summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
blob: a57455aebff6fc58e24c4a4da2d60d78e59f439f (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
// SPDX-License-Identifier: GPL-2.0
/* Marvell RVU Physical Function ethernet driver
 *
 * Copyright (C) 2020 Marvell.
 *
 */

#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
#include <linux/etherdevice.h>
#include <linux/of.h>
#include <linux/if_vlan.h>
#include <linux/iommu.h>
#include <net/ip.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/bitfield.h>
#include <net/page_pool/types.h>

#include "otx2_reg.h"
#include "otx2_common.h"
#include "otx2_txrx.h"
#include "otx2_struct.h"
#include "otx2_ptp.h"
#include "cn10k.h"
#include "qos.h"
#include <rvu_trace.h>

#define DRV_NAME	"rvu_nicpf"
#define DRV_STRING	"Marvell RVU NIC Physical Function Driver"

/* Supported devices */
static const struct pci_device_id otx2_pf_id_table[] = {
	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_RVU_PF) },
	{ 0, }  /* end of table */
};

MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>");
MODULE_DESCRIPTION(DRV_STRING);
MODULE_LICENSE("GPL v2");
MODULE_DEVICE_TABLE(pci, otx2_pf_id_table);

static void otx2_vf_link_event_task(struct work_struct *work);

enum {
	TYPE_PFAF,
	TYPE_PFVF,
};

static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable);
static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable);

static int otx2_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	bool if_up = netif_running(netdev);
	int err = 0;

	if (pf->xdp_prog && new_mtu > MAX_XDP_MTU) {
		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
			    netdev->mtu);
		return -EINVAL;
	}
	if (if_up)
		otx2_stop(netdev);

	netdev_info(netdev, "Changing MTU from %d to %d\n",
		    netdev->mtu, new_mtu);
	netdev->mtu = new_mtu;

	if (if_up)
		err = otx2_open(netdev);

	return err;
}

static void otx2_disable_flr_me_intr(struct otx2_nic *pf)
{
	int irq, vfs = pf->total_vfs;

	/* Disable VFs ME interrupts */
	otx2_write64(pf, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs));
	irq = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME0);
	free_irq(irq, pf);

	/* Disable VFs FLR interrupts */
	otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
	irq = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR0);
	free_irq(irq, pf);

	if (vfs <= 64)
		return;

	otx2_write64(pf, RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
	irq = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME1);
	free_irq(irq, pf);

	otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
	irq = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR1);
	free_irq(irq, pf);
}

static void otx2_flr_wq_destroy(struct otx2_nic *pf)
{
	if (!pf->flr_wq)
		return;
	destroy_workqueue(pf->flr_wq);
	pf->flr_wq = NULL;
	devm_kfree(pf->dev, pf->flr_wrk);
}

static void otx2_flr_handler(struct work_struct *work)
{
	struct flr_work *flrwork = container_of(work, struct flr_work, work);
	struct otx2_nic *pf = flrwork->pf;
	struct mbox *mbox = &pf->mbox;
	struct msg_req *req;
	int vf, reg = 0;

	vf = flrwork - pf->flr_wrk;

	mutex_lock(&mbox->lock);
	req = otx2_mbox_alloc_msg_vf_flr(mbox);
	if (!req) {
		mutex_unlock(&mbox->lock);
		return;
	}
	req->hdr.pcifunc &= RVU_PFVF_FUNC_MASK;
	req->hdr.pcifunc |= (vf + 1) & RVU_PFVF_FUNC_MASK;

	if (!otx2_sync_mbox_msg(&pf->mbox)) {
		if (vf >= 64) {
			reg = 1;
			vf = vf - 64;
		}
		/* clear transcation pending bit */
		otx2_write64(pf, RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
		otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf));
	}

	mutex_unlock(&mbox->lock);
}

static irqreturn_t otx2_pf_flr_intr_handler(int irq, void *pf_irq)
{
	struct otx2_nic *pf = (struct otx2_nic *)pf_irq;
	int reg, dev, vf, start_vf, num_reg = 1;
	u64 intr;

	if (pf->total_vfs > 64)
		num_reg = 2;

	for (reg = 0; reg < num_reg; reg++) {
		intr = otx2_read64(pf, RVU_PF_VFFLR_INTX(reg));
		if (!intr)
			continue;
		start_vf = 64 * reg;
		for (vf = 0; vf < 64; vf++) {
			if (!(intr & BIT_ULL(vf)))
				continue;
			dev = vf + start_vf;
			queue_work(pf->flr_wq, &pf->flr_wrk[dev].work);
			/* Clear interrupt */
			otx2_write64(pf, RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
			/* Disable the interrupt */
			otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1CX(reg),
				     BIT_ULL(vf));
		}
	}
	return IRQ_HANDLED;
}

static irqreturn_t otx2_pf_me_intr_handler(int irq, void *pf_irq)
{
	struct otx2_nic *pf = (struct otx2_nic *)pf_irq;
	int vf, reg, num_reg = 1;
	u64 intr;

	if (pf->total_vfs > 64)
		num_reg = 2;

	for (reg = 0; reg < num_reg; reg++) {
		intr = otx2_read64(pf, RVU_PF_VFME_INTX(reg));
		if (!intr)
			continue;
		for (vf = 0; vf < 64; vf++) {
			if (!(intr & BIT_ULL(vf)))
				continue;
			/* clear trpend bit */
			otx2_write64(pf, RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
			/* clear interrupt */
			otx2_write64(pf, RVU_PF_VFME_INTX(reg), BIT_ULL(vf));
		}
	}
	return IRQ_HANDLED;
}

static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
{
	struct otx2_hw *hw = &pf->hw;
	char *irq_name;
	int ret;

	/* Register ME interrupt handler*/
	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME0 * NAME_SIZE];
	snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0", rvu_get_pf(pf->pcifunc));
	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME0),
			  otx2_pf_me_intr_handler, 0, irq_name, pf);
	if (ret) {
		dev_err(pf->dev,
			"RVUPF: IRQ registration failed for ME0\n");
	}

	/* Register FLR interrupt handler */
	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR0 * NAME_SIZE];
	snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0", rvu_get_pf(pf->pcifunc));
	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR0),
			  otx2_pf_flr_intr_handler, 0, irq_name, pf);
	if (ret) {
		dev_err(pf->dev,
			"RVUPF: IRQ registration failed for FLR0\n");
		return ret;
	}

	if (numvfs > 64) {
		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME1 * NAME_SIZE];
		snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME1",
			 rvu_get_pf(pf->pcifunc));
		ret = request_irq(pci_irq_vector
				  (pf->pdev, RVU_PF_INT_VEC_VFME1),
				  otx2_pf_me_intr_handler, 0, irq_name, pf);
		if (ret) {
			dev_err(pf->dev,
				"RVUPF: IRQ registration failed for ME1\n");
		}
		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR1 * NAME_SIZE];
		snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR1",
			 rvu_get_pf(pf->pcifunc));
		ret = request_irq(pci_irq_vector
				  (pf->pdev, RVU_PF_INT_VEC_VFFLR1),
				  otx2_pf_flr_intr_handler, 0, irq_name, pf);
		if (ret) {
			dev_err(pf->dev,
				"RVUPF: IRQ registration failed for FLR1\n");
			return ret;
		}
	}

	/* Enable ME interrupt for all VFs*/
	otx2_write64(pf, RVU_PF_VFME_INTX(0), INTR_MASK(numvfs));
	otx2_write64(pf, RVU_PF_VFME_INT_ENA_W1SX(0), INTR_MASK(numvfs));

	/* Enable FLR interrupt for all VFs*/
	otx2_write64(pf, RVU_PF_VFFLR_INTX(0), INTR_MASK(numvfs));
	otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(numvfs));

	if (numvfs > 64) {
		numvfs -= 64;

		otx2_write64(pf, RVU_PF_VFME_INTX(1), INTR_MASK(numvfs));
		otx2_write64(pf, RVU_PF_VFME_INT_ENA_W1SX(1),
			     INTR_MASK(numvfs));

		otx2_write64(pf, RVU_PF_VFFLR_INTX(1), INTR_MASK(numvfs));
		otx2_write64(pf, RVU_PF_VFFLR_INT_ENA_W1SX(1),
			     INTR_MASK(numvfs));
	}
	return 0;
}

static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs)
{
	int vf;

	pf->flr_wq = alloc_ordered_workqueue("otx2_pf_flr_wq", WQ_HIGHPRI);
	if (!pf->flr_wq)
		return -ENOMEM;

	pf->flr_wrk = devm_kcalloc(pf->dev, num_vfs,
				   sizeof(struct flr_work), GFP_KERNEL);
	if (!pf->flr_wrk) {
		destroy_workqueue(pf->flr_wq);
		return -ENOMEM;
	}

	for (vf = 0; vf < num_vfs; vf++) {
		pf->flr_wrk[vf].pf = pf;
		INIT_WORK(&pf->flr_wrk[vf].work, otx2_flr_handler);
	}

	return 0;
}

static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
			    int first, int mdevs, u64 intr, int type)
{
	struct otx2_mbox_dev *mdev;
	struct otx2_mbox *mbox;
	struct mbox_hdr *hdr;
	int i;

	for (i = first; i < mdevs; i++) {
		/* start from 0 */
		if (!(intr & BIT_ULL(i - first)))
			continue;

		mbox = &mw->mbox;
		mdev = &mbox->dev[i];
		if (type == TYPE_PFAF)
			otx2_sync_mbox_bbuf(mbox, i);
		hdr = mdev->mbase + mbox->rx_start;
		/* The hdr->num_msgs is set to zero immediately in the interrupt
		 * handler to  ensure that it holds a correct value next time
		 * when the interrupt handler is called.
		 * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler
		 * pf>mbox.up_num_msgs holds the data for use in
		 * pfaf_mbox_up_handler.
		 */
		if (hdr->num_msgs) {
			mw[i].num_msgs = hdr->num_msgs;
			hdr->num_msgs = 0;
			if (type == TYPE_PFAF)
				memset(mbox->hwbase + mbox->rx_start, 0,
				       ALIGN(sizeof(struct mbox_hdr),
					     sizeof(u64)));

			queue_work(mbox_wq, &mw[i].mbox_wrk);
		}

		mbox = &mw->mbox_up;
		mdev = &mbox->dev[i];
		if (type == TYPE_PFAF)
			otx2_sync_mbox_bbuf(mbox, i);
		hdr = mdev->mbase + mbox->rx_start;
		if (hdr->num_msgs) {
			mw[i].up_num_msgs = hdr->num_msgs;
			hdr->num_msgs = 0;
			if (type == TYPE_PFAF)
				memset(mbox->hwbase + mbox->rx_start, 0,
				       ALIGN(sizeof(struct mbox_hdr),
					     sizeof(u64)));

			queue_work(mbox_wq, &mw[i].mbox_up_wrk);
		}
	}
}

static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev,
				  struct otx2_mbox *pfvf_mbox, void *bbuf_base,
				  int devid)
{
	struct otx2_mbox_dev *src_mdev = mdev;
	int offset;

	/* Msgs are already copied, trigger VF's mbox irq */
	smp_wmb();

	offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift);
	writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset);

	/* Restore VF's mbox bounce buffer region address */
	src_mdev->mbase = bbuf_base;
}

static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf,
				     struct otx2_mbox *src_mbox,
				     int dir, int vf, int num_msgs)
{
	struct otx2_mbox_dev *src_mdev, *dst_mdev;
	struct mbox_hdr *mbox_hdr;
	struct mbox_hdr *req_hdr;
	struct mbox *dst_mbox;
	int dst_size, err;

	if (dir == MBOX_DIR_PFAF) {
		/* Set VF's mailbox memory as PF's bounce buffer memory, so
		 * that explicit copying of VF's msgs to PF=>AF mbox region
		 * and AF=>PF responses to VF's mbox region can be avoided.
		 */
		src_mdev = &src_mbox->dev[vf];
		mbox_hdr = src_mbox->hwbase +
				src_mbox->rx_start + (vf * MBOX_SIZE);

		dst_mbox = &pf->mbox;
		dst_size = dst_mbox->mbox.tx_size -
				ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN);
		/* Check if msgs fit into destination area and has valid size */
		if (mbox_hdr->msg_size > dst_size || !mbox_hdr->msg_size)
			return -EINVAL;

		dst_mdev = &dst_mbox->mbox.dev[0];

		mutex_lock(&pf->mbox.lock);
		dst_mdev->mbase = src_mdev->mbase;
		dst_mdev->msg_size = mbox_hdr->msg_size;
		dst_mdev->num_msgs = num_msgs;
		err = otx2_sync_mbox_msg(dst_mbox);
		/* Error code -EIO indicate there is a communication failure
		 * to the AF. Rest of the error codes indicate that AF processed
		 * VF messages and set the error codes in response messages
		 * (if any) so simply forward responses to VF.
		 */
		if (err == -EIO) {
			dev_warn(pf->dev,
				 "AF not responding to VF%d messages\n", vf);
			/* restore PF mbase and exit */
			dst_mdev->mbase = pf->mbox.bbuf_base;
			mutex_unlock(&pf->mbox.lock);
			return err;
		}
		/* At this point, all the VF messages sent to AF are acked
		 * with proper responses and responses are copied to VF
		 * mailbox hence raise interrupt to VF.
		 */
		req_hdr = (struct mbox_hdr *)(dst_mdev->mbase +
					      dst_mbox->mbox.rx_start);
		req_hdr->num_msgs = num_msgs;

