summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/sfc/ef10.c
blob: 7022fb2005a2f6214ea07c6fecf83efdc7697c6f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
// SPDX-License-Identifier: GPL-2.0-only
/****************************************************************************
 * Driver for Solarflare network controllers and boards
 * Copyright 2012-2013 Solarflare Communications Inc.
 */

#include "net_driver.h"
#include "rx_common.h"
#include "tx_common.h"
#include "ef10_regs.h"
#include "io.h"
#include "mcdi.h"
#include "mcdi_pcol.h"
#include "mcdi_port.h"
#include "mcdi_port_common.h"
#include "mcdi_functions.h"
#include "nic.h"
#include "mcdi_filters.h"
#include "workarounds.h"
#include "selftest.h"
#include "ef10_sriov.h"
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <net/udp_tunnel.h>

/* Hardware control for EF10 architecture including 'Huntington'. */

#define EFX_EF10_DRVGEN_EV		7
enum {
	EFX_EF10_TEST = 1,
	EFX_EF10_REFILL,
};

/* VLAN list entry */
struct efx_ef10_vlan {
	struct list_head list;
	u16 vid;
};

static int efx_ef10_set_udp_tnl_ports(struct efx_nic *efx, bool unloading);
static const struct udp_tunnel_nic_info efx_ef10_udp_tunnels;

static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
{
	efx_dword_t reg;

	efx_readd(efx, &reg, ER_DZ_BIU_MC_SFT_STATUS);
	return EFX_DWORD_FIELD(reg, EFX_WORD_1) == 0xb007 ?
		EFX_DWORD_FIELD(reg, EFX_WORD_0) : -EIO;
}

/* On all EF10s up to and including SFC9220 (Medford1), all PFs use BAR 0 for
 * I/O space and BAR 2(&3) for memory.  On SFC9250 (Medford2), there is no I/O
 * bar; PFs use BAR 0/1 for memory.
 */
static unsigned int efx_ef10_pf_mem_bar(struct efx_nic *efx)
{
	switch (efx->pci_dev->device) {
	case 0x0b03: /* SFC9250 PF */
		return 0;
	default:
		return 2;
	}
}

/* All VFs use BAR 0/1 for memory */
static unsigned int efx_ef10_vf_mem_bar(struct efx_nic *efx)
{
	return 0;
}

static unsigned int efx_ef10_mem_map_size(struct efx_nic *efx)
{
	int bar;

	bar = efx->type->mem_bar(efx);
	return resource_size(&efx->pci_dev->resource[bar]);
}

static bool efx_ef10_is_vf(struct efx_nic *efx)
{
	return efx->type->is_vf;
}

#ifdef CONFIG_SFC_SRIOV
static int efx_ef10_get_vf_index(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	size_t outlen;
	int rc;

	rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
			  sizeof(outbuf), &outlen);
	if (rc)
		return rc;
	if (outlen < sizeof(outbuf))
		return -EIO;

	nic_data->vf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_VF);
	return 0;
}
#endif

static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V4_OUT_LEN);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	size_t outlen;
	int rc;

	BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0);

	rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0,
			  outbuf, sizeof(outbuf), &outlen);
	if (rc)
		return rc;
	if (outlen < MC_CMD_GET_CAPABILITIES_OUT_LEN) {
		netif_err(efx, drv, efx->net_dev,
			  "unable to read datapath firmware capabilities\n");
		return -EIO;
	}

	nic_data->datapath_caps =
		MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1);

	if (outlen >= MC_CMD_GET_CAPABILITIES_V2_OUT_LEN) {
		nic_data->datapath_caps2 = MCDI_DWORD(outbuf,
				GET_CAPABILITIES_V2_OUT_FLAGS2);
		nic_data->piobuf_size = MCDI_WORD(outbuf,
				GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF);
	} else {
		nic_data->datapath_caps2 = 0;
		nic_data->piobuf_size = ER_DZ_TX_PIOBUF_SIZE;
	}

	/* record the DPCPU firmware IDs to determine VEB vswitching support.
	 */
	nic_data->rx_dpcpu_fw_id =
		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID);
	nic_data->tx_dpcpu_fw_id =
		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID);

	if (!(nic_data->datapath_caps &
	      (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_LBN))) {
		netif_err(efx, probe, efx->net_dev,
			  "current firmware does not support an RX prefix\n");
		return -ENODEV;
	}

	if (outlen >= MC_CMD_GET_CAPABILITIES_V3_OUT_LEN) {
		u8 vi_window_mode = MCDI_BYTE(outbuf,
				GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE);

		rc = efx_mcdi_window_mode_to_stride(efx, vi_window_mode);
		if (rc)
			return rc;
	} else {
		/* keep default VI stride */
		netif_dbg(efx, probe, efx->net_dev,
			  "firmware did not report VI window mode, assuming vi_stride = %u\n",
			  efx->vi_stride);
	}

	if (outlen >= MC_CMD_GET_CAPABILITIES_V4_OUT_LEN) {
		efx->num_mac_stats = MCDI_WORD(outbuf,
				GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS);
		netif_dbg(efx, probe, efx->net_dev,
			  "firmware reports num_mac_stats = %u\n",
			  efx->num_mac_stats);
	} else {
		/* leave num_mac_stats as the default value, MC_CMD_MAC_NSTATS */
		netif_dbg(efx, probe, efx->net_dev,
			  "firmware did not report num_mac_stats, assuming %u\n",
			  efx->num_mac_stats);
	}

	return 0;
}

static void efx_ef10_read_licensed_features(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_LICENSING_V3_IN_LEN);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_LICENSING_V3_OUT_LEN);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	size_t outlen;
	int rc;

	MCDI_SET_DWORD(inbuf, LICENSING_V3_IN_OP,
		       MC_CMD_LICENSING_V3_IN_OP_REPORT_LICENSE);
	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_LICENSING_V3, inbuf, sizeof(inbuf),
				outbuf, sizeof(outbuf), &outlen);
	if (rc || (outlen < MC_CMD_LICENSING_V3_OUT_LEN))
		return;

	nic_data->licensed_features = MCDI_QWORD(outbuf,
					 LICENSING_V3_OUT_LICENSED_FEATURES);
}

static int efx_ef10_get_sysclk_freq(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CLOCK_OUT_LEN);
	int rc;

	rc = efx_mcdi_rpc(efx, MC_CMD_GET_CLOCK, NULL, 0,
			  outbuf, sizeof(outbuf), NULL);
	if (rc)
		return rc;
	rc = MCDI_DWORD(outbuf, GET_CLOCK_OUT_SYS_FREQ);
	return rc > 0 ? rc : -ERANGE;
}

static int efx_ef10_get_timer_workarounds(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	unsigned int implemented;
	unsigned int enabled;
	int rc;

	nic_data->workaround_35388 = false;
	nic_data->workaround_61265 = false;

	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);

	if (rc == -ENOSYS) {
		/* Firmware without GET_WORKAROUNDS - not a problem. */
		rc = 0;
	} else if (rc == 0) {
		/* Bug61265 workaround is always enabled if implemented. */
		if (enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG61265)
			nic_data->workaround_61265 = true;

		if (enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG35388) {
			nic_data->workaround_35388 = true;
		} else if (implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG35388) {
			/* Workaround is implemented but not enabled.
			 * Try to enable it.
			 */
			rc = efx_mcdi_set_workaround(efx,
						     MC_CMD_WORKAROUND_BUG35388,
						     true, NULL);
			if (rc == 0)
				nic_data->workaround_35388 = true;
			/* If we failed to set the workaround just carry on. */
			rc = 0;
		}
	}

	netif_dbg(efx, probe, efx->net_dev,
		  "workaround for bug 35388 is %sabled\n",
		  nic_data->workaround_35388 ? "en" : "dis");
	netif_dbg(efx, probe, efx->net_dev,
		  "workaround for bug 61265 is %sabled\n",
		  nic_data->workaround_61265 ? "en" : "dis");

	return rc;
}

static void efx_ef10_process_timer_config(struct efx_nic *efx,
					  const efx_dword_t *data)
{
	unsigned int max_count;

	if (EFX_EF10_WORKAROUND_61265(efx)) {
		efx->timer_quantum_ns = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_MCDI_TMR_STEP_NS);
		efx->timer_max_ns = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_MCDI_TMR_MAX_NS);
	} else if (EFX_EF10_WORKAROUND_35388(efx)) {
		efx->timer_quantum_ns = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT);
		max_count = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT);
		efx->timer_max_ns = max_count * efx->timer_quantum_ns;
	} else {
		efx->timer_quantum_ns = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_TMR_REG_NS_PER_COUNT);
		max_count = MCDI_DWORD(data,
			GET_EVQ_TMR_PROPERTIES_OUT_TMR_REG_MAX_COUNT);
		efx->timer_max_ns = max_count * efx->timer_quantum_ns;
	}

	netif_dbg(efx, probe, efx->net_dev,
		  "got timer properties from MC: quantum %u ns; max %u ns\n",
		  efx->timer_quantum_ns, efx->timer_max_ns);
}

static int efx_ef10_get_timer_config(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_LEN);
	int rc;

	rc = efx_ef10_get_timer_workarounds(efx);
	if (rc)
		return rc;

	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_EVQ_TMR_PROPERTIES, NULL, 0,
				outbuf, sizeof(outbuf), NULL);

	if (rc == 0) {
		efx_ef10_process_timer_config(efx, outbuf);
	} else if (rc == -ENOSYS || rc == -EPERM) {
		/* Not available - fall back to Huntington defaults. */
		unsigned int quantum;

		rc = efx_ef10_get_sysclk_freq(efx);
		if (rc < 0)
			return rc;

		quantum = 1536000 / rc; /* 1536 cycles */
		efx->timer_quantum_ns = quantum;
		efx->timer_max_ns = efx->type->timer_period_max * quantum;
		rc = 0;
	} else {
		efx_mcdi_display_error(efx, MC_CMD_GET_EVQ_TMR_PROPERTIES,
				       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_LEN,
				       NULL, 0, rc);
	}

	return rc;
}

static int efx_ef10_get_mac_address_pf(struct efx_nic *efx, u8 *mac_address)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN);
	size_t outlen;
	int rc;

	BUILD_BUG_ON(MC_CMD_GET_MAC_ADDRESSES_IN_LEN != 0);

	rc = efx_mcdi_rpc(efx, MC_CMD_GET_MAC_ADDRESSES, NULL, 0,
			  outbuf, sizeof(outbuf), &outlen);
	if (rc)
		return rc;
	if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN)
		return -EIO;

	ether_addr_copy(mac_address,
			MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE));
	return 0;
}

static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_LEN);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMAX);
	size_t outlen;
	int num_addrs, rc;

	MCDI_SET_DWORD(inbuf, VPORT_GET_MAC_ADDRESSES_IN_VPORT_ID,
		       EVB_PORT_ID_ASSIGNED);
	rc = efx_mcdi_rpc(efx, MC_CMD_VPORT_GET_MAC_ADDRESSES, inbuf,
			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);

	if (rc)
		return rc;
	if (outlen < MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMIN)
		return -EIO;

	num_addrs = MCDI_DWORD(outbuf,
			       VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_COUNT);

	WARN_ON(num_addrs != 1);

	ether_addr_copy(mac_address,
			MCDI_PTR(outbuf, VPORT_GET_MAC_ADDRESSES_OUT_MACADDR));

	return 0;
}

static ssize_t link_control_flag_show(struct device *dev,
				      struct device_attribute *attr,
				      char *buf)
{
	struct efx_nic *efx = dev_get_drvdata(dev);

	return sprintf(buf, "%d\n",
		       ((efx->mcdi->fn_flags) &
			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL))
		       ? 1 : 0);
}

static ssize_t primary_flag_show(struct device *dev,
				 struct device_attribute *attr,
				 char *buf)
{
	struct efx_nic *efx = dev_get_drvdata(dev);

	return sprintf(buf, "%d\n",
		       ((efx->mcdi->fn_flags) &
			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY))
		       ? 1 : 0);
}

static struct efx_ef10_vlan *efx_ef10_find_vlan(struct efx_nic *efx, u16 vid)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	struct efx_ef10_vlan *vlan;

	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));

	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
		if (vlan->vid == vid)
			return vlan;
	}

	return NULL;
}

static int efx_ef10_add_vlan(struct efx_nic *efx, u16 vid)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	struct efx_ef10_vlan *vlan;
	int rc;

	mutex_lock(&nic_data->vlan_lock);

	vlan = efx_ef10_find_vlan(efx, vid);
	if (vlan) {
		/* We add VID 0 on init. 8021q adds it on module init
		 * for all interfaces with VLAN filtring feature.
		 */
		if (vid == 0)
			goto done_unlock;
		netif_warn(efx, drv, efx->net_dev,
			   "VLAN %u already added\n", vid);
		rc = -EALREADY;
		goto fail_exist;
	}

	rc = -ENOMEM;
	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
	if (!vlan)
		goto fail_alloc;

	vlan->vid = vid;

	list_add_tail(&vlan->list, &nic_data->vlan_list);

	if (efx->filter_state) {
		mutex_lock(&efx->mac_lock);
		down_write(&efx->filter_sem);
		rc = efx_mcdi_filter_add_vlan(efx, vlan->vid);
		up_write(&efx->filter_sem);
		mutex_unlock(&efx->mac_lock);
		if (rc)
			goto fail_filter_add_vlan;
	}

done_unlock:
	mutex_unlock(&nic_data->vlan_lock);
	return 0;

fail_filter_add_vlan:
	list_del(&vlan->list);
	kfree(vlan);
fail_alloc:
fail_exist:
	mutex_unlock(&nic_data->vlan_lock);
	return rc;
}

static void efx_ef10_del_vlan_internal(struct efx_nic *efx,
				       struct efx_ef10_vlan *vlan)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));

	if (efx->filter_state) {
		down_write(&efx->filter_sem);
		efx_mcdi_filter_del_vlan(efx, vlan->vid);
		up_write(&efx->filter_sem);
	}

	list_del(&vlan->list);
	kfree(vlan);
}

static int efx_ef10_del_vlan(struct efx_nic *efx, u16 vid)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	struct efx_ef10_vlan *vlan;
	int rc = 0;

	/* 8021q removes VID 0 on module unload for all interfaces
	 * with VLAN filtering feature. We need to keep it to receive
	 * untagged traffic.
	 */
	if (vid == 0)
		return 0;

	mutex_lock(&nic_data->vlan_lock);

	vlan = efx_ef10_find_vlan(efx, vid);
	if (!vlan) {
		netif_err(efx, drv, efx->net_dev,
			  "VLAN %u to be deleted not found\n", vid);
		rc = -ENOENT;
	} else {
		efx_ef10_del_vlan_internal(efx, vlan);
	}

	mutex_unlock(&nic_data->vlan_lock);

	return rc;
}

static void efx_ef10_cleanup_vlans(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	struct efx_ef10_vlan *vlan, *next_vlan;

	mutex_lock(&nic_data->vlan_lock);
	list_for_each_entry_safe(vlan, next_vlan, &nic_data->vlan_list, list)
		efx_ef10_del_vlan_internal(efx, vlan);
	mutex_unlock(&nic_data->vlan_lock);
}

static DEVICE_ATTR_RO(link_control_flag);
static DEVICE_ATTR_RO(primary_flag);

static int efx_ef10_probe(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data;
	int i, rc;

	nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL);
	if (!nic_data)
		return -ENOMEM;
	efx->nic_data = nic_data;

	/* we assume later that we can copy from this buffer in dwords */
	BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4);

	rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf,
				  8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL);
	if (rc)
		goto fail1;

	/* Get the MC's warm boot count.  In case it's rebooting right
	 * now, be prepared to retry.
	 */
	i = 0;
	for (;;) {
		rc = efx_ef10_get_warm_boot_count(efx);
		if (rc >= 0)
			break;
		if (++i == 5)
			goto fail2;
		ssleep(1);
	}
	nic_data->warm_boot_count = rc;

	/* In case we're recovering from a crash (kexec), we want to
	 * cancel any outstanding request by the previous user of this
	 * function.  We send a special message using the least
	 * significant bits of the 'high' (doorbell) register.
	 */
	_efx_writed(efx, cpu_to_le32(1), ER_DZ_MC_DB_HWRD);

	rc = efx_mcdi_init(efx);
	if (rc)
		goto fail2;

	mutex_init(&nic_data->udp_tunnels_lock);
	for (i = 0; i < ARRAY_SIZE(nic_data->udp_tunnels); ++i)
		nic_data->udp_tunnels[i].type =
			TUNNEL_ENCAP_UDP_PORT_ENTRY_INVALID;

	/* Reset (most) configuration for this function */
	rc = efx_mcdi_reset(efx, RESET_TYPE_ALL);
	if (rc)
		goto fail3;

	/* Enable event logging */
	rc = efx_mcdi_log_ctrl(efx, true, false, 0);
	if (rc)
		goto fail3;

	rc = device_create_file(&efx->pci_dev->dev,
				&dev_attr_link_control_flag);
	if (rc)
		goto fail3;

	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
	if (rc)
		goto fail4;

	rc = efx_get_pf_index(efx, &nic_data->pf_index);
	if (rc)
		goto fail5;

	rc = efx_ef10_init_datapath_caps(efx);
	if (rc < 0)
		goto fail5;

	efx_ef10_read_licensed_features(efx);

	/* We can have one VI for each vi_stride-byte region.
	 * However, until we use TX option descriptors we need up to four
	 * TX queues per channel for different checksumming combinations.
	 */
	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN))
		efx->tx_queues_per_channel = 4;
	else
		efx->tx_queues_per_channel = 2;
	efx->max_vis = efx_ef10_mem_map_size(efx) / efx->vi_stride;
	if (!efx->max_vis) {
		netif_err(efx, drv, efx->net_dev, "error determining max VIs\n");
		rc = -EIO;
		goto fail5;
	}
	efx->max_channels = min_t(unsigned int, EFX_MAX_CHANNELS,
				  efx->max_vis / efx->tx_queues_per_channel);
	efx->max_tx_channels = efx->max_channels;
	if (WARN_ON(efx->max_channels == 0)) {
		rc = -EIO;
		goto fail5;
	}

	efx->rx_packet_len_offset =
		ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE;

	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_INCLUDE_FCS_LBN))
		efx->net_dev->hw_features |= NETIF_F_RXFCS;

	rc = efx_mcdi_port_get_number(efx);
	if (rc < 0)
		goto fail5;
	efx->port_num = rc;

	rc = efx->type->get_mac_address(efx, efx->net_dev->perm_addr);
	if (rc)
		goto fail5;

	rc = efx_ef10_get_timer_config(efx);
	if (rc < 0)
		goto fail5;

	rc = efx_mcdi_mon_probe(efx);
	if (rc && rc != -EPERM)
		goto fail5;

	efx_ptp_defer_probe_with_channel(efx);

#ifdef CONFIG_SFC_SRIOV
	if ((efx->pci_dev->physfn) && (!efx->pci_dev->is_physfn)) {
		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);

		efx_pf->type->get_mac_address(efx_pf, nic_data->port_id);
	} else
#endif
		ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr);

	INIT_LIST_HEAD(&nic_data->vlan_list);
	mutex_init(&nic_data->vlan_lock);

	/* Add unspecified VID to support VLAN filtering being disabled */
	rc = efx_ef10_add_vlan(efx, EFX_FILTER_VID_UNSPEC);
	if (rc)
		goto fail_add_vid_unspec;

	/* If VLAN filtering is enabled, we need VID 0 to get untagged
	 * traffic.  It is added automatically if 8021q module is loaded,
	 * but we can't rely on it since module may be not loaded.
	 */
	rc = efx_ef10_add_vlan(efx, 0);
	if (rc)
		goto fail_add_vid_0;

