summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/sfc/farch.c
blob: c72adf8b52eac62fd31cf16f3dbae15ee1404381 (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
/****************************************************************************
 * Driver for Solarflare network controllers and boards
 * Copyright 2005-2006 Fen Systems Ltd.
 * Copyright 2006-2013 Solarflare Communications Inc.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation, incorporated herein by reference.
 */

#include <linux/bitops.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/crc32.h>
#include "net_driver.h"
#include "bitfield.h"
#include "efx.h"
#include "nic.h"
#include "farch_regs.h"
#include "sriov.h"
#include "siena_sriov.h"
#include "io.h"
#include "workarounds.h"

/* Falcon-architecture (SFC9000-family) support */

/**************************************************************************
 *
 * Configurable values
 *
 **************************************************************************
 */

/* This is set to 16 for a good reason.  In summary, if larger than
 * 16, the descriptor cache holds more than a default socket
 * buffer's worth of packets (for UDP we can only have at most one
 * socket buffer's worth outstanding).  This combined with the fact
 * that we only get 1 TX event per descriptor cache means the NIC
 * goes idle.
 */
#define TX_DC_ENTRIES 16
#define TX_DC_ENTRIES_ORDER 1

#define RX_DC_ENTRIES 64
#define RX_DC_ENTRIES_ORDER 3

/* If EFX_MAX_INT_ERRORS internal errors occur within
 * EFX_INT_ERROR_EXPIRE seconds, we consider the NIC broken and
 * disable it.
 */
#define EFX_INT_ERROR_EXPIRE 3600
#define EFX_MAX_INT_ERRORS 5

/* Depth of RX flush request fifo */
#define EFX_RX_FLUSH_COUNT 4

/* Driver generated events */
#define _EFX_CHANNEL_MAGIC_TEST		0x000101
#define _EFX_CHANNEL_MAGIC_FILL		0x000102
#define _EFX_CHANNEL_MAGIC_RX_DRAIN	0x000103
#define _EFX_CHANNEL_MAGIC_TX_DRAIN	0x000104

#define _EFX_CHANNEL_MAGIC(_code, _data)	((_code) << 8 | (_data))
#define _EFX_CHANNEL_MAGIC_CODE(_magic)		((_magic) >> 8)

#define EFX_CHANNEL_MAGIC_TEST(_channel)				\
	_EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_TEST, (_channel)->channel)
#define EFX_CHANNEL_MAGIC_FILL(_rx_queue)				\
	_EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_FILL,			\
			   efx_rx_queue_index(_rx_queue))
#define EFX_CHANNEL_MAGIC_RX_DRAIN(_rx_queue)				\
	_EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_RX_DRAIN,			\
			   efx_rx_queue_index(_rx_queue))
#define EFX_CHANNEL_MAGIC_TX_DRAIN(_tx_queue)				\
	_EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_TX_DRAIN,			\
			   (_tx_queue)->queue)

static void efx_farch_magic_event(struct efx_channel *channel, u32 magic);

/**************************************************************************
 *
 * Hardware access
 *
 **************************************************************************/

static inline void efx_write_buf_tbl(struct efx_nic *efx, efx_qword_t *value,
				     unsigned int index)
{
	efx_sram_writeq(efx, efx->membase + efx->type->buf_tbl_base,
			value, index);
}

static bool efx_masked_compare_oword(const efx_oword_t *a, const efx_oword_t *b,
				     const efx_oword_t *mask)
{
	return ((a->u64[0] ^ b->u64[0]) & mask->u64[0]) ||
		((a->u64[1] ^ b->u64[1]) & mask->u64[1]);
}

int efx_farch_test_registers(struct efx_nic *efx,
			     const struct efx_farch_register_test *regs,
			     size_t n_regs)
{
	unsigned address = 0;
	int i, j;
	efx_oword_t mask, imask, original, reg, buf;

	for (i = 0; i < n_regs; ++i) {
		address = regs[i].address;
		mask = imask = regs[i].mask;
		EFX_INVERT_OWORD(imask);

		efx_reado(efx, &original, address);

		/* bit sweep on and off */
		for (j = 0; j < 128; j++) {
			if (!EFX_EXTRACT_OWORD32(mask, j, j))
				continue;

			/* Test this testable bit can be set in isolation */
			EFX_AND_OWORD(reg, original, mask);
			EFX_SET_OWORD32(reg, j, j, 1);

			efx_writeo(efx, &reg, address);
			efx_reado(efx, &buf, address);

			if (efx_masked_compare_oword(&reg, &buf, &mask))
				goto fail;

			/* Test this testable bit can be cleared in isolation */
			EFX_OR_OWORD(reg, original, mask);
			EFX_SET_OWORD32(reg, j, j, 0);

			efx_writeo(efx, &reg, address);
			efx_reado(efx, &buf, address);

			if (efx_masked_compare_oword(&reg, &buf, &mask))
				goto fail;
		}

		efx_writeo(efx, &original, address);
	}

	return 0;

fail:
	netif_err(efx, hw, efx->net_dev,
		  "wrote "EFX_OWORD_FMT" read "EFX_OWORD_FMT
		  " at address 0x%x mask "EFX_OWORD_FMT"\n", EFX_OWORD_VAL(reg),
		  EFX_OWORD_VAL(buf), address, EFX_OWORD_VAL(mask));
	return -EIO;
}