		otx2_forward_msg_pfvf(dst_mdev, &pf->mbox_pfvf[0].mbox,
				      pf->mbox.bbuf_base, vf);
		mutex_unlock(&pf->mbox.lock);
	} else if (dir == MBOX_DIR_PFVF_UP) {
		src_mdev = &src_mbox->dev[0];
		mbox_hdr = src_mbox->hwbase + src_mbox->rx_start;
		req_hdr = (struct mbox_hdr *)(src_mdev->mbase +
					      src_mbox->rx_start);
		req_hdr->num_msgs = num_msgs;

		dst_mbox = &pf->mbox_pfvf[0];
		dst_size = dst_mbox->mbox_up.tx_size -
				ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN);
		/* Check if msgs fit into destination area */
		if (mbox_hdr->msg_size > dst_size)
			return -EINVAL;

		dst_mdev = &dst_mbox->mbox_up.dev[vf];
		dst_mdev->mbase = src_mdev->mbase;
		dst_mdev->msg_size = mbox_hdr->msg_size;
		dst_mdev->num_msgs = mbox_hdr->num_msgs;
		err = otx2_sync_mbox_up_msg(dst_mbox, vf);
		if (err) {
			dev_warn(pf->dev,
				 "VF%d is not responding to mailbox\n", vf);
			return err;
		}
	} else if (dir == MBOX_DIR_VFPF_UP) {
		req_hdr = (struct mbox_hdr *)(src_mbox->dev[0].mbase +
					      src_mbox->rx_start);
		req_hdr->num_msgs = num_msgs;
		otx2_forward_msg_pfvf(&pf->mbox_pfvf->mbox_up.dev[vf],
				      &pf->mbox.mbox_up,
				      pf->mbox_pfvf[vf].bbuf_base,
				      0);
	}

	return 0;
}

static void otx2_pfvf_mbox_handler(struct work_struct *work)
{
	struct mbox_msghdr *msg = NULL;
	int offset, vf_idx, id, err;
	struct otx2_mbox_dev *mdev;
	struct mbox_hdr *req_hdr;
	struct otx2_mbox *mbox;
	struct mbox *vf_mbox;
	struct otx2_nic *pf;

	vf_mbox = container_of(work, struct mbox, mbox_wrk);
	pf = vf_mbox->pfvf;
	vf_idx = vf_mbox - pf->mbox_pfvf;

	mbox = &pf->mbox_pfvf[0].mbox;
	mdev = &mbox->dev[vf_idx];
	req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);

	offset = ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);

	for (id = 0; id < vf_mbox->num_msgs; id++) {
		msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start +
					     offset);

		if (msg->sig != OTX2_MBOX_REQ_SIG)
			goto inval_msg;

		/* Set VF's number in each of the msg */
		msg->pcifunc &= RVU_PFVF_FUNC_MASK;
		msg->pcifunc |= (vf_idx + 1) & RVU_PFVF_FUNC_MASK;
		offset = msg->next_msgoff;
	}
	err = otx2_forward_vf_mbox_msgs(pf, mbox, MBOX_DIR_PFAF, vf_idx,
					vf_mbox->num_msgs);
	if (err)
		goto inval_msg;
	return;

inval_msg:
	otx2_reply_invalid_msg(mbox, vf_idx, 0, msg->id);
	otx2_mbox_msg_send(mbox, vf_idx);
}

static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
{
	struct mbox *vf_mbox = container_of(work, struct mbox, mbox_up_wrk);
	struct otx2_nic *pf = vf_mbox->pfvf;
	struct otx2_mbox_dev *mdev;
	int offset, id, vf_idx = 0;
	struct mbox_hdr *rsp_hdr;
	struct mbox_msghdr *msg;
	struct otx2_mbox *mbox;

	vf_idx = vf_mbox - pf->mbox_pfvf;
	mbox = &pf->mbox_pfvf[0].mbox_up;
	mdev = &mbox->dev[vf_idx];

	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);

	for (id = 0; id < vf_mbox->up_num_msgs; id++) {
		msg = mdev->mbase + offset;

		if (msg->id >= MBOX_MSG_MAX) {
			dev_err(pf->dev,
				"Mbox msg with unknown ID 0x%x\n", msg->id);
			goto end;
		}

		if (msg->sig != OTX2_MBOX_RSP_SIG) {
			dev_err(pf->dev,
				"Mbox msg with wrong signature %x, ID 0x%x\n",
				msg->sig, msg->id);
			goto end;
		}

		switch (msg->id) {
		case MBOX_MSG_CGX_LINK_EVENT:
			break;
		default:
			if (msg->rc)
				dev_err(pf->dev,
					"Mbox msg response has err %d, ID 0x%x\n",
					msg->rc, msg->id);
			break;
		}

end:
		offset = mbox->rx_start + msg->next_msgoff;
		if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1))
			__otx2_mbox_reset(mbox, 0);
		mdev->msgs_acked++;
	}
}

static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
{
	struct otx2_nic *pf = (struct otx2_nic *)(pf_irq);
	int vfs = pf->total_vfs;
	struct mbox *mbox;
	u64 intr;

	mbox = pf->mbox_pfvf;
	/* Handle VF interrupts */
	if (vfs > 64) {
		intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1));
		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr);
		otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr,
				TYPE_PFVF);
		if (intr)
			trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
		vfs = 64;
	}

	intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0));
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr);

	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);

	if (intr)
		trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);

	return IRQ_HANDLED;
}

static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
{
	void __iomem *hwbase;
	struct mbox *mbox;
	int err, vf;
	u64 base;

	if (!numvfs)
		return -EINVAL;

	pf->mbox_pfvf = devm_kcalloc(&pf->pdev->dev, numvfs,
				     sizeof(struct mbox), GFP_KERNEL);
	if (!pf->mbox_pfvf)
		return -ENOMEM;

	pf->mbox_pfvf_wq = alloc_ordered_workqueue("otx2_pfvf_mailbox",
						   WQ_HIGHPRI | WQ_MEM_RECLAIM);
	if (!pf->mbox_pfvf_wq)
		return -ENOMEM;

	/* On CN10K platform, PF <-> VF mailbox region follows after
	 * PF <-> AF mailbox region.
	 */
	if (test_bit(CN10K_MBOX, &pf->hw.cap_flag))
		base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
		       MBOX_SIZE;
	else
		base = readq((void __iomem *)((u64)pf->reg_base +
					      RVU_PF_VF_BAR4_ADDR));

	hwbase = ioremap_wc(base, MBOX_SIZE * pf->total_vfs);
	if (!hwbase) {
		err = -ENOMEM;
		goto free_wq;
	}

	mbox = &pf->mbox_pfvf[0];
	err = otx2_mbox_init(&mbox->mbox, hwbase, pf->pdev, pf->reg_base,
			     MBOX_DIR_PFVF, numvfs);
	if (err)
		goto free_iomem;

	err = otx2_mbox_init(&mbox->mbox_up, hwbase, pf->pdev, pf->reg_base,
			     MBOX_DIR_PFVF_UP, numvfs);
	if (err)
		goto free_iomem;

	for (vf = 0; vf < numvfs; vf++) {
		mbox->pfvf = pf;
		INIT_WORK(&mbox->mbox_wrk, otx2_pfvf_mbox_handler);
		INIT_WORK(&mbox->mbox_up_wrk, otx2_pfvf_mbox_up_handler);
		mbox++;
	}

	return 0;

free_iomem:
	if (hwbase)
		iounmap(hwbase);
free_wq:
	destroy_workqueue(pf->mbox_pfvf_wq);
	return err;
}

static void otx2_pfvf_mbox_destroy(struct otx2_nic *pf)
{
	struct mbox *mbox = &pf->mbox_pfvf[0];

	if (!mbox)
		return;

	if (pf->mbox_pfvf_wq) {
		destroy_workqueue(pf->mbox_pfvf_wq);
		pf->mbox_pfvf_wq = NULL;
	}

	if (mbox->mbox.hwbase)
		iounmap(mbox->mbox.hwbase);

	otx2_mbox_destroy(&mbox->mbox);
}

static void otx2_enable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
{
	/* Clear PF <=> VF mailbox IRQ */
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), ~0ull);
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), ~0ull);

	/* Enable PF <=> VF mailbox IRQ */
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0), INTR_MASK(numvfs));
	if (numvfs > 64) {
		numvfs -= 64;
		otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
			     INTR_MASK(numvfs));
	}
}

static void otx2_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
{
	int vector;

	/* Disable PF <=> VF mailbox IRQ */
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ull);
	otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ull);

	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), ~0ull);
	vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
	free_irq(vector, pf);

	if (numvfs > 64) {
		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), ~0ull);
		vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
		free_irq(vector, pf);
	}
}

static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
{
	struct otx2_hw *hw = &pf->hw;
	char *irq_name;
	int err;

	/* Register MBOX0 interrupt handler */
	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX0 * NAME_SIZE];
	if (pf->pcifunc)
		snprintf(irq_name, NAME_SIZE,
			 "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pcifunc));
	else
		snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox0");
	err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0),
			  otx2_pfvf_mbox_intr_handler, 0, irq_name, pf);
	if (err) {
		dev_err(pf->dev,
			"RVUPF: IRQ registration failed for PFVF mbox0 irq\n");
		return err;
	}

	if (numvfs > 64) {
		/* Register MBOX1 interrupt handler */
		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX1 * NAME_SIZE];
		if (pf->pcifunc)
			snprintf(irq_name, NAME_SIZE,
				 "RVUPF%d_VF Mbox1", rvu_get_pf(pf->pcifunc));
		else
			snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox1");
		err = request_irq(pci_irq_vector(pf->pdev,
						 RVU_PF_INT_VEC_VFPF_MBOX1),
						 otx2_pfvf_mbox_intr_handler,
						 0, irq_name, pf);
		if (err) {
			dev_err(pf->dev,
				"RVUPF: IRQ registration failed for PFVF mbox1 irq\n");
			return err;
		}
	}

	otx2_enable_pfvf_mbox_intr(pf, numvfs);

	return 0;
}

static void otx2_process_pfaf_mbox_msg(struct otx2_nic *pf,
				       struct mbox_msghdr *msg)
{
	int devid;

	if (msg->id >= MBOX_MSG_MAX) {
		dev_err(pf->dev,
			"Mbox msg with unknown ID 0x%x\n", msg->id);
		return;
	}

	if (msg->sig != OTX2_MBOX_RSP_SIG) {
		dev_err(pf->dev,
			"Mbox msg with wrong signature %x, ID 0x%x\n",
			 msg->sig, msg->id);
		return;
	}

	/* message response heading VF */
	devid = msg->pcifunc & RVU_PFVF_FUNC_MASK;
	if (devid) {
		struct otx2_vf_config *config = &pf->vf_configs[devid - 1];
		struct delayed_work *dwork;

		switch (msg->id) {
		case MBOX_MSG_NIX_LF_START_RX:
			config->intf_down = false;
			dwork = &config->link_event_work;
			schedule_delayed_work(dwork, msecs_to_jiffies(100));
			break;
		case MBOX_MSG_NIX_LF_STOP_RX:
			config->intf_down = true;
			break;
		}

		return;
	}

	switch (msg->id) {
	case MBOX_MSG_READY:
		pf->pcifunc = msg->pcifunc;
		break;
	case MBOX_MSG_MSIX_OFFSET:
		mbox_handler_msix_offset(pf, (struct msix_offset_rsp *)msg);
		break;
	case MBOX_MSG_NPA_LF_ALLOC:
		mbox_handler_npa_lf_alloc(pf, (struct npa_lf_alloc_rsp *)msg);
		break;
	case MBOX_MSG_NIX_LF_ALLOC:
		mbox_handler_nix_lf_alloc(pf, (struct nix_lf_alloc_rsp *)msg);
		break;
	case MBOX_MSG_NIX_BP_ENABLE:
		mbox_handler_nix_bp_enable(pf, (struct nix_bp_cfg_rsp *)msg);
		break;
	case MBOX_MSG_CGX_STATS:
		mbox_handler_cgx_stats(pf, (struct cgx_stats_rsp *)msg);
		break;
	case MBOX_MSG_CGX_FEC_STATS:
		mbox_handler_cgx_fec_stats(pf, (struct cgx_fec_stats_rsp *)msg);
		break;
	default:
		if (msg->rc)
			dev_err(pf->dev,
				"Mbox msg response has err %d, ID 0x%x\n",
				msg->rc, msg->id);
		break;
	}
}

static void otx2_pfaf_mbox_handler(struct work_struct *work)
{
	struct otx2_mbox_dev *mdev;
	struct mbox_hdr *rsp_hdr;
	struct mbox_msghdr *msg;
	struct otx2_mbox *mbox;
	struct mbox *af_mbox;
	struct otx2_nic *pf;
	int offset, id;

	af_mbox = container_of(work, struct mbox, mbox_wrk);
	mbox = &af_mbox->mbox;
	mdev = &mbox->dev[0];
	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);