	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN) &&
	    efx->mcdi->fn_flags &
	    (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED))
		efx->net_dev->udp_tunnel_nic_info = &efx_ef10_udp_tunnels;

	return 0;

fail_add_vid_0:
	efx_ef10_cleanup_vlans(efx);
fail_add_vid_unspec:
	mutex_destroy(&nic_data->vlan_lock);
	efx_ptp_remove(efx);
	efx_mcdi_mon_remove(efx);
fail5:
	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
fail4:
	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);
fail3:
	efx_mcdi_detach(efx);

	mutex_lock(&nic_data->udp_tunnels_lock);
	memset(nic_data->udp_tunnels, 0, sizeof(nic_data->udp_tunnels));
	(void)efx_ef10_set_udp_tnl_ports(efx, true);
	mutex_unlock(&nic_data->udp_tunnels_lock);
	mutex_destroy(&nic_data->udp_tunnels_lock);

	efx_mcdi_fini(efx);
fail2:
	efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
fail1:
	kfree(nic_data);
	efx->nic_data = NULL;
	return rc;
}

#ifdef EFX_USE_PIO

static void efx_ef10_free_piobufs(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	MCDI_DECLARE_BUF(inbuf, MC_CMD_FREE_PIOBUF_IN_LEN);
	unsigned int i;
	int rc;

	BUILD_BUG_ON(MC_CMD_FREE_PIOBUF_OUT_LEN != 0);

	for (i = 0; i < nic_data->n_piobufs; i++) {
		MCDI_SET_DWORD(inbuf, FREE_PIOBUF_IN_PIOBUF_HANDLE,
			       nic_data->piobuf_handle[i]);
		rc = efx_mcdi_rpc(efx, MC_CMD_FREE_PIOBUF, inbuf, sizeof(inbuf),
				  NULL, 0, NULL);
		WARN_ON(rc);
	}

	nic_data->n_piobufs = 0;
}

static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_PIOBUF_OUT_LEN);
	unsigned int i;
	size_t outlen;
	int rc = 0;

	BUILD_BUG_ON(MC_CMD_ALLOC_PIOBUF_IN_LEN != 0);

	for (i = 0; i < n; i++) {
		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0,
					outbuf, sizeof(outbuf), &outlen);
		if (rc) {
			/* Don't display the MC error if we didn't have space
			 * for a VF.
			 */
			if (!(efx_ef10_is_vf(efx) && rc == -ENOSPC))
				efx_mcdi_display_error(efx, MC_CMD_ALLOC_PIOBUF,
						       0, outbuf, outlen, rc);
			break;
		}
		if (outlen < MC_CMD_ALLOC_PIOBUF_OUT_LEN) {
			rc = -EIO;
			break;
		}
		nic_data->piobuf_handle[i] =
			MCDI_DWORD(outbuf, ALLOC_PIOBUF_OUT_PIOBUF_HANDLE);
		netif_dbg(efx, probe, efx->net_dev,
			  "allocated PIO buffer %u handle %x\n", i,
			  nic_data->piobuf_handle[i]);
	}

	nic_data->n_piobufs = i;
	if (rc)
		efx_ef10_free_piobufs(efx);
	return rc;
}

static int efx_ef10_link_piobufs(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	MCDI_DECLARE_BUF(inbuf, MC_CMD_LINK_PIOBUF_IN_LEN);
	struct efx_channel *channel;
	struct efx_tx_queue *tx_queue;
	unsigned int offset, index;
	int rc;

	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
	BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);

	/* Link a buffer to each VI in the write-combining mapping */
	for (index = 0; index < nic_data->n_piobufs; ++index) {
		MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
			       nic_data->piobuf_handle[index]);
		MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_TXQ_INSTANCE,
			       nic_data->pio_write_vi_base + index);
		rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
				  inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
				  NULL, 0, NULL);
		if (rc) {
			netif_err(efx, drv, efx->net_dev,
				  "failed to link VI %u to PIO buffer %u (%d)\n",
				  nic_data->pio_write_vi_base + index, index,
				  rc);
			goto fail;
		}
		netif_dbg(efx, probe, efx->net_dev,
			  "linked VI %u to PIO buffer %u\n",
			  nic_data->pio_write_vi_base + index, index);
	}

	/* Link a buffer to each TX queue */
	efx_for_each_channel(channel, efx) {
		/* Extra channels, even those with TXQs (PTP), do not require
		 * PIO resources.
		 */
		if (!channel->type->want_pio ||
		    channel->channel >= efx->xdp_channel_offset)
			continue;

		efx_for_each_channel_tx_queue(tx_queue, channel) {
			/* We assign the PIO buffers to queues in
			 * reverse order to allow for the following
			 * special case.
			 */
			offset = ((efx->tx_channel_offset + efx->n_tx_channels -
				   tx_queue->channel->channel - 1) *
				  efx_piobuf_size);
			index = offset / nic_data->piobuf_size;
			offset = offset % nic_data->piobuf_size;

			/* When the host page size is 4K, the first
			 * host page in the WC mapping may be within
			 * the same VI page as the last TX queue.  We
			 * can only link one buffer to each VI.
			 */
			if (tx_queue->queue == nic_data->pio_write_vi_base) {
				BUG_ON(index != 0);
				rc = 0;
			} else {
				MCDI_SET_DWORD(inbuf,
					       LINK_PIOBUF_IN_PIOBUF_HANDLE,
					       nic_data->piobuf_handle[index]);
				MCDI_SET_DWORD(inbuf,
					       LINK_PIOBUF_IN_TXQ_INSTANCE,
					       tx_queue->queue);
				rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
						  inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
						  NULL, 0, NULL);
			}

			if (rc) {
				/* This is non-fatal; the TX path just
				 * won't use PIO for this queue
				 */
				netif_err(efx, drv, efx->net_dev,
					  "failed to link VI %u to PIO buffer %u (%d)\n",
					  tx_queue->queue, index, rc);
				tx_queue->piobuf = NULL;
			} else {
				tx_queue->piobuf =
					nic_data->pio_write_base +
					index * efx->vi_stride + offset;
				tx_queue->piobuf_offset = offset;
				netif_dbg(efx, probe, efx->net_dev,
					  "linked VI %u to PIO buffer %u offset %x addr %p\n",
					  tx_queue->queue, index,
					  tx_queue->piobuf_offset,
					  tx_queue->piobuf);
			}
		}
	}

	return 0;

fail:
	/* inbuf was defined for MC_CMD_LINK_PIOBUF.  We can use the same
	 * buffer for MC_CMD_UNLINK_PIOBUF because it's shorter.
	 */
	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_IN_LEN < MC_CMD_UNLINK_PIOBUF_IN_LEN);
	while (index--) {
		MCDI_SET_DWORD(inbuf, UNLINK_PIOBUF_IN_TXQ_INSTANCE,
			       nic_data->pio_write_vi_base + index);
		efx_mcdi_rpc(efx, MC_CMD_UNLINK_PIOBUF,
			     inbuf, MC_CMD_UNLINK_PIOBUF_IN_LEN,
			     NULL, 0, NULL);
	}
	return rc;
}

static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
{
	struct efx_channel *channel;
	struct efx_tx_queue *tx_queue;

	/* All our existing PIO buffers went away */
	efx_for_each_channel(channel, efx)
		efx_for_each_channel_tx_queue(tx_queue, channel)
			tx_queue->piobuf = NULL;
}

#else /* !EFX_USE_PIO */

static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
{
	return n == 0 ? 0 : -ENOBUFS;
}

static int efx_ef10_link_piobufs(struct efx_nic *efx)
{
	return 0;
}

static void efx_ef10_free_piobufs(struct efx_nic *efx)
{
}

static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
{
}

#endif /* EFX_USE_PIO */

static void efx_ef10_remove(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	int rc;

#ifdef CONFIG_SFC_SRIOV
	struct efx_ef10_nic_data *nic_data_pf;
	struct pci_dev *pci_dev_pf;
	struct efx_nic *efx_pf;
	struct ef10_vf *vf;

	if (efx->pci_dev->is_virtfn) {
		pci_dev_pf = efx->pci_dev->physfn;
		if (pci_dev_pf) {
			efx_pf = pci_get_drvdata(pci_dev_pf);
			nic_data_pf = efx_pf->nic_data;
			vf = nic_data_pf->vf + nic_data->vf_index;
			vf->efx = NULL;
		} else
			netif_info(efx, drv, efx->net_dev,
				   "Could not get the PF id from VF\n");
	}
#endif

	efx_ef10_cleanup_vlans(efx);
	mutex_destroy(&nic_data->vlan_lock);

	efx_ptp_remove(efx);

	efx_mcdi_mon_remove(efx);

	efx_mcdi_rx_free_indir_table(efx);

	if (nic_data->wc_membase)
		iounmap(nic_data->wc_membase);

	rc = efx_mcdi_free_vis(efx);
	WARN_ON(rc != 0);

	if (!nic_data->must_restore_piobufs)
		efx_ef10_free_piobufs(efx);

	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);

	efx_mcdi_detach(efx);

	memset(nic_data->udp_tunnels, 0, sizeof(nic_data->udp_tunnels));
	mutex_lock(&nic_data->udp_tunnels_lock);
	(void)efx_ef10_set_udp_tnl_ports(efx, true);
	mutex_unlock(&nic_data->udp_tunnels_lock);

	mutex_destroy(&nic_data->udp_tunnels_lock);

	efx_mcdi_fini(efx);
	efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
	kfree(nic_data);
}

static int efx_ef10_probe_pf(struct efx_nic *efx)
{
	return efx_ef10_probe(efx);
}

int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id,
			    u32 *port_flags, u32 *vadaptor_flags,
			    unsigned int *vlan_tags)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_QUERY_IN_LEN);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_VADAPTOR_QUERY_OUT_LEN);
	size_t outlen;
	int rc;

	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_LBN)) {
		MCDI_SET_DWORD(inbuf, VADAPTOR_QUERY_IN_UPSTREAM_PORT_ID,
			       port_id);

		rc = efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_QUERY, inbuf, sizeof(inbuf),
				  outbuf, sizeof(outbuf), &outlen);
		if (rc)
			return rc;

		if (outlen < sizeof(outbuf)) {
			rc = -EIO;
			return rc;
		}
	}

	if (port_flags)
		*port_flags = MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_PORT_FLAGS);
	if (vadaptor_flags)
		*vadaptor_flags =
			MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_VADAPTOR_FLAGS);
	if (vlan_tags)
		*vlan_tags =
			MCDI_DWORD(outbuf,
				   VADAPTOR_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS);

	return 0;
}

int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);

	MCDI_SET_DWORD(inbuf, VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID, port_id);
	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_ALLOC, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_FREE_IN_LEN);

	MCDI_SET_DWORD(inbuf, VADAPTOR_FREE_IN_UPSTREAM_PORT_ID, port_id);
	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_FREE, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

int efx_ef10_vport_add_mac(struct efx_nic *efx,
			   unsigned int port_id, const u8 *mac)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN);

	MCDI_SET_DWORD(inbuf, VPORT_ADD_MAC_ADDRESS_IN_VPORT_ID, port_id);
	ether_addr_copy(MCDI_PTR(inbuf, VPORT_ADD_MAC_ADDRESS_IN_MACADDR), mac);

	return efx_mcdi_rpc(efx, MC_CMD_VPORT_ADD_MAC_ADDRESS, inbuf,
			    sizeof(inbuf), NULL, 0, NULL);
}

int efx_ef10_vport_del_mac(struct efx_nic *efx,
			   unsigned int port_id, const u8 *mac)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN);

	MCDI_SET_DWORD(inbuf, VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID, port_id);
	ether_addr_copy(MCDI_PTR(inbuf, VPORT_DEL_MAC_ADDRESS_IN_MACADDR), mac);

	return efx_mcdi_rpc(efx, MC_CMD_VPORT_DEL_MAC_ADDRESS, inbuf,
			    sizeof(inbuf), NULL, 0, NULL);
}

#ifdef CONFIG_SFC_SRIOV
static int efx_ef10_probe_vf(struct efx_nic *efx)
{
	int rc;
	struct pci_dev *pci_dev_pf;

	/* If the parent PF has no VF data structure, it doesn't know about this
	 * VF so fail probe.  The VF needs to be re-created.  This can happen
	 * if the PF driver was unloaded while any VF was assigned to a guest
	 * (using Xen, only).
	 */
	pci_dev_pf = efx->pci_dev->physfn;
	if (pci_dev_pf) {
		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
		struct efx_ef10_nic_data *nic_data_pf = efx_pf->nic_data;

		if (!nic_data_pf->vf) {
			netif_info(efx, drv, efx->net_dev,
				   "The VF cannot link to its parent PF; "
				   "please destroy and re-create the VF\n");
			return -EBUSY;
		}
	}

	rc = efx_ef10_probe(efx);
	if (rc)
		return rc;

	rc = efx_ef10_get_vf_index(efx);
	if (rc)
		goto fail;

	if (efx->pci_dev->is_virtfn) {
		if (efx->pci_dev->physfn) {
			struct efx_nic *efx_pf =
				pci_get_drvdata(efx->pci_dev->physfn);
			struct efx_ef10_nic_data *nic_data_p = efx_pf->nic_data;
			struct efx_ef10_nic_data *nic_data = efx->nic_data;

			nic_data_p->vf[nic_data->vf_index].efx = efx;
			nic_data_p->vf[nic_data->vf_index].pci_dev =
				efx->pci_dev;
		} else
			netif_info(efx, drv, efx->net_dev,
				   "Could not get the PF id from VF\n");
	}

	return 0;

fail:
	efx_ef10_remove(efx);
	return rc;
}
#else
static int efx_ef10_probe_vf(struct efx_nic *efx __attribute__ ((unused)))
{
	return 0;
}
#endif

static int efx_ef10_alloc_vis(struct efx_nic *efx,
			      unsigned int min_vis, unsigned int max_vis)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	return efx_mcdi_alloc_vis(efx, min_vis, max_vis, &nic_data->vi_base,
				  &nic_data->n_allocated_vis);
}

/* Note that the failure path of this function does not free
 * resources, as this will be done by efx_ef10_remove().
 */
static int efx_ef10_dimension_resources(struct efx_nic *efx)
{
	unsigned int min_vis = max_t(unsigned int, efx->tx_queues_per_channel,
				     efx_separate_tx_channels ? 2 : 1);
	unsigned int channel_vis, pio_write_vi_base, max_vis;
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	unsigned int uc_mem_map_size, wc_mem_map_size;
	void __iomem *membase;
	int rc;

	channel_vis = max(efx->n_channels,
			  ((efx->n_tx_channels + efx->n_extra_tx_channels) *
			   efx->tx_queues_per_channel) +
			   efx->n_xdp_channels * efx->xdp_tx_per_channel);
	if (efx->max_vis && efx->max_vis < channel_vis) {
		netif_dbg(efx, drv, efx->net_dev,
			  "Reducing channel VIs from %u to %u\n",
			  channel_vis, efx->max_vis);
		channel_vis = efx->max_vis;
	}

#ifdef EFX_USE_PIO
	/* Try to allocate PIO buffers if wanted and if the full
	 * number of PIO buffers would be sufficient to allocate one
	 * copy-buffer per TX channel.  Failure is non-fatal, as there
	 * are only a small number of PIO buffers shared between all
	 * functions of the controller.
	 */
	if (efx_piobuf_size != 0 &&
	    nic_data->piobuf_size / efx_piobuf_size * EF10_TX_PIOBUF_COUNT >=
	    efx->n_tx_channels) {
		unsigned int n_piobufs =
			DIV_ROUND_UP(efx->n_tx_channels,
				     nic_data->piobuf_size / efx_piobuf_size);

		rc = efx_ef10_alloc_piobufs(efx, n_piobufs);
		if (rc == -ENOSPC)
			netif_dbg(efx, probe, efx->net_dev,
				  "out of PIO buffers; cannot allocate more\n");
		else if (rc == -EPERM)
			netif_dbg(efx, probe, efx->net_dev,
				  "not permitted to allocate PIO buffers\n");
		else if (rc)
			netif_err(efx, probe, efx->net_dev,
				  "failed to allocate PIO buffers (%d)\n", rc);
		else
			netif_dbg(efx, probe, efx->net_dev,
				  "allocated %u PIO buffers\n", n_piobufs);
	}
#else
	nic_data->n_piobufs = 0;
#endif

	/* PIO buffers should be mapped with write-combining enabled,
	 * and we want to make single UC and WC mappings rather than
	 * several of each (in fact that's the only option if host
	 * page size is >4K).  So we may allocate some extra VIs just
	 * for writing PIO buffers through.
	 *
	 * The UC mapping contains (channel_vis - 1) complete VIs and the
	 * first 4K of the next VI.  Then the WC mapping begins with
	 * the remainder of this last VI.
	 */
	uc_mem_map_size = PAGE_ALIGN((channel_vis - 1) * efx->vi_stride +
				     ER_DZ_TX_PIOBUF);
	if (nic_data->n_piobufs) {
		/* pio_write_vi_base rounds down to give the number of complete
		 * VIs inside the UC mapping.
		 */
		pio_write_vi_base = uc_mem_map_size / efx->vi_stride;
		wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
					       nic_data->n_piobufs) *
					      efx->vi_stride) -
				   uc_mem_map_size);
		max_vis = pio_write_vi_base + nic_data->n_piobufs;
	} else {
		pio_write_vi_base = 0;
		wc_mem_map_size = 0;
		max_vis = channel_vis;
	}

	/* In case the last attached driver failed to free VIs, do it now */
	rc = efx_mcdi_free_vis(efx);
	if (rc != 0)
		return rc;

	rc = efx_ef10_alloc_vis(efx, min_vis, max_vis);
	if (rc != 0)
		return rc;

	if (nic_data->n_allocated_vis < channel_vis) {
		netif_info(efx, drv, efx->net_dev,
			   "Could not allocate enough VIs to satisfy RSS"
			   " requirements. Performance may not be optimal.\n");
		/* We didn't get the VIs to populate our channels.
		 * We could keep what we got but then we'd have more
		 * interrupts than we need.
		 * Instead calculate new max_channels and restart
		 */
		efx->max_channels = nic_data->n_allocated_vis;
		efx->max_tx_channels =
			nic_data->n_allocated_vis / efx->tx_queues_per_channel;

		efx_mcdi_free_vis(efx);
		return -EAGAIN;
	}

	/* If we didn't get enough VIs to map all the PIO buffers, free the
	 * PIO buffers
	 */
	if (nic_data->n_piobufs &&
	    nic_data->n_allocated_vis <
	    pio_write_vi_base + nic_data->n_piobufs) {
		netif_dbg(efx, probe, efx->net_dev,
			  "%u VIs are not sufficient to map %u PIO buffers\n",
			  nic_data->n_allocated_vis, nic_data->n_piobufs);
		efx_ef10_free_piobufs(efx);
	}

	/* Shrink the original UC mapping of the memory BAR */
	membase = ioremap(efx->membase_phys, uc_mem_map_size);
	if (!membase) {
		netif_err(efx, probe, efx->net_dev,
			  "could not shrink memory BAR to %x\n",
			  uc_mem_map_size);
		return -ENOMEM;
	}
	iounmap(efx->membase);
	efx->membase = membase;