/**************************************************************************
 *
 * Special buffer handling
 * Special buffers are used for event queues and the TX and RX
 * descriptor rings.
 *
 *************************************************************************/

/*
 * Initialise a special buffer
 *
 * This will define a buffer (previously allocated via
 * efx_alloc_special_buffer()) in the buffer table, allowing
 * it to be used for event queues, descriptor rings etc.
 */
static void
efx_init_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
{
	efx_qword_t buf_desc;
	unsigned int index;
	dma_addr_t dma_addr;
	int i;

	EFX_WARN_ON_PARANOID(!buffer->buf.addr);

	/* Write buffer descriptors to NIC */
	for (i = 0; i < buffer->entries; i++) {
		index = buffer->index + i;
		dma_addr = buffer->buf.dma_addr + (i * EFX_BUF_SIZE);
		netif_dbg(efx, probe, efx->net_dev,
			  "mapping special buffer %d at %llx\n",
			  index, (unsigned long long)dma_addr);
		EFX_POPULATE_QWORD_3(buf_desc,
				     FRF_AZ_BUF_ADR_REGION, 0,
				     FRF_AZ_BUF_ADR_FBUF, dma_addr >> 12,
				     FRF_AZ_BUF_OWNER_ID_FBUF, 0);
		efx_write_buf_tbl(efx, &buf_desc, index);
	}
}

/* Unmaps a buffer and clears the buffer table entries */
static void
efx_fini_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
{
	efx_oword_t buf_tbl_upd;
	unsigned int start = buffer->index;
	unsigned int end = (buffer->index + buffer->entries - 1);

	if (!buffer->entries)
		return;

	netif_dbg(efx, hw, efx->net_dev, "unmapping special buffers %d-%d\n",
		  buffer->index, buffer->index + buffer->entries - 1);

	EFX_POPULATE_OWORD_4(buf_tbl_upd,
			     FRF_AZ_BUF_UPD_CMD, 0,
			     FRF_AZ_BUF_CLR_CMD, 1,
			     FRF_AZ_BUF_CLR_END_ID, end,
			     FRF_AZ_BUF_CLR_START_ID, start);
	efx_writeo(efx, &buf_tbl_upd, FR_AZ_BUF_TBL_UPD);
}

/*
 * Allocate a new special buffer
 *
 * This allocates memory for a new buffer, clears it and allocates a
 * new buffer ID range.  It does not write into the buffer table.
 *
 * This call will allocate 4KB buffers, since 8KB buffers can't be
 * used for event queues and descriptor rings.
 */
static int efx_alloc_special_buffer(struct efx_nic *efx,
				    struct efx_special_buffer *buffer,
				    unsigned int len)
{
#ifdef CONFIG_SFC_SRIOV
	struct siena_nic_data *nic_data = efx->nic_data;
#endif
	len = ALIGN(len, EFX_BUF_SIZE);

	if (efx_nic_alloc_buffer(efx, &buffer->buf, len, GFP_KERNEL))
		return -ENOMEM;
	buffer->entries = len / EFX_BUF_SIZE;
	BUG_ON(buffer->buf.dma_addr & (EFX_BUF_SIZE - 1));

	/* Select new buffer ID */
	buffer->index = efx->next_buffer_table;
	efx->next_buffer_table += buffer->entries;
#ifdef CONFIG_SFC_SRIOV
	BUG_ON(efx_siena_sriov_enabled(efx) &&
	       nic_data->vf_buftbl_base < efx->next_buffer_table);
#endif

	netif_dbg(efx, probe, efx->net_dev,
		  "allocating special buffers %d-%d at %llx+%x "
		  "(virt %p phys %llx)\n", buffer->index,
		  buffer->index + buffer->entries - 1,
		  (u64)buffer->buf.dma_addr, len,
		  buffer->buf.addr, (u64)virt_to_phys(buffer->buf.addr));

	return 0;
}

static void
efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
{
	if (!buffer->buf.addr)
		return;

	netif_dbg(efx, hw, efx->net_dev,
		  "deallocating special buffers %d-%d at %llx+%x "
		  "(virt %p phys %llx)\n", buffer->index,
		  buffer->index + buffer->entries - 1,
		  (u64)buffer->buf.dma_addr, buffer->buf.len,
		  buffer->buf.addr, (u64)virt_to_phys(buffer->buf.addr));

	efx_nic_free_buffer(efx, &buffer->buf);
	buffer->entries = 0;
}

/**************************************************************************
 *
 * TX path
 *
 **************************************************************************/

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

	write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
	EFX_POPULATE_DWORD_1(reg, FRF_AZ_TX_DESC_WPTR_DWORD, write_ptr);
	efx_writed_page(tx_queue->efx, &reg,
			FR_AZ_TX_DESC_UPD_DWORD_P0, tx_queue->queue);
}

/* Write pointer and first descriptor for TX descriptor ring */
static inline void efx_farch_push_tx_desc(struct efx_tx_queue *tx_queue,
					  const efx_qword_t *txd)
{
	unsigned write_ptr;
	efx_oword_t reg;

