERS;
	e->rx_jumbo_max_pending = MAX_RX_JUMBO_BUFFERS;
	e->tx_max_pending = MAX_TXQ_ENTRIES;

	e->rx_pending = q->fl_size;
	e->rx_mini_pending = q->rspq_size;
	e->rx_jumbo_pending = q->jumbo_size;
	e->tx_pending = q->txq_size[0];
}

static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct qset_params *q;
	int i;

	if (e->rx_pending > MAX_RX_BUFFERS ||
	    e->rx_jumbo_pending > MAX_RX_JUMBO_BUFFERS ||
	    e->tx_pending > MAX_TXQ_ENTRIES ||
	    e->rx_mini_pending > MAX_RSPQ_ENTRIES ||
	    e->rx_mini_pending < MIN_RSPQ_ENTRIES ||
	    e->rx_pending < MIN_FL_ENTRIES ||
	    e->rx_jumbo_pending < MIN_FL_ENTRIES ||
	    e->tx_pending < adapter->params.nports * MIN_TXQ_ENTRIES)
		return -EINVAL;

	if (adapter->flags & FULL_INIT_DONE)
		return -EBUSY;

	q = &adapter->params.sge.qset[pi->first_qset];
	for (i = 0; i < pi->nqsets; ++i, ++q) {
		q->rspq_size = e->rx_mini_pending;
		q->fl_size = e->rx_pending;
		q->jumbo_size = e->rx_jumbo_pending;
		q->txq_size[0] = e->tx_pending;
		q->txq_size[1] = e->tx_pending;
		q->txq_size[2] = e->tx_pending;
	}
	return 0;
}

static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct qset_params *qsp;
	struct sge_qset *qs;
	int i;

	if (c->rx_coalesce_usecs * 10 > M_NEWTIMER)
		return -EINVAL;

	for (i = 0; i < pi->nqsets; i++) {
		qsp = &adapter->params.sge.qset[i];
		qs = &adapter->sge.qs[i];
		qsp->coalesce_usecs = c->rx_coalesce_usecs;
		t3_update_qset_coalesce(qs, qsp);
	}

	return 0;
}

static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct qset_params *q = adapter->params.sge.qset;

	c->rx_coalesce_usecs = q->coalesce_usecs;
	return 0;
}

static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e,
		      u8 * data)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	int i, err = 0;

	u8 *buf = kmalloc(EEPROMSIZE, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	e->magic = EEPROM_MAGIC;
	for (i = e->offset & ~3; !err && i < e->offset + e->len; i += 4)
		err = t3_seeprom_read(adapter, i, (__le32 *) & buf[i]);

	if (!err)
		memcpy(data, buf + e->offset, e->len);
	kfree(buf);
	return err;
}

static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
		      u8 * data)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	u32 aligned_offset, aligned_len;
	__le32 *p;
	u8 *buf;
	int err;

	if (eeprom->magic != EEPROM_MAGIC)
		return -EINVAL;

	aligned_offset = eeprom->offset & ~3;
	aligned_len = (eeprom->len + (eeprom->offset & 3) + 3) & ~3;

	if (aligned_offset != eeprom->offset || aligned_len != eeprom->len) {
		buf = kmalloc(aligned_len, GFP_KERNEL);
		if (!buf)
			return -ENOMEM;
		err = t3_seeprom_read(adapter, aligned_offset, (__le32 *) buf);
		if (!err && aligned_len > 4)
			err = t3_seeprom_read(adapter,
					      aligned_offset + aligned_len - 4,
					      (__le32 *) & buf[aligned_len - 4]);
		if (err)
			goto out;
		memcpy(buf + (eeprom->offset & 3), data, eeprom->len);
	} else
		buf = data;

	err = t3_seeprom_wp(adapter, 0);
	if (err)
		goto out;

	for (p = (__le32 *) buf; !err && aligned_len; aligned_len -= 4, p++) {
		err = t3_seeprom_write(adapter, aligned_offset, *p);
		aligned_offset += 4;
	}

	if (!err)
		err = t3_seeprom_wp(adapter, 1);
out:
	if (buf != data)
		kfree(buf);
	return err;
}

static void get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
{
	wol->supported = 0;
	wol->wolopts = 0;
	memset(&wol->sopass, 0, sizeof(wol->sopass));
}

static const struct ethtool_ops cxgb_ethtool_ops = {
	.get_settings = get_settings,
	.set_settings = set_settings,
	.get_drvinfo = get_drvinfo,
	.get_msglevel = get_msglevel,
	.set_msglevel = set_msglevel,
	.get_ringparam = get_sge_param,
	.set_ringparam = set_sge_param,
	.get_coalesce = get_coalesce,
	.set_coalesce = set_coalesce,
	.get_eeprom_len = get_eeprom_len,
	.get_eeprom = get_eeprom,
	.set_eeprom = set_eeprom,
	.get_pauseparam = get_pauseparam,
	.set_pauseparam = set_pauseparam,
	.get_link = ethtool_op_get_link,
	.get_strings = get_strings,
	.set_phys_id = set_phys_id,
	.nway_reset = restart_autoneg,
	.get_sset_count = get_sset_count,
	.get_ethtool_stats = get_stats,
	.get_regs_len = get_regs_len,
	.get_regs = get_regs,
	.get_wol = get_wol,
};

static int in_range(int val, int lo, int hi)
{
	return val < 0 || (val <= hi && val >= lo);
}

static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	u32 cmd;
	int ret;

	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
		return -EFAULT;

	switch (cmd) {
	case CHELSIO_SET_QSET_PARAMS:{
		int i;
		struct qset_params *q;
		struct ch_qset_params t;
		int q1 = pi->first_qset;
		int nqsets = pi->nqsets;