	/* Set up the WC mapping if needed */
	if (wc_mem_map_size) {
		nic_data->wc_membase = ioremap_wc(efx->membase_phys +
						  uc_mem_map_size,
						  wc_mem_map_size);
		if (!nic_data->wc_membase) {
			netif_err(efx, probe, efx->net_dev,
				  "could not allocate WC mapping of size %x\n",
				  wc_mem_map_size);
			return -ENOMEM;
		}
		nic_data->pio_write_vi_base = pio_write_vi_base;
		nic_data->pio_write_base =
			nic_data->wc_membase +
			(pio_write_vi_base * efx->vi_stride + ER_DZ_TX_PIOBUF -
			 uc_mem_map_size);

		rc = efx_ef10_link_piobufs(efx);
		if (rc)
			efx_ef10_free_piobufs(efx);
	}

	netif_dbg(efx, probe, efx->net_dev,
		  "memory BAR at %pa (virtual %p+%x UC, %p+%x WC)\n",
		  &efx->membase_phys, efx->membase, uc_mem_map_size,
		  nic_data->wc_membase, wc_mem_map_size);

	return 0;
}

static void efx_ef10_fini_nic(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	kfree(nic_data->mc_stats);
	nic_data->mc_stats = NULL;
}

static int efx_ef10_init_nic(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	netdev_features_t hw_enc_features = 0;
	int rc;

	if (nic_data->must_check_datapath_caps) {
		rc = efx_ef10_init_datapath_caps(efx);
		if (rc)
			return rc;
		nic_data->must_check_datapath_caps = false;
	}

	if (efx->must_realloc_vis) {
		/* We cannot let the number of VIs change now */
		rc = efx_ef10_alloc_vis(efx, nic_data->n_allocated_vis,
					nic_data->n_allocated_vis);
		if (rc)
			return rc;
		efx->must_realloc_vis = false;
	}

	nic_data->mc_stats = kmalloc(efx->num_mac_stats * sizeof(__le64),
				     GFP_KERNEL);
	if (!nic_data->mc_stats)
		return -ENOMEM;

	if (nic_data->must_restore_piobufs && nic_data->n_piobufs) {
		rc = efx_ef10_alloc_piobufs(efx, nic_data->n_piobufs);
		if (rc == 0) {
			rc = efx_ef10_link_piobufs(efx);
			if (rc)
				efx_ef10_free_piobufs(efx);
		}

		/* Log an error on failure, but this is non-fatal.
		 * Permission errors are less important - we've presumably
		 * had the PIO buffer licence removed.
		 */
		if (rc == -EPERM)
			netif_dbg(efx, drv, efx->net_dev,
				  "not permitted to restore PIO buffers\n");
		else if (rc)
			netif_err(efx, drv, efx->net_dev,
				  "failed to restore PIO buffers (%d)\n", rc);
		nic_data->must_restore_piobufs = false;
	}

	/* add encapsulated checksum offload features */
	if (efx_has_cap(efx, VXLAN_NVGRE) && !efx_ef10_is_vf(efx))
		hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
	/* add encapsulated TSO features */
	if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) {
		netdev_features_t encap_tso_features;

		encap_tso_features = NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
			NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM;

		hw_enc_features |= encap_tso_features | NETIF_F_TSO;
		efx->net_dev->features |= encap_tso_features;
	}
	efx->net_dev->hw_enc_features = hw_enc_features;

	/* don't fail init if RSS setup doesn't work */
	rc = efx->type->rx_push_rss_config(efx, false,
					   efx->rss_context.rx_indir_table, NULL);

	return 0;
}

static void efx_ef10_table_reset_mc_allocations(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
#ifdef CONFIG_SFC_SRIOV
	unsigned int i;
#endif

	/* All our allocations have been reset */
	efx->must_realloc_vis = true;
	efx_mcdi_filter_table_reset_mc_allocations(efx);
	nic_data->must_restore_piobufs = true;
	efx_ef10_forget_old_piobufs(efx);
	efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;

	/* Driver-created vswitches and vports must be re-created */
	nic_data->must_probe_vswitching = true;
	efx->vport_id = EVB_PORT_ID_ASSIGNED;
#ifdef CONFIG_SFC_SRIOV
	if (nic_data->vf)
		for (i = 0; i < efx->vf_count; i++)
			nic_data->vf[i].vport_id = 0;
#endif
}

static enum reset_type efx_ef10_map_reset_reason(enum reset_type reason)
{
	if (reason == RESET_TYPE_MC_FAILURE)
		return RESET_TYPE_DATAPATH;

	return efx_mcdi_map_reset_reason(reason);
}

static int efx_ef10_map_reset_flags(u32 *flags)
{
	enum {
		EF10_RESET_PORT = ((ETH_RESET_MAC | ETH_RESET_PHY) <<
				   ETH_RESET_SHARED_SHIFT),
		EF10_RESET_MC = ((ETH_RESET_DMA | ETH_RESET_FILTER |
				  ETH_RESET_OFFLOAD | ETH_RESET_MAC |
				  ETH_RESET_PHY | ETH_RESET_MGMT) <<
				 ETH_RESET_SHARED_SHIFT)
	};

	/* We assume for now that our PCI function is permitted to
	 * reset everything.
	 */

	if ((*flags & EF10_RESET_MC) == EF10_RESET_MC) {
		*flags &= ~EF10_RESET_MC;
		return RESET_TYPE_WORLD;
	}

	if ((*flags & EF10_RESET_PORT) == EF10_RESET_PORT) {
		*flags &= ~EF10_RESET_PORT;
		return RESET_TYPE_ALL;
	}

	/* no invisible reset implemented */

	return -EINVAL;
}

static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type)
{
	int rc = efx_mcdi_reset(efx, reset_type);

	/* Unprivileged functions return -EPERM, but need to return success
	 * here so that the datapath is brought back up.
	 */
	if (reset_type == RESET_TYPE_WORLD && rc == -EPERM)
		rc = 0;

	/* If it was a port reset, trigger reallocation of MC resources.
	 * Note that on an MC reset nothing needs to be done now because we'll
	 * detect the MC reset later and handle it then.
	 * For an FLR, we never get an MC reset event, but the MC has reset all
	 * resources assigned to us, so we have to trigger reallocation now.
	 */
	if ((reset_type == RESET_TYPE_ALL ||
	     reset_type == RESET_TYPE_MCDI_TIMEOUT) && !rc)
		efx_ef10_table_reset_mc_allocations(efx);
	return rc;
}

#define EF10_DMA_STAT(ext_name, mcdi_name)			\
	[EF10_STAT_ ## ext_name] =				\
	{ #ext_name, 64, 8 * MC_CMD_MAC_ ## mcdi_name }
#define EF10_DMA_INVIS_STAT(int_name, mcdi_name)		\
	[EF10_STAT_ ## int_name] =				\
	{ NULL, 64, 8 * MC_CMD_MAC_ ## mcdi_name }
#define EF10_OTHER_STAT(ext_name)				\
	[EF10_STAT_ ## ext_name] = { #ext_name, 0, 0 }

static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
	EF10_DMA_STAT(port_tx_bytes, TX_BYTES),
	EF10_DMA_STAT(port_tx_packets, TX_PKTS),
	EF10_DMA_STAT(port_tx_pause, TX_PAUSE_PKTS),
	EF10_DMA_STAT(port_tx_control, TX_CONTROL_PKTS),
	EF10_DMA_STAT(port_tx_unicast, TX_UNICAST_PKTS),
	EF10_DMA_STAT(port_tx_multicast, TX_MULTICAST_PKTS),
	EF10_DMA_STAT(port_tx_broadcast, TX_BROADCAST_PKTS),
	EF10_DMA_STAT(port_tx_lt64, TX_LT64_PKTS),
	EF10_DMA_STAT(port_tx_64, TX_64_PKTS),
	EF10_DMA_STAT(port_tx_65_to_127, TX_65_TO_127_PKTS),
	EF10_DMA_STAT(port_tx_128_to_255, TX_128_TO_255_PKTS),
	EF10_DMA_STAT(port_tx_256_to_511, TX_256_TO_511_PKTS),
	EF10_DMA_STAT(port_tx_512_to_1023, TX_512_TO_1023_PKTS),
	EF10_DMA_STAT(port_tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
	EF10_DMA_STAT(port_tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
	EF10_DMA_STAT(port_rx_bytes, RX_BYTES),
	EF10_DMA_INVIS_STAT(port_rx_bytes_minus_good_bytes, RX_BAD_BYTES),
	EF10_OTHER_STAT(port_rx_good_bytes),
	EF10_OTHER_STAT(port_rx_bad_bytes),
	EF10_DMA_STAT(port_rx_packets, RX_PKTS),
	EF10_DMA_STAT(port_rx_good, RX_GOOD_PKTS),
	EF10_DMA_STAT(port_rx_bad, RX_BAD_FCS_PKTS),
	EF10_DMA_STAT(port_rx_pause, RX_PAUSE_PKTS),
	EF10_DMA_STAT(port_rx_control, RX_CONTROL_PKTS),
	EF10_DMA_STAT(port_rx_unicast, RX_UNICAST_PKTS),
	EF10_DMA_STAT(port_rx_multicast, RX_MULTICAST_PKTS),
	EF10_DMA_STAT(port_rx_broadcast, RX_BROADCAST_PKTS),
	EF10_DMA_STAT(port_rx_lt64, RX_UNDERSIZE_PKTS),
	EF10_DMA_STAT(port_rx_64, RX_64_PKTS),
	EF10_DMA_STAT(port_rx_65_to_127, RX_65_TO_127_PKTS),
	EF10_DMA_STAT(port_rx_128_to_255, RX_128_TO_255_PKTS),
	EF10_DMA_STAT(port_rx_256_to_511, RX_256_TO_511_PKTS),
	EF10_DMA_STAT(port_rx_512_to_1023, RX_512_TO_1023_PKTS),
	EF10_DMA_STAT(port_rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
	EF10_DMA_STAT(port_rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
	EF10_DMA_STAT(port_rx_gtjumbo, RX_GTJUMBO_PKTS),
	EF10_DMA_STAT(port_rx_bad_gtjumbo, RX_JABBER_PKTS),
	EF10_DMA_STAT(port_rx_overflow, RX_OVERFLOW_PKTS),
	EF10_DMA_STAT(port_rx_align_error, RX_ALIGN_ERROR_PKTS),
	EF10_DMA_STAT(port_rx_length_error, RX_LENGTH_ERROR_PKTS),
	EF10_DMA_STAT(port_rx_nodesc_drops, RX_NODESC_DROPS),
	EFX_GENERIC_SW_STAT(rx_nodesc_trunc),
	EFX_GENERIC_SW_STAT(rx_noskb_drops),
	EF10_DMA_STAT(port_rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
	EF10_DMA_STAT(port_rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
	EF10_DMA_STAT(port_rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
	EF10_DMA_STAT(port_rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
	EF10_DMA_STAT(port_rx_pm_trunc_qbb, PM_TRUNC_QBB),
	EF10_DMA_STAT(port_rx_pm_discard_qbb, PM_DISCARD_QBB),
	EF10_DMA_STAT(port_rx_pm_discard_mapping, PM_DISCARD_MAPPING),
	EF10_DMA_STAT(port_rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
	EF10_DMA_STAT(port_rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
	EF10_DMA_STAT(port_rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
	EF10_DMA_STAT(port_rx_dp_hlb_fetch, RXDP_HLB_FETCH_CONDITIONS),
	EF10_DMA_STAT(port_rx_dp_hlb_wait, RXDP_HLB_WAIT_CONDITIONS),
	EF10_DMA_STAT(rx_unicast, VADAPTER_RX_UNICAST_PACKETS),
	EF10_DMA_STAT(rx_unicast_bytes, VADAPTER_RX_UNICAST_BYTES),
	EF10_DMA_STAT(rx_multicast, VADAPTER_RX_MULTICAST_PACKETS),
	EF10_DMA_STAT(rx_multicast_bytes, VADAPTER_RX_MULTICAST_BYTES),
	EF10_DMA_STAT(rx_broadcast, VADAPTER_RX_BROADCAST_PACKETS),
	EF10_DMA_STAT(rx_broadcast_bytes, VADAPTER_RX_BROADCAST_BYTES),
	EF10_DMA_STAT(rx_bad, VADAPTER_RX_BAD_PACKETS),
	EF10_DMA_STAT(rx_bad_bytes, VADAPTER_RX_BAD_BYTES),
	EF10_DMA_STAT(rx_overflow, VADAPTER_RX_OVERFLOW),
	EF10_DMA_STAT(tx_unicast, VADAPTER_TX_UNICAST_PACKETS),
	EF10_DMA_STAT(tx_unicast_bytes, VADAPTER_TX_UNICAST_BYTES),
	EF10_DMA_STAT(tx_multicast, VADAPTER_TX_MULTICAST_PACKETS),
	EF10_DMA_STAT(tx_multicast_bytes, VADAPTER_TX_MULTICAST_BYTES),
	EF10_DMA_STAT(tx_broadcast, VADAPTER_TX_BROADCAST_PACKETS),
	EF10_DMA_STAT(tx_broadcast_bytes, VADAPTER_TX_BROADCAST_BYTES),
	EF10_DMA_STAT(tx_bad, VADAPTER_TX_BAD_PACKETS),
	EF10_DMA_STAT(tx_bad_bytes, VADAPTER_TX_BAD_BYTES),
	EF10_DMA_STAT(tx_overflow, VADAPTER_TX_OVERFLOW),
	EF10_DMA_STAT(fec_uncorrected_errors, FEC_UNCORRECTED_ERRORS),
	EF10_DMA_STAT(fec_corrected_errors, FEC_CORRECTED_ERRORS),
	EF10_DMA_STAT(fec_corrected_symbols_lane0, FEC_CORRECTED_SYMBOLS_LANE0),
	EF10_DMA_STAT(fec_corrected_symbols_lane1, FEC_CORRECTED_SYMBOLS_LANE1),
	EF10_DMA_STAT(fec_corrected_symbols_lane2, FEC_CORRECTED_SYMBOLS_LANE2),
	EF10_DMA_STAT(fec_corrected_symbols_lane3, FEC_CORRECTED_SYMBOLS_LANE3),
	EF10_DMA_STAT(ctpio_vi_busy_fallback, CTPIO_VI_BUSY_FALLBACK),
	EF10_DMA_STAT(ctpio_long_write_success, CTPIO_LONG_WRITE_SUCCESS),
	EF10_DMA_STAT(ctpio_missing_dbell_fail, CTPIO_MISSING_DBELL_FAIL),
	EF10_DMA_STAT(ctpio_overflow_fail, CTPIO_OVERFLOW_FAIL),
	EF10_DMA_STAT(ctpio_underflow_fail, CTPIO_UNDERFLOW_FAIL),
	EF10_DMA_STAT(ctpio_timeout_fail, CTPIO_TIMEOUT_FAIL),
	EF10_DMA_STAT(ctpio_noncontig_wr_fail, CTPIO_NONCONTIG_WR_FAIL),
	EF10_DMA_STAT(ctpio_frm_clobber_fail, CTPIO_FRM_CLOBBER_FAIL),
	EF10_DMA_STAT(ctpio_invalid_wr_fail, CTPIO_INVALID_WR_FAIL),
	EF10_DMA_STAT(ctpio_vi_clobber_fallback, CTPIO_VI_CLOBBER_FALLBACK),
	EF10_DMA_STAT(ctpio_unqualified_fallback, CTPIO_UNQUALIFIED_FALLBACK),
	EF10_DMA_STAT(ctpio_runt_fallback, CTPIO_RUNT_FALLBACK),
	EF10_DMA_STAT(ctpio_success, CTPIO_SUCCESS),
	EF10_DMA_STAT(ctpio_fallback, CTPIO_FALLBACK),
	EF10_DMA_STAT(ctpio_poison, CTPIO_POISON),
	EF10_DMA_STAT(ctpio_erase, CTPIO_ERASE),
};

#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_port_tx_bytes) |	\
			       (1ULL << EF10_STAT_port_tx_packets) |	\
			       (1ULL << EF10_STAT_port_tx_pause) |	\
			       (1ULL << EF10_STAT_port_tx_unicast) |	\
			       (1ULL << EF10_STAT_port_tx_multicast) |	\
			       (1ULL << EF10_STAT_port_tx_broadcast) |	\
			       (1ULL << EF10_STAT_port_rx_bytes) |	\
			       (1ULL <<                                 \
				EF10_STAT_port_rx_bytes_minus_good_bytes) | \
			       (1ULL << EF10_STAT_port_rx_good_bytes) |	\
			       (1ULL << EF10_STAT_port_rx_bad_bytes) |	\
			       (1ULL << EF10_STAT_port_rx_packets) |	\
			       (1ULL << EF10_STAT_port_rx_good) |	\
			       (1ULL << EF10_STAT_port_rx_bad) |	\
			       (1ULL << EF10_STAT_port_rx_pause) |	\
			       (1ULL << EF10_STAT_port_rx_control) |	\
			       (1ULL << EF10_STAT_port_rx_unicast) |	\
			       (1ULL << EF10_STAT_port_rx_multicast) |	\
			       (1ULL << EF10_STAT_port_rx_broadcast) |	\
			       (1ULL << EF10_STAT_port_rx_lt64) |	\
			       (1ULL << EF10_STAT_port_rx_64) |		\
			       (1ULL << EF10_STAT_port_rx_65_to_127) |	\
			       (1ULL << EF10_STAT_port_rx_128_to_255) |	\
			       (1ULL << EF10_STAT_port_rx_256_to_511) |	\
			       (1ULL << EF10_STAT_port_rx_512_to_1023) |\
			       (1ULL << EF10_STAT_port_rx_1024_to_15xx) |\
			       (1ULL << EF10_STAT_port_rx_15xx_to_jumbo) |\
			       (1ULL << EF10_STAT_port_rx_gtjumbo) |	\
			       (1ULL << EF10_STAT_port_rx_bad_gtjumbo) |\
			       (1ULL << EF10_STAT_port_rx_overflow) |	\
			       (1ULL << EF10_STAT_port_rx_nodesc_drops) |\
			       (1ULL << GENERIC_STAT_rx_nodesc_trunc) |	\
			       (1ULL << GENERIC_STAT_rx_noskb_drops))

/* On 7000 series NICs, these statistics are only provided by the 10G MAC.
 * For a 10G/40G switchable port we do not expose these because they might
 * not include all the packets they should.
 * On 8000 series NICs these statistics are always provided.
 */
#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_port_tx_control) |	\
				 (1ULL << EF10_STAT_port_tx_lt64) |	\
				 (1ULL << EF10_STAT_port_tx_64) |	\
				 (1ULL << EF10_STAT_port_tx_65_to_127) |\
				 (1ULL << EF10_STAT_port_tx_128_to_255) |\
				 (1ULL << EF10_STAT_port_tx_256_to_511) |\
				 (1ULL << EF10_STAT_port_tx_512_to_1023) |\
				 (1ULL << EF10_STAT_port_tx_1024_to_15xx) |\
				 (1ULL << EF10_STAT_port_tx_15xx_to_jumbo))

/* These statistics are only provided by the 40G MAC.  For a 10G/40G
 * switchable port we do expose these because the errors will otherwise
 * be silent.
 */
#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_port_rx_align_error) |\
				  (1ULL << EF10_STAT_port_rx_length_error))

/* These statistics are only provided if the firmware supports the
 * capability PM_AND_RXDP_COUNTERS.
 */
#define HUNT_PM_AND_RXDP_STAT_MASK (					\
	(1ULL << EF10_STAT_port_rx_pm_trunc_bb_overflow) |		\
	(1ULL << EF10_STAT_port_rx_pm_discard_bb_overflow) |		\
	(1ULL << EF10_STAT_port_rx_pm_trunc_vfifo_full) |		\
	(1ULL << EF10_STAT_port_rx_pm_discard_vfifo_full) |		\
	(1ULL << EF10_STAT_port_rx_pm_trunc_qbb) |			\
	(1ULL << EF10_STAT_port_rx_pm_discard_qbb) |			\
	(1ULL << EF10_STAT_port_rx_pm_discard_mapping) |		\
	(1ULL << EF10_STAT_port_rx_dp_q_disabled_packets) |		\
	(1ULL << EF10_STAT_port_rx_dp_di_dropped_packets) |		\
	(1ULL << EF10_STAT_port_rx_dp_streaming_packets) |		\
	(1ULL << EF10_STAT_port_rx_dp_hlb_fetch) |			\
	(1ULL << EF10_STAT_port_rx_dp_hlb_wait))