	BUILD_BUG_ON(FRF_AZ_TX_DESC_LBN != 0);
	BUILD_BUG_ON(FR_AA_TX_DESC_UPD_KER != FR_BZ_TX_DESC_UPD_P0);

	write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
	EFX_POPULATE_OWORD_2(reg, FRF_AZ_TX_DESC_PUSH_CMD, true,
			     FRF_AZ_TX_DESC_WPTR, write_ptr);
	reg.qword[0] = *txd;
	efx_writeo_page(tx_queue->efx, &reg,
			FR_BZ_TX_DESC_UPD_P0, tx_queue->queue);
}


/* For each entry inserted into the software descriptor ring, create a
 * descriptor in the hardware TX descriptor ring (in host memory), and
 * write a doorbell.
 */
void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
{
	struct efx_tx_buffer *buffer;
	efx_qword_t *txd;
	unsigned write_ptr;
	unsigned old_write_count = tx_queue->write_count;

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

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

		EFX_WARN_ON_ONCE_PARANOID(buffer->flags & EFX_TX_BUF_OPTION);

		/* Create TX descriptor ring entry */
		BUILD_BUG_ON(EFX_TX_BUF_CONT != 1);
		EFX_POPULATE_QWORD_4(*txd,
				     FSF_AZ_TX_KER_CONT,
				     buffer->flags & EFX_TX_BUF_CONT,
				     FSF_AZ_TX_KER_BYTE_COUNT, buffer->len,
				     FSF_AZ_TX_KER_BUF_REGION, 0,
				     FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr);
	} while (tx_queue->write_count != tx_queue->insert_count);

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

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

unsigned int efx_farch_tx_limit_len(struct efx_tx_queue *tx_queue,
				    dma_addr_t dma_addr, unsigned int len)
{
	/* Don't cross 4K boundaries with descriptors. */
	unsigned int limit = (~dma_addr & (EFX_PAGE_SIZE - 1)) + 1;

	len = min(limit, len);

	return len;
}


/* Allocate hardware resources for a TX queue */
int efx_farch_tx_probe(struct efx_tx_queue *tx_queue)
{
	struct efx_nic *efx = tx_queue->efx;
	unsigned entries;

	entries = tx_queue->ptr_mask + 1;
	return efx_alloc_special_buffer(efx, &tx_queue->txd,
					entries * sizeof(efx_qword_t));
}

void efx_farch_tx_init(struct efx_tx_queue *tx_queue)
{
	int csum = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
	struct efx_nic *efx = tx_queue->efx;
	efx_oword_t reg;

	/* Pin TX descriptor ring */
	efx_init_special_buffer(efx, &tx_queue->txd);

	/* Push TX descriptor ring to card */
	EFX_POPULATE_OWORD_10(reg,
			      FRF_AZ_TX_DESCQ_EN, 1,
			      FRF_AZ_TX_ISCSI_DDIG_EN, 0,
			      FRF_AZ_TX_ISCSI_HDIG_EN, 0,
			      FRF_AZ_TX_DESCQ_BUF_BASE_ID, tx_queue->txd.index,
			      FRF_AZ_TX_DESCQ_EVQ_ID,
			      tx_queue->channel->channel,
			      FRF_AZ_TX_DESCQ_OWNER_ID, 0,
			      FRF_AZ_TX_DESCQ_LABEL, tx_queue->queue,
			      FRF_AZ_TX_DESCQ_SIZE,
			      __ffs(tx_queue->txd.entries),
			      FRF_AZ_TX_DESCQ_TYPE, 0,
			      FRF_BZ_TX_NON_IP_DROP_DIS, 1);

	EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_IP_CHKSM_DIS, !csum);
	EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_TCP_CHKSM_DIS, !csum);

	efx_writeo_table(efx, &reg, efx->type->txd_ptr_tbl_base,
			 tx_queue->queue);

	EFX_POPULATE_OWORD_1(reg,
			     FRF_BZ_TX_PACE,
			     (tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI) ?
			     FFE_BZ_TX_PACE_OFF :
			     FFE_BZ_TX_PACE_RESERVED);
	efx_writeo_table(efx, &reg, FR_BZ_TX_PACE_TBL, tx_queue->queue);
}

static void efx_farch_flush_tx_queue(struct efx_tx_queue *tx_queue)
{
	struct efx_nic *efx = tx_queue->efx;
	efx_oword_t tx_flush_descq;

	WARN_ON(atomic_read(&tx_queue->flush_outstanding));
	atomic_set(&tx_queue->flush_outstanding, 1);

	EFX_POPULATE_OWORD_2(tx_flush_descq,
			     FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
			     FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue);
	efx_writeo(efx, &tx_flush_descq, FR_AZ_TX_FLUSH_DESCQ);
}

void efx_farch_tx_fini(struct efx_tx_queue *tx_queue)
{
	struct efx_nic *efx = tx_queue->efx;
	efx_oword_t tx_desc_ptr;

	/* Remove TX descriptor ring from card */
	EFX_ZERO_OWORD(tx_desc_ptr);
	efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base,
			 tx_queue->queue);