	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
	pf = af_mbox->pfvf;

	for (id = 0; id < af_mbox->num_msgs; id++) {
		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
		otx2_process_pfaf_mbox_msg(pf, msg);
		offset = mbox->rx_start + msg->next_msgoff;
		if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
			__otx2_mbox_reset(mbox, 0);
		mdev->msgs_acked++;
	}

}

static void otx2_handle_link_event(struct otx2_nic *pf)
{
	struct cgx_link_user_info *linfo = &pf->linfo;
	struct net_device *netdev = pf->netdev;

	pr_info("%s NIC Link is %s %d Mbps %s duplex\n", netdev->name,
		linfo->link_up ? "UP" : "DOWN", linfo->speed,
		linfo->full_duplex ? "Full" : "Half");
	if (linfo->link_up) {
		netif_carrier_on(netdev);
		netif_tx_start_all_queues(netdev);
	} else {
		netif_tx_stop_all_queues(netdev);
		netif_carrier_off(netdev);
	}
}

int otx2_mbox_up_handler_mcs_intr_notify(struct otx2_nic *pf,
					 struct mcs_intr_info *event,
					 struct msg_rsp *rsp)
{
	cn10k_handle_mcs_event(pf, event);

	return 0;
}

int otx2_mbox_up_handler_cgx_link_event(struct otx2_nic *pf,
					struct cgx_link_info_msg *msg,
					struct msg_rsp *rsp)
{
	int i;

	/* Copy the link info sent by AF */
	pf->linfo = msg->link_info;

	/* notify VFs about link event */
	for (i = 0; i < pci_num_vf(pf->pdev); i++) {
		struct otx2_vf_config *config = &pf->vf_configs[i];
		struct delayed_work *dwork = &config->link_event_work;

		if (config->intf_down)
			continue;

		schedule_delayed_work(dwork, msecs_to_jiffies(100));
	}

	/* interface has not been fully configured yet */
	if (pf->flags & OTX2_FLAG_INTF_DOWN)
		return 0;

	otx2_handle_link_event(pf);
	return 0;
}

static int otx2_process_mbox_msg_up(struct otx2_nic *pf,
				    struct mbox_msghdr *req)
{
	/* Check if valid, if not reply with a invalid msg */
	if (req->sig != OTX2_MBOX_REQ_SIG) {
		otx2_reply_invalid_msg(&pf->mbox.mbox_up, 0, 0, req->id);
		return -ENODEV;
	}

	switch (req->id) {
#define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
	case _id: {							\
		struct _rsp_type *rsp;					\
		int err;						\
									\
		rsp = (struct _rsp_type *)otx2_mbox_alloc_msg(		\
			&pf->mbox.mbox_up, 0,				\
			sizeof(struct _rsp_type));			\
		if (!rsp)						\
			return -ENOMEM;					\
									\
		rsp->hdr.id = _id;					\
		rsp->hdr.sig = OTX2_MBOX_RSP_SIG;			\
		rsp->hdr.pcifunc = 0;					\
		rsp->hdr.rc = 0;					\
									\
		err = otx2_mbox_up_handler_ ## _fn_name(		\
			pf, (struct _req_type *)req, rsp);		\
		return err;						\
	}
MBOX_UP_CGX_MESSAGES
MBOX_UP_MCS_MESSAGES
#undef M
		break;
	default:
		otx2_reply_invalid_msg(&pf->mbox.mbox_up, 0, 0, req->id);
		return -ENODEV;
	}
	return 0;
}

static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
{
	struct mbox *af_mbox = container_of(work, struct mbox, mbox_up_wrk);
	struct otx2_mbox *mbox = &af_mbox->mbox_up;
	struct otx2_mbox_dev *mdev = &mbox->dev[0];
	struct otx2_nic *pf = af_mbox->pfvf;
	int offset, id, devid = 0;
	struct mbox_hdr *rsp_hdr;
	struct mbox_msghdr *msg;

	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);

	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);

	for (id = 0; id < af_mbox->up_num_msgs; id++) {
		msg = (struct mbox_msghdr *)(mdev->mbase + offset);

		devid = msg->pcifunc & RVU_PFVF_FUNC_MASK;
		/* Skip processing VF's messages */
		if (!devid)
			otx2_process_mbox_msg_up(pf, msg);
		offset = mbox->rx_start + msg->next_msgoff;
	}
	if (devid) {
		otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up,
					  MBOX_DIR_PFVF_UP, devid - 1,
					  af_mbox->up_num_msgs);
		return;
	}

	otx2_mbox_msg_send(mbox, 0);
}

static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
{
	struct otx2_nic *pf = (struct otx2_nic *)pf_irq;
	struct mbox *mbox;

	/* Clear the IRQ */
	otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));

	mbox = &pf->mbox;

	trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0));

	otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF);

	return IRQ_HANDLED;
}

static void otx2_disable_mbox_intr(struct otx2_nic *pf)
{
	int vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX);

	/* Disable AF => PF mailbox IRQ */
	otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0));
	free_irq(vector, pf);
}

static int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af)
{
	struct otx2_hw *hw = &pf->hw;
	struct msg_req *req;
	char *irq_name;
	int err;

	/* Register mailbox interrupt handler */
	irq_name = &hw->irq_name[RVU_PF_INT_VEC_AFPF_MBOX * NAME_SIZE];
	snprintf(irq_name, NAME_SIZE, "RVUPFAF Mbox");
	err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX),
			  otx2_pfaf_mbox_intr_handler, 0, irq_name, pf);
	if (err) {
		dev_err(pf->dev,
			"RVUPF: IRQ registration failed for PFAF mbox irq\n");
		return err;
	}

	/* Enable mailbox interrupt for msgs coming from AF.
	 * First clear to avoid spurious interrupts, if any.
	 */
	otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
	otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0));

	if (!probe_af)
		return 0;

	/* Check mailbox communication with AF */
	req = otx2_mbox_alloc_msg_ready(&pf->mbox);
	if (!req) {
		otx2_disable_mbox_intr(pf);
		return -ENOMEM;
	}
	err = otx2_sync_mbox_msg(&pf->mbox);
	if (err) {
		dev_warn(pf->dev,
			 "AF not responding to mailbox, deferring probe\n");
		otx2_disable_mbox_intr(pf);
		return -EPROBE_DEFER;
	}

	return 0;
}

static void otx2_pfaf_mbox_destroy(struct otx2_nic *pf)
{
	struct mbox *mbox = &pf->mbox;

	if (pf->mbox_wq) {
		destroy_workqueue(pf->mbox_wq);
		pf->mbox_wq = NULL;
	}

	if (mbox->mbox.hwbase)
		iounmap((void __iomem *)mbox->mbox.hwbase);

	otx2_mbox_destroy(&mbox->mbox);
	otx2_mbox_destroy(&mbox->mbox_up);
}

static int otx2_pfaf_mbox_init(struct otx2_nic *pf)
{
	struct mbox *mbox = &pf->mbox;
	void __iomem *hwbase;
	int err;

	mbox->pfvf = pf;
	pf->mbox_wq = alloc_ordered_workqueue("otx2_pfaf_mailbox",
					      WQ_HIGHPRI | WQ_MEM_RECLAIM);
	if (!pf->mbox_wq)
		return -ENOMEM;

	/* Mailbox is a reserved memory (in RAM) region shared between
	 * admin function (i.e AF) and this PF, shouldn't be mapped as
	 * device memory to allow unaligned accesses.
	 */
	hwbase = ioremap_wc(pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM),
			    MBOX_SIZE);
	if (!hwbase) {
		dev_err(pf->dev, "Unable to map PFAF mailbox region\n");
		err = -ENOMEM;
		goto exit;
	}

	err = otx2_mbox_init(&mbox->mbox, hwbase, pf->pdev, pf->reg_base,
			     MBOX_DIR_PFAF, 1);
	if (err)
		goto exit;

	err = otx2_mbox_init(&mbox->mbox_up, hwbase, pf->pdev, pf->reg_base,
			     MBOX_DIR_PFAF_UP, 1);
	if (err)
		goto exit;

	err = otx2_mbox_bbuf_init(mbox, pf->pdev);
	if (err)
		goto exit;

	INIT_WORK(&mbox->mbox_wrk, otx2_pfaf_mbox_handler);
	INIT_WORK(&mbox->mbox_up_wrk, otx2_pfaf_mbox_up_handler);
	mutex_init(&mbox->lock);

	return 0;
exit:
	otx2_pfaf_mbox_destroy(pf);
	return err;
}

static int otx2_cgx_config_linkevents(struct otx2_nic *pf, bool enable)
{
	struct msg_req *msg;
	int err;

	mutex_lock(&pf->mbox.lock);
	if (enable)
		msg = otx2_mbox_alloc_msg_cgx_start_linkevents(&pf->mbox);
	else
		msg = otx2_mbox_alloc_msg_cgx_stop_linkevents(&pf->mbox);

	if (!msg) {
		mutex_unlock(&pf->mbox.lock);
		return -ENOMEM;
	}

	err = otx2_sync_mbox_msg(&pf->mbox);
	mutex_unlock(&pf->mbox.lock);
	return err;
}

static int otx2_cgx_config_loopback(struct otx2_nic *pf, bool enable)
{
	struct msg_req *msg;
	int err;

	if (enable && !bitmap_empty(pf->flow_cfg->dmacflt_bmap,
				    pf->flow_cfg->dmacflt_max_flows))
		netdev_warn(pf->netdev,
			    "CGX/RPM internal loopback might not work as DMAC filters are active\n");

	mutex_lock(&pf->mbox.lock);
	if (enable)
		msg = otx2_mbox_alloc_msg_cgx_intlbk_enable(&pf->mbox);
	else
		msg = otx2_mbox_alloc_msg_cgx_intlbk_disable(&pf->mbox);

	if (!msg) {
		mutex_unlock(&pf->mbox.lock);
		return -ENOMEM;
	}

	err = otx2_sync_mbox_msg(&pf->mbox);
	mutex_unlock(&pf->mbox.lock);
	return err;
}

int otx2_set_real_num_queues(struct net_device *netdev,
			     int tx_queues, int rx_queues)
{
	int err;

	err = netif_set_real_num_tx_queues(netdev, tx_queues);
	if (err) {
		netdev_err(netdev,
			   "Failed to set no of Tx queues: %d\n", tx_queues);
		return err;
	}

	err = netif_set_real_num_rx_queues(netdev, rx_queues);
	if (err)
		netdev_err(netdev,
			   "Failed to set no of Rx queues: %d\n", rx_queues);
	return err;
}
EXPORT_SYMBOL(otx2_set_real_num_queues);

static char *nix_sqoperr_e_str[NIX_SQOPERR_MAX] = {
	"NIX_SQOPERR_OOR",
	"NIX_SQOPERR_CTX_FAULT",
	"NIX_SQOPERR_CTX_POISON",
	"NIX_SQOPERR_DISABLED",
	"NIX_SQOPERR_SIZE_ERR",
	"NIX_SQOPERR_OFLOW",
	"NIX_SQOPERR_SQB_NULL",
	"NIX_SQOPERR_SQB_FAULT",
	"NIX_SQOPERR_SQE_SZ_ZERO",
};

static char *nix_mnqerr_e_str[NIX_MNQERR_MAX] = {
	"NIX_MNQERR_SQ_CTX_FAULT",
	"NIX_MNQERR_SQ_CTX_POISON",
	"NIX_MNQERR_SQB_FAULT",
	"NIX_MNQERR_SQB_POISON",
	"NIX_MNQERR_TOTAL_ERR",
	"NIX_MNQERR_LSO_ERR",
	"NIX_MNQERR_CQ_QUERY_ERR",
	"NIX_MNQERR_MAX_SQE_SIZE_ERR",
	"NIX_MNQERR_MAXLEN_ERR",
	"NIX_MNQERR_SQE_SIZEM1_ZERO",
};