		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (copy_from_user(&t, useraddr, sizeof(t)))
			return -EFAULT;
		if (t.qset_idx >= SGE_QSETS)
			return -EINVAL;
		if (!in_range(t.intr_lat, 0, M_NEWTIMER) ||
		    !in_range(t.cong_thres, 0, 255) ||
		    !in_range(t.txq_size[0], MIN_TXQ_ENTRIES,
			      MAX_TXQ_ENTRIES) ||
		    !in_range(t.txq_size[1], MIN_TXQ_ENTRIES,
			      MAX_TXQ_ENTRIES) ||
		    !in_range(t.txq_size[2], MIN_CTRL_TXQ_ENTRIES,
			      MAX_CTRL_TXQ_ENTRIES) ||
		    !in_range(t.fl_size[0], MIN_FL_ENTRIES,
			      MAX_RX_BUFFERS) ||
		    !in_range(t.fl_size[1], MIN_FL_ENTRIES,
			      MAX_RX_JUMBO_BUFFERS) ||
		    !in_range(t.rspq_size, MIN_RSPQ_ENTRIES,
			      MAX_RSPQ_ENTRIES))
			return -EINVAL;

		if ((adapter->flags & FULL_INIT_DONE) &&
			(t.rspq_size >= 0 || t.fl_size[0] >= 0 ||
			t.fl_size[1] >= 0 || t.txq_size[0] >= 0 ||
			t.txq_size[1] >= 0 || t.txq_size[2] >= 0 ||
			t.polling >= 0 || t.cong_thres >= 0))
			return -EBUSY;

		/* Allow setting of any available qset when offload enabled */
		if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) {
			q1 = 0;
			for_each_port(adapter, i) {
				pi = adap2pinfo(adapter, i);
				nqsets += pi->first_qset + pi->nqsets;
			}
		}

		if (t.qset_idx < q1)
			return -EINVAL;
		if (t.qset_idx > q1 + nqsets - 1)
			return -EINVAL;

		q = &adapter->params.sge.qset[t.qset_idx];

		if (t.rspq_size >= 0)
			q->rspq_size = t.rspq_size;
		if (t.fl_size[0] >= 0)
			q->fl_size = t.fl_size[0];
		if (t.fl_size[1] >= 0)
			q->jumbo_size = t.fl_size[1];
		if (t.txq_size[0] >= 0)
			q->txq_size[0] = t.txq_size[0];
		if (t.txq_size[1] >= 0)
			q->txq_size[1] = t.txq_size[1];
		if (t.txq_size[2] >= 0)
			q->txq_size[2] = t.txq_size[2];
		if (t.cong_thres >= 0)
			q->cong_thres = t.cong_thres;
		if (t.intr_lat >= 0) {
			struct sge_qset *qs =
				&adapter->sge.qs[t.qset_idx];

			q->coalesce_usecs = t.intr_lat;
			t3_update_qset_coalesce(qs, q);
		}
		if (t.polling >= 0) {
			if (adapter->flags & USING_MSIX)
				q->polling = t.polling;
			else {
				/* No polling with INTx for T3A */
				if (adapter->params.rev == 0 &&
					!(adapter->flags & USING_MSI))
					t.polling = 0;

				for (i = 0; i < SGE_QSETS; i++) {
					q = &adapter->params.sge.
						qset[i];
					q->polling = t.polling;
				}
			}
		}

		if (t.lro >= 0) {
			if (t.lro)
				dev->wanted_features |= NETIF_F_GRO;
			else
				dev->wanted_features &= ~NETIF_F_GRO;
			netdev_update_features(dev);
		}

		break;
	}
	case CHELSIO_GET_QSET_PARAMS:{
		struct qset_params *q;
		struct ch_qset_params t;
		int q1 = pi->first_qset;
		int nqsets = pi->nqsets;
		int i;

		if (copy_from_user(&t, useraddr, sizeof(t)))
			return -EFAULT;

		/* Display qsets for all ports when offload enabled */
		if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) {
			q1 = 0;
			for_each_port(adapter, i) {
				pi = adap2pinfo(adapter, i);
				nqsets = pi->first_qset + pi->nqsets;
			}
		}

		if (t.qset_idx >= nqsets)
			return -EINVAL;

		q = &adapter->params.sge.qset[q1 + t.qset_idx];
		t.rspq_size = q->rspq_size;
		t.txq_size[0] = q->txq_size[0];
		t.txq_size[1] = q->txq_size[1];
		t.txq_size[2] = q->txq_size[2];
		t.fl_size[0] = q->fl_size;
		t.fl_size[1] = q->jumbo_size;
		t.polling = q->polling;
		t.lro = !!(dev->features & NETIF_F_GRO);
		t.intr_lat = q->coalesce_usecs;
		t.cong_thres = q->cong_thres;
		t.qnum = q1;

		if (adapter->flags & USING_MSIX)
			t.vector = adapter->msix_info[q1 + t.qset_idx + 1].vec;
		else
			t.vector = adapter->pdev->irq;

		if (copy_to_user(useraddr, &t, sizeof(t)))
			return -EFAULT;
		break;
	}
	case CHELSIO_SET_QSET_NUM:{
		struct ch_reg edata;
		unsigned int i, first_qset = 0, other_qsets = 0;

		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (adapter->flags & FULL_INIT_DONE)
			return -EBUSY;
		if (copy_from_user(&edata, useraddr, sizeof(edata)))
			return -EFAULT;
		if (edata.val < 1 ||
			(edata.val > 1 && !(adapter->flags & USING_MSIX)))
			return -EINVAL;

		for_each_port(adapter, i)
			if (adapter->port[i] && adapter->port[i] != dev)
				other_qsets += adap2pinfo(adapter, i)->nqsets;

		if (edata.val + other_qsets > SGE_QSETS)
			return -EINVAL;

		pi->nqsets = edata.val;

		for_each_port(adapter, i)
			if (adapter->port[i]) {
				pi = adap2pinfo(adapter, i);
				pi->first_qset = first_qset;
				first_qset += pi->nqsets;
			}
		break;
	}
	case CHELSIO_GET_QSET_NUM:{
		struct ch_reg edata;

		memset(&edata, 0, sizeof(struct ch_reg));

		edata.cmd = CHELSIO_GET_QSET_NUM;
		edata.val = pi->nqsets;
		if (copy_to_user(useraddr, &edata, sizeof(edata)))
			return -EFAULT;
		break;
	}
	case CHELSIO_LOAD_FW:{
		u8 *fw_data;
		struct ch_mem_range t;