	/* Unpin TX descriptor ring */
	efx_fini_special_buffer(efx, &tx_queue->txd);
}

/* Free buffers backing TX queue */
void efx_farch_tx_remove(struct efx_tx_queue *tx_queue)
{
	efx_free_special_buffer(tx_queue->efx, &tx_queue->txd);
}

/**************************************************************************
 *
 * RX path
 *
 **************************************************************************/

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

	rxd = efx_rx_desc(rx_queue, index);
	rx_buf = efx_rx_buffer(rx_queue, index);
	EFX_POPULATE_QWORD_3(*rxd,
			     FSF_AZ_RX_KER_BUF_SIZE,
			     rx_buf->len -
			     rx_queue->efx->type->rx_buffer_padding,
			     FSF_AZ_RX_KER_BUF_REGION, 0,
			     FSF_AZ_RX_KER_BUF_ADDR, rx_buf->dma_addr);
}

/* This writes to the RX_DESC_WPTR register for the specified receive
 * descriptor ring.
 */
void efx_farch_rx_write(struct efx_rx_queue *rx_queue)
{
	struct efx_nic *efx = rx_queue->efx;
	efx_dword_t reg;
	unsigned write_ptr;

	while (rx_queue->notified_count != rx_queue->added_count) {
		efx_farch_build_rx_desc(
			rx_queue,
			rx_queue->notified_count & rx_queue->ptr_mask);
		++rx_queue->notified_count;
	}

	wmb();
	write_ptr = rx_queue->added_count & rx_queue->ptr_mask;
	EFX_POPULATE_DWORD_1(reg, FRF_AZ_RX_DESC_WPTR_DWORD, write_ptr);
	efx_writed_page(efx, &reg, FR_AZ_RX_DESC_UPD_DWORD_P0,
			efx_rx_queue_index(rx_queue));
}

int efx_farch_rx_probe(struct efx_rx_queue *rx_queue)
{
	struct efx_nic *efx = rx_queue->efx;
	unsigned entries;

	entries = rx_queue->ptr_mask + 1;
	return efx_alloc_special_buffer(efx, &rx_queue->rxd,
					entries * sizeof(efx_qword_t));
}

void efx_farch_rx_init(struct efx_rx_queue *rx_queue)
{
	efx_oword_t rx_desc_ptr;
	struct efx_nic *efx = rx_queue->efx;
	bool jumbo_en;

	/* For kernel-mode queues in Siena, the JUMBO flag enables scatter. */
	jumbo_en = efx->rx_scatter;

	netif_dbg(efx, hw, efx->net_dev,
		  "RX queue %d ring in special buffers %d-%d\n",
		  efx_rx_queue_index(rx_queue), rx_queue->rxd.index,
		  rx_queue->rxd.index + rx_queue->rxd.entries - 1);

	rx_queue->scatter_n = 0;

	/* Pin RX descriptor ring */
	efx_init_special_buffer(efx, &rx_queue->rxd);

	/* Push RX descriptor ring to card */
	EFX_POPULATE_OWORD_10(rx_desc_ptr,
			      FRF_AZ_RX_ISCSI_DDIG_EN, true,
			      FRF_AZ_RX_ISCSI_HDIG_EN, true,
			      FRF_AZ_RX_DESCQ_BUF_BASE_ID, rx_queue->rxd.index,
			      FRF_AZ_RX_DESCQ_EVQ_ID,
			      efx_rx_queue_channel(rx_queue)->channel,
			      FRF_AZ_RX_DESCQ_OWNER_ID, 0,
			      FRF_AZ_RX_DESCQ_LABEL,
			      efx_rx_queue_index(rx_queue),
			      FRF_AZ_RX_DESCQ_SIZE,
			      __ffs(rx_queue->rxd.entries),
			      FRF_AZ_RX_DESCQ_TYPE, 0 /* kernel queue */ ,
			      FRF_AZ_RX_DESCQ_JUMBO, jumbo_en,
			      FRF_AZ_RX_DESCQ_EN, 1);
	efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
			 efx_rx_queue_index(rx_queue));
}

static void efx_farch_flush_rx_queue(struct efx_rx_queue *rx_queue)
{
	struct efx_nic *efx = rx_queue->efx;
	efx_oword_t rx_flush_descq;

	EFX_POPULATE_OWORD_2(rx_flush_descq,
			     FRF_AZ_RX_FLUSH_DESCQ_CMD, 1,
			     FRF_AZ_RX_FLUSH_DESCQ,
			     efx_rx_queue_index(rx_queue));
	efx_writeo(efx, &rx_flush_descq, FR_AZ_RX_FLUSH_DESCQ);
}

void efx_farch_rx_fini(struct efx_rx_queue *rx_queue)
{
	efx_oword_t rx_desc_ptr;
	struct efx_nic *efx = rx_queue->efx;

	/* Remove RX descriptor ring from card */
	EFX_ZERO_OWORD(rx_desc_ptr);
	efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
			 efx_rx_queue_index(rx_queue));

	/* Unpin RX descriptor ring */
	efx_fini_special_buffer(efx, &rx_queue->rxd);
}

/* Free buffers backing RX queue */
void efx_farch_rx_remove(struct efx_rx_queue *rx_queue)
{
	efx_free_special_buffer(rx_queue->efx, &rx_queue->rxd);
}