/* These statistics are only provided if the NIC supports MC_CMD_MAC_STATS_V2,
 * indicated by returning a value >= MC_CMD_MAC_NSTATS_V2 in
 * MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS.
 * These bits are in the second u64 of the raw mask.
 */
#define EF10_FEC_STAT_MASK (						\
	(1ULL << (EF10_STAT_fec_uncorrected_errors - 64)) |		\
	(1ULL << (EF10_STAT_fec_corrected_errors - 64)) |		\
	(1ULL << (EF10_STAT_fec_corrected_symbols_lane0 - 64)) |	\
	(1ULL << (EF10_STAT_fec_corrected_symbols_lane1 - 64)) |	\
	(1ULL << (EF10_STAT_fec_corrected_symbols_lane2 - 64)) |	\
	(1ULL << (EF10_STAT_fec_corrected_symbols_lane3 - 64)))

/* These statistics are only provided if the NIC supports MC_CMD_MAC_STATS_V3,
 * indicated by returning a value >= MC_CMD_MAC_NSTATS_V3 in
 * MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS.
 * These bits are in the second u64 of the raw mask.
 */
#define EF10_CTPIO_STAT_MASK (						\
	(1ULL << (EF10_STAT_ctpio_vi_busy_fallback - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_long_write_success - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_missing_dbell_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_overflow_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_underflow_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_timeout_fail - 64)) |			\
	(1ULL << (EF10_STAT_ctpio_noncontig_wr_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_frm_clobber_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_invalid_wr_fail - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_vi_clobber_fallback - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_unqualified_fallback - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_runt_fallback - 64)) |		\
	(1ULL << (EF10_STAT_ctpio_success - 64)) |			\
	(1ULL << (EF10_STAT_ctpio_fallback - 64)) |			\
	(1ULL << (EF10_STAT_ctpio_poison - 64)) |			\
	(1ULL << (EF10_STAT_ctpio_erase - 64)))

static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx)
{
	u64 raw_mask = HUNT_COMMON_STAT_MASK;
	u32 port_caps = efx_mcdi_phy_get_caps(efx);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	if (!(efx->mcdi->fn_flags &
	      1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL))
		return 0;

	if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) {
		raw_mask |= HUNT_40G_EXTRA_STAT_MASK;
		/* 8000 series have everything even at 40G */
		if (nic_data->datapath_caps2 &
		    (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN))
			raw_mask |= HUNT_10G_ONLY_STAT_MASK;
	} else {
		raw_mask |= HUNT_10G_ONLY_STAT_MASK;
	}

	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN))
		raw_mask |= HUNT_PM_AND_RXDP_STAT_MASK;

	return raw_mask;
}

static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u64 raw_mask[2];

	raw_mask[0] = efx_ef10_raw_stat_mask(efx);

	/* Only show vadaptor stats when EVB capability is present */
	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN)) {
		raw_mask[0] |= ~((1ULL << EF10_STAT_rx_unicast) - 1);
		raw_mask[1] = (1ULL << (EF10_STAT_V1_COUNT - 64)) - 1;
	} else {
		raw_mask[1] = 0;
	}
	/* Only show FEC stats when NIC supports MC_CMD_MAC_STATS_V2 */
	if (efx->num_mac_stats >= MC_CMD_MAC_NSTATS_V2)
		raw_mask[1] |= EF10_FEC_STAT_MASK;

	/* CTPIO stats appear in V3. Only show them on devices that actually
	 * support CTPIO. Although this driver doesn't use CTPIO others might,
	 * and we may be reporting the stats for the underlying port.
	 */
	if (efx->num_mac_stats >= MC_CMD_MAC_NSTATS_V3 &&
	    (nic_data->datapath_caps2 &
	     (1 << MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_LBN)))
		raw_mask[1] |= EF10_CTPIO_STAT_MASK;

#if BITS_PER_LONG == 64
	BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 2);
	mask[0] = raw_mask[0];
	mask[1] = raw_mask[1];
#else
	BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 3);
	mask[0] = raw_mask[0] & 0xffffffff;
	mask[1] = raw_mask[0] >> 32;
	mask[2] = raw_mask[1] & 0xffffffff;
#endif
}

static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names)
{
	DECLARE_BITMAP(mask, EF10_STAT_COUNT);

	efx_ef10_get_stat_mask(efx, mask);
	return efx_nic_describe_stats(efx_ef10_stat_desc, EF10_STAT_COUNT,
				      mask, names);
}

static void efx_ef10_get_fec_stats(struct efx_nic *efx,
				   struct ethtool_fec_stats *fec_stats)
{
	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u64 *stats = nic_data->stats;

	efx_ef10_get_stat_mask(efx, mask);
	if (test_bit(EF10_STAT_fec_corrected_errors, mask))
		fec_stats->corrected_blocks.total =
			stats[EF10_STAT_fec_corrected_errors];
	if (test_bit(EF10_STAT_fec_uncorrected_errors, mask))
		fec_stats->uncorrectable_blocks.total =
			stats[EF10_STAT_fec_uncorrected_errors];
}

static size_t efx_ef10_update_stats_common(struct efx_nic *efx, u64 *full_stats,
					   struct rtnl_link_stats64 *core_stats)
{
	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u64 *stats = nic_data->stats;
	size_t stats_count = 0, index;

	efx_ef10_get_stat_mask(efx, mask);

	if (full_stats) {
		for_each_set_bit(index, mask, EF10_STAT_COUNT) {
			if (efx_ef10_stat_desc[index].name) {
				*full_stats++ = stats[index];
				++stats_count;
			}
		}
	}

	if (!core_stats)
		return stats_count;

	if (nic_data->datapath_caps &
			1 << MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN) {
		/* Use vadaptor stats. */
		core_stats->rx_packets = stats[EF10_STAT_rx_unicast] +
					 stats[EF10_STAT_rx_multicast] +
					 stats[EF10_STAT_rx_broadcast];
		core_stats->tx_packets = stats[EF10_STAT_tx_unicast] +
					 stats[EF10_STAT_tx_multicast] +
					 stats[EF10_STAT_tx_broadcast];
		core_stats->rx_bytes = stats[EF10_STAT_rx_unicast_bytes] +
				       stats[EF10_STAT_rx_multicast_bytes] +
				       stats[EF10_STAT_rx_broadcast_bytes];
		core_stats->tx_bytes = stats[EF10_STAT_tx_unicast_bytes] +
				       stats[EF10_STAT_tx_multicast_bytes] +
				       stats[EF10_STAT_tx_broadcast_bytes];
		core_stats->rx_dropped = stats[GENERIC_STAT_rx_nodesc_trunc] +
					 stats[GENERIC_STAT_rx_noskb_drops];
		core_stats->multicast = stats[EF10_STAT_rx_multicast];
		core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad];
		core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow];
		core_stats->rx_errors = core_stats->rx_crc_errors;
		core_stats->tx_errors = stats[EF10_STAT_tx_bad];
	} else {
		/* Use port stats. */
		core_stats->rx_packets = stats[EF10_STAT_port_rx_packets];
		core_stats->tx_packets = stats[EF10_STAT_port_tx_packets];
		core_stats->rx_bytes = stats[EF10_STAT_port_rx_bytes];
		core_stats->tx_bytes = stats[EF10_STAT_port_tx_bytes];
		core_stats->rx_dropped = stats[EF10_STAT_port_rx_nodesc_drops] +
					 stats[GENERIC_STAT_rx_nodesc_trunc] +
					 stats[GENERIC_STAT_rx_noskb_drops];
		core_stats->multicast = stats[EF10_STAT_port_rx_multicast];
		core_stats->rx_length_errors =
				stats[EF10_STAT_port_rx_gtjumbo] +
				stats[EF10_STAT_port_rx_length_error];
		core_stats->rx_crc_errors = stats[EF10_STAT_port_rx_bad];
		core_stats->rx_frame_errors =
				stats[EF10_STAT_port_rx_align_error];
		core_stats->rx_fifo_errors = stats[EF10_STAT_port_rx_overflow];
		core_stats->rx_errors = (core_stats->rx_length_errors +
					 core_stats->rx_crc_errors +
					 core_stats->rx_frame_errors);
	}

	return stats_count;
}

static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats,
				       struct rtnl_link_stats64 *core_stats)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
	u64 *stats = nic_data->stats;

	efx_ef10_get_stat_mask(efx, mask);

	efx_nic_copy_stats(efx, nic_data->mc_stats);
	efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT,
			     mask, stats, nic_data->mc_stats, false);

	/* Update derived statistics */
	efx_nic_fix_nodesc_drop_stat(efx,
				     &stats[EF10_STAT_port_rx_nodesc_drops]);
	/* MC Firmware reads RX_BYTES and RX_GOOD_BYTES from the MAC.
	 * It then calculates RX_BAD_BYTES and DMAs it to us with RX_BYTES.
	 * We report these as port_rx_ stats. We are not given RX_GOOD_BYTES.
	 * Here we calculate port_rx_good_bytes.
	 */
	stats[EF10_STAT_port_rx_good_bytes] =
		stats[EF10_STAT_port_rx_bytes] -
		stats[EF10_STAT_port_rx_bytes_minus_good_bytes];

	/* The asynchronous reads used to calculate RX_BAD_BYTES in
	 * MC Firmware are done such that we should not see an increase in
	 * RX_BAD_BYTES when a good packet has arrived. Unfortunately this
	 * does mean that the stat can decrease at times. Here we do not
	 * update the stat unless it has increased or has gone to zero
	 * (In the case of the NIC rebooting).
	 * Please see Bug 33781 for a discussion of why things work this way.
	 */
	efx_update_diff_stat(&stats[EF10_STAT_port_rx_bad_bytes],
			     stats[EF10_STAT_port_rx_bytes_minus_good_bytes]);
	efx_update_sw_stats(efx, stats);

	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
}

static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx)
	__must_hold(&efx->stats_lock)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN);
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
	__le64 generation_start, generation_end;
	u64 *stats = nic_data->stats;
	u32 dma_len = efx->num_mac_stats * sizeof(u64);
	struct efx_buffer stats_buf;
	__le64 *dma_stats;
	int rc;

	spin_unlock_bh(&efx->stats_lock);

	efx_ef10_get_stat_mask(efx, mask);

	rc = efx_nic_alloc_buffer(efx, &stats_buf, dma_len, GFP_KERNEL);
	if (rc) {
		spin_lock_bh(&efx->stats_lock);
		return rc;
	}

	dma_stats = stats_buf.addr;
	dma_stats[efx->num_mac_stats - 1] = EFX_MC_STATS_GENERATION_INVALID;

	MCDI_SET_QWORD(inbuf, MAC_STATS_IN_DMA_ADDR, stats_buf.dma_addr);
	MCDI_POPULATE_DWORD_1(inbuf, MAC_STATS_IN_CMD,
			      MAC_STATS_IN_DMA, 1);
	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);

	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
				NULL, 0, NULL);
	spin_lock_bh(&efx->stats_lock);
	if (rc) {
		/* Expect ENOENT if DMA queues have not been set up */
		if (rc != -ENOENT || atomic_read(&efx->active_queues))
			efx_mcdi_display_error(efx, MC_CMD_MAC_STATS,
					       sizeof(inbuf), NULL, 0, rc);
		goto out;
	}

	generation_end = dma_stats[efx->num_mac_stats - 1];
	if (generation_end == EFX_MC_STATS_GENERATION_INVALID) {
		WARN_ON_ONCE(1);
		goto out;
	}
	rmb();
	efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask,
			     stats, stats_buf.addr, false);
	rmb();
	generation_start = dma_stats[MC_CMD_MAC_GENERATION_START];
	if (generation_end != generation_start) {
		rc = -EAGAIN;
		goto out;
	}

	efx_update_sw_stats(efx, stats);
out:
	/* releasing a DMA coherent buffer with BH disabled can panic */
	spin_unlock_bh(&efx->stats_lock);
	efx_nic_free_buffer(efx, &stats_buf);
	spin_lock_bh(&efx->stats_lock);
	return rc;
}

static size_t efx_ef10_update_stats_vf(struct efx_nic *efx, u64 *full_stats,
				       struct rtnl_link_stats64 *core_stats)
{
	if (efx_ef10_try_update_nic_stats_vf(efx))
		return 0;

	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
}

static size_t efx_ef10_update_stats_atomic_vf(struct efx_nic *efx, u64 *full_stats,
					      struct rtnl_link_stats64 *core_stats)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	/* In atomic context, cannot update HW stats.  Just update the
	 * software stats and return so the caller can continue.
	 */
	efx_update_sw_stats(efx, nic_data->stats);
	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
}

static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;
	unsigned int mode, usecs;
	efx_dword_t timer_cmd;

	if (channel->irq_moderation_us) {
		mode = 3;
		usecs = channel->irq_moderation_us;
	} else {
		mode = 0;
		usecs = 0;
	}

	if (EFX_EF10_WORKAROUND_61265(efx)) {
		MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_EVQ_TMR_IN_LEN);
		unsigned int ns = usecs * 1000;

		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_INSTANCE,
			       channel->channel);
		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_LOAD_REQ_NS, ns);
		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_RELOAD_REQ_NS, ns);
		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_MODE, mode);

		efx_mcdi_rpc_async(efx, MC_CMD_SET_EVQ_TMR,
				   inbuf, sizeof(inbuf), 0, NULL, 0);
	} else if (EFX_EF10_WORKAROUND_35388(efx)) {
		unsigned int ticks = efx_usecs_to_ticks(efx, usecs);

		EFX_POPULATE_DWORD_3(timer_cmd, ERF_DD_EVQ_IND_TIMER_FLAGS,
				     EFE_DD_EVQ_IND_TIMER_FLAGS,
				     ERF_DD_EVQ_IND_TIMER_MODE, mode,
				     ERF_DD_EVQ_IND_TIMER_VAL, ticks);
		efx_writed_page(efx, &timer_cmd, ER_DD_EVQ_INDIRECT,
				channel->channel);
	} else {
		unsigned int ticks = efx_usecs_to_ticks(efx, usecs);

		EFX_POPULATE_DWORD_3(timer_cmd, ERF_DZ_TC_TIMER_MODE, mode,
				     ERF_DZ_TC_TIMER_VAL, ticks,
				     ERF_FZ_TC_TMR_REL_VAL, ticks);
		efx_writed_page(efx, &timer_cmd, ER_DZ_EVQ_TMR,
				channel->channel);
	}
}

static void efx_ef10_get_wol_vf(struct efx_nic *efx,
				struct ethtool_wolinfo *wol) {}

static int efx_ef10_set_wol_vf(struct efx_nic *efx, u32 type)
{
	return -EOPNOTSUPP;
}

static void efx_ef10_get_wol(struct efx_nic *efx, struct ethtool_wolinfo *wol)
{
	wol->supported = 0;
	wol->wolopts = 0;
	memset(&wol->sopass, 0, sizeof(wol->sopass));
}

static int efx_ef10_set_wol(struct efx_nic *efx, u32 type)
{
	if (type != 0)
		return -EINVAL;
	return 0;
}

static void efx_ef10_mcdi_request(struct efx_nic *efx,
				  const efx_dword_t *hdr, size_t hdr_len,
				  const efx_dword_t *sdu, size_t sdu_len)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u8 *pdu = nic_data->mcdi_buf.addr;

	memcpy(pdu, hdr, hdr_len);
	memcpy(pdu + hdr_len, sdu, sdu_len);
	wmb();

	/* The hardware provides 'low' and 'high' (doorbell) registers
	 * for passing the 64-bit address of an MCDI request to
	 * firmware.  However the dwords are swapped by firmware.  The
	 * least significant bits of the doorbell are then 0 for all
	 * MCDI requests due to alignment.
	 */
	_efx_writed(efx, cpu_to_le32((u64)nic_data->mcdi_buf.dma_addr >> 32),
		    ER_DZ_MC_DB_LWRD);
	_efx_writed(efx, cpu_to_le32((u32)nic_data->mcdi_buf.dma_addr),
		    ER_DZ_MC_DB_HWRD);
}

static bool efx_ef10_mcdi_poll_response(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	const efx_dword_t hdr = *(const efx_dword_t *)nic_data->mcdi_buf.addr;

	rmb();
	return EFX_DWORD_FIELD(hdr, MCDI_HEADER_RESPONSE);
}

static void
efx_ef10_mcdi_read_response(struct efx_nic *efx, efx_dword_t *outbuf,
			    size_t offset, size_t outlen)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	const u8 *pdu = nic_data->mcdi_buf.addr;

	memcpy(outbuf, pdu + offset, outlen);
}

static void efx_ef10_mcdi_reboot_detected(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	/* All our allocations have been reset */
	efx_ef10_table_reset_mc_allocations(efx);

	/* The datapath firmware might have been changed */
	nic_data->must_check_datapath_caps = true;

	/* MAC statistics have been cleared on the NIC; clear the local
	 * statistic that we update with efx_update_diff_stat().
	 */
	nic_data->stats[EF10_STAT_port_rx_bad_bytes] = 0;
}

static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	int rc;

	rc = efx_ef10_get_warm_boot_count(efx);
	if (rc < 0) {
		/* The firmware is presumably in the process of
		 * rebooting.  However, we are supposed to report each
		 * reboot just once, so we must only do that once we
		 * can read and store the updated warm boot count.
		 */
		return 0;
	}

	if (rc == nic_data->warm_boot_count)
		return 0;

	nic_data->warm_boot_count = rc;
	efx_ef10_mcdi_reboot_detected(efx);

	return -EIO;
}

/* Handle an MSI interrupt
 *
 * Handle an MSI hardware interrupt.  This routine schedules event
 * queue processing.  No interrupt acknowledgement cycle is necessary.
 * Also, we never need to check that the interrupt is for us, since
 * MSI interrupts cannot be shared.
 */
static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id)
{
	struct efx_msi_context *context = dev_id;
	struct efx_nic *efx = context->efx;

	netif_vdbg(efx, intr, efx->net_dev,
		   "IRQ %d on CPU %d\n", irq, raw_smp_processor_id());

	if (likely(READ_ONCE(efx->irq_soft_enabled))) {
		/* Note test interrupts */
		if (context->index == efx->irq_level)
			efx->last_irq_cpu = raw_smp_processor_id();

		/* Schedule processing of the channel */
		efx_schedule_channel_irq(efx->channel[context->index]);
	}

	return IRQ_HANDLED;
}

static irqreturn_t efx_ef10_legacy_interrupt(int irq, void *dev_id)
{
	struct efx_nic *efx = dev_id;
	bool soft_enabled = READ_ONCE(efx->irq_soft_enabled);
	struct efx_channel *channel;
	efx_dword_t reg;
	u32 queues;