		if (!capable(CAP_SYS_RAWIO))
			return -EPERM;
		if (copy_from_user(&t, useraddr, sizeof(t)))
			return -EFAULT;
		/* Check t.len sanity ? */
		fw_data = memdup_user(useraddr + sizeof(t), t.len);
		if (IS_ERR(fw_data))
			return PTR_ERR(fw_data);

		ret = t3_load_fw(adapter, fw_data, t.len);
		kfree(fw_data);
		if (ret)
			return ret;
		break;
	}
	case CHELSIO_SETMTUTAB:{
		struct ch_mtus m;
		int i;

		if (!is_offload(adapter))
			return -EOPNOTSUPP;
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (offload_running(adapter))
			return -EBUSY;
		if (copy_from_user(&m, useraddr, sizeof(m)))
			return -EFAULT;
		if (m.nmtus != NMTUS)
			return -EINVAL;
		if (m.mtus[0] < 81)	/* accommodate SACK */
			return -EINVAL;

		/* MTUs must be in ascending order */
		for (i = 1; i < NMTUS; ++i)
			if (m.mtus[i] < m.mtus[i - 1])
				return -EINVAL;

		memcpy(adapter->params.mtus, m.mtus,
			sizeof(adapter->params.mtus));
		break;
	}
	case CHELSIO_GET_PM:{
		struct tp_params *p = &adapter->params.tp;
		struct ch_pm m = {.cmd = CHELSIO_GET_PM };

		if (!is_offload(adapter))
			return -EOPNOTSUPP;
		m.tx_pg_sz = p->tx_pg_size;
		m.tx_num_pg = p->tx_num_pgs;
		m.rx_pg_sz = p->rx_pg_size;
		m.rx_num_pg = p->rx_num_pgs;
		m.pm_total = p->pmtx_size + p->chan_rx_size * p->nchan;
		if (copy_to_user(useraddr, &m, sizeof(m)))
			return -EFAULT;
		break;
	}
	case CHELSIO_SET_PM:{
		struct ch_pm m;
		struct tp_params *p = &adapter->params.tp;

		if (!is_offload(adapter))
			return -EOPNOTSUPP;
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (adapter->flags & FULL_INIT_DONE)
			return -EBUSY;
		if (copy_from_user(&m, useraddr, sizeof(m)))
			return -EFAULT;
		if (!is_power_of_2(m.rx_pg_sz) ||
			!is_power_of_2(m.tx_pg_sz))
			return -EINVAL;	/* not power of 2 */
		if (!(m.rx_pg_sz & 0x14000))
			return -EINVAL;	/* not 16KB or 64KB */
		if (!(m.tx_pg_sz & 0x1554000))
			return -EINVAL;
		if (m.tx_num_pg == -1)
			m.tx_num_pg = p->tx_num_pgs;
		if (m.rx_num_pg == -1)
			m.rx_num_pg = p->rx_num_pgs;
		if (m.tx_num_pg % 24 || m.rx_num_pg % 24)
			return -EINVAL;
		if (m.rx_num_pg * m.rx_pg_sz > p->chan_rx_size ||
			m.tx_num_pg * m.tx_pg_sz > p->chan_tx_size)
			return -EINVAL;
		p->rx_pg_size = m.rx_pg_sz;
		p->tx_pg_size = m.tx_pg_sz;
		p->rx_num_pgs = m.rx_num_pg;
		p->tx_num_pgs = m.tx_num_pg;
		break;
	}
	case CHELSIO_GET_MEM:{
		struct ch_mem_range t;
		struct mc7 *mem;
		u64 buf[32];

		if (!is_offload(adapter))
			return -EOPNOTSUPP;
		if (!(adapter->flags & FULL_INIT_DONE))
			return -EIO;	/* need the memory controllers */
		if (copy_from_user(&t, useraddr, sizeof(t)))
			return -EFAULT;
		if ((t.addr & 7) || (t.len & 7))
			return -EINVAL;
		if (t.mem_id == MEM_CM)
			mem = &adapter->cm;
		else if (t.mem_id == MEM_PMRX)
			mem = &adapter->pmrx;
		else if (t.mem_id == MEM_PMTX)
			mem = &adapter->pmtx;
		else
			return -EINVAL;

		/*
		 * Version scheme:
		 * bits 0..9: chip version
		 * bits 10..15: chip revision
		 */
		t.version = 3 | (adapter->params.rev << 10);
		if (copy_to_user(useraddr, &t, sizeof(t)))
			return -EFAULT;

		/*
		 * Read 256 bytes at a time as len can be large and we don't
		 * want to use huge intermediate buffers.
		 */
		useraddr += sizeof(t);	/* advance to start of buffer */
		while (t.len) {
			unsigned int chunk =
				min_t(unsigned int, t.len, sizeof(buf));

			ret =
				t3_mc7_bd_read(mem, t.addr / 8, chunk / 8,
						buf);
			if (ret)
				return ret;
			if (copy_to_user(useraddr, buf, chunk))
				return -EFAULT;
			useraddr += chunk;
			t.addr += chunk;
			t.len -= chunk;
		}
		break;
	}
	case CHELSIO_SET_TRACE_FILTER:{
		struct ch_trace t;
		const struct trace_params *tp;