/**************************************************************************
 *
 * Flush handling
 *
 **************************************************************************/

/* efx_farch_flush_queues() must be woken up when all flushes are completed,
 * or more RX flushes can be kicked off.
 */
static bool efx_farch_flush_wake(struct efx_nic *efx)
{
	/* Ensure that all updates are visible to efx_farch_flush_queues() */
	smp_mb();

	return (atomic_read(&efx->active_queues) == 0 ||
		(atomic_read(&efx->rxq_flush_outstanding) < EFX_RX_FLUSH_COUNT
		 && atomic_read(&efx->rxq_flush_pending) > 0));
}

static bool efx_check_tx_flush_complete(struct efx_nic *efx)
{
	bool i = true;
	efx_oword_t txd_ptr_tbl;
	struct efx_channel *channel;
	struct efx_tx_queue *tx_queue;

	efx_for_each_channel(channel, efx) {
		efx_for_each_channel_tx_queue(tx_queue, channel) {
			efx_reado_table(efx, &txd_ptr_tbl,
					FR_BZ_TX_DESC_PTR_TBL, tx_queue->queue);
			if (EFX_OWORD_FIELD(txd_ptr_tbl,
					    FRF_AZ_TX_DESCQ_FLUSH) ||
			    EFX_OWORD_FIELD(txd_ptr_tbl,
					    FRF_AZ_TX_DESCQ_EN)) {
				netif_dbg(efx, hw, efx->net_dev,
					  "flush did not complete on TXQ %d\n",
					  tx_queue->queue);
				i = false;
			} else if (atomic_cmpxchg(&tx_queue->flush_outstanding,
						  1, 0)) {
				/* The flush is complete, but we didn't
				 * receive a flush completion event
				 */
				netif_dbg(efx, hw, efx->net_dev,
					  "flush complete on TXQ %d, so drain "
					  "the queue\n", tx_queue->queue);
				/* Don't need to increment active_queues as it
				 * has already been incremented for the queues
				 * which did not drain
				 */
				efx_farch_magic_event(channel,
						      EFX_CHANNEL_MAGIC_TX_DRAIN(
							      tx_queue));
			}
		}
	}

	return i;
}

/* Flush all the transmit queues, and continue flushing receive queues until
 * they're all flushed. Wait for the DRAIN events to be received so that there
 * are no more RX and TX events left on any channel. */
static int efx_farch_do_flush(struct efx_nic *efx)
{
	unsigned timeout = msecs_to_jiffies(5000); /* 5s for all flushes and drains */
	struct efx_channel *channel;
	struct efx_rx_queue *rx_queue;
	struct efx_tx_queue *tx_queue;
	int rc = 0;

	efx_for_each_channel(channel, efx) {
		efx_for_each_channel_tx_queue(tx_queue, channel) {
			efx_farch_flush_tx_queue(tx_queue);
		}
		efx_for_each_channel_rx_queue(rx_queue, channel) {
			rx_queue->flush_pending = true;
			atomic_inc(&efx->rxq_flush_pending);
		}
	}

	while (timeout && atomic_read(&efx->active_queues) > 0) {
		/* If SRIOV is enabled, then offload receive queue flushing to
		 * the firmware (though we will still have to poll for
		 * completion). If that fails, fall back to the old scheme.
		 */
		if (efx_siena_sriov_enabled(efx)) {
			rc = efx_mcdi_flush_rxqs(efx);
			if (!rc)
				goto wait;
		}

		/* The hardware supports four concurrent rx flushes, each of
		 * which may need to be retried if there is an outstanding
		 * descriptor fetch
		 */
		efx_for_each_channel(channel, efx) {
			efx_for_each_channel_rx_queue(rx_queue, channel) {
				if (atomic_read(&efx->rxq_flush_outstanding) >=
				    EFX_RX_FLUSH_COUNT)
					break;

				if (rx_queue->flush_pending) {
					rx_queue->flush_pending = false;
					atomic_dec(&efx->rxq_flush_pending);
					atomic_inc(&efx->rxq_flush_outstanding);
					efx_farch_flush_rx_queue(rx_queue);
				}
			}
		}

	wait:
		timeout = wait_event_timeout(efx->flush_wq,
					     efx_farch_flush_wake(efx),
					     timeout);
	}

	if (atomic_read(&efx->active_queues) &&
	    !efx_check_tx_flush_complete(efx)) {
		netif_err(efx, hw, efx->net_dev, "failed to flush %d queues "
			  "(rx %d+%d)\n", atomic_read(&efx->active_queues),
			  atomic_read(&efx->rxq_flush_outstanding),
			  atomic_read(&efx->rxq_flush_pending));
		rc = -ETIMEDOUT;

		atomic_set(&efx->active_queues, 0);
		atomic_set(&efx->rxq_flush_pending, 0);
		atomic_set(&efx->rxq_flush_outstanding, 0);
	}

	return rc;
}

int efx_farch_fini_dmaq(struct efx_nic *efx)
{
	struct efx_channel *channel;
	struct efx_tx_queue *tx_queue;
	struct efx_rx_queue *rx_queue;
	int rc = 0;