static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] =  {
	[NIX_SND_STATUS_GOOD] = "NIX_SND_STATUS_GOOD",
	[NIX_SND_STATUS_SQ_CTX_FAULT] = "NIX_SND_STATUS_SQ_CTX_FAULT",
	[NIX_SND_STATUS_SQ_CTX_POISON] = "NIX_SND_STATUS_SQ_CTX_POISON",
	[NIX_SND_STATUS_SQB_FAULT] = "NIX_SND_STATUS_SQB_FAULT",
	[NIX_SND_STATUS_SQB_POISON] = "NIX_SND_STATUS_SQB_POISON",
	[NIX_SND_STATUS_HDR_ERR] = "NIX_SND_STATUS_HDR_ERR",
	[NIX_SND_STATUS_EXT_ERR] = "NIX_SND_STATUS_EXT_ERR",
	[NIX_SND_STATUS_JUMP_FAULT] = "NIX_SND_STATUS_JUMP_FAULT",
	[NIX_SND_STATUS_JUMP_POISON] = "NIX_SND_STATUS_JUMP_POISON",
	[NIX_SND_STATUS_CRC_ERR] = "NIX_SND_STATUS_CRC_ERR",
	[NIX_SND_STATUS_IMM_ERR] = "NIX_SND_STATUS_IMM_ERR",
	[NIX_SND_STATUS_SG_ERR] = "NIX_SND_STATUS_SG_ERR",
	[NIX_SND_STATUS_MEM_ERR] = "NIX_SND_STATUS_MEM_ERR",
	[NIX_SND_STATUS_INVALID_SUBDC] = "NIX_SND_STATUS_INVALID_SUBDC",
	[NIX_SND_STATUS_SUBDC_ORDER_ERR] = "NIX_SND_STATUS_SUBDC_ORDER_ERR",
	[NIX_SND_STATUS_DATA_FAULT] = "NIX_SND_STATUS_DATA_FAULT",
	[NIX_SND_STATUS_DATA_POISON] = "NIX_SND_STATUS_DATA_POISON",
	[NIX_SND_STATUS_NPC_DROP_ACTION] = "NIX_SND_STATUS_NPC_DROP_ACTION",
	[NIX_SND_STATUS_LOCK_VIOL] = "NIX_SND_STATUS_LOCK_VIOL",
	[NIX_SND_STATUS_NPC_UCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_UCAST_CHAN_ERR",
	[NIX_SND_STATUS_NPC_MCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_MCAST_CHAN_ERR",
	[NIX_SND_STATUS_NPC_MCAST_ABORT] = "NIX_SND_STATUS_NPC_MCAST_ABORT",
	[NIX_SND_STATUS_NPC_VTAG_PTR_ERR] = "NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
	[NIX_SND_STATUS_NPC_VTAG_SIZE_ERR] = "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
	[NIX_SND_STATUS_SEND_MEM_FAULT] = "NIX_SND_STATUS_SEND_MEM_FAULT",
	[NIX_SND_STATUS_SEND_STATS_ERR] = "NIX_SND_STATUS_SEND_STATS_ERR",
};

static irqreturn_t otx2_q_intr_handler(int irq, void *data)
{
	struct otx2_nic *pf = data;
	struct otx2_snd_queue *sq;
	u64 val, *ptr;
	u64 qidx = 0;

	/* CQ */
	for (qidx = 0; qidx < pf->qset.cq_cnt; qidx++) {
		ptr = otx2_get_regaddr(pf, NIX_LF_CQ_OP_INT);
		val = otx2_atomic64_add((qidx << 44), ptr);

		otx2_write64(pf, NIX_LF_CQ_OP_INT, (qidx << 44) |
			     (val & NIX_CQERRINT_BITS));
		if (!(val & (NIX_CQERRINT_BITS | BIT_ULL(42))))
			continue;

		if (val & BIT_ULL(42)) {
			netdev_err(pf->netdev,
				   "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
		} else {
			if (val & BIT_ULL(NIX_CQERRINT_DOOR_ERR))
				netdev_err(pf->netdev, "CQ%lld: Doorbell error",
					   qidx);
			if (val & BIT_ULL(NIX_CQERRINT_CQE_FAULT))
				netdev_err(pf->netdev,
					   "CQ%lld: Memory fault on CQE write to LLC/DRAM",
					   qidx);
		}

		schedule_work(&pf->reset_task);
	}

	/* SQ */
	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
		u64 sq_op_err_dbg, mnq_err_dbg, snd_err_dbg;
		u8 sq_op_err_code, mnq_err_code, snd_err_code;

		sq = &pf->qset.sq[qidx];
		if (!sq->sqb_ptrs)
			continue;

		/* Below debug registers captures first errors corresponding to
		 * those registers. We don't have to check against SQ qid as
		 * these are fatal errors.
		 */

		ptr = otx2_get_regaddr(pf, NIX_LF_SQ_OP_INT);
		val = otx2_atomic64_add((qidx << 44), ptr);
		otx2_write64(pf, NIX_LF_SQ_OP_INT, (qidx << 44) |
			     (val & NIX_SQINT_BITS));

		if (val & BIT_ULL(42)) {
			netdev_err(pf->netdev,
				   "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
			goto done;
		}

		sq_op_err_dbg = otx2_read64(pf, NIX_LF_SQ_OP_ERR_DBG);
		if (!(sq_op_err_dbg & BIT(44)))
			goto chk_mnq_err_dbg;

		sq_op_err_code = FIELD_GET(GENMASK(7, 0), sq_op_err_dbg);
		netdev_err(pf->netdev,
			   "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(0x%llx)  err=%s(%#x)\n",
			   qidx, sq_op_err_dbg,
			   nix_sqoperr_e_str[sq_op_err_code],
			   sq_op_err_code);

		otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, BIT_ULL(44));

		if (sq_op_err_code == NIX_SQOPERR_SQB_NULL)
			goto chk_mnq_err_dbg;

		/* Err is not NIX_SQOPERR_SQB_NULL, call aq function to read SQ structure.
		 * TODO: But we are in irq context. How to call mbox functions which does sleep
		 */

chk_mnq_err_dbg:
		mnq_err_dbg = otx2_read64(pf, NIX_LF_MNQ_ERR_DBG);
		if (!(mnq_err_dbg & BIT(44)))
			goto chk_snd_err_dbg;

		mnq_err_code = FIELD_GET(GENMASK(7, 0), mnq_err_dbg);
		netdev_err(pf->netdev,
			   "SQ%lld: NIX_LF_MNQ_ERR_DBG(0x%llx)  err=%s(%#x)\n",
			   qidx, mnq_err_dbg,  nix_mnqerr_e_str[mnq_err_code],
			   mnq_err_code);
		otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, BIT_ULL(44));

chk_snd_err_dbg:
		snd_err_dbg = otx2_read64(pf, NIX_LF_SEND_ERR_DBG);
		if (snd_err_dbg & BIT(44)) {
			snd_err_code = FIELD_GET(GENMASK(7, 0), snd_err_dbg);
			netdev_err(pf->netdev,
				   "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s(%#x)\n",
				   qidx, snd_err_dbg,
				   nix_snd_status_e_str[snd_err_code],
				   snd_err_code);
			otx2_write64(pf, NIX_LF_SEND_ERR_DBG, BIT_ULL(44));
		}

done:
		/* Print values and reset */
		if (val & BIT_ULL(NIX_SQINT_SQB_ALLOC_FAIL))
			netdev_err(pf->netdev, "SQ%lld: SQB allocation failed",
				   qidx);

		schedule_work(&pf->reset_task);
	}

	return IRQ_HANDLED;
}

static irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq)
{
	struct otx2_cq_poll *cq_poll = (struct otx2_cq_poll *)cq_irq;
	struct otx2_nic *pf = (struct otx2_nic *)cq_poll->dev;
	int qidx = cq_poll->cint_idx;

	/* Disable interrupts.
	 *
	 * Completion interrupts behave in a level-triggered interrupt
	 * fashion, and hence have to be cleared only after it is serviced.
	 */
	otx2_write64(pf, NIX_LF_CINTX_ENA_W1C(qidx), BIT_ULL(0));

	/* Schedule NAPI */
	pf->napi_events++;
	napi_schedule_irqoff(&cq_poll->napi);

	return IRQ_HANDLED;
}

static void otx2_disable_napi(struct otx2_nic *pf)
{
	struct otx2_qset *qset = &pf->qset;
	struct otx2_cq_poll *cq_poll;
	int qidx;

	for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) {
		cq_poll = &qset->napi[qidx];
		cancel_work_sync(&cq_poll->dim.work);
		napi_disable(&cq_poll->napi);
		netif_napi_del(&cq_poll->napi);
	}
}

static void otx2_free_cq_res(struct otx2_nic *pf)
{
	struct otx2_qset *qset = &pf->qset;
	struct otx2_cq_queue *cq;
	int qidx;

	/* Disable CQs */
	otx2_ctx_disable(&pf->mbox, NIX_AQ_CTYPE_CQ, false);
	for (qidx = 0; qidx < qset->cq_cnt; qidx++) {
		cq = &qset->cq[qidx];
		qmem_free(pf->dev, cq->cqe);
	}
}

static void otx2_free_sq_res(struct otx2_nic *pf)
{
	struct otx2_qset *qset = &pf->qset;
	struct otx2_snd_queue *sq;
	int qidx;

	/* Disable SQs */
	otx2_ctx_disable(&pf->mbox, NIX_AQ_CTYPE_SQ, false);
	/* Free SQB pointers */
	otx2_sq_free_sqbs(pf);
	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
		sq = &qset->sq[qidx];
		/* Skip freeing Qos queues if they are not initialized */
		if (!sq->sqe)
			continue;
		qmem_free(pf->dev, sq->sqe);
		qmem_free(pf->dev, sq->tso_hdrs);
		kfree(sq->sg);
		kfree(sq->sqb_ptrs);
	}
}

static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu)
{
	int frame_size;
	int total_size;
	int rbuf_size;

	if (pf->hw.rbuf_len)
		return ALIGN(pf->hw.rbuf_len, OTX2_ALIGN) + OTX2_HEAD_ROOM;

	/* The data transferred by NIX to memory consists of actual packet
	 * plus additional data which has timestamp and/or EDSA/HIGIG2
	 * headers if interface is configured in corresponding modes.
	 * NIX transfers entire data using 6 segments/buffers and writes
	 * a CQE_RX descriptor with those segment addresses. First segment
	 * has additional data prepended to packet. Also software omits a
	 * headroom of 128 bytes in each segment. Hence the total size of
	 * memory needed to receive a packet with 'mtu' is:
	 * frame size =  mtu + additional data;
	 * memory = frame_size + headroom * 6;
	 * each receive buffer size = memory / 6;
	 */
	frame_size = mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN;
	total_size = frame_size + OTX2_HEAD_ROOM * 6;
	rbuf_size = total_size / 6;

	return ALIGN(rbuf_size, 2048);
}

static int otx2_init_hw_resources(struct otx2_nic *pf)
{
	struct nix_lf_free_req *free_req;
	struct mbox *mbox = &pf->mbox;
	struct otx2_hw *hw = &pf->hw;
	struct msg_req *req;
	int err = 0, lvl;

	/* Set required NPA LF's pool counts
	 * Auras and Pools are used in a 1:1 mapping,
	 * so, aura count = pool count.
	 */
	hw->rqpool_cnt = hw->rx_queues;
	hw->sqpool_cnt = otx2_get_total_tx_queues(pf);
	hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt;

	/* Maximum hardware supported transmit length */
	pf->tx_max_pktlen = pf->netdev->max_mtu + OTX2_ETH_HLEN;

	pf->rbsize = otx2_get_rbuf_size(pf, pf->netdev->mtu);

	mutex_lock(&mbox->lock);
	/* NPA init */
	err = otx2_config_npa(pf);
	if (err)
		goto exit;

	/* NIX init */
	err = otx2_config_nix(pf);
	if (err)
		goto err_free_npa_lf;

	/* Enable backpressure for CGX mapped PF/VFs */
	if (!is_otx2_lbkvf(pf->pdev))
		otx2_nix_config_bp(pf, true);

	/* Init Auras and pools used by NIX RQ, for free buffer ptrs */
	err = otx2_rq_aura_pool_init(pf);
	if (err) {
		mutex_unlock(&mbox->lock);
		goto err_free_nix_lf;
	}
	/* Init Auras and pools used by NIX SQ, for queueing SQEs */
	err = otx2_sq_aura_pool_init(pf);
	if (err) {
		mutex_unlock(&mbox->lock);
		goto err_free_rq_ptrs;
	}

	err = otx2_txsch_alloc(pf);
	if (err) {
		mutex_unlock(&mbox->lock);
		goto err_free_sq_ptrs;
	}

#ifdef CONFIG_DCB
	if (pf->pfc_en) {
		err = otx2_pfc_txschq_alloc(pf);
		if (err) {
			mutex_unlock(&mbox->lock);
			goto err_free_sq_ptrs;
		}
	}
#endif

	err = otx2_config_nix_queues(pf);
	if (err) {
		mutex_unlock(&mbox->lock);
		goto err_free_txsch;
	}

	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
		err = otx2_txschq_config(pf, lvl, 0, false);
		if (err) {
			mutex_unlock(&mbox->lock);
			goto err_free_nix_queues;
		}
	}

#ifdef CONFIG_DCB
	if (pf->pfc_en) {
		err = otx2_pfc_txschq_config(pf);
		if (err) {
			mutex_unlock(&mbox->lock);
			goto err_free_nix_queues;
		}
	}
#endif

	mutex_unlock(&mbox->lock);
	return err;

err_free_nix_queues:
	otx2_free_sq_res(pf);
	otx2_free_cq_res(pf);
	otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false);
err_free_txsch:
	otx2_txschq_stop(pf);
err_free_sq_ptrs:
	otx2_sq_free_sqbs(pf);
err_free_rq_ptrs:
	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
	otx2_ctx_disable(mbox, NPA_AQ_CTYPE_POOL, true);
	otx2_ctx_disable(mbox, NPA_AQ_CTYPE_AURA, true);
	otx2_aura_pool_free(pf);
err_free_nix_lf:
	mutex_lock(&mbox->lock);
	free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
	if (free_req) {
		free_req->flags = NIX_LF_DISABLE_FLOWS;
		if (otx2_sync_mbox_msg(mbox))
			dev_err(pf->dev, "%s failed to free nixlf\n", __func__);
	}
err_free_npa_lf:
	/* Reset NPA LF */
	req = otx2_mbox_alloc_msg_npa_lf_free(mbox);
	if (req) {
		if (otx2_sync_mbox_msg(mbox))
			dev_err(pf->dev, "%s failed to free npalf\n", __func__);
	}
exit:
	mutex_unlock(&mbox->lock);
	return err;
}

static void otx2_free_hw_resources(struct otx2_nic *pf)
{
	struct otx2_qset *qset = &pf->qset;
	struct nix_lf_free_req *free_req;
	struct mbox *mbox = &pf->mbox;
	struct otx2_cq_queue *cq;
	struct otx2_pool *pool;
	struct msg_req *req;
	int pool_id;
	int qidx;