		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (!offload_running(adapter))
			return -EAGAIN;
		if (copy_from_user(&t, useraddr, sizeof(t)))
			return -EFAULT;

		tp = (const struct trace_params *)&t.sip;
		if (t.config_tx)
			t3_config_trace_filter(adapter, tp, 0,
						t.invert_match,
						t.trace_tx);
		if (t.config_rx)
			t3_config_trace_filter(adapter, tp, 1,
						t.invert_match,
						t.trace_rx);
		break;
	}
	default:
		return -EOPNOTSUPP;
	}
	return 0;
}

static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
{
	struct mii_ioctl_data *data = if_mii(req);
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	switch (cmd) {
	case SIOCGMIIREG:
	case SIOCSMIIREG:
		/* Convert phy_id from older PRTAD/DEVAD format */
		if (is_10G(adapter) &&
		    !mdio_phy_id_is_c45(data->phy_id) &&
		    (data->phy_id & 0x1f00) &&
		    !(data->phy_id & 0xe0e0))
			data->phy_id = mdio_phy_id_c45(data->phy_id >> 8,
						       data->phy_id & 0x1f);
		/* FALLTHRU */
	case SIOCGMIIPHY:
		return mdio_mii_ioctl(&pi->phy.mdio, data, cmd);
	case SIOCCHIOCTL:
		return cxgb_extension_ioctl(dev, req->ifr_data);
	default:
		return -EOPNOTSUPP;
	}
}

static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	int ret;

	if (new_mtu < 81)	/* accommodate SACK */
		return -EINVAL;
	if ((ret = t3_mac_set_mtu(&pi->mac, new_mtu)))
		return ret;
	dev->mtu = new_mtu;
	init_port_mtus(adapter);
	if (adapter->params.rev == 0 && offload_running(adapter))
		t3_load_mtus(adapter, adapter->params.mtus,
			     adapter->params.a_wnd, adapter->params.b_wnd,
			     adapter->port[0]->mtu);
	return 0;
}

static int cxgb_set_mac_addr(struct net_device *dev, void *p)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	struct sockaddr *addr = p;

	if (!is_valid_ether_addr(addr->sa_data))
		return -EINVAL;

	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
	t3_mac_set_address(&pi->mac, LAN_MAC_IDX, dev->dev_addr);
	if (offload_running(adapter))
		write_smt_entry(adapter, pi->port_id);
	return 0;
}

/**
 * t3_synchronize_rx - wait for current Rx processing on a port to complete
 * @adap: the adapter
 * @p: the port
 *
 * Ensures that current Rx processing on any of the queues associated with
 * the given port completes before returning.  We do this by acquiring and
 * releasing the locks of the response queues associated with the port.
 */
static void t3_synchronize_rx(struct adapter *adap, const struct port_info *p)
{
	int i;

	for (i = p->first_qset; i < p->first_qset + p->nqsets; i++) {
		struct sge_rspq *q = &adap->sge.qs[i].rspq;

		spin_lock_irq(&q->lock);
		spin_unlock_irq(&q->lock);
	}
}

static void cxgb_vlan_mode(struct net_device *dev, u32 features)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	if (adapter->params.rev > 0) {
		t3_set_vlan_accel(adapter, 1 << pi->port_id,
				  features & NETIF_F_HW_VLAN_RX);
	} else {
		/* single control for all ports */
		unsigned int i, have_vlans = features & NETIF_F_HW_VLAN_RX;

		for_each_port(adapter, i)
			have_vlans |=
				adapter->port[i]->features & NETIF_F_HW_VLAN_RX;

		t3_set_vlan_accel(adapter, 1, have_vlans);
	}
	t3_synchronize_rx(adapter, pi);
}

static u32 cxgb_fix_features(struct net_device *dev, u32 features)
{
	/*
	 * Since there is no support for separate rx/tx vlan accel
	 * enable/disable make sure tx flag is always in same state as rx.
	 */
	if (features & NETIF_F_HW_VLAN_RX)
		features |= NETIF_F_HW_VLAN_TX;
	else
		features &= ~NETIF_F_HW_VLAN_TX;

	return features;
}

static int cxgb_set_features(struct net_device *dev, u32 features)
{
	u32 changed = dev->features ^ features;

	if (changed & NETIF_F_HW_VLAN_RX)
		cxgb_vlan_mode(dev, features);

	return 0;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void cxgb_netpoll(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;
	int qidx;

	for (qidx = pi->first_qset; qidx < pi->first_qset + pi->nqsets; qidx++) {
		struct sge_qset *qs = &adapter->sge.qs[qidx];
		void *source;

		if (adapter->flags & USING_MSIX)
			source = qs;
		else
			source = adapter;

		t3_intr_handler(adapter, qs->rspq.polling) (0, source);
	}
}
#endif

/*
 * Periodic accumulation of MAC statistics.
 */
static void mac_stats_update(struct adapter *adapter)
{
	int i;

	for_each_port(adapter, i) {
		struct net_device *dev = adapter->port[i];
		struct port_info *p = netdev_priv(dev);

		if (netif_running(dev)) {
			spin_lock(&adapter->stats_lock);
			t3_mac_update_stats(&p->mac);
			spin_unlock(&adapter->stats_lock);
		}
	}
}

static void check_link_status(struct adapter *adapter)
{
	int i;

	for_each_port(adapter, i) {
		struct net_device *dev = adapter->port[i];
		struct port_info *p = netdev_priv(dev);
		int link_fault;

		spin_lock_irq(&adapter->work_lock);
		link_fault = p->link_fault;
		spin_unlock_irq(&adapter->work_lock);

		if (link_fault) {
			t3_link_fault(adapter, i);
			continue;
		}

		if (!(p->phy.caps & SUPPORTED_IRQ) && netif_running(dev)) {
			t3_xgm_intr_disable(adapter, i);
			t3_read_reg(adapter, A_XGM_INT_STATUS + p->mac.offset);

			t3_link_changed(adapter, i);
			t3_xgm_intr_enable(adapter, i);
		}
	}
}

static void check_t3b2_mac(struct adapter *adapter)
{
	int i;

	if (!rtnl_trylock())	/* synchronize with ifdown */
		return;

	for_each_port(adapter, i) {
		struct net_device *dev = adapter->port[i];
		struct port_info *p = netdev_priv(dev);
		int status;

		if (!netif_running(dev))
			continue;

		status = 0;
		if (netif_running(dev) && netif_carrier_ok(dev))
			status = t3b2_mac_watchdog_task(&p->mac);
		if (status == 1)
			p->mac.stats.num_toggled++;
		else if (status == 2) {
			struct cmac *mac = &p->mac;

			t3_mac_set_mtu(mac, dev->mtu);
			t3_mac_set_address(mac, LAN_MAC_IDX, dev->dev_addr);
			cxgb_set_rxmode(dev);
			t3_link_start(&p->phy, mac, &p->link_config);
			t3_mac_enable(mac, MAC_DIRECTION_RX | MAC_DIRECTION_TX);
			t3_port_intr_enable(adapter, p->port_id);
			p->mac.stats.num_resets++;
		}
	}
	rtnl_unlock();
}


static void t3_adap_check_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       adap_check_task.work);
	const struct adapter_params *p = &adapter->params;
	int port;
	unsigned int v, status, reset;

	adapter->check_task_cnt++;

	check_link_status(adapter);