	/* Do not attempt to write to the NIC during EEH recovery */
	if (efx->state != STATE_RECOVERY) {
		/* Only perform flush if DMA is enabled */
		if (efx->pci_dev->is_busmaster) {
			efx->type->prepare_flush(efx);
			rc = efx_farch_do_flush(efx);
			efx->type->finish_flush(efx);
		}

		efx_for_each_channel(channel, efx) {
			efx_for_each_channel_rx_queue(rx_queue, channel)
				efx_farch_rx_fini(rx_queue);
			efx_for_each_channel_tx_queue(tx_queue, channel)
				efx_farch_tx_fini(tx_queue);
		}
	}

	return rc;
}

/* Reset queue and flush accounting after FLR
 *
 * One possible cause of FLR recovery is that DMA may be failing (eg. if bus
 * mastering was disabled), in which case we don't receive (RXQ) flush
 * completion events.  This means that efx->rxq_flush_outstanding remained at 4
 * after the FLR; also, efx->active_queues was non-zero (as no flush completion
 * events were received, and we didn't go through efx_check_tx_flush_complete())
 * If we don't fix this up, on the next call to efx_realloc_channels() we won't
 * flush any RX queues because efx->rxq_flush_outstanding is at the limit of 4
 * for batched flush requests; and the efx->active_queues gets messed up because
 * we keep incrementing for the newly initialised queues, but it never went to
 * zero previously.  Then we get a timeout every time we try to restart the
 * queues, as it doesn't go back to zero when we should be flushing the queues.
 */
void efx_farch_finish_flr(struct efx_nic *efx)
{
	atomic_set(&efx->rxq_flush_pending, 0);
	atomic_set(&efx->rxq_flush_outstanding, 0);
	atomic_set(&efx->active_queues, 0);
}


/**************************************************************************
 *
 * Event queue processing
 * Event queues are processed by per-channel tasklets.
 *
 **************************************************************************/

/* Update a channel's event queue's read pointer (RPTR) register
 *
 * This writes the EVQ_RPTR_REG register for the specified channel's
 * event queue.
 */
void efx_farch_ev_read_ack(struct efx_channel *channel)
{
	efx_dword_t reg;
	struct efx_nic *efx = channel->efx;

	EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR,
			     channel->eventq_read_ptr & channel->eventq_mask);

	/* For Falcon A1, EVQ_RPTR_KER is documented as having a step size
	 * of 4 bytes, but it is really 16 bytes just like later revisions.
	 */
	efx_writed(efx, &reg,
		   efx->type->evq_rptr_tbl_base +
		   FR_BZ_EVQ_RPTR_STEP * channel->channel);
}

/* Use HW to insert a SW defined event */
void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq,
			      efx_qword_t *event)
{
	efx_oword_t drv_ev_reg;

	BUILD_BUG_ON(FRF_AZ_DRV_EV_DATA_LBN != 0 ||
		     FRF_AZ_DRV_EV_DATA_WIDTH != 64);
	drv_ev_reg.u32[0] = event->u32[0];
	drv_ev_reg.u32[1] = event->u32[1];
	drv_ev_reg.u32[2] = 0;
	drv_ev_reg.u32[3] = 0;
	EFX_SET_OWORD_FIELD(drv_ev_reg, FRF_AZ_DRV_EV_QID, evq);
	efx_writeo(efx, &drv_ev_reg, FR_AZ_DRV_EV);
}

static void efx_farch_magic_event(struct efx_channel *channel, u32 magic)
{
	efx_qword_t event;

	EFX_POPULATE_QWORD_2(event, FSF_AZ_EV_CODE,
			     FSE_AZ_EV_CODE_DRV_GEN_EV,
			     FSF_AZ_DRV_GEN_EV_MAGIC, magic);
	efx_farch_generate_event(channel->efx, channel->channel, &event);
}

/* Handle a transmit completion event
 *
 * The NIC batches TX completion events; the message we receive is of
 * the form "complete all TX events up to this index".
 */
static void
efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
{
	unsigned int tx_ev_desc_ptr;
	unsigned int tx_ev_q_label;
	struct efx_tx_queue *tx_queue;
	struct efx_nic *efx = channel->efx;

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

	if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) {
		/* Transmit completion */
		tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR);
		tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
		tx_queue = efx_channel_get_tx_queue(
			channel, tx_ev_q_label % EFX_TXQ_TYPES);
		efx_xmit_done(tx_queue, tx_ev_desc_ptr);
	} else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) {
		/* Rewrite the FIFO write pointer */
		tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
		tx_queue = efx_channel_get_tx_queue(
			channel, tx_ev_q_label % EFX_TXQ_TYPES);

		netif_tx_lock(efx->net_dev);
		efx_farch_notify_tx_desc(tx_queue);
		netif_tx_unlock(efx->net_dev);
	} else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_PKT_ERR)) {
		efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
	} else {
		netif_err(efx, tx_err, efx->net_dev,
			  "channel %d unexpected TX event "
			  EFX_QWORD_FMT"\n", channel->channel,
			  EFX_QWORD_VAL(*event));
	}
}