	/* Ensure all SQE are processed */
	otx2_sqb_flush(pf);

	/* Stop transmission */
	otx2_txschq_stop(pf);

#ifdef CONFIG_DCB
	if (pf->pfc_en)
		otx2_pfc_txschq_stop(pf);
#endif

	otx2_clean_qos_queues(pf);

	mutex_lock(&mbox->lock);
	/* Disable backpressure */
	if (!(pf->pcifunc & RVU_PFVF_FUNC_MASK))
		otx2_nix_config_bp(pf, false);
	mutex_unlock(&mbox->lock);

	/* Disable RQs */
	otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false);

	/*Dequeue all CQEs */
	for (qidx = 0; qidx < qset->cq_cnt; qidx++) {
		cq = &qset->cq[qidx];
		if (cq->cq_type == CQ_RX)
			otx2_cleanup_rx_cqes(pf, cq, qidx);
		else
			otx2_cleanup_tx_cqes(pf, cq);
	}
	otx2_free_pending_sqe(pf);

	otx2_free_sq_res(pf);

	/* Free RQ buffer pointers*/
	otx2_free_aura_ptr(pf, AURA_NIX_RQ);

	for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) {
		pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx);
		pool = &pf->qset.pool[pool_id];
		page_pool_destroy(pool->page_pool);
		pool->page_pool = NULL;
	}

	otx2_free_cq_res(pf);

	/* Free all ingress bandwidth profiles allocated */
	cn10k_free_all_ipolicers(pf);

	mutex_lock(&mbox->lock);
	/* Reset NIX LF */
	free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
	if (free_req) {
		free_req->flags = NIX_LF_DISABLE_FLOWS;
		if (!(pf->flags & OTX2_FLAG_PF_SHUTDOWN))
			free_req->flags |= NIX_LF_DONT_FREE_TX_VTAG;
		if (otx2_sync_mbox_msg(mbox))
			dev_err(pf->dev, "%s failed to free nixlf\n", __func__);
	}
	mutex_unlock(&mbox->lock);

	/* Disable NPA Pool and Aura hw context */
	otx2_ctx_disable(mbox, NPA_AQ_CTYPE_POOL, true);
	otx2_ctx_disable(mbox, NPA_AQ_CTYPE_AURA, true);
	otx2_aura_pool_free(pf);

	mutex_lock(&mbox->lock);
	/* Reset NPA LF */
	req = otx2_mbox_alloc_msg_npa_lf_free(mbox);
	if (req) {
		if (otx2_sync_mbox_msg(mbox))
			dev_err(pf->dev, "%s failed to free npalf\n", __func__);
	}
	mutex_unlock(&mbox->lock);
}

static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf)
{
	int vf;

	/* The AF driver will determine whether to allow the VF netdev or not */
	if (is_otx2_vf(pfvf->pcifunc))
		return true;

	/* check if there are any trusted VFs associated with the PF netdev */
	for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++)
		if (pfvf->vf_configs[vf].trusted)
			return true;
	return false;
}

static void otx2_do_set_rx_mode(struct otx2_nic *pf)
{
	struct net_device *netdev = pf->netdev;
	struct nix_rx_mode *req;
	bool promisc = false;

	if (!(netdev->flags & IFF_UP))
		return;

	if ((netdev->flags & IFF_PROMISC) ||
	    (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) {
		promisc = true;
	}

	/* Write unicast address to mcam entries or del from mcam */
	if (!promisc && netdev->priv_flags & IFF_UNICAST_FLT)
		__dev_uc_sync(netdev, otx2_add_macfilter, otx2_del_macfilter);

	mutex_lock(&pf->mbox.lock);
	req = otx2_mbox_alloc_msg_nix_set_rx_mode(&pf->mbox);
	if (!req) {
		mutex_unlock(&pf->mbox.lock);
		return;
	}

	req->mode = NIX_RX_MODE_UCAST;

	if (promisc)
		req->mode |= NIX_RX_MODE_PROMISC;
	if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
		req->mode |= NIX_RX_MODE_ALLMULTI;

	if (otx2_promisc_use_mce_list(pf))
		req->mode |= NIX_RX_MODE_USE_MCE;

	otx2_sync_mbox_msg(&pf->mbox);
	mutex_unlock(&pf->mbox.lock);
}

static void otx2_set_irq_coalesce(struct otx2_nic *pfvf)
{
	int cint;

	for (cint = 0; cint < pfvf->hw.cint_cnt; cint++)
		otx2_config_irq_coalescing(pfvf, cint);
}

static void otx2_dim_work(struct work_struct *w)
{
	struct dim_cq_moder cur_moder;
	struct otx2_cq_poll *cq_poll;
	struct otx2_nic *pfvf;
	struct dim *dim;

	dim = container_of(w, struct dim, work);
	cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
	cq_poll = container_of(dim, struct otx2_cq_poll, dim);
	pfvf = (struct otx2_nic *)cq_poll->dev;
	pfvf->hw.cq_time_wait = (cur_moder.usec > CQ_TIMER_THRESH_MAX) ?
		CQ_TIMER_THRESH_MAX : cur_moder.usec;
	pfvf->hw.cq_ecount_wait = (cur_moder.pkts > NAPI_POLL_WEIGHT) ?
		NAPI_POLL_WEIGHT : cur_moder.pkts;
	otx2_set_irq_coalesce(pfvf);
	dim->state = DIM_START_MEASURE;
}

int otx2_open(struct net_device *netdev)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct otx2_cq_poll *cq_poll = NULL;
	struct otx2_qset *qset = &pf->qset;
	int err = 0, qidx, vec;
	char *irq_name;

	netif_carrier_off(netdev);

	/* RQ and SQs are mapped to different CQs,
	 * so find out max CQ IRQs (i.e CINTs) needed.
	 */
	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
			       pf->hw.tc_tx_queues);

	pf->qset.cq_cnt = pf->hw.rx_queues + otx2_get_total_tx_queues(pf);

	qset->napi = kcalloc(pf->hw.cint_cnt, sizeof(*cq_poll), GFP_KERNEL);
	if (!qset->napi)
		return -ENOMEM;

	/* CQ size of RQ */
	qset->rqe_cnt = qset->rqe_cnt ? qset->rqe_cnt : Q_COUNT(Q_SIZE_256);
	/* CQ size of SQ */
	qset->sqe_cnt = qset->sqe_cnt ? qset->sqe_cnt : Q_COUNT(Q_SIZE_4K);

	err = -ENOMEM;
	qset->cq = kcalloc(pf->qset.cq_cnt,
			   sizeof(struct otx2_cq_queue), GFP_KERNEL);
	if (!qset->cq)
		goto err_free_mem;

	qset->sq = kcalloc(otx2_get_total_tx_queues(pf),
			   sizeof(struct otx2_snd_queue), GFP_KERNEL);
	if (!qset->sq)
		goto err_free_mem;

	qset->rq = kcalloc(pf->hw.rx_queues,
			   sizeof(struct otx2_rcv_queue), GFP_KERNEL);
	if (!qset->rq)
		goto err_free_mem;

	err = otx2_init_hw_resources(pf);
	if (err)
		goto err_free_mem;

	/* Register NAPI handler */
	for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) {
		cq_poll = &qset->napi[qidx];
		cq_poll->cint_idx = qidx;
		/* RQ0 & SQ0 are mapped to CINT0 and so on..
		 * 'cq_ids[0]' points to RQ's CQ and
		 * 'cq_ids[1]' points to SQ's CQ and
		 * 'cq_ids[2]' points to XDP's CQ and
		 */
		cq_poll->cq_ids[CQ_RX] =
			(qidx <  pf->hw.rx_queues) ? qidx : CINT_INVALID_CQ;
		cq_poll->cq_ids[CQ_TX] = (qidx < pf->hw.tx_queues) ?
				      qidx + pf->hw.rx_queues : CINT_INVALID_CQ;
		if (pf->xdp_prog)
			cq_poll->cq_ids[CQ_XDP] = (qidx < pf->hw.xdp_queues) ?
						  (qidx + pf->hw.rx_queues +
						  pf->hw.tx_queues) :
						  CINT_INVALID_CQ;
		else
			cq_poll->cq_ids[CQ_XDP] = CINT_INVALID_CQ;

		cq_poll->cq_ids[CQ_QOS] = (qidx < pf->hw.tc_tx_queues) ?
					  (qidx + pf->hw.rx_queues +
					   pf->hw.non_qos_queues) :
					  CINT_INVALID_CQ;

		cq_poll->dev = (void *)pf;
		cq_poll->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
		INIT_WORK(&cq_poll->dim.work, otx2_dim_work);
		netif_napi_add(netdev, &cq_poll->napi, otx2_napi_handler);
		napi_enable(&cq_poll->napi);
	}

	/* Set maximum frame size allowed in HW */
	err = otx2_hw_set_mtu(pf, netdev->mtu);
	if (err)
		goto err_disable_napi;

	/* Setup segmentation algorithms, if failed, clear offload capability */
	otx2_setup_segmentation(pf);

	/* Initialize RSS */
	err = otx2_rss_init(pf);
	if (err)
		goto err_disable_napi;

	/* Register Queue IRQ handlers */
	vec = pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START;
	irq_name = &pf->hw.irq_name[vec * NAME_SIZE];

	snprintf(irq_name, NAME_SIZE, "%s-qerr", pf->netdev->name);

	err = request_irq(pci_irq_vector(pf->pdev, vec),
			  otx2_q_intr_handler, 0, irq_name, pf);
	if (err) {
		dev_err(pf->dev,
			"RVUPF%d: IRQ registration failed for QERR\n",
			rvu_get_pf(pf->pcifunc));
		goto err_disable_napi;
	}

	/* Enable QINT IRQ */
	otx2_write64(pf, NIX_LF_QINTX_ENA_W1S(0), BIT_ULL(0));

	/* Register CQ IRQ handlers */
	vec = pf->hw.nix_msixoff + NIX_LF_CINT_VEC_START;
	for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) {
		irq_name = &pf->hw.irq_name[vec * NAME_SIZE];

		snprintf(irq_name, NAME_SIZE, "%s-rxtx-%d", pf->netdev->name,
			 qidx);

		err = request_irq(pci_irq_vector(pf->pdev, vec),
				  otx2_cq_intr_handler, 0, irq_name,
				  &qset->napi[qidx]);
		if (err) {
			dev_err(pf->dev,
				"RVUPF%d: IRQ registration failed for CQ%d\n",
				rvu_get_pf(pf->pcifunc), qidx);
			goto err_free_cints;
		}
		vec++;

		otx2_config_irq_coalescing(pf, qidx);

		/* Enable CQ IRQ */
		otx2_write64(pf, NIX_LF_CINTX_INT(qidx), BIT_ULL(0));
		otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(qidx), BIT_ULL(0));
	}

	otx2_set_cints_affinity(pf);

	if (pf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
		otx2_enable_rxvlan(pf, true);

	/* When reinitializing enable time stamping if it is enabled before */
	if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) {
		pf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED;
		otx2_config_hw_tx_tstamp(pf, true);
	}
	if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) {
		pf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED;
		otx2_config_hw_rx_tstamp(pf, true);
	}

	pf->flags &= ~OTX2_FLAG_INTF_DOWN;
	/* 'intf_down' may be checked on any cpu */
	smp_wmb();

	/* Enable QoS configuration before starting tx queues */
	otx2_qos_config_txschq(pf);

	/* we have already received link status notification */
	if (pf->linfo.link_up && !(pf->pcifunc & RVU_PFVF_FUNC_MASK))
		otx2_handle_link_event(pf);