	/* Read the ISR which also ACKs the interrupts */
	efx_readd(efx, &reg, ER_DZ_BIU_INT_ISR);
	queues = EFX_DWORD_FIELD(reg, ERF_DZ_ISR_REG);

	if (queues == 0)
		return IRQ_NONE;

	if (likely(soft_enabled)) {
		/* Note test interrupts */
		if (queues & (1U << efx->irq_level))
			efx->last_irq_cpu = raw_smp_processor_id();

		efx_for_each_channel(channel, efx) {
			if (queues & 1)
				efx_schedule_channel_irq(channel);
			queues >>= 1;
		}
	}

	netif_vdbg(efx, intr, efx->net_dev,
		   "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n",
		   irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg));

	return IRQ_HANDLED;
}

static int efx_ef10_irq_test_generate(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_TRIGGER_INTERRUPT_IN_LEN);

	if (efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG41750, true,
				    NULL) == 0)
		return -ENOTSUPP;

	BUILD_BUG_ON(MC_CMD_TRIGGER_INTERRUPT_OUT_LEN != 0);

	MCDI_SET_DWORD(inbuf, TRIGGER_INTERRUPT_IN_INTR_LEVEL, efx->irq_level);
	return efx_mcdi_rpc(efx, MC_CMD_TRIGGER_INTERRUPT,
			    inbuf, sizeof(inbuf), NULL, 0, NULL);
}

static int efx_ef10_tx_probe(struct efx_tx_queue *tx_queue)
{
	/* low two bits of label are what we want for type */
	BUILD_BUG_ON((EFX_TXQ_TYPE_OUTER_CSUM | EFX_TXQ_TYPE_INNER_CSUM) != 3);
	tx_queue->type = tx_queue->label & 3;
	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf,
				    (tx_queue->ptr_mask + 1) *
				    sizeof(efx_qword_t),
				    GFP_KERNEL);
}

/* This writes to the TX_DESC_WPTR and also pushes data */
static inline void efx_ef10_push_tx_desc(struct efx_tx_queue *tx_queue,
					 const efx_qword_t *txd)
{
	unsigned int write_ptr;
	efx_oword_t reg;

	write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
	EFX_POPULATE_OWORD_1(reg, ERF_DZ_TX_DESC_WPTR, write_ptr);
	reg.qword[0] = *txd;
	efx_writeo_page(tx_queue->efx, &reg,
			ER_DZ_TX_DESC_UPD, tx_queue->queue);
}

/* Add Firmware-Assisted TSO v2 option descriptors to a queue.
 */
int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
			 bool *data_mapped)
{
	struct efx_tx_buffer *buffer;
	u16 inner_ipv4_id = 0;
	u16 outer_ipv4_id = 0;
	struct tcphdr *tcp;
	struct iphdr *ip;
	u16 ip_tot_len;
	u32 seqnum;
	u32 mss;

	EFX_WARN_ON_ONCE_PARANOID(tx_queue->tso_version != 2);

	mss = skb_shinfo(skb)->gso_size;

	if (unlikely(mss < 4)) {
		WARN_ONCE(1, "MSS of %u is too small for TSO v2\n", mss);
		return -EINVAL;
	}

	if (skb->encapsulation) {
		if (!tx_queue->tso_encap)
			return -EINVAL;
		ip = ip_hdr(skb);
		if (ip->version == 4)
			outer_ipv4_id = ntohs(ip->id);

		ip = inner_ip_hdr(skb);
		tcp = inner_tcp_hdr(skb);
	} else {
		ip = ip_hdr(skb);
		tcp = tcp_hdr(skb);
	}

	/* 8000-series EF10 hardware requires that IP Total Length be
	 * greater than or equal to the value it will have in each segment
	 * (which is at most mss + 208 + TCP header length), but also less
	 * than (0x10000 - inner_network_header).  Otherwise the TCP
	 * checksum calculation will be broken for encapsulated packets.
	 * We fill in ip->tot_len with 0xff30, which should satisfy the
	 * first requirement unless the MSS is ridiculously large (which
	 * should be impossible as the driver max MTU is 9216); it is
	 * guaranteed to satisfy the second as we only attempt TSO if
	 * inner_network_header <= 208.
	 */
	ip_tot_len = 0x10000 - EFX_TSO2_MAX_HDRLEN;
	EFX_WARN_ON_ONCE_PARANOID(mss + EFX_TSO2_MAX_HDRLEN +
				  (tcp->doff << 2u) > ip_tot_len);

	if (ip->version == 4) {
		ip->tot_len = htons(ip_tot_len);
		ip->check = 0;
		inner_ipv4_id = ntohs(ip->id);
	} else {
		((struct ipv6hdr *)ip)->payload_len = htons(ip_tot_len);
	}

	seqnum = ntohl(tcp->seq);

	buffer = efx_tx_queue_get_insert_buffer(tx_queue);

	buffer->flags = EFX_TX_BUF_OPTION;
	buffer->len = 0;
	buffer->unmap_len = 0;
	EFX_POPULATE_QWORD_5(buffer->option,
			ESF_DZ_TX_DESC_IS_OPT, 1,
			ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
			ESF_DZ_TX_TSO_OPTION_TYPE,
			ESE_DZ_TX_TSO_OPTION_DESC_FATSO2A,
			ESF_DZ_TX_TSO_IP_ID, inner_ipv4_id,
			ESF_DZ_TX_TSO_TCP_SEQNO, seqnum
			);
	++tx_queue->insert_count;

	buffer = efx_tx_queue_get_insert_buffer(tx_queue);

	buffer->flags = EFX_TX_BUF_OPTION;
	buffer->len = 0;
	buffer->unmap_len = 0;
	EFX_POPULATE_QWORD_5(buffer->option,
			ESF_DZ_TX_DESC_IS_OPT, 1,
			ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
			ESF_DZ_TX_TSO_OPTION_TYPE,
			ESE_DZ_TX_TSO_OPTION_DESC_FATSO2B,
			ESF_DZ_TX_TSO_OUTER_IPID, outer_ipv4_id,
			ESF_DZ_TX_TSO_TCP_MSS, mss
			);
	++tx_queue->insert_count;

	return 0;
}

static u32 efx_ef10_tso_versions(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u32 tso_versions = 0;

	if (nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))
		tso_versions |= BIT(1);
	if (nic_data->datapath_caps2 &
	    (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN))
		tso_versions |= BIT(2);
	return tso_versions;
}

static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
{
	bool csum_offload = tx_queue->type & EFX_TXQ_TYPE_OUTER_CSUM;
	bool inner_csum = tx_queue->type & EFX_TXQ_TYPE_INNER_CSUM;
	struct efx_channel *channel = tx_queue->channel;
	struct efx_nic *efx = tx_queue->efx;
	struct efx_ef10_nic_data *nic_data;
	efx_qword_t *txd;
	int rc;

	nic_data = efx->nic_data;

	/* Only attempt to enable TX timestamping if we have the license for it,
	 * otherwise TXQ init will fail
	 */
	if (!(nic_data->licensed_features &
	      (1 << LICENSED_V3_FEATURES_TX_TIMESTAMPS_LBN))) {
		tx_queue->timestamping = false;
		/* Disable sync events on this channel. */
		if (efx->type->ptp_set_ts_sync_events)
			efx->type->ptp_set_ts_sync_events(efx, false, false);
	}

	/* TSOv2 is a limited resource that can only be configured on a limited
	 * number of queues. TSO without checksum offload is not really a thing,
	 * so we only enable it for those queues.
	 * TSOv2 cannot be used with Hardware timestamping, and is never needed
	 * for XDP tx.
	 */
	if (efx_has_cap(efx, TX_TSO_V2)) {
		if ((csum_offload || inner_csum) &&
		    !tx_queue->timestamping && !tx_queue->xdp_tx) {
			tx_queue->tso_version = 2;
			netif_dbg(efx, hw, efx->net_dev, "Using TSOv2 for channel %u\n",
				  channel->channel);
		}
	} else if (efx_has_cap(efx, TX_TSO)) {
		tx_queue->tso_version = 1;
	}

	rc = efx_mcdi_tx_init(tx_queue);
	if (rc)
		goto fail;

	/* A previous user of this TX queue might have set us up the
	 * bomb by writing a descriptor to the TX push collector but
	 * not the doorbell.  (Each collector belongs to a port, not a
	 * queue or function, so cannot easily be reset.)  We must
	 * attempt to push a no-op descriptor in its place.
	 */
	tx_queue->buffer[0].flags = EFX_TX_BUF_OPTION;
	tx_queue->insert_count = 1;
	txd = efx_tx_desc(tx_queue, 0);
	EFX_POPULATE_QWORD_7(*txd,
			     ESF_DZ_TX_DESC_IS_OPT, true,
			     ESF_DZ_TX_OPTION_TYPE,
			     ESE_DZ_TX_OPTION_DESC_CRC_CSUM,
			     ESF_DZ_TX_OPTION_UDP_TCP_CSUM, csum_offload,
			     ESF_DZ_TX_OPTION_IP_CSUM, csum_offload && tx_queue->tso_version != 2,
			     ESF_DZ_TX_OPTION_INNER_UDP_TCP_CSUM, inner_csum,
			     ESF_DZ_TX_OPTION_INNER_IP_CSUM, inner_csum && tx_queue->tso_version != 2,
			     ESF_DZ_TX_TIMESTAMP, tx_queue->timestamping);
	tx_queue->write_count = 1;

	if (tx_queue->tso_version == 2 && efx_has_cap(efx, TX_TSO_V2_ENCAP))
		tx_queue->tso_encap = true;

	wmb();
	efx_ef10_push_tx_desc(tx_queue, txd);

	return;

fail:
	netdev_WARN(efx->net_dev, "failed to initialise TXQ %d\n",
		    tx_queue->queue);
}

/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */
static inline void efx_ef10_notify_tx_desc(struct efx_tx_queue *tx_queue)
{
	unsigned int write_ptr;
	efx_dword_t reg;

	write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
	EFX_POPULATE_DWORD_1(reg, ERF_DZ_TX_DESC_WPTR_DWORD, write_ptr);
	efx_writed_page(tx_queue->efx, &reg,
			ER_DZ_TX_DESC_UPD_DWORD, tx_queue->queue);
}

#define EFX_EF10_MAX_TX_DESCRIPTOR_LEN 0x3fff

static unsigned int efx_ef10_tx_limit_len(struct efx_tx_queue *tx_queue,
					  dma_addr_t dma_addr, unsigned int len)
{
	if (len > EFX_EF10_MAX_TX_DESCRIPTOR_LEN) {
		/* If we need to break across multiple descriptors we should
		 * stop at a page boundary. This assumes the length limit is
		 * greater than the page size.
		 */
		dma_addr_t end = dma_addr + EFX_EF10_MAX_TX_DESCRIPTOR_LEN;

		BUILD_BUG_ON(EFX_EF10_MAX_TX_DESCRIPTOR_LEN < EFX_PAGE_SIZE);
		len = (end & (~(EFX_PAGE_SIZE - 1))) - dma_addr;
	}

	return len;
}

static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
{
	unsigned int old_write_count = tx_queue->write_count;
	struct efx_tx_buffer *buffer;
	unsigned int write_ptr;
	efx_qword_t *txd;

	tx_queue->xmit_pending = false;
	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
		return;

	do {
		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
		buffer = &tx_queue->buffer[write_ptr];
		txd = efx_tx_desc(tx_queue, write_ptr);
		++tx_queue->write_count;

		/* Create TX descriptor ring entry */
		if (buffer->flags & EFX_TX_BUF_OPTION) {
			*txd = buffer->option;
			if (EFX_QWORD_FIELD(*txd, ESF_DZ_TX_OPTION_TYPE) == 1)
				/* PIO descriptor */
				tx_queue->packet_write_count = tx_queue->write_count;
		} else {
			tx_queue->packet_write_count = tx_queue->write_count;
			BUILD_BUG_ON(EFX_TX_BUF_CONT != 1);
			EFX_POPULATE_QWORD_3(
				*txd,
				ESF_DZ_TX_KER_CONT,
				buffer->flags & EFX_TX_BUF_CONT,
				ESF_DZ_TX_KER_BYTE_CNT, buffer->len,
				ESF_DZ_TX_KER_BUF_ADDR, buffer->dma_addr);
		}
	} while (tx_queue->write_count != tx_queue->insert_count);

	wmb(); /* Ensure descriptors are written before they are fetched */

	if (efx_nic_may_push_tx_desc(tx_queue, old_write_count)) {
		txd = efx_tx_desc(tx_queue,
				  old_write_count & tx_queue->ptr_mask);
		efx_ef10_push_tx_desc(tx_queue, txd);
		++tx_queue->pushes;
	} else {
		efx_ef10_notify_tx_desc(tx_queue);
	}
}

static int efx_ef10_probe_multicast_chaining(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	unsigned int enabled, implemented;
	bool want_workaround_26807;
	int rc;

	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);
	if (rc == -ENOSYS) {
		/* GET_WORKAROUNDS was implemented before this workaround,
		 * thus it must be unavailable in this firmware.
		 */
		nic_data->workaround_26807 = false;
		return 0;
	}
	if (rc)
		return rc;
	want_workaround_26807 =
		implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807;
	nic_data->workaround_26807 =
		!!(enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807);

	if (want_workaround_26807 && !nic_data->workaround_26807) {
		unsigned int flags;

		rc = efx_mcdi_set_workaround(efx,
					     MC_CMD_WORKAROUND_BUG26807,
					     true, &flags);
		if (!rc) {
			if (flags &
			    1 << MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_LBN) {
				netif_info(efx, drv, efx->net_dev,
					   "other functions on NIC have been reset\n");

				/* With MCFW v4.6.x and earlier, the
				 * boot count will have incremented,
				 * so re-read the warm_boot_count
				 * value now to ensure this function
				 * doesn't think it has changed next
				 * time it checks.
				 */
				rc = efx_ef10_get_warm_boot_count(efx);
				if (rc >= 0) {
					nic_data->warm_boot_count = rc;
					rc = 0;
				}
			}
			nic_data->workaround_26807 = true;
		} else if (rc == -EPERM) {
			rc = 0;
		}
	}
	return rc;
}

static int efx_ef10_filter_table_probe(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	int rc = efx_ef10_probe_multicast_chaining(efx);
	struct efx_mcdi_filter_vlan *vlan;

	if (rc)
		return rc;
	down_write(&efx->filter_sem);
	rc = efx_mcdi_filter_table_probe(efx, nic_data->workaround_26807);

	if (rc)
		goto out_unlock;

	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
		rc = efx_mcdi_filter_add_vlan(efx, vlan->vid);
		if (rc)
			goto fail_add_vlan;
	}
	goto out_unlock;

fail_add_vlan:
	efx_mcdi_filter_table_remove(efx);
out_unlock:
	up_write(&efx->filter_sem);
	return rc;
}

static void efx_ef10_filter_table_remove(struct efx_nic *efx)
{
	down_write(&efx->filter_sem);
	efx_mcdi_filter_table_remove(efx);
	up_write(&efx->filter_sem);
}

/* This creates an entry in the RX descriptor queue */
static inline void
efx_ef10_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
{
	struct efx_rx_buffer *rx_buf;
	efx_qword_t *rxd;

	rxd = efx_rx_desc(rx_queue, index);
	rx_buf = efx_rx_buffer(rx_queue, index);
	EFX_POPULATE_QWORD_2(*rxd,
			     ESF_DZ_RX_KER_BYTE_CNT, rx_buf->len,
			     ESF_DZ_RX_KER_BUF_ADDR, rx_buf->dma_addr);
}

static void efx_ef10_rx_write(struct efx_rx_queue *rx_queue)
{
	struct efx_nic *efx = rx_queue->efx;
	unsigned int write_count;
	efx_dword_t reg;

	/* Firmware requires that RX_DESC_WPTR be a multiple of 8 */
	write_count = rx_queue->added_count & ~7;
	if (rx_queue->notified_count == write_count)
		return;

	do
		efx_ef10_build_rx_desc(
			rx_queue,
			rx_queue->notified_count & rx_queue->ptr_mask);
	while (++rx_queue->notified_count != write_count);

	wmb();
	EFX_POPULATE_DWORD_1(reg, ERF_DZ_RX_DESC_WPTR,
			     write_count & rx_queue->ptr_mask);
	efx_writed_page(efx, &reg, ER_DZ_RX_DESC_UPD,
			efx_rx_queue_index(rx_queue));
}

static efx_mcdi_async_completer efx_ef10_rx_defer_refill_complete;

static void efx_ef10_rx_defer_refill(struct efx_rx_queue *rx_queue)
{
	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
	MCDI_DECLARE_BUF(inbuf, MC_CMD_DRIVER_EVENT_IN_LEN);
	efx_qword_t event;

	EFX_POPULATE_QWORD_2(event,
			     ESF_DZ_EV_CODE, EFX_EF10_DRVGEN_EV,
			     ESF_DZ_EV_DATA, EFX_EF10_REFILL);

	MCDI_SET_DWORD(inbuf, DRIVER_EVENT_IN_EVQ, channel->channel);

	/* MCDI_SET_QWORD is not appropriate here since EFX_POPULATE_* has
	 * already swapped the data to little-endian order.
	 */
	memcpy(MCDI_PTR(inbuf, DRIVER_EVENT_IN_DATA), &event.u64[0],
	       sizeof(efx_qword_t));

	efx_mcdi_rpc_async(channel->efx, MC_CMD_DRIVER_EVENT,
			   inbuf, sizeof(inbuf), 0,
			   efx_ef10_rx_defer_refill_complete, 0);
}

static void
efx_ef10_rx_defer_refill_complete(struct efx_nic *efx, unsigned long cookie,
				  int rc, efx_dword_t *outbuf,
				  size_t outlen_actual)
{
	/* nothing to do */
}

static int efx_ef10_ev_init(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;
	struct efx_ef10_nic_data *nic_data;
	bool use_v2, cut_thru;

	nic_data = efx->nic_data;
	use_v2 = nic_data->datapath_caps2 &
			    1 << MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN;
	cut_thru = !(nic_data->datapath_caps &
			      1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
	return efx_mcdi_ev_init(channel, cut_thru, use_v2);
}

static void efx_ef10_handle_rx_wrong_queue(struct efx_rx_queue *rx_queue,
					   unsigned int rx_queue_label)
{
	struct efx_nic *efx = rx_queue->efx;

	netif_info(efx, hw, efx->net_dev,
		   "rx event arrived on queue %d labeled as queue %u\n",
		   efx_rx_queue_index(rx_queue), rx_queue_label);

	efx_schedule_reset(efx, RESET_TYPE_DISABLE);
}

static void
efx_ef10_handle_rx_bad_lbits(struct efx_rx_queue *rx_queue,
			     unsigned int actual, unsigned int expected)
{
	unsigned int dropped = (actual - expected) & rx_queue->ptr_mask;
	struct efx_nic *efx = rx_queue->efx;

	netif_info(efx, hw, efx->net_dev,
		   "dropped %d events (index=%d expected=%d)\n",
		   dropped, actual, expected);

	efx_schedule_reset(efx, RESET_TYPE_DISABLE);
}

/* partially received RX was aborted. clean up. */
static void efx_ef10_handle_rx_abort(struct efx_rx_queue *rx_queue)
{
	unsigned int rx_desc_ptr;

	netif_dbg(rx_queue->efx, hw, rx_queue->efx->net_dev,
		  "scattered RX aborted (dropping %u buffers)\n",
		  rx_queue->scatter_n);

	rx_desc_ptr = rx_queue->removed_count & rx_queue->ptr_mask;

	efx_rx_packet(rx_queue, rx_desc_ptr, rx_queue->scatter_n,
		      0, EFX_RX_PKT_DISCARD);

	rx_queue->removed_count += rx_queue->scatter_n;
	rx_queue->scatter_n = 0;
	rx_queue->scatter_len = 0;
	++efx_rx_queue_channel(rx_queue)->n_rx_nodesc_trunc;
}

static u16 efx_ef10_handle_rx_event_errors(struct efx_channel *channel,
					   unsigned int n_packets,
					   unsigned int rx_encap_hdr,
					   unsigned int rx_l3_class,
					   unsigned int rx_l4_class,
					   const efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	bool handled = false;