/* Detect errors included in the rx_evt_pkt_ok bit. */
static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
				      const efx_qword_t *event)
{
	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
	struct efx_nic *efx = rx_queue->efx;
	bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err;
	bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err;
	bool rx_ev_frm_trunc, rx_ev_tobe_disc;
	bool rx_ev_other_err, rx_ev_pause_frm;
	bool rx_ev_hdr_type, rx_ev_mcast_pkt;
	unsigned rx_ev_pkt_type;

	rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
	rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
	rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC);
	rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE);
	rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event,
						 FSF_AZ_RX_EV_BUF_OWNER_ID_ERR);
	rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event,
						  FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR);
	rx_ev_tcp_udp_chksum_err = EFX_QWORD_FIELD(*event,
						   FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR);
	rx_ev_eth_crc_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_ETH_CRC_ERR);
	rx_ev_frm_trunc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_FRM_TRUNC);
	rx_ev_pause_frm = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR);

	/* Every error apart from tobe_disc and pause_frm */
	rx_ev_other_err = (rx_ev_tcp_udp_chksum_err |
			   rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
			   rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);

	/* Count errors that are not in MAC stats.  Ignore expected
	 * checksum errors during self-test. */
	if (rx_ev_frm_trunc)
		++channel->n_rx_frm_trunc;
	else if (rx_ev_tobe_disc)
		++channel->n_rx_tobe_disc;
	else if (!efx->loopback_selftest) {
		if (rx_ev_ip_hdr_chksum_err)
			++channel->n_rx_ip_hdr_chksum_err;
		else if (rx_ev_tcp_udp_chksum_err)
			++channel->n_rx_tcp_udp_chksum_err;
	}

	/* TOBE_DISC is expected on unicast mismatches; don't print out an
	 * error message.  FRM_TRUNC indicates RXDP dropped the packet due
	 * to a FIFO overflow.
	 */
#ifdef DEBUG
	if (rx_ev_other_err && net_ratelimit()) {
		netif_dbg(efx, rx_err, efx->net_dev,
			  " RX queue %d unexpected RX event "
			  EFX_QWORD_FMT "%s%s%s%s%s%s%s\n",
			  efx_rx_queue_index(rx_queue), EFX_QWORD_VAL(*event),
			  rx_ev_buf_owner_id_err ? " [OWNER_ID_ERR]" : "",
			  rx_ev_ip_hdr_chksum_err ?
			  " [IP_HDR_CHKSUM_ERR]" : "",
			  rx_ev_tcp_udp_chksum_err ?
			  " [TCP_UDP_CHKSUM_ERR]" : "",
			  rx_ev_eth_crc_err ? " [ETH_CRC_ERR]" : "",
			  rx_ev_frm_trunc ? " [FRM_TRUNC]" : "",
			  rx_ev_tobe_disc ? " [TOBE_DISC]" : "",
			  rx_ev_pause_frm ? " [PAUSE]" : "");
	}
#endif

	if (efx->net_dev->features & NETIF_F_RXALL)
		/* don't discard frame for CRC error */
		rx_ev_eth_crc_err = false;

	/* The frame must be discarded if any of these are true. */
	return (rx_ev_eth_crc_err | rx_ev_frm_trunc |
		rx_ev_tobe_disc | rx_ev_pause_frm) ?
		EFX_RX_PKT_DISCARD : 0;
}

/* Handle receive events that are not in-order. Return true if this
 * can be handled as a partial packet discard, false if it's more
 * serious.
 */
static bool
efx_farch_handle_rx_bad_index(struct efx_rx_queue *rx_queue, unsigned index)
{
	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
	struct efx_nic *efx = rx_queue->efx;
	unsigned expected, dropped;

	if (rx_queue->scatter_n &&
	    index == ((rx_queue->removed_count + rx_queue->scatter_n - 1) &
		      rx_queue->ptr_mask)) {
		++channel->n_rx_nodesc_trunc;
		return true;
	}

	expected = rx_queue->removed_count & rx_queue->ptr_mask;
	dropped = (index - expected) & rx_queue->ptr_mask;
	netif_info(efx, rx_err, efx->net_dev,
		   "dropped %d events (index=%d expected=%d)\n",
		   dropped, index, expected);

	efx_schedule_reset(efx, RESET_TYPE_DISABLE);
	return false;
}

/* Handle a packet received event
 *
 * The NIC gives a "discard" flag if it's a unicast packet with the
 * wrong destination address
 * Also "is multicast" and "matches multicast filter" flags can be used to
 * discard non-matching multicast packets.
 */
static void
efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
{
	unsigned int rx_ev_desc_ptr, rx_ev_byte_cnt;
	unsigned int rx_ev_hdr_type, rx_ev_mcast_pkt;
	unsigned expected_ptr;
	bool rx_ev_pkt_ok, rx_ev_sop, rx_ev_cont;
	u16 flags;
	struct efx_rx_queue *rx_queue;
	struct efx_nic *efx = channel->efx;