	/* Accumulate MAC stats if needed */
	if (!p->linkpoll_period ||
	    (adapter->check_task_cnt * p->linkpoll_period) / 10 >=
	    p->stats_update_period) {
		mac_stats_update(adapter);
		adapter->check_task_cnt = 0;
	}

	if (p->rev == T3_REV_B2)
		check_t3b2_mac(adapter);

	/*
	 * Scan the XGMAC's to check for various conditions which we want to
	 * monitor in a periodic polling manner rather than via an interrupt
	 * condition.  This is used for conditions which would otherwise flood
	 * the system with interrupts and we only really need to know that the
	 * conditions are "happening" ...  For each condition we count the
	 * detection of the condition and reset it for the next polling loop.
	 */
	for_each_port(adapter, port) {
		struct cmac *mac =  &adap2pinfo(adapter, port)->mac;
		u32 cause;

		cause = t3_read_reg(adapter, A_XGM_INT_CAUSE + mac->offset);
		reset = 0;
		if (cause & F_RXFIFO_OVERFLOW) {
			mac->stats.rx_fifo_ovfl++;
			reset |= F_RXFIFO_OVERFLOW;
		}

		t3_write_reg(adapter, A_XGM_INT_CAUSE + mac->offset, reset);
	}

	/*
	 * We do the same as above for FL_EMPTY interrupts.
	 */
	status = t3_read_reg(adapter, A_SG_INT_CAUSE);
	reset = 0;

	if (status & F_FLEMPTY) {
		struct sge_qset *qs = &adapter->sge.qs[0];
		int i = 0;

		reset |= F_FLEMPTY;

		v = (t3_read_reg(adapter, A_SG_RSPQ_FL_STATUS) >> S_FL0EMPTY) &
		    0xffff;

		while (v) {
			qs->fl[i].empty += (v & 1);
			if (i)
				qs++;
			i ^= 1;
			v >>= 1;
		}
	}

	t3_write_reg(adapter, A_SG_INT_CAUSE, reset);

	/* Schedule the next check update if any port is active. */
	spin_lock_irq(&adapter->work_lock);
	if (adapter->open_device_map & PORT_MASK)
		schedule_chk_task(adapter);
	spin_unlock_irq(&adapter->work_lock);
}

static void db_full_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       db_full_task);

	cxgb3_event_notify(&adapter->tdev, OFFLOAD_DB_FULL, 0);
}

static void db_empty_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       db_empty_task);

	cxgb3_event_notify(&adapter->tdev, OFFLOAD_DB_EMPTY, 0);
}

static void db_drop_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       db_drop_task);
	unsigned long delay = 1000;
	unsigned short r;

	cxgb3_event_notify(&adapter->tdev, OFFLOAD_DB_DROP, 0);

	/*
	 * Sleep a while before ringing the driver qset dbs.
	 * The delay is between 1000-2023 usecs.
	 */
	get_random_bytes(&r, 2);
	delay += r & 1023;
	set_current_state(TASK_UNINTERRUPTIBLE);
	schedule_timeout(usecs_to_jiffies(delay));
	ring_dbs(adapter);
}

/*
 * Processes external (PHY) interrupts in process context.
 */
static void ext_intr_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       ext_intr_handler_task);
	int i;

	/* Disable link fault interrupts */
	for_each_port(adapter, i) {
		struct net_device *dev = adapter->port[i];
		struct port_info *p = netdev_priv(dev);

		t3_xgm_intr_disable(adapter, i);
		t3_read_reg(adapter, A_XGM_INT_STATUS + p->mac.offset);
	}

	/* Re-enable link fault interrupts */
	t3_phy_intr_handler(adapter);

	for_each_port(adapter, i)
		t3_xgm_intr_enable(adapter, i);

	/* Now reenable external interrupts */
	spin_lock_irq(&adapter->work_lock);
	if (adapter->slow_intr_mask) {
		adapter->slow_intr_mask |= F_T3DBG;
		t3_write_reg(adapter, A_PL_INT_CAUSE0, F_T3DBG);
		t3_write_reg(adapter, A_PL_INT_ENABLE0,
			     adapter->slow_intr_mask);
	}
	spin_unlock_irq(&adapter->work_lock);
}

/*
 * Interrupt-context handler for external (PHY) interrupts.
 */
void t3_os_ext_intr_handler(struct adapter *adapter)
{
	/*
	 * Schedule a task to handle external interrupts as they may be slow
	 * and we use a mutex to protect MDIO registers.  We disable PHY
	 * interrupts in the meantime and let the task reenable them when
	 * it's done.
	 */
	spin_lock(&adapter->work_lock);
	if (adapter->slow_intr_mask) {
		adapter->slow_intr_mask &= ~F_T3DBG;
		t3_write_reg(adapter, A_PL_INT_ENABLE0,
			     adapter->slow_intr_mask);
		queue_work(cxgb3_wq, &adapter->ext_intr_handler_task);
	}
	spin_unlock(&adapter->work_lock);
}

void t3_os_link_fault_handler(struct adapter *adapter, int port_id)
{
	struct net_device *netdev = adapter->port[port_id];
	struct port_info *pi = netdev_priv(netdev);

	spin_lock(&adapter->work_lock);
	pi->link_fault = 1;
	spin_unlock(&adapter->work_lock);
}

static int t3_adapter_error(struct adapter *adapter, int reset, int on_wq)
{
	int i, ret = 0;

	if (is_offload(adapter) &&
	    test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) {
		cxgb3_event_notify(&adapter->tdev, OFFLOAD_STATUS_DOWN, 0);
		offload_close(&adapter->tdev);
	}