	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_ECRC_ERR)) {
		if (!(efx->net_dev->features & NETIF_F_RXALL)) {
			if (!efx->loopback_selftest)
				channel->n_rx_eth_crc_err += n_packets;
			return EFX_RX_PKT_DISCARD;
		}
		handled = true;
	}
	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_IPCKSUM_ERR)) {
		if (unlikely(rx_encap_hdr != ESE_EZ_ENCAP_HDR_VXLAN &&
			     rx_l3_class != ESE_DZ_L3_CLASS_IP4 &&
			     rx_l3_class != ESE_DZ_L3_CLASS_IP4_FRAG &&
			     rx_l3_class != ESE_DZ_L3_CLASS_IP6 &&
			     rx_l3_class != ESE_DZ_L3_CLASS_IP6_FRAG))
			netdev_WARN(efx->net_dev,
				    "invalid class for RX_IPCKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		if (!efx->loopback_selftest)
			*(rx_encap_hdr ?
			  &channel->n_rx_outer_ip_hdr_chksum_err :
			  &channel->n_rx_ip_hdr_chksum_err) += n_packets;
		return 0;
	}
	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_TCPUDP_CKSUM_ERR)) {
		if (unlikely(rx_encap_hdr != ESE_EZ_ENCAP_HDR_VXLAN &&
			     ((rx_l3_class != ESE_DZ_L3_CLASS_IP4 &&
			       rx_l3_class != ESE_DZ_L3_CLASS_IP6) ||
			      (rx_l4_class != ESE_FZ_L4_CLASS_TCP &&
			       rx_l4_class != ESE_FZ_L4_CLASS_UDP))))
			netdev_WARN(efx->net_dev,
				    "invalid class for RX_TCPUDP_CKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		if (!efx->loopback_selftest)
			*(rx_encap_hdr ?
			  &channel->n_rx_outer_tcp_udp_chksum_err :
			  &channel->n_rx_tcp_udp_chksum_err) += n_packets;
		return 0;
	}
	if (EFX_QWORD_FIELD(*event, ESF_EZ_RX_IP_INNER_CHKSUM_ERR)) {
		if (unlikely(!rx_encap_hdr))
			netdev_WARN(efx->net_dev,
				    "invalid encapsulation type for RX_IP_INNER_CHKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		else if (unlikely(rx_l3_class != ESE_DZ_L3_CLASS_IP4 &&
				  rx_l3_class != ESE_DZ_L3_CLASS_IP4_FRAG &&
				  rx_l3_class != ESE_DZ_L3_CLASS_IP6 &&
				  rx_l3_class != ESE_DZ_L3_CLASS_IP6_FRAG))
			netdev_WARN(efx->net_dev,
				    "invalid class for RX_IP_INNER_CHKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		if (!efx->loopback_selftest)
			channel->n_rx_inner_ip_hdr_chksum_err += n_packets;
		return 0;
	}
	if (EFX_QWORD_FIELD(*event, ESF_EZ_RX_TCP_UDP_INNER_CHKSUM_ERR)) {
		if (unlikely(!rx_encap_hdr))
			netdev_WARN(efx->net_dev,
				    "invalid encapsulation type for RX_TCP_UDP_INNER_CHKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		else if (unlikely((rx_l3_class != ESE_DZ_L3_CLASS_IP4 &&
				   rx_l3_class != ESE_DZ_L3_CLASS_IP6) ||
				  (rx_l4_class != ESE_FZ_L4_CLASS_TCP &&
				   rx_l4_class != ESE_FZ_L4_CLASS_UDP)))
			netdev_WARN(efx->net_dev,
				    "invalid class for RX_TCP_UDP_INNER_CHKSUM_ERR: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		if (!efx->loopback_selftest)
			channel->n_rx_inner_tcp_udp_chksum_err += n_packets;
		return 0;
	}

	WARN_ON(!handled); /* No error bits were recognised */
	return 0;
}

static int efx_ef10_handle_rx_event(struct efx_channel *channel,
				    const efx_qword_t *event)
{
	unsigned int rx_bytes, next_ptr_lbits, rx_queue_label;
	unsigned int rx_l3_class, rx_l4_class, rx_encap_hdr;
	unsigned int n_descs, n_packets, i;
	struct efx_nic *efx = channel->efx;
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	struct efx_rx_queue *rx_queue;
	efx_qword_t errors;
	bool rx_cont;
	u16 flags = 0;

	if (unlikely(READ_ONCE(efx->reset_pending)))
		return 0;

	/* Basic packet information */
	rx_bytes = EFX_QWORD_FIELD(*event, ESF_DZ_RX_BYTES);
	next_ptr_lbits = EFX_QWORD_FIELD(*event, ESF_DZ_RX_DSC_PTR_LBITS);
	rx_queue_label = EFX_QWORD_FIELD(*event, ESF_DZ_RX_QLABEL);
	rx_l3_class = EFX_QWORD_FIELD(*event, ESF_DZ_RX_L3_CLASS);
	rx_l4_class = EFX_QWORD_FIELD(*event, ESF_FZ_RX_L4_CLASS);
	rx_cont = EFX_QWORD_FIELD(*event, ESF_DZ_RX_CONT);
	rx_encap_hdr =
		nic_data->datapath_caps &
			(1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN) ?
		EFX_QWORD_FIELD(*event, ESF_EZ_RX_ENCAP_HDR) :
		ESE_EZ_ENCAP_HDR_NONE;

	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_DROP_EVENT))
		netdev_WARN(efx->net_dev, "saw RX_DROP_EVENT: event="
			    EFX_QWORD_FMT "\n",
			    EFX_QWORD_VAL(*event));

	rx_queue = efx_channel_get_rx_queue(channel);

	if (unlikely(rx_queue_label != efx_rx_queue_index(rx_queue)))
		efx_ef10_handle_rx_wrong_queue(rx_queue, rx_queue_label);

	n_descs = ((next_ptr_lbits - rx_queue->removed_count) &
		   ((1 << ESF_DZ_RX_DSC_PTR_LBITS_WIDTH) - 1));

	if (n_descs != rx_queue->scatter_n + 1) {
		struct efx_ef10_nic_data *nic_data = efx->nic_data;

		/* detect rx abort */
		if (unlikely(n_descs == rx_queue->scatter_n)) {
			if (rx_queue->scatter_n == 0 || rx_bytes != 0)
				netdev_WARN(efx->net_dev,
					    "invalid RX abort: scatter_n=%u event="
					    EFX_QWORD_FMT "\n",
					    rx_queue->scatter_n,
					    EFX_QWORD_VAL(*event));
			efx_ef10_handle_rx_abort(rx_queue);
			return 0;
		}

		/* Check that RX completion merging is valid, i.e.
		 * the current firmware supports it and this is a
		 * non-scattered packet.
		 */
		if (!(nic_data->datapath_caps &
		      (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN)) ||
		    rx_queue->scatter_n != 0 || rx_cont) {
			efx_ef10_handle_rx_bad_lbits(
				rx_queue, next_ptr_lbits,
				(rx_queue->removed_count +
				 rx_queue->scatter_n + 1) &
				((1 << ESF_DZ_RX_DSC_PTR_LBITS_WIDTH) - 1));
			return 0;
		}

		/* Merged completion for multiple non-scattered packets */
		rx_queue->scatter_n = 1;
		rx_queue->scatter_len = 0;
		n_packets = n_descs;
		++channel->n_rx_merge_events;
		channel->n_rx_merge_packets += n_packets;
		flags |= EFX_RX_PKT_PREFIX_LEN;
	} else {
		++rx_queue->scatter_n;
		rx_queue->scatter_len += rx_bytes;
		if (rx_cont)
			return 0;
		n_packets = 1;
	}

	EFX_POPULATE_QWORD_5(errors, ESF_DZ_RX_ECRC_ERR, 1,
				     ESF_DZ_RX_IPCKSUM_ERR, 1,
				     ESF_DZ_RX_TCPUDP_CKSUM_ERR, 1,
				     ESF_EZ_RX_IP_INNER_CHKSUM_ERR, 1,
				     ESF_EZ_RX_TCP_UDP_INNER_CHKSUM_ERR, 1);
	EFX_AND_QWORD(errors, *event, errors);
	if (unlikely(!EFX_QWORD_IS_ZERO(errors))) {
		flags |= efx_ef10_handle_rx_event_errors(channel, n_packets,
							 rx_encap_hdr,
							 rx_l3_class, rx_l4_class,
							 event);
	} else {
		bool tcpudp = rx_l4_class == ESE_FZ_L4_CLASS_TCP ||
			      rx_l4_class == ESE_FZ_L4_CLASS_UDP;

		switch (rx_encap_hdr) {
		case ESE_EZ_ENCAP_HDR_VXLAN: /* VxLAN or GENEVE */
			flags |= EFX_RX_PKT_CSUMMED; /* outer UDP csum */
			if (tcpudp)
				flags |= EFX_RX_PKT_CSUM_LEVEL; /* inner L4 */
			break;
		case ESE_EZ_ENCAP_HDR_GRE:
		case ESE_EZ_ENCAP_HDR_NONE:
			if (tcpudp)
				flags |= EFX_RX_PKT_CSUMMED;
			break;
		default:
			netdev_WARN(efx->net_dev,
				    "unknown encapsulation type: event="
				    EFX_QWORD_FMT "\n",
				    EFX_QWORD_VAL(*event));
		}
	}

	if (rx_l4_class == ESE_FZ_L4_CLASS_TCP)
		flags |= EFX_RX_PKT_TCP;

	channel->irq_mod_score += 2 * n_packets;

	/* Handle received packet(s) */
	for (i = 0; i < n_packets; i++) {
		efx_rx_packet(rx_queue,
			      rx_queue->removed_count & rx_queue->ptr_mask,
			      rx_queue->scatter_n, rx_queue->scatter_len,
			      flags);
		rx_queue->removed_count += rx_queue->scatter_n;
	}

	rx_queue->scatter_n = 0;
	rx_queue->scatter_len = 0;

	return n_packets;
}

static u32 efx_ef10_extract_event_ts(efx_qword_t *event)
{
	u32 tstamp;

	tstamp = EFX_QWORD_FIELD(*event, TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI);
	tstamp <<= 16;
	tstamp |= EFX_QWORD_FIELD(*event, TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO);

	return tstamp;
}

static void
efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	struct efx_tx_queue *tx_queue;
	unsigned int tx_ev_desc_ptr;
	unsigned int tx_ev_q_label;
	unsigned int tx_ev_type;
	u64 ts_part;

	if (unlikely(READ_ONCE(efx->reset_pending)))
		return;

	if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT)))
		return;

	/* Get the transmit queue */
	tx_ev_q_label = EFX_QWORD_FIELD(*event, ESF_DZ_TX_QLABEL);
	tx_queue = channel->tx_queue + (tx_ev_q_label % EFX_MAX_TXQ_PER_CHANNEL);

	if (!tx_queue->timestamping) {
		/* Transmit completion */
		tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, ESF_DZ_TX_DESCR_INDX);
		efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask);
		return;
	}

	/* Transmit timestamps are only available for 8XXX series. They result
	 * in up to three events per packet. These occur in order, and are:
	 *  - the normal completion event (may be omitted)
	 *  - the low part of the timestamp
	 *  - the high part of the timestamp
	 *
	 * It's possible for multiple completion events to appear before the
	 * corresponding timestamps. So we can for example get:
	 *  COMP N
	 *  COMP N+1
	 *  TS_LO N
	 *  TS_HI N
	 *  TS_LO N+1
	 *  TS_HI N+1
	 *
	 * In addition it's also possible for the adjacent completions to be
	 * merged, so we may not see COMP N above. As such, the completion
	 * events are not very useful here.
	 *
	 * Each part of the timestamp is itself split across two 16 bit
	 * fields in the event.
	 */
	tx_ev_type = EFX_QWORD_FIELD(*event, ESF_EZ_TX_SOFT1);

	switch (tx_ev_type) {
	case TX_TIMESTAMP_EVENT_TX_EV_COMPLETION:
		/* Ignore this event - see above. */
		break;

	case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_LO:
		ts_part = efx_ef10_extract_event_ts(event);
		tx_queue->completed_timestamp_minor = ts_part;
		break;

	case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_HI:
		ts_part = efx_ef10_extract_event_ts(event);
		tx_queue->completed_timestamp_major = ts_part;

		efx_xmit_done_single(tx_queue);
		break;

	default:
		netif_err(efx, hw, efx->net_dev,
			  "channel %d unknown tx event type %d (data "
			  EFX_QWORD_FMT ")\n",
			  channel->channel, tx_ev_type,
			  EFX_QWORD_VAL(*event));
		break;
	}
}

static void
efx_ef10_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	int subcode;

	subcode = EFX_QWORD_FIELD(*event, ESF_DZ_DRV_SUB_CODE);

	switch (subcode) {
	case ESE_DZ_DRV_TIMER_EV:
	case ESE_DZ_DRV_WAKE_UP_EV:
		break;
	case ESE_DZ_DRV_START_UP_EV:
		/* event queue init complete. ok. */
		break;
	default:
		netif_err(efx, hw, efx->net_dev,
			  "channel %d unknown driver event type %d"
			  " (data " EFX_QWORD_FMT ")\n",
			  channel->channel, subcode,
			  EFX_QWORD_VAL(*event));

	}
}

static void efx_ef10_handle_driver_generated_event(struct efx_channel *channel,
						   efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	u32 subcode;

	subcode = EFX_QWORD_FIELD(*event, EFX_DWORD_0);

	switch (subcode) {
	case EFX_EF10_TEST:
		channel->event_test_cpu = raw_smp_processor_id();
		break;
	case EFX_EF10_REFILL:
		/* The queue must be empty, so we won't receive any rx
		 * events, so efx_process_channel() won't refill the
		 * queue. Refill it here
		 */
		efx_fast_push_rx_descriptors(&channel->rx_queue, true);
		break;
	default:
		netif_err(efx, hw, efx->net_dev,
			  "channel %d unknown driver event type %u"
			  " (data " EFX_QWORD_FMT ")\n",
			  channel->channel, (unsigned) subcode,
			  EFX_QWORD_VAL(*event));
	}
}

static int efx_ef10_ev_process(struct efx_channel *channel, int quota)
{
	struct efx_nic *efx = channel->efx;
	efx_qword_t event, *p_event;
	unsigned int read_ptr;
	int ev_code;
	int spent = 0;

	if (quota <= 0)
		return spent;

	read_ptr = channel->eventq_read_ptr;

	for (;;) {
		p_event = efx_event(channel, read_ptr);
		event = *p_event;

		if (!efx_event_present(&event))
			break;

		EFX_SET_QWORD(*p_event);

		++read_ptr;

		ev_code = EFX_QWORD_FIELD(event, ESF_DZ_EV_CODE);

		netif_vdbg(efx, drv, efx->net_dev,
			   "processing event on %d " EFX_QWORD_FMT "\n",
			   channel->channel, EFX_QWORD_VAL(event));

		switch (ev_code) {
		case ESE_DZ_EV_CODE_MCDI_EV:
			efx_mcdi_process_event(channel, &event);
			break;
		case ESE_DZ_EV_CODE_RX_EV:
			spent += efx_ef10_handle_rx_event(channel, &event);
			if (spent >= quota) {
				/* XXX can we split a merged event to
				 * avoid going over-quota?
				 */
				spent = quota;
				goto out;
			}
			break;
		case ESE_DZ_EV_CODE_TX_EV:
			efx_ef10_handle_tx_event(channel, &event);
			break;
		case ESE_DZ_EV_CODE_DRIVER_EV:
			efx_ef10_handle_driver_event(channel, &event);
			if (++spent == quota)
				goto out;
			break;
		case EFX_EF10_DRVGEN_EV:
			efx_ef10_handle_driver_generated_event(channel, &event);
			break;
		default:
			netif_err(efx, hw, efx->net_dev,
				  "channel %d unknown event type %d"
				  " (data " EFX_QWORD_FMT ")\n",
				  channel->channel, ev_code,
				  EFX_QWORD_VAL(event));
		}
	}

out:
	channel->eventq_read_ptr = read_ptr;
	return spent;
}

static void efx_ef10_ev_read_ack(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;
	efx_dword_t rptr;

	if (EFX_EF10_WORKAROUND_35388(efx)) {
		BUILD_BUG_ON(EFX_MIN_EVQ_SIZE <
			     (1 << ERF_DD_EVQ_IND_RPTR_WIDTH));
		BUILD_BUG_ON(EFX_MAX_EVQ_SIZE >
			     (1 << 2 * ERF_DD_EVQ_IND_RPTR_WIDTH));

		EFX_POPULATE_DWORD_2(rptr, ERF_DD_EVQ_IND_RPTR_FLAGS,
				     EFE_DD_EVQ_IND_RPTR_FLAGS_HIGH,
				     ERF_DD_EVQ_IND_RPTR,
				     (channel->eventq_read_ptr &
				      channel->eventq_mask) >>
				     ERF_DD_EVQ_IND_RPTR_WIDTH);
		efx_writed_page(efx, &rptr, ER_DD_EVQ_INDIRECT,
				channel->channel);
		EFX_POPULATE_DWORD_2(rptr, ERF_DD_EVQ_IND_RPTR_FLAGS,
				     EFE_DD_EVQ_IND_RPTR_FLAGS_LOW,
				     ERF_DD_EVQ_IND_RPTR,
				     channel->eventq_read_ptr &
				     ((1 << ERF_DD_EVQ_IND_RPTR_WIDTH) - 1));
		efx_writed_page(efx, &rptr, ER_DD_EVQ_INDIRECT,
				channel->channel);
	} else {
		EFX_POPULATE_DWORD_1(rptr, ERF_DZ_EVQ_RPTR,
				     channel->eventq_read_ptr &
				     channel->eventq_mask);
		efx_writed_page(efx, &rptr, ER_DZ_EVQ_RPTR, channel->channel);
	}
}

static void efx_ef10_ev_test_generate(struct efx_channel *channel)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_DRIVER_EVENT_IN_LEN);
	struct efx_nic *efx = channel->efx;
	efx_qword_t event;
	int rc;

	EFX_POPULATE_QWORD_2(event,
			     ESF_DZ_EV_CODE, EFX_EF10_DRVGEN_EV,
			     ESF_DZ_EV_DATA, EFX_EF10_TEST);

	MCDI_SET_DWORD(inbuf, DRIVER_EVENT_IN_EVQ, channel->channel);

	/* MCDI_SET_QWORD is not appropriate here since EFX_POPULATE_* has
	 * already swapped the data to little-endian order.
	 */
	memcpy(MCDI_PTR(inbuf, DRIVER_EVENT_IN_DATA), &event.u64[0],
	       sizeof(efx_qword_t));

	rc = efx_mcdi_rpc(efx, MC_CMD_DRIVER_EVENT, inbuf, sizeof(inbuf),
			  NULL, 0, NULL);
	if (rc != 0)
		goto fail;

	return;

fail:
	WARN_ON(true);
	netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
}

static void efx_ef10_prepare_flr(struct efx_nic *efx)
{
	atomic_set(&efx->active_queues, 0);
}

static int efx_ef10_vport_set_mac_address(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	u8 mac_old[ETH_ALEN];
	int rc, rc2;