	/* Install DMAC Filters */
	if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
		otx2_dmacflt_reinstall_flows(pf);

	otx2_tc_apply_ingress_police_rules(pf);

	err = otx2_rxtx_enable(pf, true);
	/* If a mbox communication error happens at this point then interface
	 * will end up in a state such that it is in down state but hardware
	 * mcam entries are enabled to receive the packets. Hence disable the
	 * packet I/O.
	 */
	if (err == EIO)
		goto err_disable_rxtx;
	else if (err)
		goto err_tx_stop_queues;

	otx2_do_set_rx_mode(pf);

	return 0;

err_disable_rxtx:
	otx2_rxtx_enable(pf, false);
err_tx_stop_queues:
	netif_tx_stop_all_queues(netdev);
	netif_carrier_off(netdev);
	pf->flags |= OTX2_FLAG_INTF_DOWN;
err_free_cints:
	otx2_free_cints(pf, qidx);
	vec = pci_irq_vector(pf->pdev,
			     pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START);
	otx2_write64(pf, NIX_LF_QINTX_ENA_W1C(0), BIT_ULL(0));
	free_irq(vec, pf);
err_disable_napi:
	otx2_disable_napi(pf);
	otx2_free_hw_resources(pf);
err_free_mem:
	kfree(qset->sq);
	kfree(qset->cq);
	kfree(qset->rq);
	kfree(qset->napi);
	return err;
}
EXPORT_SYMBOL(otx2_open);

int otx2_stop(struct net_device *netdev)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct otx2_cq_poll *cq_poll = NULL;
	struct otx2_qset *qset = &pf->qset;
	struct otx2_rss_info *rss;
	int qidx, vec, wrk;

	/* If the DOWN flag is set resources are already freed */
	if (pf->flags & OTX2_FLAG_INTF_DOWN)
		return 0;

	netif_carrier_off(netdev);
	netif_tx_stop_all_queues(netdev);

	pf->flags |= OTX2_FLAG_INTF_DOWN;
	/* 'intf_down' may be checked on any cpu */
	smp_wmb();

	/* First stop packet Rx/Tx */
	otx2_rxtx_enable(pf, false);

	/* Clear RSS enable flag */
	rss = &pf->hw.rss_info;
	rss->enable = false;
	if (!netif_is_rxfh_configured(netdev))
		kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]);

	/* Cleanup Queue IRQ */
	vec = pci_irq_vector(pf->pdev,
			     pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START);
	otx2_write64(pf, NIX_LF_QINTX_ENA_W1C(0), BIT_ULL(0));
	free_irq(vec, pf);

	/* Cleanup CQ NAPI and IRQ */
	vec = pf->hw.nix_msixoff + NIX_LF_CINT_VEC_START;
	for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) {
		/* Disable interrupt */
		otx2_write64(pf, NIX_LF_CINTX_ENA_W1C(qidx), BIT_ULL(0));

		synchronize_irq(pci_irq_vector(pf->pdev, vec));

		cq_poll = &qset->napi[qidx];
		napi_synchronize(&cq_poll->napi);
		vec++;
	}

	netif_tx_disable(netdev);

	for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++)
		cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work);
	devm_kfree(pf->dev, pf->refill_wrk);

	otx2_free_hw_resources(pf);
	otx2_free_cints(pf, pf->hw.cint_cnt);
	otx2_disable_napi(pf);

	for (qidx = 0; qidx < netdev->num_tx_queues; qidx++)
		netdev_tx_reset_queue(netdev_get_tx_queue(netdev, qidx));


	kfree(qset->sq);
	kfree(qset->cq);
	kfree(qset->rq);
	kfree(qset->napi);
	/* Do not clear RQ/SQ ringsize settings */
	memset_startat(qset, 0, sqe_cnt);
	return 0;
}
EXPORT_SYMBOL(otx2_stop);

static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	int qidx = skb_get_queue_mapping(skb);
	struct otx2_snd_queue *sq;
	struct netdev_queue *txq;
	int sq_idx;

	/* XDP SQs are not mapped with TXQs
	 * advance qid to derive correct sq mapped with QOS
	 */
	sq_idx = (qidx >= pf->hw.tx_queues) ? (qidx + pf->hw.xdp_queues) : qidx;

	/* Check for minimum and maximum packet length */
	if (skb->len <= ETH_HLEN ||
	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
		dev_kfree_skb(skb);
		return NETDEV_TX_OK;
	}

	sq = &pf->qset.sq[sq_idx];
	txq = netdev_get_tx_queue(netdev, qidx);

	if (!otx2_sq_append_skb(netdev, sq, skb, qidx)) {
		netif_tx_stop_queue(txq);

		/* Check again, incase SQBs got freed up */
		smp_mb();
		if (((sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb)
							> sq->sqe_thresh)
			netif_tx_wake_queue(txq);

		return NETDEV_TX_BUSY;
	}

	return NETDEV_TX_OK;
}

static int otx2_qos_select_htb_queue(struct otx2_nic *pf, struct sk_buff *skb,
				     u16 htb_maj_id)
{
	u16 classid;

	if ((TC_H_MAJ(skb->priority) >> 16) == htb_maj_id)
		classid = TC_H_MIN(skb->priority);
	else
		classid = READ_ONCE(pf->qos.defcls);

	if (!classid)
		return 0;

	return otx2_get_txq_by_classid(pf, classid);
}

u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
		      struct net_device *sb_dev)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	bool qos_enabled;
#ifdef CONFIG_DCB
	u8 vlan_prio;
#endif
	int txq;

	qos_enabled = netdev->real_num_tx_queues > pf->hw.tx_queues;
	if (unlikely(qos_enabled)) {
		/* This smp_load_acquire() pairs with smp_store_release() in
		 * otx2_qos_root_add() called from htb offload root creation
		 */
		u16 htb_maj_id = smp_load_acquire(&pf->qos.maj_id);

		if (unlikely(htb_maj_id)) {
			txq = otx2_qos_select_htb_queue(pf, skb, htb_maj_id);
			if (txq > 0)
				return txq;
			goto process_pfc;
		}
	}

process_pfc:
#ifdef CONFIG_DCB
	if (!skb_vlan_tag_present(skb))
		goto pick_tx;

	vlan_prio = skb->vlan_tci >> 13;
	if ((vlan_prio > pf->hw.tx_queues - 1) ||
	    !pf->pfc_alloc_status[vlan_prio])
		goto pick_tx;

	return vlan_prio;

pick_tx:
#endif
	txq = netdev_pick_tx(netdev, skb, NULL);
	if (unlikely(qos_enabled))
		return txq % pf->hw.tx_queues;

	return txq;
}
EXPORT_SYMBOL(otx2_select_queue);

static netdev_features_t otx2_fix_features(struct net_device *dev,
					   netdev_features_t features)
{
	if (features & NETIF_F_HW_VLAN_CTAG_RX)
		features |= NETIF_F_HW_VLAN_STAG_RX;
	else
		features &= ~NETIF_F_HW_VLAN_STAG_RX;

	return features;
}

static void otx2_set_rx_mode(struct net_device *netdev)
{
	struct otx2_nic *pf = netdev_priv(netdev);

	queue_work(pf->otx2_wq, &pf->rx_mode_work);
}

static void otx2_rx_mode_wrk_handler(struct work_struct *work)
{
	struct otx2_nic *pf = container_of(work, struct otx2_nic, rx_mode_work);

	otx2_do_set_rx_mode(pf);
}

static int otx2_set_features(struct net_device *netdev,
			     netdev_features_t features)
{
	netdev_features_t changed = features ^ netdev->features;
	struct otx2_nic *pf = netdev_priv(netdev);

	if ((changed & NETIF_F_LOOPBACK) && netif_running(netdev))
		return otx2_cgx_config_loopback(pf,
						features & NETIF_F_LOOPBACK);

	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(netdev))
		return otx2_enable_rxvlan(pf,
					  features & NETIF_F_HW_VLAN_CTAG_RX);

	return otx2_handle_ntuple_tc_features(netdev, features);
}

static void otx2_reset_task(struct work_struct *work)
{
	struct otx2_nic *pf = container_of(work, struct otx2_nic, reset_task);

	if (!netif_running(pf->netdev))
		return;

	rtnl_lock();
	otx2_stop(pf->netdev);
	pf->reset_count++;
	otx2_open(pf->netdev);
	netif_trans_update(pf->netdev);
	rtnl_unlock();
}

static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable)
{
	struct msg_req *req;
	int err;

	if (pfvf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED && enable)
		return 0;

	mutex_lock(&pfvf->mbox.lock);
	if (enable)
		req = otx2_mbox_alloc_msg_cgx_ptp_rx_enable(&pfvf->mbox);
	else
		req = otx2_mbox_alloc_msg_cgx_ptp_rx_disable(&pfvf->mbox);
	if (!req) {
		mutex_unlock(&pfvf->mbox.lock);
		return -ENOMEM;
	}

	err = otx2_sync_mbox_msg(&pfvf->mbox);
	if (err) {
		mutex_unlock(&pfvf->mbox.lock);
		return err;
	}

	mutex_unlock(&pfvf->mbox.lock);
	if (enable)
		pfvf->flags |= OTX2_FLAG_RX_TSTAMP_ENABLED;
	else
		pfvf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED;
	return 0;
}

static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable)
{
	struct msg_req *req;
	int err;

	if (pfvf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED && enable)
		return 0;

	mutex_lock(&pfvf->mbox.lock);
	if (enable)
		req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_enable(&pfvf->mbox);
	else
		req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_disable(&pfvf->mbox);
	if (!req) {
		mutex_unlock(&pfvf->mbox.lock);
		return -ENOMEM;
	}

	err = otx2_sync_mbox_msg(&pfvf->mbox);
	if (err) {
		mutex_unlock(&pfvf->mbox.lock);
		return err;
	}

	mutex_unlock(&pfvf->mbox.lock);
	if (enable)
		pfvf->flags |= OTX2_FLAG_TX_TSTAMP_ENABLED;
	else
		pfvf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED;
	return 0;
}

int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
{
	struct otx2_nic *pfvf = netdev_priv(netdev);
	struct hwtstamp_config config;

	if (!pfvf->ptp)
		return -ENODEV;

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

	switch (config.tx_type) {
	case HWTSTAMP_TX_OFF:
		if (pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC)
			pfvf->flags &= ~OTX2_FLAG_PTP_ONESTEP_SYNC;

		cancel_delayed_work(&pfvf->ptp->synctstamp_work);
		otx2_config_hw_tx_tstamp(pfvf, false);
		break;
	case HWTSTAMP_TX_ONESTEP_SYNC:
		if (!test_bit(CN10K_PTP_ONESTEP, &pfvf->hw.cap_flag))
			return -ERANGE;
		pfvf->flags |= OTX2_FLAG_PTP_ONESTEP_SYNC;
		schedule_delayed_work(&pfvf->ptp->synctstamp_work,
				      msecs_to_jiffies(500));
		fallthrough;
	case HWTSTAMP_TX_ON:
		otx2_config_hw_tx_tstamp(pfvf, true);
		break;
	default:
		return -ERANGE;
	}

	switch (config.rx_filter) {
	case HWTSTAMP_FILTER_NONE:
		otx2_config_hw_rx_tstamp(pfvf, false);
		break;
	case HWTSTAMP_FILTER_ALL:
	case HWTSTAMP_FILTER_SOME:
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
		otx2_config_hw_rx_tstamp(pfvf, true);
		config.rx_filter = HWTSTAMP_FILTER_ALL;
		break;
	default:
		return -ERANGE;
	}

	memcpy(&pfvf->tstamp, &config, sizeof(config));

	return copy_to_user(ifr->ifr_data, &config,
			    sizeof(config)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(otx2_config_hwtstamp);

int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
{
	struct otx2_nic *pfvf = netdev_priv(netdev);
	struct hwtstamp_config *cfg = &pfvf->tstamp;

	switch (cmd) {
	case SIOCSHWTSTAMP:
		return otx2_config_hwtstamp(netdev, req);
	case SIOCGHWTSTAMP:
		return copy_to_user(req->ifr_data, cfg,
				    sizeof(*cfg)) ? -EFAULT : 0;
	default:
		return -EOPNOTSUPP;
	}
}
EXPORT_SYMBOL(otx2_ioctl);

static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac)
{
	struct npc_install_flow_req *req;
	int err;

	mutex_lock(&pf->mbox.lock);
	req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
	if (!req) {
		err = -ENOMEM;
		goto out;
	}

	ether_addr_copy(req->packet.dmac, mac);
	eth_broadcast_addr((u8 *)&req->mask.dmac);
	req->features = BIT_ULL(NPC_DMAC);
	req->channel = pf->hw.rx_chan_base;
	req->intf = NIX_INTF_RX;
	req->default_rule = 1;
	req->append = 1;
	req->vf = vf + 1;
	req->op = NIX_RX_ACTION_DEFAULT;

	err = otx2_sync_mbox_msg(&pf->mbox);
out:
	mutex_unlock(&pf->mbox.lock);
	return err;
}

static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct pci_dev *pdev = pf->pdev;
	struct otx2_vf_config *config;
	int ret;

	if (!netif_running(netdev))
		return -EAGAIN;

	if (vf >= pf->total_vfs)
		return -EINVAL;

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

	config = &pf->vf_configs[vf];
	ether_addr_copy(config->mac, mac);

	ret = otx2_do_set_vf_mac(pf, vf, mac);
	if (ret == 0)
		dev_info(&pdev->dev,
			 "Load/Reload VF driver\n");

	return ret;
}

static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
			       __be16 proto)
{
	struct otx2_flow_config *flow_cfg = pf->flow_cfg;
	struct nix_vtag_config_rsp *vtag_rsp;
	struct npc_delete_flow_req *del_req;
	struct nix_vtag_config *vtag_req;
	struct npc_install_flow_req *req;
	struct otx2_vf_config *config;
	int err = 0;
	u32 idx;

	config = &pf->vf_configs[vf];

	if (!vlan && !config->vlan)
		goto out;

	mutex_lock(&pf->mbox.lock);