	/* Stop all ports */
	for_each_port(adapter, i) {
		struct net_device *netdev = adapter->port[i];

		if (netif_running(netdev))
			__cxgb_close(netdev, on_wq);
	}

	/* Stop SGE timers */
	t3_stop_sge_timers(adapter);

	adapter->flags &= ~FULL_INIT_DONE;

	if (reset)
		ret = t3_reset_adapter(adapter);

	pci_disable_device(adapter->pdev);

	return ret;
}

static int t3_reenable_adapter(struct adapter *adapter)
{
	if (pci_enable_device(adapter->pdev)) {
		dev_err(&adapter->pdev->dev,
			"Cannot re-enable PCI device after reset.\n");
		goto err;
	}
	pci_set_master(adapter->pdev);
	pci_restore_state(adapter->pdev);
	pci_save_state(adapter->pdev);

	/* Free sge resources */
	t3_free_sge_resources(adapter);

	if (t3_replay_prep_adapter(adapter))
		goto err;

	return 0;
err:
	return -1;
}

static void t3_resume_ports(struct adapter *adapter)
{
	int i;

	/* Restart the ports */
	for_each_port(adapter, i) {
		struct net_device *netdev = adapter->port[i];

		if (netif_running(netdev)) {
			if (cxgb_open(netdev)) {
				dev_err(&adapter->pdev->dev,
					"can't bring device back up"
					" after reset\n");
				continue;
			}
		}
	}

	if (is_offload(adapter) && !ofld_disable)
		cxgb3_event_notify(&adapter->tdev, OFFLOAD_STATUS_UP, 0);
}

/*
 * processes a fatal error.
 * Bring the ports down, reset the chip, bring the ports back up.
 */
static void fatal_error_task(struct work_struct *work)
{
	struct adapter *adapter = container_of(work, struct adapter,
					       fatal_error_handler_task);
	int err = 0;

	rtnl_lock();
	err = t3_adapter_error(adapter, 1, 1);
	if (!err)
		err = t3_reenable_adapter(adapter);
	if (!err)
		t3_resume_ports(adapter);

	CH_ALERT(adapter, "adapter reset %s\n", err ? "failed" : "succeeded");
	rtnl_unlock();
}

void t3_fatal_err(struct adapter *adapter)
{
	unsigned int fw_status[4];

	if (adapter->flags & FULL_INIT_DONE) {
		t3_sge_stop(adapter);
		t3_write_reg(adapter, A_XGM_TX_CTRL, 0);
		t3_write_reg(adapter, A_XGM_RX_CTRL, 0);
		t3_write_reg(adapter, XGM_REG(A_XGM_TX_CTRL, 1), 0);
		t3_write_reg(adapter, XGM_REG(A_XGM_RX_CTRL, 1), 0);

		spin_lock(&adapter->work_lock);
		t3_intr_disable(adapter);
		queue_work(cxgb3_wq, &adapter->fatal_error_handler_task);
		spin_unlock(&adapter->work_lock);
	}
	CH_ALERT(adapter, "encountered fatal error, operation suspended\n");
	if (!t3_cim_ctl_blk_read(adapter, 0xa0, 4, fw_status))
		CH_ALERT(adapter, "FW status: 0x%x, 0x%x, 0x%x, 0x%x\n",
			 fw_status[0], fw_status[1],
			 fw_status[2], fw_status[3]);
}

/**
 * t3_io_error_detected - called when PCI error is detected
 * @pdev: Pointer to PCI device
 * @state: The current pci connection state
 *
 * This function is called after a PCI bus error affecting
 * this device has been detected.
 */
static pci_ers_result_t t3_io_error_detected(struct pci_dev *pdev,
					     pci_channel_state_t state)
{
	struct adapter *adapter = pci_get_drvdata(pdev);

	if (state == pci_channel_io_perm_failure)
		return PCI_ERS_RESULT_DISCONNECT;

	t3_adapter_error(adapter, 0, 0);

	/* Request a slot reset. */
	return PCI_ERS_RESULT_NEED_RESET;
}

/**
 * t3_io_slot_reset - called after the pci bus has been reset.
 * @pdev: Pointer to PCI device
 *
 * Restart the card from scratch, as if from a cold-boot.
 */
static pci_ers_result_t t3_io_slot_reset(struct pci_dev *pdev)
{
	struct adapter *adapter = pci_get_drvdata(pdev);

	if (!t3_reenable_adapter(adapter))
		return PCI_ERS_RESULT_RECOVERED;

	return PCI_ERS_RESULT_DISCONNECT;
}

/**
 * t3_io_resume - called when traffic can start flowing again.
 * @pdev: Pointer to PCI device
 *
 * This callback is called when the error recovery driver tells us that
 * its OK to resume normal operation.
 */
static void t3_io_resume(struct pci_dev *pdev)
{
	struct adapter *adapter = pci_get_drvdata(pdev);

	CH_ALERT(adapter, "adapter recovering, PEX ERR 0x%x\n",
		 t3_read_reg(adapter, A_PCIE_PEX_ERR));

	t3_resume_ports(adapter);
}

static struct pci_error_handlers t3_err_handler = {
	.error_detected = t3_io_error_detected,
	.slot_reset = t3_io_slot_reset,
	.resume = t3_io_resume,
};

/*
 * Set the number of qsets based on the number of CPUs and the number of ports,
 * not to exceed the number of available qsets, assuming there are enough qsets
 * per port in HW.
 */
static void set_nqsets(struct adapter *adap)
{
	int i, j = 0;
	int num_cpus = num_online_cpus();
	int hwports = adap->params.nports;
	int nqsets = adap->msix_nvectors - 1;

	if (adap->params.rev > 0 && adap->flags & USING_MSIX) {
		if (hwports == 2 &&
		    (hwports * nqsets > SGE_QSETS ||
		     num_cpus >= nqsets / hwports))
			nqsets /= hwports;
		if (nqsets > num_cpus)
			nqsets = num_cpus;
		if (nqsets < 1 || hwports == 4)
			nqsets = 1;
	} else
		nqsets = 1;

	for_each_port(adap, i) {
		struct port_info *pi = adap2pinfo(adap, i);

		pi->first_qset = j;
		pi->nqsets = nqsets;
		j = pi->first_qset + nqsets;

		dev_info(&adap->pdev->dev,
			 "Port %d using %d queue sets.\n", i, nqsets);
	}
}

static int __devinit cxgb_enable_msix(struct adapter *adap)
{
	struct msix_entry entries[SGE_QSETS + 1];
	int vectors;
	int i, err;