	/* Only reconfigure a PF-created vport */
	if (is_zero_ether_addr(nic_data->vport_mac))
		return 0;

	efx_device_detach_sync(efx);
	efx_net_stop(efx->net_dev);
	efx_ef10_filter_table_remove(efx);

	rc = efx_ef10_vadaptor_free(efx, efx->vport_id);
	if (rc)
		goto restore_filters;

	ether_addr_copy(mac_old, nic_data->vport_mac);
	rc = efx_ef10_vport_del_mac(efx, efx->vport_id,
				    nic_data->vport_mac);
	if (rc)
		goto restore_vadaptor;

	rc = efx_ef10_vport_add_mac(efx, efx->vport_id,
				    efx->net_dev->dev_addr);
	if (!rc) {
		ether_addr_copy(nic_data->vport_mac, efx->net_dev->dev_addr);
	} else {
		rc2 = efx_ef10_vport_add_mac(efx, efx->vport_id, mac_old);
		if (rc2) {
			/* Failed to add original MAC, so clear vport_mac */
			eth_zero_addr(nic_data->vport_mac);
			goto reset_nic;
		}
	}

restore_vadaptor:
	rc2 = efx_ef10_vadaptor_alloc(efx, efx->vport_id);
	if (rc2)
		goto reset_nic;
restore_filters:
	rc2 = efx_ef10_filter_table_probe(efx);
	if (rc2)
		goto reset_nic;

	rc2 = efx_net_open(efx->net_dev);
	if (rc2)
		goto reset_nic;

	efx_device_attach_if_not_resetting(efx);

	return rc;

reset_nic:
	netif_err(efx, drv, efx->net_dev,
		  "Failed to restore when changing MAC address - scheduling reset\n");
	efx_schedule_reset(efx, RESET_TYPE_DATAPATH);

	return rc ? rc : rc2;
}

static int efx_ef10_set_mac_address(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_SET_MAC_IN_LEN);
	bool was_enabled = efx->port_enabled;
	int rc;

#ifdef CONFIG_SFC_SRIOV
	/* If this function is a VF and we have access to the parent PF,
	 * then use the PF control path to attempt to change the VF MAC address.
	 */
	if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) {
		struct efx_nic *efx_pf = pci_get_drvdata(efx->pci_dev->physfn);
		struct efx_ef10_nic_data *nic_data = efx->nic_data;
		u8 mac[ETH_ALEN];

		/* net_dev->dev_addr can be zeroed by efx_net_stop in
		 * efx_ef10_sriov_set_vf_mac, so pass in a copy.
		 */
		ether_addr_copy(mac, efx->net_dev->dev_addr);

		rc = efx_ef10_sriov_set_vf_mac(efx_pf, nic_data->vf_index, mac);
		if (!rc)
			return 0;

		netif_dbg(efx, drv, efx->net_dev,
			  "Updating VF mac via PF failed (%d), setting directly\n",
			  rc);
	}
#endif

	efx_device_detach_sync(efx);
	efx_net_stop(efx->net_dev);

	mutex_lock(&efx->mac_lock);
	efx_ef10_filter_table_remove(efx);

	ether_addr_copy(MCDI_PTR(inbuf, VADAPTOR_SET_MAC_IN_MACADDR),
			efx->net_dev->dev_addr);
	MCDI_SET_DWORD(inbuf, VADAPTOR_SET_MAC_IN_UPSTREAM_PORT_ID,
		       efx->vport_id);
	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
				sizeof(inbuf), NULL, 0, NULL);

	efx_ef10_filter_table_probe(efx);
	mutex_unlock(&efx->mac_lock);

	if (was_enabled)
		efx_net_open(efx->net_dev);
	efx_device_attach_if_not_resetting(efx);

	if (rc == -EPERM) {
		netif_err(efx, drv, efx->net_dev,
			  "Cannot change MAC address; use sfboot to enable"
			  " mac-spoofing on this interface\n");
	} else if (rc == -ENOSYS && !efx_ef10_is_vf(efx)) {
		/* If the active MCFW does not support MC_CMD_VADAPTOR_SET_MAC
		 * fall-back to the method of changing the MAC address on the
		 * vport.  This only applies to PFs because such versions of
		 * MCFW do not support VFs.
		 */
		rc = efx_ef10_vport_set_mac_address(efx);
	} else if (rc) {
		efx_mcdi_display_error(efx, MC_CMD_VADAPTOR_SET_MAC,
				       sizeof(inbuf), NULL, 0, rc);
	}

	return rc;
}

static int efx_ef10_mac_reconfigure(struct efx_nic *efx, bool mtu_only)
{
	WARN_ON(!mutex_is_locked(&efx->mac_lock));

	efx_mcdi_filter_sync_rx_mode(efx);

	if (mtu_only && efx_has_cap(efx, SET_MAC_ENHANCED))
		return efx_mcdi_set_mtu(efx);
	return efx_mcdi_set_mac(efx);
}

static int efx_ef10_start_bist(struct efx_nic *efx, u32 bist_type)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN);

	MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_type);
	return efx_mcdi_rpc(efx, MC_CMD_START_BIST, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

/* MC BISTs follow a different poll mechanism to phy BISTs.
 * The BIST is done in the poll handler on the MC, and the MCDI command
 * will block until the BIST is done.
 */
static int efx_ef10_poll_bist(struct efx_nic *efx)
{
	int rc;
	MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_LEN);
	size_t outlen;
	u32 result;

	rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0,
			   outbuf, sizeof(outbuf), &outlen);
	if (rc != 0)
		return rc;

	if (outlen < MC_CMD_POLL_BIST_OUT_LEN)
		return -EIO;

	result = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT);
	switch (result) {
	case MC_CMD_POLL_BIST_PASSED:
		netif_dbg(efx, hw, efx->net_dev, "BIST passed.\n");
		return 0;
	case MC_CMD_POLL_BIST_TIMEOUT:
		netif_err(efx, hw, efx->net_dev, "BIST timed out\n");
		return -EIO;
	case MC_CMD_POLL_BIST_FAILED:
		netif_err(efx, hw, efx->net_dev, "BIST failed.\n");
		return -EIO;
	default:
		netif_err(efx, hw, efx->net_dev,
			  "BIST returned unknown result %u", result);
		return -EIO;
	}
}

static int efx_ef10_run_bist(struct efx_nic *efx, u32 bist_type)
{
	int rc;

	netif_dbg(efx, drv, efx->net_dev, "starting BIST type %u\n", bist_type);

	rc = efx_ef10_start_bist(efx, bist_type);
	if (rc != 0)
		return rc;

	return efx_ef10_poll_bist(efx);
}

static int
efx_ef10_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
{
	int rc, rc2;

	efx_reset_down(efx, RESET_TYPE_WORLD);

	rc = efx_mcdi_rpc(efx, MC_CMD_ENABLE_OFFLINE_BIST,
			  NULL, 0, NULL, 0, NULL);
	if (rc != 0)
		goto out;

	tests->memory = efx_ef10_run_bist(efx, MC_CMD_MC_MEM_BIST) ? -1 : 1;
	tests->registers = efx_ef10_run_bist(efx, MC_CMD_REG_BIST) ? -1 : 1;

	rc = efx_mcdi_reset(efx, RESET_TYPE_WORLD);

out:
	if (rc == -EPERM)
		rc = 0;
	rc2 = efx_reset_up(efx, RESET_TYPE_WORLD, rc == 0);
	return rc ? rc : rc2;
}

#ifdef CONFIG_SFC_MTD

struct efx_ef10_nvram_type_info {
	u16 type, type_mask;
	u8 port;
	const char *name;
};

static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
	{ NVRAM_PARTITION_TYPE_MC_FIRMWARE,	   0,    0, "sfc_mcfw" },
	{ NVRAM_PARTITION_TYPE_MC_FIRMWARE_BACKUP, 0,    0, "sfc_mcfw_backup" },
	{ NVRAM_PARTITION_TYPE_EXPANSION_ROM,	   0,    0, "sfc_exp_rom" },
	{ NVRAM_PARTITION_TYPE_STATIC_CONFIG,	   0,    0, "sfc_static_cfg" },
	{ NVRAM_PARTITION_TYPE_DYNAMIC_CONFIG,	   0,    0, "sfc_dynamic_cfg" },
	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT0, 0,   0, "sfc_exp_rom_cfg" },
	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1, 0,   1, "sfc_exp_rom_cfg" },
	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT2, 0,   2, "sfc_exp_rom_cfg" },
	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0,   3, "sfc_exp_rom_cfg" },
	{ NVRAM_PARTITION_TYPE_LICENSE,		   0,    0, "sfc_license" },
	{ NVRAM_PARTITION_TYPE_PHY_MIN,		   0xff, 0, "sfc_phy_fw" },
	{ NVRAM_PARTITION_TYPE_MUM_FIRMWARE,	   0,    0, "sfc_mumfw" },
	{ NVRAM_PARTITION_TYPE_EXPANSION_UEFI,	   0,    0, "sfc_uefi" },
	{ NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS, 0,    0, "sfc_dynamic_cfg_dflt" },
	{ NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS, 0,    0, "sfc_exp_rom_cfg_dflt" },
	{ NVRAM_PARTITION_TYPE_STATUS,		   0,    0, "sfc_status" },
	{ NVRAM_PARTITION_TYPE_BUNDLE,		   0,    0, "sfc_bundle" },
	{ NVRAM_PARTITION_TYPE_BUNDLE_METADATA,	   0,    0, "sfc_bundle_metadata" },
};
#define EF10_NVRAM_PARTITION_COUNT	ARRAY_SIZE(efx_ef10_nvram_types)

static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
					struct efx_mcdi_mtd_partition *part,
					unsigned int type,
					unsigned long *found)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
	const struct efx_ef10_nvram_type_info *info;
	size_t size, erase_size, outlen;
	int type_idx = 0;
	bool protected;
	int rc;

	for (type_idx = 0; ; type_idx++) {
		if (type_idx == EF10_NVRAM_PARTITION_COUNT)
			return -ENODEV;
		info = efx_ef10_nvram_types + type_idx;
		if ((type & ~info->type_mask) == info->type)
			break;
	}
	if (info->port != efx_port_num(efx))
		return -ENODEV;

	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
	if (rc)
		return rc;
	if (protected &&
	    (type != NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS &&
	     type != NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS))
		/* Hide protected partitions that don't provide defaults. */
		return -ENODEV;

	if (protected)
		/* Protected partitions are read only. */
		erase_size = 0;

	/* If we've already exposed a partition of this type, hide this
	 * duplicate.  All operations on MTDs are keyed by the type anyway,
	 * so we can't act on the duplicate.
	 */
	if (__test_and_set_bit(type_idx, found))
		return -EEXIST;

	part->nvram_type = type;

	MCDI_SET_DWORD(inbuf, NVRAM_METADATA_IN_TYPE, type);
	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_METADATA, inbuf, sizeof(inbuf),
			  outbuf, sizeof(outbuf), &outlen);
	if (rc)
		return rc;
	if (outlen < MC_CMD_NVRAM_METADATA_OUT_LENMIN)
		return -EIO;
	if (MCDI_DWORD(outbuf, NVRAM_METADATA_OUT_FLAGS) &
	    (1 << MC_CMD_NVRAM_METADATA_OUT_SUBTYPE_VALID_LBN))
		part->fw_subtype = MCDI_DWORD(outbuf,
					      NVRAM_METADATA_OUT_SUBTYPE);

	part->common.dev_type_name = "EF10 NVRAM manager";
	part->common.type_name = info->name;

	part->common.mtd.type = MTD_NORFLASH;
	part->common.mtd.flags = MTD_CAP_NORFLASH;
	part->common.mtd.size = size;
	part->common.mtd.erasesize = erase_size;
	/* sfc_status is read-only */
	if (!erase_size)
		part->common.mtd.flags |= MTD_NO_ERASE;

	return 0;
}

static int efx_ef10_mtd_probe(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };
	struct efx_mcdi_mtd_partition *parts;
	size_t outlen, n_parts_total, i, n_parts;
	unsigned int type;
	int rc;

	ASSERT_RTNL();

	BUILD_BUG_ON(MC_CMD_NVRAM_PARTITIONS_IN_LEN != 0);
	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_PARTITIONS, NULL, 0,
			  outbuf, sizeof(outbuf), &outlen);
	if (rc)
		return rc;
	if (outlen < MC_CMD_NVRAM_PARTITIONS_OUT_LENMIN)
		return -EIO;

	n_parts_total = MCDI_DWORD(outbuf, NVRAM_PARTITIONS_OUT_NUM_PARTITIONS);
	if (n_parts_total >
	    MCDI_VAR_ARRAY_LEN(outlen, NVRAM_PARTITIONS_OUT_TYPE_ID))
		return -EIO;

	parts = kcalloc(n_parts_total, sizeof(*parts), GFP_KERNEL);
	if (!parts)
		return -ENOMEM;

	n_parts = 0;
	for (i = 0; i < n_parts_total; i++) {
		type = MCDI_ARRAY_DWORD(outbuf, NVRAM_PARTITIONS_OUT_TYPE_ID,
					i);
		rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type,
						  found);
		if (rc == -EEXIST || rc == -ENODEV)
			continue;
		if (rc)
			goto fail;
		n_parts++;
	}

	if (!n_parts) {
		kfree(parts);
		return 0;
	}

	rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
fail:
	if (rc)
		kfree(parts);
	return rc;
}

#endif /* CONFIG_SFC_MTD */

static void efx_ef10_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
{
	_efx_writed(efx, cpu_to_le32(host_time), ER_DZ_MC_DB_LWRD);
}

static void efx_ef10_ptp_write_host_time_vf(struct efx_nic *efx,
					    u32 host_time) {}

static int efx_ef10_rx_enable_timestamping(struct efx_channel *channel,
					   bool temp)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN);
	int rc;

	if (channel->sync_events_state == SYNC_EVENTS_REQUESTED ||
	    channel->sync_events_state == SYNC_EVENTS_VALID ||
	    (temp && channel->sync_events_state == SYNC_EVENTS_DISABLED))
		return 0;
	channel->sync_events_state = SYNC_EVENTS_REQUESTED;

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE,
		       channel->channel);

	rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
			  inbuf, sizeof(inbuf), NULL, 0, NULL);

	if (rc != 0)
		channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
						    SYNC_EVENTS_DISABLED;

	return rc;
}

static int efx_ef10_rx_disable_timestamping(struct efx_channel *channel,
					    bool temp)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN);
	int rc;

	if (channel->sync_events_state == SYNC_EVENTS_DISABLED ||
	    (temp && channel->sync_events_state == SYNC_EVENTS_QUIESCENT))
		return 0;
	if (channel->sync_events_state == SYNC_EVENTS_QUIESCENT) {
		channel->sync_events_state = SYNC_EVENTS_DISABLED;
		return 0;
	}
	channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
					    SYNC_EVENTS_DISABLED;

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL,
		       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE);
	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE,
		       channel->channel);

	rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
			  inbuf, sizeof(inbuf), NULL, 0, NULL);

	return rc;
}

static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en,
					   bool temp)
{
	int (*set)(struct efx_channel *channel, bool temp);
	struct efx_channel *channel;

	set = en ?
	      efx_ef10_rx_enable_timestamping :
	      efx_ef10_rx_disable_timestamping;

	channel = efx_ptp_channel(efx);
	if (channel) {
		int rc = set(channel, temp);
		if (en && rc != 0) {
			efx_ef10_ptp_set_ts_sync_events(efx, false, temp);
			return rc;
		}
	}

	return 0;
}

static int efx_ef10_ptp_set_ts_config_vf(struct efx_nic *efx,
					 struct hwtstamp_config *init)
{
	return -EOPNOTSUPP;
}

static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
				      struct hwtstamp_config *init)
{
	int rc;

	switch (init->rx_filter) {
	case HWTSTAMP_FILTER_NONE:
		efx_ef10_ptp_set_ts_sync_events(efx, false, false);
		/* if TX timestamping is still requested then leave PTP on */
		return efx_ptp_change_mode(efx,
					   init->tx_type != HWTSTAMP_TX_OFF, 0);
	case HWTSTAMP_FILTER_ALL:
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
	case HWTSTAMP_FILTER_NTP_ALL:
		init->rx_filter = HWTSTAMP_FILTER_ALL;
		rc = efx_ptp_change_mode(efx, true, 0);
		if (!rc)
			rc = efx_ef10_ptp_set_ts_sync_events(efx, true, false);
		if (rc)
			efx_ptp_change_mode(efx, false, 0);
		return rc;
	default:
		return -ERANGE;
	}
}

static int efx_ef10_get_phys_port_id(struct efx_nic *efx,
				     struct netdev_phys_item_id *ppid)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	if (!is_valid_ether_addr(nic_data->port_id))
		return -EOPNOTSUPP;

	ppid->id_len = ETH_ALEN;
	memcpy(ppid->id, nic_data->port_id, ppid->id_len);

	return 0;
}

static int efx_ef10_vlan_rx_add_vid(struct efx_nic *efx, __be16 proto, u16 vid)
{
	if (proto != htons(ETH_P_8021Q))
		return -EINVAL;

	return efx_ef10_add_vlan(efx, vid);
}

static int efx_ef10_vlan_rx_kill_vid(struct efx_nic *efx, __be16 proto, u16 vid)
{
	if (proto != htons(ETH_P_8021Q))
		return -EINVAL;

	return efx_ef10_del_vlan(efx, vid);
}

/* We rely on the MCDI wiping out our TX rings if it made any changes to the
 * ports table, ensuring that any TSO descriptors that were made on a now-
 * removed tunnel port will be blown away and won't break things when we try
 * to transmit them using the new ports table.
 */
static int efx_ef10_set_udp_tnl_ports(struct efx_nic *efx, bool unloading)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LENMAX);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_LEN);
	bool will_reset = false;
	size_t num_entries = 0;
	size_t inlen, outlen;
	size_t i;
	int rc;
	efx_dword_t flags_and_num_entries;

	WARN_ON(!mutex_is_locked(&nic_data->udp_tunnels_lock));

	nic_data->udp_tunnels_dirty = false;

	if (!(nic_data->datapath_caps &
	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN))) {
		efx_device_attach_if_not_resetting(efx);
		return 0;
	}

	BUILD_BUG_ON(ARRAY_SIZE(nic_data->udp_tunnels) >
		     MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_MAXNUM);

	for (i = 0; i < ARRAY_SIZE(nic_data->udp_tunnels); ++i) {
		if (nic_data->udp_tunnels[i].type !=
		    TUNNEL_ENCAP_UDP_PORT_ENTRY_INVALID) {
			efx_dword_t entry;

			EFX_POPULATE_DWORD_2(entry,
				TUNNEL_ENCAP_UDP_PORT_ENTRY_UDP_PORT,
					ntohs(nic_data->udp_tunnels[i].port),
				TUNNEL_ENCAP_UDP_PORT_ENTRY_PROTOCOL,
					nic_data->udp_tunnels[i].type);
			*_MCDI_ARRAY_DWORD(inbuf,
				SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES,
				num_entries++) = entry;
		}
	}

	BUILD_BUG_ON((MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_OFST -
		      MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS_OFST) * 8 !=
		     EFX_WORD_1_LBN);
	BUILD_BUG_ON(MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_LEN * 8 !=
		     EFX_WORD_1_WIDTH);
	EFX_POPULATE_DWORD_2(flags_and_num_entries,
			     MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_UNLOADING,
				!!unloading,
			     EFX_WORD_1, num_entries);
	*_MCDI_DWORD(inbuf, SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS) =
		flags_and_num_entries;

	inlen = MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LEN(num_entries);