	/* free old tx vtag entry */
	if (config->vlan) {
		vtag_req = otx2_mbox_alloc_msg_nix_vtag_cfg(&pf->mbox);
		if (!vtag_req) {
			err = -ENOMEM;
			goto out;
		}
		vtag_req->cfg_type = 0;
		vtag_req->tx.free_vtag0 = 1;
		vtag_req->tx.vtag0_idx = config->tx_vtag_idx;

		err = otx2_sync_mbox_msg(&pf->mbox);
		if (err)
			goto out;
	}

	if (!vlan && config->vlan) {
		/* rx */
		del_req = otx2_mbox_alloc_msg_npc_delete_flow(&pf->mbox);
		if (!del_req) {
			err = -ENOMEM;
			goto out;
		}
		idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
		del_req->entry =
			flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
		err = otx2_sync_mbox_msg(&pf->mbox);
		if (err)
			goto out;

		/* tx */
		del_req = otx2_mbox_alloc_msg_npc_delete_flow(&pf->mbox);
		if (!del_req) {
			err = -ENOMEM;
			goto out;
		}
		idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
		del_req->entry =
			flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
		err = otx2_sync_mbox_msg(&pf->mbox);

		goto out;
	}

	/* rx */
	req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
	if (!req) {
		err = -ENOMEM;
		goto out;
	}

	idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
	req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
	req->packet.vlan_tci = htons(vlan);
	req->mask.vlan_tci = htons(VLAN_VID_MASK);
	/* af fills the destination mac addr */
	eth_broadcast_addr((u8 *)&req->mask.dmac);
	req->features = BIT_ULL(NPC_OUTER_VID) | BIT_ULL(NPC_DMAC);
	req->channel = pf->hw.rx_chan_base;
	req->intf = NIX_INTF_RX;
	req->vf = vf + 1;
	req->op = NIX_RX_ACTION_DEFAULT;
	req->vtag0_valid = true;
	req->vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE7;
	req->set_cntr = 1;

	err = otx2_sync_mbox_msg(&pf->mbox);
	if (err)
		goto out;

	/* tx */
	vtag_req = otx2_mbox_alloc_msg_nix_vtag_cfg(&pf->mbox);
	if (!vtag_req) {
		err = -ENOMEM;
		goto out;
	}

	/* configure tx vtag params */
	vtag_req->vtag_size = VTAGSIZE_T4;
	vtag_req->cfg_type = 0; /* tx vlan cfg */
	vtag_req->tx.cfg_vtag0 = 1;
	vtag_req->tx.vtag0 = ((u64)ntohs(proto) << 16) | vlan;

	err = otx2_sync_mbox_msg(&pf->mbox);
	if (err)
		goto out;

	vtag_rsp = (struct nix_vtag_config_rsp *)otx2_mbox_get_rsp
			(&pf->mbox.mbox, 0, &vtag_req->hdr);
	if (IS_ERR(vtag_rsp)) {
		err = PTR_ERR(vtag_rsp);
		goto out;
	}
	config->tx_vtag_idx = vtag_rsp->vtag0_idx;

	req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
	if (!req) {
		err = -ENOMEM;
		goto out;
	}

	eth_zero_addr((u8 *)&req->mask.dmac);
	idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
	req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
	req->features = BIT_ULL(NPC_DMAC);
	req->channel = pf->hw.tx_chan_base;
	req->intf = NIX_INTF_TX;
	req->vf = vf + 1;
	req->op = NIX_TX_ACTIONOP_UCAST_DEFAULT;
	req->vtag0_def = vtag_rsp->vtag0_idx;
	req->vtag0_op = VTAG_INSERT;
	req->set_cntr = 1;

	err = otx2_sync_mbox_msg(&pf->mbox);
out:
	config->vlan = vlan;
	mutex_unlock(&pf->mbox.lock);
	return err;
}

static int otx2_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
			    __be16 proto)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct pci_dev *pdev = pf->pdev;

	if (!netif_running(netdev))
		return -EAGAIN;

	if (vf >= pci_num_vf(pdev))
		return -EINVAL;

	/* qos is currently unsupported */
	if (vlan >= VLAN_N_VID || qos)
		return -EINVAL;

	if (proto != htons(ETH_P_8021Q))
		return -EPROTONOSUPPORT;

	if (!(pf->flags & OTX2_FLAG_VF_VLAN_SUPPORT))
		return -EOPNOTSUPP;

	return otx2_do_set_vf_vlan(pf, vf, vlan, qos, proto);
}

static int otx2_get_vf_config(struct net_device *netdev, int vf,
			      struct ifla_vf_info *ivi)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct pci_dev *pdev = pf->pdev;
	struct otx2_vf_config *config;

	if (!netif_running(netdev))
		return -EAGAIN;

	if (vf >= pci_num_vf(pdev))
		return -EINVAL;

	config = &pf->vf_configs[vf];
	ivi->vf = vf;
	ether_addr_copy(ivi->mac, config->mac);
	ivi->vlan = config->vlan;
	ivi->trusted = config->trusted;

	return 0;
}

static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
			    int qidx)
{
	struct page *page;
	u64 dma_addr;
	int err = 0;

	dma_addr = otx2_dma_map_page(pf, virt_to_page(xdpf->data),
				     offset_in_page(xdpf->data), xdpf->len,
				     DMA_TO_DEVICE);
	if (dma_mapping_error(pf->dev, dma_addr))
		return -ENOMEM;

	err = otx2_xdp_sq_append_pkt(pf, dma_addr, xdpf->len, qidx);
	if (!err) {
		otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE);
		page = virt_to_page(xdpf->data);
		put_page(page);
		return -ENOMEM;
	}
	return 0;
}

static int otx2_xdp_xmit(struct net_device *netdev, int n,
			 struct xdp_frame **frames, u32 flags)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	int qidx = smp_processor_id();
	struct otx2_snd_queue *sq;
	int drops = 0, i;

	if (!netif_running(netdev))
		return -ENETDOWN;

	qidx += pf->hw.tx_queues;
	sq = pf->xdp_prog ? &pf->qset.sq[qidx] : NULL;

	/* Abort xmit if xdp queue is not */
	if (unlikely(!sq))
		return -ENXIO;

	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
		return -EINVAL;

	for (i = 0; i < n; i++) {
		struct xdp_frame *xdpf = frames[i];
		int err;

		err = otx2_xdp_xmit_tx(pf, xdpf, qidx);
		if (err)
			drops++;
	}
	return n - drops;
}

static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
{
	struct net_device *dev = pf->netdev;
	bool if_up = netif_running(pf->netdev);
	struct bpf_prog *old_prog;

	if (prog && dev->mtu > MAX_XDP_MTU) {
		netdev_warn(dev, "Jumbo frames not yet supported with XDP\n");
		return -EOPNOTSUPP;
	}

	if (if_up)
		otx2_stop(pf->netdev);

	old_prog = xchg(&pf->xdp_prog, prog);

	if (old_prog)
		bpf_prog_put(old_prog);

	if (pf->xdp_prog)
		bpf_prog_add(pf->xdp_prog, pf->hw.rx_queues - 1);

	/* Network stack and XDP shared same rx queues.
	 * Use separate tx queues for XDP and network stack.
	 */
	if (pf->xdp_prog) {
		pf->hw.xdp_queues = pf->hw.rx_queues;
		xdp_features_set_redirect_target(dev, false);
	} else {
		pf->hw.xdp_queues = 0;
		xdp_features_clear_redirect_target(dev);
	}

	pf->hw.non_qos_queues += pf->hw.xdp_queues;

	if (if_up)
		otx2_open(pf->netdev);

	return 0;
}

static int otx2_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
{
	struct otx2_nic *pf = netdev_priv(netdev);

	switch (xdp->command) {
	case XDP_SETUP_PROG:
		return otx2_xdp_setup(pf, xdp->prog);
	default:
		return -EINVAL;
	}
}

static int otx2_set_vf_permissions(struct otx2_nic *pf, int vf,
				   int req_perm)
{
	struct set_vf_perm *req;
	int rc;

	mutex_lock(&pf->mbox.lock);
	req = otx2_mbox_alloc_msg_set_vf_perm(&pf->mbox);
	if (!req) {
		rc = -ENOMEM;
		goto out;
	}

	/* Let AF reset VF permissions as sriov is disabled */
	if (req_perm == OTX2_RESET_VF_PERM) {
		req->flags |= RESET_VF_PERM;
	} else if (req_perm == OTX2_TRUSTED_VF) {
		if (pf->vf_configs[vf].trusted)
			req->flags |= VF_TRUSTED;
	}

	req->vf = vf;
	rc = otx2_sync_mbox_msg(&pf->mbox);
out:
	mutex_unlock(&pf->mbox.lock);
	return rc;
}

static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf,
				 bool enable)
{
	struct otx2_nic *pf = netdev_priv(netdev);
	struct pci_dev *pdev = pf->pdev;
	int rc;

	if (vf >= pci_num_vf(pdev))
		return -EINVAL;

	if (pf->vf_configs[vf].trusted == enable)
		return 0;

	pf->vf_configs[vf].trusted = enable;
	rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);

	if (rc) {
		pf->vf_configs[vf].trusted = !enable;
	} else {
		netdev_info(pf->netdev, "VF %d is %strusted\n",
			    vf, enable ? "" : "not ");
		otx2_set_rx_mode(netdev);
	}

	return rc;
}

static const struct net_device_ops otx2_netdev_ops = {
	.ndo_open		= otx2_open,
	.ndo_stop		= otx2_stop,
	.ndo_start_xmit		= otx2_xmit,
	.ndo_select_queue	= otx2_select_queue,
	.ndo_fix_features	= otx2_fix_features,
	.ndo_set_mac_address    = otx2_set_mac_address,
	.ndo_change_mtu		= otx2_change_mtu,
	.ndo_set_rx_mode	= otx2_set_rx_mode,
	.ndo_set_features	= otx2_set_features,
	.ndo_tx_timeout		= otx2_tx_timeout,
	.ndo_get_stats64	= otx2_get_stats64,
	.ndo_eth_ioctl		= otx2_ioctl,
	.ndo_set_vf_mac		= otx2_set_vf_mac,
	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
	.ndo_get_vf_config	= otx2_get_vf_config,
	.ndo_bpf		= otx2_xdp,
	.ndo_xdp_xmit           = otx2_xdp_xmit,
	.ndo_setup_tc		= otx2_setup_tc,
	.ndo_set_vf_trust	= otx2_ndo_set_vf_trust,
};

static int otx2_wq_init(struct otx2_nic *pf)
{
	pf->otx2_wq = create_singlethread_workqueue("otx2_wq");
	if (!pf->otx2_wq)
		return -ENOMEM;

	INIT_WORK(&pf->rx_mode_work, otx2_rx_mode_wrk_handler);
	INIT_WORK(&pf->reset_task, otx2_reset_task);
	return 0;
}

static int otx2_check_pf_usable(struct otx2_nic *nic)
{
	u64 rev;

	rev = otx2_read64(nic, RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_RVUM));
	rev = (rev >> 12) & 0xFF;
	/* Check if AF has setup revision for RVUM block,
	 * otherwise this driver probe should be deferred
	 * until AF driver comes up.
	 */
	if (!rev) {
		dev_warn(nic->dev,
			 "AF is not initialized, deferring probe\n");
		return -EPROBE_DEFER;
	}
	return 0;
}

static int otx2_realloc_msix_vectors(struct otx2_nic *pf)
{
	struct otx2_hw *hw = &pf->hw;
	int num_vec, err;

	/* NPA interrupts are inot registered, so alloc only
	 * upto NIX vector offset.
	 */
	num_vec = hw->nix_msixoff;
	num_vec += NIX_LF_CINT_VEC_START + hw->max_queues;

	otx2_disable_mbox_intr(pf);
	pci_free_irq_vectors(hw->pdev);
	err = pci_alloc_irq_vectors(hw->pdev, num_vec, num_vec, PCI_IRQ_MSIX);
	if (err < 0) {
		dev_err(pf->dev, "%s: Failed to realloc %d IRQ vectors\n",
			__func__, num_vec);
		return err;
	}

	return otx2_register_mbox_intr(pf, false);
}

static int otx2_sriov_vfcfg_init(struct otx2_nic *pf)
{
	int i;

	pf->vf_configs = devm_kcalloc(pf->dev, pf->total_vfs,
				      sizeof(struct otx2_vf_config),
				      GFP_KERNEL);
	if (!pf->vf_configs)
		return -ENOMEM;

	for (i = 0; i < pf->total_vfs; i++) {
		pf->vf_configs[i].pf = pf;
		pf->vf_configs[i].intf_down = true;
		pf->vf_configs[i].trusted = false;
		INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work,
				  otx2_vf_link_event_task);
	}

	return 0;
}

static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf)
{
	int i;

	if (!pf->vf_configs)
		return;

	for (i = 0; i < pf->total_vfs; i++) {
		cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work);
		otx2_set_vf_permissions(pf, i, OTX2_RESET_VF_PERM);
	}
}

static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct device *dev = &pdev->dev;
	int err, qcount, qos_txqs;
	struct net_device *netdev;
	struct otx2_nic *pf;
	struct otx2_hw *hw;
	int num_vec;

	err = pcim_enable_device(pdev);
	if (err) {
		dev_err(dev, "Failed to enable PCI device\n");
		return err;
	}

	err = pci_request_regions(pdev, DRV_NAME);
	if (err) {
		dev_err(dev, "PCI request regions failed 0x%x\n", err);
		return err;
	}