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

	while ((err = pci_enable_msix(adap->pdev, entries, vectors)) > 0)
		vectors = err;

	if (err < 0)
		pci_disable_msix(adap->pdev);

	if (!err && vectors < (adap->params.nports + 1)) {
		pci_disable_msix(adap->pdev);
		err = -1;
	}

	if (!err) {
		for (i = 0; i < vectors; ++i)
			adap->msix_info[i].vec = entries[i].vector;
		adap->msix_nvectors = vectors;
	}

	return err;
}

static void __devinit print_port_info(struct adapter *adap,
				      const struct adapter_info *ai)
{
	static const char *pci_variant[] = {
		"PCI", "PCI-X", "PCI-X ECC", "PCI-X 266", "PCI Express"
	};

	int i;
	char buf[80];

	if (is_pcie(adap))
		snprintf(buf, sizeof(buf), "%s x%d",
			 pci_variant[adap->params.pci.variant],
			 adap->params.pci.width);
	else
		snprintf(buf, sizeof(buf), "%s %dMHz/%d-bit",
			 pci_variant[adap->params.pci.variant],
			 adap->params.pci.speed, adap->params.pci.width);

	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];
		const struct port_info *pi = netdev_priv(dev);

		if (!test_bit(i, &adap->registered_device_map))
			continue;
		printk(KERN_INFO "%s: %s %s %sNIC (rev %d) %s%s\n",
		       dev->name, ai->desc, pi->phy.desc,
		       is_offload(adap) ? "R" : "", adap->params.rev, buf,
		       (adap->flags & USING_MSIX) ? " MSI-X" :
		       (adap->flags & USING_MSI) ? " MSI" : "");
		if (adap->name == dev->name && adap->params.vpd.mclk)
			printk(KERN_INFO
			       "%s: %uMB CM, %uMB PMTX, %uMB PMRX, S/N: %s\n",
			       adap->name, t3_mc7_size(&adap->cm) >> 20,
			       t3_mc7_size(&adap->pmtx) >> 20,
			       t3_mc7_size(&adap->pmrx) >> 20,
			       adap->params.vpd.sn);
	}
}

static const struct net_device_ops cxgb_netdev_ops = {
	.ndo_open		= cxgb_open,
	.ndo_stop		= cxgb_close,
	.ndo_start_xmit		= t3_eth_xmit,
	.ndo_get_stats		= cxgb_get_stats,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_set_rx_mode	= cxgb_set_rxmode,
	.ndo_do_ioctl		= cxgb_ioctl,
	.ndo_change_mtu		= cxgb_change_mtu,
	.ndo_set_mac_address	= cxgb_set_mac_addr,
	.ndo_fix_features	= cxgb_fix_features,
	.ndo_set_features	= cxgb_set_features,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= cxgb_netpoll,
#endif
};

static void __devinit cxgb3_init_iscsi_mac(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);

	memcpy(pi->iscsic.mac_addr, dev->dev_addr, ETH_ALEN);
	pi->iscsic.mac_addr[3] |= 0x80;
}

static int __devinit init_one(struct pci_dev *pdev,
			      const struct pci_device_id *ent)
{
	static int version_printed;

	int i, err, pci_using_dac = 0;
	resource_size_t mmio_start, mmio_len;
	const struct adapter_info *ai;
	struct adapter *adapter = NULL;
	struct port_info *pi;

	if (!version_printed) {
		printk(KERN_INFO "%s - version %s\n", DRV_DESC, DRV_VERSION);
		++version_printed;
	}

	if (!cxgb3_wq) {
		cxgb3_wq = create_singlethread_workqueue(DRV_NAME);
		if (!cxgb3_wq) {
			printk(KERN_ERR DRV_NAME
			       ": cannot initialize work queue\n");
			return -ENOMEM;
		}
	}

	err = pci_enable_device(pdev);
	if (err) {
		dev_err(&pdev->dev, "cannot enable PCI device\n");
		goto out;
	}

	err = pci_request_regions(pdev, DRV_NAME);
	if (err) {
		/* Just info, some other driver may have claimed the device. */
		dev_info(&pdev->dev, "cannot obtain PCI resources\n");
		goto out_disable_device;
	}

	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
		pci_using_dac = 1;
		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
		if (err) {
			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
			       "coherent allocations\n");
			goto out_release_regions;
		}
	} else if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) != 0) {
		dev_err(&pdev->dev, "no usable DMA configuration\n");
		goto out_release_regions;
	}

	pci_set_master(pdev);
	pci_save_state(pdev);

	mmio_start = pci_resource_start(pdev, 0);
	mmio_len = pci_resource_len(pdev, 0);
	ai = t3_get_adapter_info(ent->driver_data);

	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
	if (!adapter) {
		err = -ENOMEM;
		goto out_release_regions;
	}

	adapter->nofail_skb =
		alloc_skb(sizeof(struct cpl_set_tcb_field), GFP_KERNEL);
	if (!adapter->nofail_skb) {
		dev_err(&pdev->dev, "cannot allocate nofail buffer\n");
		err = -ENOMEM;
		goto out_free_adapter;
	}

	adapter->regs = ioremap_nocache(mmio_start, mmio_len);
	if (!adapter->regs) {
		dev_err(&pdev->dev, "cannot map device registers\n");
		err = -ENOMEM;
		goto out_free_adapter;
	}

	adapter->pdev = pdev;
	adapter->name = pci_name(pdev);
	adapter->msg_enable = dflt_msg_enable;
	adapter->mmio_len = mmio_len;

	mutex_init(&adapter->mdio_lock);
	spin_lock_init(&adapter->work_lock);
	spin_lock_init(&adapter->stats_lock);