	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS,
				inbuf, inlen, outbuf, sizeof(outbuf), &outlen);
	if (rc == -EIO) {
		/* Most likely the MC rebooted due to another function also
		 * setting its tunnel port list. Mark the tunnel port list as
		 * dirty, so it will be pushed upon coming up from the reboot.
		 */
		nic_data->udp_tunnels_dirty = true;
		return 0;
	}

	if (rc) {
		/* expected not available on unprivileged functions */
		if (rc != -EPERM)
			netif_warn(efx, drv, efx->net_dev,
				   "Unable to set UDP tunnel ports; rc=%d.\n", rc);
	} else if (MCDI_DWORD(outbuf, SET_TUNNEL_ENCAP_UDP_PORTS_OUT_FLAGS) &
		   (1 << MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_LBN)) {
		netif_info(efx, drv, efx->net_dev,
			   "Rebooting MC due to UDP tunnel port list change\n");
		will_reset = true;
		if (unloading)
			/* Delay for the MC reset to complete. This will make
			 * unloading other functions a bit smoother. This is a
			 * race, but the other unload will work whichever way
			 * it goes, this just avoids an unnecessary error
			 * message.
			 */
			msleep(100);
	}
	if (!will_reset && !unloading) {
		/* The caller will have detached, relying on the MC reset to
		 * trigger a re-attach.  Since there won't be an MC reset, we
		 * have to do the attach ourselves.
		 */
		efx_device_attach_if_not_resetting(efx);
	}

	return rc;
}

static int efx_ef10_udp_tnl_push_ports(struct efx_nic *efx)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	int rc = 0;

	mutex_lock(&nic_data->udp_tunnels_lock);
	if (nic_data->udp_tunnels_dirty) {
		/* Make sure all TX are stopped while we modify the table, else
		 * we might race against an efx_features_check().
		 */
		efx_device_detach_sync(efx);
		rc = efx_ef10_set_udp_tnl_ports(efx, false);
	}
	mutex_unlock(&nic_data->udp_tunnels_lock);
	return rc;
}

static int efx_ef10_udp_tnl_set_port(struct net_device *dev,
				     unsigned int table, unsigned int entry,
				     struct udp_tunnel_info *ti)
{
	struct efx_nic *efx = efx_netdev_priv(dev);
	struct efx_ef10_nic_data *nic_data;
	int efx_tunnel_type, rc;

	if (ti->type == UDP_TUNNEL_TYPE_VXLAN)
		efx_tunnel_type = TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN;
	else
		efx_tunnel_type = TUNNEL_ENCAP_UDP_PORT_ENTRY_GENEVE;

	nic_data = efx->nic_data;
	if (!(nic_data->datapath_caps &
	      (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN)))
		return -EOPNOTSUPP;

	mutex_lock(&nic_data->udp_tunnels_lock);
	/* Make sure all TX are stopped while we add to the table, else we
	 * might race against an efx_features_check().
	 */
	efx_device_detach_sync(efx);
	nic_data->udp_tunnels[entry].type = efx_tunnel_type;
	nic_data->udp_tunnels[entry].port = ti->port;
	rc = efx_ef10_set_udp_tnl_ports(efx, false);
	mutex_unlock(&nic_data->udp_tunnels_lock);

	return rc;
}

/* Called under the TX lock with the TX queue running, hence no-one can be
 * in the middle of updating the UDP tunnels table.  However, they could
 * have tried and failed the MCDI, in which case they'll have set the dirty
 * flag before dropping their locks.
 */
static bool efx_ef10_udp_tnl_has_port(struct efx_nic *efx, __be16 port)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;
	size_t i;

	if (!(nic_data->datapath_caps &
	      (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN)))
		return false;

	if (nic_data->udp_tunnels_dirty)
		/* SW table may not match HW state, so just assume we can't
		 * use any UDP tunnel offloads.
		 */
		return false;

	for (i = 0; i < ARRAY_SIZE(nic_data->udp_tunnels); ++i)
		if (nic_data->udp_tunnels[i].type !=
		    TUNNEL_ENCAP_UDP_PORT_ENTRY_INVALID &&
		    nic_data->udp_tunnels[i].port == port)
			return true;

	return false;
}

static int efx_ef10_udp_tnl_unset_port(struct net_device *dev,
				       unsigned int table, unsigned int entry,
				       struct udp_tunnel_info *ti)
{
	struct efx_nic *efx = efx_netdev_priv(dev);
	struct efx_ef10_nic_data *nic_data;
	int rc;

	nic_data = efx->nic_data;

	mutex_lock(&nic_data->udp_tunnels_lock);
	/* Make sure all TX are stopped while we remove from the table, else we
	 * might race against an efx_features_check().
	 */
	efx_device_detach_sync(efx);
	nic_data->udp_tunnels[entry].type = TUNNEL_ENCAP_UDP_PORT_ENTRY_INVALID;
	nic_data->udp_tunnels[entry].port = 0;
	rc = efx_ef10_set_udp_tnl_ports(efx, false);
	mutex_unlock(&nic_data->udp_tunnels_lock);

	return rc;
}

static const struct udp_tunnel_nic_info efx_ef10_udp_tunnels = {
	.set_port	= efx_ef10_udp_tnl_set_port,
	.unset_port	= efx_ef10_udp_tnl_unset_port,
	.flags          = UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
	.tables         = {
		{
			.n_entries = 16,
			.tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
					UDP_TUNNEL_TYPE_GENEVE,
		},
	},
};

/* EF10 may have multiple datapath firmware variants within a
 * single version.  Report which variants are running.
 */
static size_t efx_ef10_print_additional_fwver(struct efx_nic *efx, char *buf,
					      size_t len)
{
	struct efx_ef10_nic_data *nic_data = efx->nic_data;

	return scnprintf(buf, len, " rx%x tx%x",
			 nic_data->rx_dpcpu_fw_id,
			 nic_data->tx_dpcpu_fw_id);
}

static unsigned int ef10_check_caps(const struct efx_nic *efx,
				    u8 flag,
				    u32 offset)
{
	const struct efx_ef10_nic_data *nic_data = efx->nic_data;

	switch (offset) {
	case(MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_OFST):
		return nic_data->datapath_caps & BIT_ULL(flag);
	case(MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_OFST):
		return nic_data->datapath_caps2 & BIT_ULL(flag);
	default:
		return 0;
	}
}

static unsigned int efx_ef10_recycle_ring_size(const struct efx_nic *efx)
{
	unsigned int ret = EFX_RECYCLE_RING_SIZE_10G;

	/* There is no difference between PFs and VFs. The side is based on
	 * the maximum link speed of a given NIC.
	 */
	switch (efx->pci_dev->device & 0xfff) {
	case 0x0903:	/* Farmingdale can do up to 10G */
		break;
	case 0x0923:	/* Greenport can do up to 40G */
	case 0x0a03:	/* Medford can do up to 40G */
		ret *= 4;
		break;
	default:	/* Medford2 can do up to 100G */
		ret *= 10;
	}

	if (IS_ENABLED(CONFIG_PPC64))
		ret *= 4;

	return ret;
}

#define EF10_OFFLOAD_FEATURES		\
	(NETIF_F_IP_CSUM |		\
	 NETIF_F_HW_VLAN_CTAG_FILTER |	\
	 NETIF_F_IPV6_CSUM |		\
	 NETIF_F_RXHASH |		\
	 NETIF_F_NTUPLE)

const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
	.is_vf = true,
	.mem_bar = efx_ef10_vf_mem_bar,
	.mem_map_size = efx_ef10_mem_map_size,
	.probe = efx_ef10_probe_vf,
	.remove = efx_ef10_remove,
	.dimension_resources = efx_ef10_dimension_resources,
	.init = efx_ef10_init_nic,
	.fini = efx_ef10_fini_nic,
	.map_reset_reason = efx_ef10_map_reset_reason,
	.map_reset_flags = efx_ef10_map_reset_flags,
	.reset = efx_ef10_reset,
	.probe_port = efx_mcdi_port_probe,
	.remove_port = efx_mcdi_port_remove,
	.fini_dmaq = efx_fini_dmaq,
	.prepare_flr = efx_ef10_prepare_flr,
	.finish_flr = efx_port_dummy_op_void,
	.describe_stats = efx_ef10_describe_stats,
	.update_stats = efx_ef10_update_stats_vf,
	.update_stats_atomic = efx_ef10_update_stats_atomic_vf,
	.start_stats = efx_port_dummy_op_void,
	.pull_stats = efx_port_dummy_op_void,
	.stop_stats = efx_port_dummy_op_void,
	.push_irq_moderation = efx_ef10_push_irq_moderation,
	.reconfigure_mac = efx_ef10_mac_reconfigure,
	.check_mac_fault = efx_mcdi_mac_check_fault,
	.reconfigure_port = efx_mcdi_port_reconfigure,
	.get_wol = efx_ef10_get_wol_vf,
	.set_wol = efx_ef10_set_wol_vf,
	.resume_wol = efx_port_dummy_op_void,
	.mcdi_request = efx_ef10_mcdi_request,
	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
	.mcdi_read_response = efx_ef10_mcdi_read_response,
	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
	.mcdi_reboot_detected = efx_ef10_mcdi_reboot_detected,
	.irq_enable_master = efx_port_dummy_op_void,
	.irq_test_generate = efx_ef10_irq_test_generate,
	.irq_disable_non_ev = efx_port_dummy_op_void,
	.irq_handle_msi = efx_ef10_msi_interrupt,
	.irq_handle_legacy = efx_ef10_legacy_interrupt,
	.tx_probe = efx_ef10_tx_probe,
	.tx_init = efx_ef10_tx_init,
	.tx_remove = efx_mcdi_tx_remove,
	.tx_write = efx_ef10_tx_write,
	.tx_limit_len = efx_ef10_tx_limit_len,
	.tx_enqueue = __efx_enqueue_skb,
	.rx_push_rss_config = efx_mcdi_vf_rx_push_rss_config,
	.rx_pull_rss_config = efx_mcdi_rx_pull_rss_config,
	.rx_probe = efx_mcdi_rx_probe,
	.rx_init = efx_mcdi_rx_init,
	.rx_remove = efx_mcdi_rx_remove,
	.rx_write = efx_ef10_rx_write,
	.rx_defer_refill = efx_ef10_rx_defer_refill,
	.rx_packet = __efx_rx_packet,
	.ev_probe = efx_mcdi_ev_probe,
	.ev_init = efx_ef10_ev_init,
	.ev_fini = efx_mcdi_ev_fini,
	.ev_remove = efx_mcdi_ev_remove,
	.ev_process = efx_ef10_ev_process,
	.ev_read_ack = efx_ef10_ev_read_ack,
	.ev_test_generate = efx_ef10_ev_test_generate,
	.filter_table_probe = efx_ef10_filter_table_probe,
	.filter_table_restore = efx_mcdi_filter_table_restore,
	.filter_table_remove = efx_ef10_filter_table_remove,
	.filter_update_rx_scatter = efx_mcdi_update_rx_scatter,
	.filter_insert = efx_mcdi_filter_insert,
	.filter_remove_safe = efx_mcdi_filter_remove_safe,
	.filter_get_safe = efx_mcdi_filter_get_safe,
	.filter_clear_rx = efx_mcdi_filter_clear_rx,
	.filter_count_rx_used = efx_mcdi_filter_count_rx_used,
	.filter_get_rx_id_limit = efx_mcdi_filter_get_rx_id_limit,
	.filter_get_rx_ids = efx_mcdi_filter_get_rx_ids,
#ifdef CONFIG_RFS_ACCEL
	.filter_rfs_expire_one = efx_mcdi_filter_rfs_expire_one,
#endif
#ifdef CONFIG_SFC_MTD
	.mtd_probe = efx_port_dummy_op_int,
#endif
	.ptp_write_host_time = efx_ef10_ptp_write_host_time_vf,
	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config_vf,
	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
#ifdef CONFIG_SFC_SRIOV
	.vswitching_probe = efx_ef10_vswitching_probe_vf,
	.vswitching_restore = efx_ef10_vswitching_restore_vf,
	.vswitching_remove = efx_ef10_vswitching_remove_vf,
#endif
	.get_mac_address = efx_ef10_get_mac_address_vf,
	.set_mac_address = efx_ef10_set_mac_address,

	.get_phys_port_id = efx_ef10_get_phys_port_id,
	.revision = EFX_REV_HUNT_A0,
	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
	.rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
	.rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
	.rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
	.can_rx_scatter = true,
	.always_rx_scatter = true,
	.min_interrupt_mode = EFX_INT_MODE_MSIX,
	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
	.offload_features = EF10_OFFLOAD_FEATURES,
	.mcdi_max_ver = 2,
	.max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS,
	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
			    1 << HWTSTAMP_FILTER_ALL,
	.rx_hash_key_size = 40,
	.check_caps = ef10_check_caps,
	.print_additional_fwver = efx_ef10_print_additional_fwver,
	.sensor_event = efx_mcdi_sensor_event,
	.rx_recycle_ring_size = efx_ef10_recycle_ring_size,
};

const struct efx_nic_type efx_hunt_a0_nic_type = {
	.is_vf = false,
	.mem_bar = efx_ef10_pf_mem_bar,
	.mem_map_size = efx_ef10_mem_map_size,
	.probe = efx_ef10_probe_pf,
	.remove = efx_ef10_remove,
	.dimension_resources = efx_ef10_dimension_resources,
	.init = efx_ef10_init_nic,
	.fini = efx_ef10_fini_nic,
	.map_reset_reason = efx_ef10_map_reset_reason,
	.map_reset_flags = efx_ef10_map_reset_flags,
	.reset = efx_ef10_reset,
	.probe_port = efx_mcdi_port_probe,
	.remove_port = efx_mcdi_port_remove,
	.fini_dmaq = efx_fini_dmaq,
	.prepare_flr = efx_ef10_prepare_flr,
	.finish_flr = efx_port_dummy_op_void,
	.describe_stats = efx_ef10_describe_stats,
	.update_stats = efx_ef10_update_stats_pf,
	.start_stats = efx_mcdi_mac_start_stats,
	.pull_stats = efx_mcdi_mac_pull_stats,
	.stop_stats = efx_mcdi_mac_stop_stats,
	.push_irq_moderation = efx_ef10_push_irq_moderation,
	.reconfigure_mac = efx_ef10_mac_reconfigure,
	.check_mac_fault = efx_mcdi_mac_check_fault,
	.reconfigure_port = efx_mcdi_port_reconfigure,
	.get_wol = efx_ef10_get_wol,
	.set_wol = efx_ef10_set_wol,
	.resume_wol = efx_port_dummy_op_void,
	.get_fec_stats = efx_ef10_get_fec_stats,
	.test_chip = efx_ef10_test_chip,
	.test_nvram = efx_mcdi_nvram_test_all,
	.mcdi_request = efx_ef10_mcdi_request,
	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
	.mcdi_read_response = efx_ef10_mcdi_read_response,
	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
	.mcdi_reboot_detected = efx_ef10_mcdi_reboot_detected,
	.irq_enable_master = efx_port_dummy_op_void,
	.irq_test_generate = efx_ef10_irq_test_generate,
	.irq_disable_non_ev = efx_port_dummy_op_void,
	.irq_handle_msi = efx_ef10_msi_interrupt,
	.irq_handle_legacy = efx_ef10_legacy_interrupt,
	.tx_probe = efx_ef10_tx_probe,
	.tx_init = efx_ef10_tx_init,
	.tx_remove = efx_mcdi_tx_remove,
	.tx_write = efx_ef10_tx_write,
	.tx_limit_len = efx_ef10_tx_limit_len,
	.tx_enqueue = __efx_enqueue_skb,
	.rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config,
	.rx_pull_rss_config = efx_mcdi_rx_pull_rss_config,
	.rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config,
	.rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config,
	.rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts,
	.rx_probe = efx_mcdi_rx_probe,
	.rx_init = efx_mcdi_rx_init,
	.rx_remove = efx_mcdi_rx_remove,
	.rx_write = efx_ef10_rx_write,
	.rx_defer_refill = efx_ef10_rx_defer_refill,
	.rx_packet = __efx_rx_packet,
	.ev_probe = efx_mcdi_ev_probe,
	.ev_init = efx_ef10_ev_init,
	.ev_fini = efx_mcdi_ev_fini,
	.ev_remove = efx_mcdi_ev_remove,
	.ev_process = efx_ef10_ev_process,
	.ev_read_ack = efx_ef10_ev_read_ack,
	.ev_test_generate = efx_ef10_ev_test_generate,
	.filter_table_probe = efx_ef10_filter_table_probe,
	.filter_table_restore = efx_mcdi_filter_table_restore,
	.filter_table_remove = efx_ef10_filter_table_remove,
	.filter_update_rx_scatter = efx_mcdi_update_rx_scatter,
	.filter_insert = efx_mcdi_filter_insert,
	.filter_remove_safe = efx_mcdi_filter_remove_safe,
	.filter_get_safe = efx_mcdi_filter_get_safe,
	.filter_clear_rx = efx_mcdi_filter_clear_rx,
	.filter_count_rx_used = efx_mcdi_filter_count_rx_used,
	.filter_get_rx_id_limit = efx_mcdi_filter_get_rx_id_limit,
	.filter_get_rx_ids = efx_mcdi_filter_get_rx_ids,
#ifdef CONFIG_RFS_ACCEL
	.filter_rfs_expire_one = efx_mcdi_filter_rfs_expire_one,
#endif
#ifdef CONFIG_SFC_MTD
	.mtd_probe = efx_ef10_mtd_probe,
	.mtd_rename = efx_mcdi_mtd_rename,
	.mtd_read = efx_mcdi_mtd_read,
	.mtd_erase = efx_mcdi_mtd_erase,
	.mtd_write = efx_mcdi_mtd_write,
	.mtd_sync = efx_mcdi_mtd_sync,
#endif
	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
	.udp_tnl_push_ports = efx_ef10_udp_tnl_push_ports,
	.udp_tnl_has_port = efx_ef10_udp_tnl_has_port,
#ifdef CONFIG_SFC_SRIOV
	.sriov_configure = efx_ef10_sriov_configure,
	.sriov_init = efx_ef10_sriov_init,
	.sriov_fini = efx_ef10_sriov_fini,
	.sriov_wanted = efx_ef10_sriov_wanted,
	.sriov_reset = efx_ef10_sriov_reset,
	.sriov_flr = efx_ef10_sriov_flr,
	.sriov_set_vf_mac = efx_ef10_sriov_set_vf_mac,
	.sriov_set_vf_vlan = efx_ef10_sriov_set_vf_vlan,
	.sriov_set_vf_spoofchk = efx_ef10_sriov_set_vf_spoofchk,
	.sriov_get_vf_config = efx_ef10_sriov_get_vf_config,
	.sriov_set_vf_link_state = efx_ef10_sriov_set_vf_link_state,
	.vswitching_probe = efx_ef10_vswitching_probe_pf,
	.vswitching_restore = efx_ef10_vswitching_restore_pf,
	.vswitching_remove = efx_ef10_vswitching_remove_pf,
#endif
	.get_mac_address = efx_ef10_get_mac_address_pf,
	.set_mac_address = efx_ef10_set_mac_address,
	.tso_versions = efx_ef10_tso_versions,

	.get_phys_port_id = efx_ef10_get_phys_port_id,
	.revision = EFX_REV_HUNT_A0,
	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
	.rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
	.rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
	.rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
	.can_rx_scatter = true,
	.always_rx_scatter = true,
	.option_descriptors = true,
	.min_interrupt_mode = EFX_INT_MODE_LEGACY,
	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
	.offload_features = EF10_OFFLOAD_FEATURES,
	.mcdi_max_ver = 2,
	.max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS,
	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
			    1 << HWTSTAMP_FILTER_ALL,
	.rx_hash_key_size = 40,
	.check_caps = ef10_check_caps,
	.print_additional_fwver = efx_ef10_print_additional_fwver,
	.sensor_event = efx_mcdi_sensor_event,
	.rx_recycle_ring_size = efx_ef10_recycle_ring_size,
};