	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
	if (err) {
		dev_err(dev, "DMA mask config failed, abort\n");
		goto err_release_regions;
	}

	pci_set_master(pdev);

	/* Set number of queues */
	qcount = min_t(int, num_online_cpus(), OTX2_MAX_CQ_CNT);
	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);

	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount);
	if (!netdev) {
		err = -ENOMEM;
		goto err_release_regions;
	}

	pci_set_drvdata(pdev, netdev);
	SET_NETDEV_DEV(netdev, &pdev->dev);
	pf = netdev_priv(netdev);
	pf->netdev = netdev;
	pf->pdev = pdev;
	pf->dev = dev;
	pf->total_vfs = pci_sriov_get_totalvfs(pdev);
	pf->flags |= OTX2_FLAG_INTF_DOWN;

	hw = &pf->hw;
	hw->pdev = pdev;
	hw->rx_queues = qcount;
	hw->tx_queues = qcount;
	hw->non_qos_queues = qcount;
	hw->max_queues = qcount;
	hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN;
	/* Use CQE of 128 byte descriptor size by default */
	hw->xqe_size = 128;

	num_vec = pci_msix_vec_count(pdev);
	hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
					  GFP_KERNEL);
	if (!hw->irq_name) {
		err = -ENOMEM;
		goto err_free_netdev;
	}

	hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec,
					 sizeof(cpumask_var_t), GFP_KERNEL);
	if (!hw->affinity_mask) {
		err = -ENOMEM;
		goto err_free_netdev;
	}

	/* Map CSRs */
	pf->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
	if (!pf->reg_base) {
		dev_err(dev, "Unable to map physical function CSRs, aborting\n");
		err = -ENOMEM;
		goto err_free_netdev;
	}

	err = otx2_check_pf_usable(pf);
	if (err)
		goto err_free_netdev;

	err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT,
				    RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX);
	if (err < 0) {
		dev_err(dev, "%s: Failed to alloc %d IRQ vectors\n",
			__func__, num_vec);
		goto err_free_netdev;
	}

	otx2_setup_dev_hw_settings(pf);

	/* Init PF <=> AF mailbox stuff */
	err = otx2_pfaf_mbox_init(pf);
	if (err)
		goto err_free_irq_vectors;

	/* Register mailbox interrupt */
	err = otx2_register_mbox_intr(pf, true);
	if (err)
		goto err_mbox_destroy;

	/* Request AF to attach NPA and NIX LFs to this PF.
	 * NIX and NPA LFs are needed for this PF to function as a NIC.
	 */
	err = otx2_attach_npa_nix(pf);
	if (err)
		goto err_disable_mbox_intr;

	err = otx2_realloc_msix_vectors(pf);
	if (err)
		goto err_detach_rsrc;

	err = otx2_set_real_num_queues(netdev, hw->tx_queues, hw->rx_queues);
	if (err)
		goto err_detach_rsrc;

	err = cn10k_lmtst_init(pf);
	if (err)
		goto err_detach_rsrc;

	/* Assign default mac address */
	otx2_get_mac_from_af(netdev);

	/* Don't check for error.  Proceed without ptp */
	otx2_ptp_init(pf);

	/* NPA's pool is a stack to which SW frees buffer pointers via Aura.
	 * HW allocates buffer pointer from stack and uses it for DMA'ing
	 * ingress packet. In some scenarios HW can free back allocated buffer
	 * pointers to pool. This makes it impossible for SW to maintain a
	 * parallel list where physical addresses of buffer pointers (IOVAs)
	 * given to HW can be saved for later reference.
	 *
	 * So the only way to convert Rx packet's buffer address is to use
	 * IOMMU's iova_to_phys() handler which translates the address by
	 * walking through the translation tables.
	 */
	pf->iommu_domain = iommu_get_domain_for_dev(dev);

	netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
			       NETIF_F_IPV6_CSUM | NETIF_F_RXHASH |
			       NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
			       NETIF_F_GSO_UDP_L4);
	netdev->features |= netdev->hw_features;

	err = otx2_mcam_flow_init(pf);
	if (err)
		goto err_ptp_destroy;

	err = cn10k_mcs_init(pf);
	if (err)
		goto err_del_mcam_entries;

	if (pf->flags & OTX2_FLAG_NTUPLE_SUPPORT)
		netdev->hw_features |= NETIF_F_NTUPLE;

	if (pf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT)
		netdev->priv_flags |= IFF_UNICAST_FLT;

	/* Support TSO on tag interface */
	netdev->vlan_features |= netdev->features;
	netdev->hw_features  |= NETIF_F_HW_VLAN_CTAG_TX |
				NETIF_F_HW_VLAN_STAG_TX;
	if (pf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX |
				       NETIF_F_HW_VLAN_STAG_RX;
	netdev->features |= netdev->hw_features;

	/* HW supports tc offload but mutually exclusive with n-tuple filters */
	if (pf->flags & OTX2_FLAG_TC_FLOWER_SUPPORT)
		netdev->hw_features |= NETIF_F_HW_TC;

	netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL;

	netif_set_tso_max_segs(netdev, OTX2_MAX_GSO_SEGS);
	netdev->watchdog_timeo = OTX2_TX_TIMEOUT;

	netdev->netdev_ops = &otx2_netdev_ops;
	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;

	netdev->min_mtu = OTX2_MIN_MTU;
	netdev->max_mtu = otx2_get_max_mtu(pf);

	err = register_netdev(netdev);
	if (err) {
		dev_err(dev, "Failed to register netdevice\n");
		goto err_mcs_free;
	}

	err = otx2_wq_init(pf);
	if (err)
		goto err_unreg_netdev;

	otx2_set_ethtool_ops(netdev);

	err = otx2_init_tc(pf);
	if (err)
		goto err_mcam_flow_del;

	err = otx2_register_dl(pf);
	if (err)
		goto err_mcam_flow_del;

	/* Initialize SR-IOV resources */
	err = otx2_sriov_vfcfg_init(pf);
	if (err)
		goto err_pf_sriov_init;

	/* Enable link notifications */
	otx2_cgx_config_linkevents(pf, true);

#ifdef CONFIG_DCB
	err = otx2_dcbnl_set_ops(netdev);
	if (err)
		goto err_pf_sriov_init;
#endif

	otx2_qos_init(pf, qos_txqs);

	return 0;

err_pf_sriov_init:
	otx2_shutdown_tc(pf);
err_mcam_flow_del:
	otx2_mcam_flow_del(pf);
err_unreg_netdev:
	unregister_netdev(netdev);
err_mcs_free:
	cn10k_mcs_free(pf);
err_del_mcam_entries:
	otx2_mcam_flow_del(pf);
err_ptp_destroy:
	otx2_ptp_destroy(pf);
err_detach_rsrc:
	if (pf->hw.lmt_info)
		free_percpu(pf->hw.lmt_info);
	if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
		qmem_free(pf->dev, pf->dync_lmt);
	otx2_detach_resources(&pf->mbox);
err_disable_mbox_intr:
	otx2_disable_mbox_intr(pf);
err_mbox_destroy:
	otx2_pfaf_mbox_destroy(pf);
err_free_irq_vectors:
	pci_free_irq_vectors(hw->pdev);
err_free_netdev:
	pci_set_drvdata(pdev, NULL);
	free_netdev(netdev);
err_release_regions:
	pci_release_regions(pdev);
	return err;
}

static void otx2_vf_link_event_task(struct work_struct *work)
{
	struct otx2_vf_config *config;
	struct cgx_link_info_msg *req;
	struct mbox_msghdr *msghdr;
	struct otx2_nic *pf;
	int vf_idx;

	config = container_of(work, struct otx2_vf_config,
			      link_event_work.work);
	vf_idx = config - config->pf->vf_configs;
	pf = config->pf;

	msghdr = otx2_mbox_alloc_msg_rsp(&pf->mbox_pfvf[0].mbox_up, vf_idx,
					 sizeof(*req), sizeof(struct msg_rsp));
	if (!msghdr) {
		dev_err(pf->dev, "Failed to create VF%d link event\n", vf_idx);
		return;
	}

	req = (struct cgx_link_info_msg *)msghdr;
	req->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
	req->hdr.sig = OTX2_MBOX_REQ_SIG;
	memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info));

	otx2_sync_mbox_up_msg(&pf->mbox_pfvf[0], vf_idx);
}

static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct otx2_nic *pf = netdev_priv(netdev);
	int ret;

	/* Init PF <=> VF mailbox stuff */
	ret = otx2_pfvf_mbox_init(pf, numvfs);
	if (ret)
		return ret;

	ret = otx2_register_pfvf_mbox_intr(pf, numvfs);
	if (ret)
		goto free_mbox;

	ret = otx2_pf_flr_init(pf, numvfs);
	if (ret)
		goto free_intr;

	ret = otx2_register_flr_me_intr(pf, numvfs);
	if (ret)
		goto free_flr;

	ret = pci_enable_sriov(pdev, numvfs);
	if (ret)
		goto free_flr_intr;

	return numvfs;
free_flr_intr:
	otx2_disable_flr_me_intr(pf);
free_flr:
	otx2_flr_wq_destroy(pf);
free_intr:
	otx2_disable_pfvf_mbox_intr(pf, numvfs);
free_mbox:
	otx2_pfvf_mbox_destroy(pf);
	return ret;
}

static int otx2_sriov_disable(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct otx2_nic *pf = netdev_priv(netdev);
	int numvfs = pci_num_vf(pdev);

	if (!numvfs)
		return 0;

	pci_disable_sriov(pdev);

	otx2_disable_flr_me_intr(pf);
	otx2_flr_wq_destroy(pf);
	otx2_disable_pfvf_mbox_intr(pf, numvfs);
	otx2_pfvf_mbox_destroy(pf);

	return 0;
}

static int otx2_sriov_configure(struct pci_dev *pdev, int numvfs)
{
	if (numvfs == 0)
		return otx2_sriov_disable(pdev);
	else
		return otx2_sriov_enable(pdev, numvfs);
}

static void otx2_remove(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct otx2_nic *pf;

	if (!netdev)
		return;

	pf = netdev_priv(netdev);

	pf->flags |= OTX2_FLAG_PF_SHUTDOWN;

	if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED)
		otx2_config_hw_tx_tstamp(pf, false);
	if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED)
		otx2_config_hw_rx_tstamp(pf, false);

	/* Disable 802.3x pause frames */
	if (pf->flags & OTX2_FLAG_RX_PAUSE_ENABLED ||
	    (pf->flags & OTX2_FLAG_TX_PAUSE_ENABLED)) {
		pf->flags &= ~OTX2_FLAG_RX_PAUSE_ENABLED;
		pf->flags &= ~OTX2_FLAG_TX_PAUSE_ENABLED;
		otx2_config_pause_frm(pf);
	}

#ifdef CONFIG_DCB
	/* Disable PFC config */
	if (pf->pfc_en) {
		pf->pfc_en = 0;
		otx2_config_priority_flow_ctrl(pf);
	}
#endif
	cancel_work_sync(&pf->reset_task);
	/* Disable link notifications */
	otx2_cgx_config_linkevents(pf, false);

	otx2_unregister_dl(pf);
	unregister_netdev(netdev);
	cn10k_mcs_free(pf);
	otx2_sriov_disable(pf->pdev);
	otx2_sriov_vfcfg_cleanup(pf);
	if (pf->otx2_wq)
		destroy_workqueue(pf->otx2_wq);

	otx2_ptp_destroy(pf);
	otx2_mcam_flow_del(pf);
	otx2_shutdown_tc(pf);
	otx2_shutdown_qos(pf);
	otx2_detach_resources(&pf->mbox);
	if (pf->hw.lmt_info)
		free_percpu(pf->hw.lmt_info);
	if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
		qmem_free(pf->dev, pf->dync_lmt);
	otx2_disable_mbox_intr(pf);
	otx2_pfaf_mbox_destroy(pf);
	pci_free_irq_vectors(pf->pdev);
	pci_set_drvdata(pdev, NULL);
	free_netdev(netdev);

	pci_release_regions(pdev);
}

static struct pci_driver otx2_pf_driver = {
	.name = DRV_NAME,
	.id_table = otx2_pf_id_table,
	.probe = otx2_probe,
	.shutdown = otx2_remove,
	.remove = otx2_remove,
	.sriov_configure = otx2_sriov_configure
};

static int __init otx2_rvupf_init_module(void)
{
	pr_info("%s: %s\n", DRV_NAME, DRV_STRING);

	return pci_register_driver(&otx2_pf_driver);
}

static void __exit otx2_rvupf_cleanup_module(void)
{
	pci_unregister_driver(&otx2_pf_driver);
}

module_init(otx2_rvupf_init_module);
module_exit(otx2_rvupf_cleanup_module);