	INIT_LIST_HEAD(&adapter->adapter_list);
	INIT_WORK(&adapter->ext_intr_handler_task, ext_intr_task);
	INIT_WORK(&adapter->fatal_error_handler_task, fatal_error_task);

	INIT_WORK(&adapter->db_full_task, db_full_task);
	INIT_WORK(&adapter->db_empty_task, db_empty_task);
	INIT_WORK(&adapter->db_drop_task, db_drop_task);

	INIT_DELAYED_WORK(&adapter->adap_check_task, t3_adap_check_task);

	for (i = 0; i < ai->nports0 + ai->nports1; ++i) {
		struct net_device *netdev;

		netdev = alloc_etherdev_mq(sizeof(struct port_info), SGE_QSETS);
		if (!netdev) {
			err = -ENOMEM;
			goto out_free_dev;
		}

		SET_NETDEV_DEV(netdev, &pdev->dev);

		adapter->port[i] = netdev;
		pi = netdev_priv(netdev);
		pi->adapter = adapter;
		pi->port_id = i;
		netif_carrier_off(netdev);
		netdev->irq = pdev->irq;
		netdev->mem_start = mmio_start;
		netdev->mem_end = mmio_start + mmio_len - 1;
		netdev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM |
			NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_RX;
		netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_TX;
		if (pci_using_dac)
			netdev->features |= NETIF_F_HIGHDMA;

		netdev->netdev_ops = &cxgb_netdev_ops;
		SET_ETHTOOL_OPS(netdev, &cxgb_ethtool_ops);
	}

	pci_set_drvdata(pdev, adapter);
	if (t3_prep_adapter(adapter, ai, 1) < 0) {
		err = -ENODEV;
		goto out_free_dev;
	}

	/*
	 * The card is now ready to go.  If any errors occur during device
	 * registration we do not fail the whole card but rather proceed only
	 * with the ports we manage to register successfully.  However we must
	 * register at least one net device.
	 */
	for_each_port(adapter, i) {
		err = register_netdev(adapter->port[i]);
		if (err)
			dev_warn(&pdev->dev,
				 "cannot register net device %s, skipping\n",
				 adapter->port[i]->name);
		else {
			/*
			 * Change the name we use for messages to the name of
			 * the first successfully registered interface.
			 */
			if (!adapter->registered_device_map)
				adapter->name = adapter->port[i]->name;

			__set_bit(i, &adapter->registered_device_map);
		}
	}
	if (!adapter->registered_device_map) {
		dev_err(&pdev->dev, "could not register any net devices\n");
		goto out_free_dev;
	}

	for_each_port(adapter, i)
		cxgb3_init_iscsi_mac(adapter->port[i]);

	/* Driver's ready. Reflect it on LEDs */
	t3_led_ready(adapter);

	if (is_offload(adapter)) {
		__set_bit(OFFLOAD_DEVMAP_BIT, &adapter->registered_device_map);
		cxgb3_adapter_ofld(adapter);
	}

	/* See what interrupts we'll be using */
	if (msi > 1 && cxgb_enable_msix(adapter) == 0)
		adapter->flags |= USING_MSIX;
	else if (msi > 0 && pci_enable_msi(pdev) == 0)
		adapter->flags |= USING_MSI;

	set_nqsets(adapter);

	err = sysfs_create_group(&adapter->port[0]->dev.kobj,
				 &cxgb3_attr_group);

	for_each_port(adapter, i)
		cxgb_vlan_mode(adapter->port[i], adapter->port[i]->features);

	print_port_info(adapter, ai);
	return 0;

out_free_dev:
	iounmap(adapter->regs);
	for (i = ai->nports0 + ai->nports1 - 1; i >= 0; --i)
		if (adapter->port[i])
			free_netdev(adapter->port[i]);

out_free_adapter:
	kfree(adapter);

out_release_regions:
	pci_release_regions(pdev);
out_disable_device:
	pci_disable_device(pdev);
	pci_set_drvdata(pdev, NULL);
out:
	return err;
}

static void __devexit remove_one(struct pci_dev *pdev)
{
	struct adapter *adapter = pci_get_drvdata(pdev);

	if (adapter) {
		int i;

		t3_sge_stop(adapter);
		sysfs_remove_group(&adapter->port[0]->dev.kobj,
				   &cxgb3_attr_group);

		if (is_offload(adapter)) {
			cxgb3_adapter_unofld(adapter);
			if (test_bit(OFFLOAD_DEVMAP_BIT,
				     &adapter->open_device_map))
				offload_close(&adapter->tdev);
		}

		for_each_port(adapter, i)
		    if (test_bit(i, &adapter->registered_device_map))
			unregister_netdev(adapter->port[i]);

		t3_stop_sge_timers(adapter);
		t3_free_sge_resources(adapter);
		cxgb_disable_msi(adapter);

		for_each_port(adapter, i)
			if (adapter->port[i])
				free_netdev(adapter->port[i]);

		iounmap(adapter->regs);
		if (adapter->nofail_skb)
			kfree_skb(adapter->nofail_skb);
		kfree(adapter);
		pci_release_regions(pdev);
		pci_disable_device(pdev);
		pci_set_drvdata(pdev, NULL);
	}
}

static struct pci_driver driver = {
	.name = DRV_NAME,
	.id_table = cxgb3_pci_tbl,
	.probe = init_one,
	.remove = __devexit_p(remove_one),
	.err_handler = &t3_err_handler,
};

static int __init cxgb3_init_module(void)
{
	int ret;

	cxgb3_offload_init();

	ret = pci_register_driver(&driver);
	return ret;
}

static void __exit cxgb3_cleanup_module(void)
{
	pci_unregister_driver(&driver);
	if (cxgb3_wq)
		destroy_workqueue(cxgb3_wq);
}

module_init(cxgb3_init_module);
module_exit(cxgb3_cleanup_module);