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

	rx_ev_cont = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT);
	rx_ev_sop = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_SOP);
	WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_Q_LABEL) !=
		channel->channel);

	rx_queue = efx_channel_get_rx_queue(channel);

	rx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_DESC_PTR);
	expected_ptr = ((rx_queue->removed_count + rx_queue->scatter_n) &
			rx_queue->ptr_mask);

	/* Check for partial drops and other errors */
	if (unlikely(rx_ev_desc_ptr != expected_ptr) ||
	    unlikely(rx_ev_sop != (rx_queue->scatter_n == 0))) {
		if (rx_ev_desc_ptr != expected_ptr &&
		    !efx_farch_handle_rx_bad_index(rx_queue, rx_ev_desc_ptr))
			return;

		/* Discard all pending fragments */
		if (rx_queue->scatter_n) {
			efx_rx_packet(
				rx_queue,
				rx_queue->removed_count & rx_queue->ptr_mask,
				rx_queue->scatter_n, 0, EFX_RX_PKT_DISCARD);
			rx_queue->removed_count += rx_queue->scatter_n;
			rx_queue->scatter_n = 0;
		}

		/* Return if there is no new fragment */
		if (rx_ev_desc_ptr != expected_ptr)
			return;

		/* Discard new fragment if not SOP */
		if (!rx_ev_sop) {
			efx_rx_packet(
				rx_queue,
				rx_queue->removed_count & rx_queue->ptr_mask,
				1, 0, EFX_RX_PKT_DISCARD);
			++rx_queue->removed_count;
			return;
		}
	}

	++rx_queue->scatter_n;
	if (rx_ev_cont)
		return;

	rx_ev_byte_cnt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BYTE_CNT);
	rx_ev_pkt_ok = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_OK);
	rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);

	if (likely(rx_ev_pkt_ok)) {
		/* If packet is marked as OK then we can rely on the
		 * hardware checksum and classification.
		 */
		flags = 0;
		switch (rx_ev_hdr_type) {
		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP:
			flags |= EFX_RX_PKT_TCP;
			/* fall through */
		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP:
			flags |= EFX_RX_PKT_CSUMMED;
			/* fall through */
		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
		case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
			break;
		}
	} else {
		flags = efx_farch_handle_rx_not_ok(rx_queue, event);
	}

	/* Detect multicast packets that didn't match the filter */
	rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
	if (rx_ev_mcast_pkt) {
		unsigned int rx_ev_mcast_hash_match =
			EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_HASH_MATCH);

		if (unlikely(!rx_ev_mcast_hash_match)) {
			++channel->n_rx_mcast_mismatch;
			flags |= EFX_RX_PKT_DISCARD;
		}
	}

	channel->irq_mod_score += 2;

	/* Handle received packet */
	efx_rx_packet(rx_queue,
		      rx_queue->removed_count & rx_queue->ptr_mask,
		      rx_queue->scatter_n, rx_ev_byte_cnt, flags);
	rx_queue->removed_count += rx_queue->scatter_n;
	rx_queue->scatter_n = 0;
}

/* If this flush done event corresponds to a &struct efx_tx_queue, then
 * send an %EFX_CHANNEL_MAGIC_TX_DRAIN event to drain the event queue
 * of all transmit completions.
 */
static void
efx_farch_handle_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
{
	struct efx_tx_queue *tx_queue;
	int qid;

	qid = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);
	if (qid < EFX_TXQ_TYPES * (efx->n_tx_channels + efx->n_extra_tx_channels)) {
		tx_queue = efx_get_tx_queue(efx, qid / EFX_TXQ_TYPES,
					    qid % EFX_TXQ_TYPES);
		if (atomic_cmpxchg(&tx_queue->flush_outstanding, 1, 0)) {
			efx_farch_magic_event(tx_queue->channel,
					      EFX_CHANNEL_MAGIC_TX_DRAIN(tx_queue));
		}
	}
}

/* If this flush done event corresponds to a &struct efx_rx_queue: If the flush
 * was successful then send an %EFX_CHANNEL_MAGIC_RX_DRAIN, otherwise add
 * the RX queue back to the mask of RX queues in need of flushing.
 */
static void
efx_farch_handle_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
{
	struct efx_channel *channel;
	struct efx_rx_queue *rx_queue;
	int qid;
	bool failed;

	qid = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
	failed = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
	if (qid >= efx->n_channels)
		return;
	channel = efx_get_channel(efx, qid);
	if (!efx_channel_has_rx_queue(channel))
		return;
	rx_queue = efx_channel_get_rx_queue(channel);

	if (failed) {
		netif_info(efx, hw, efx->net_dev,
			   "RXQ %d flush retry\n", qid);
		rx_queue->flush_pending = true;
		atomic_inc(&efx->rxq_flush_pending);
	} else {
		efx_farch_magic_event(efx_rx_queue_channel(rx_queue),
				      EFX_CHANNEL_MAGIC_RX_DRAIN(rx_queue));
	}
	atomic_dec(&efx->rxq_flush_outstanding);
	if (efx_farch_flush_wake(efx))
		wake_up(&efx->flush_wq);
}

static void
efx_farch_handle_drain_event(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;

	WARN_ON(atomic_read(&efx->active_queues) == 0);
	atomic_dec(&efx->active_queues);
	if (efx_farch_flush_wake(efx))
		wake_up(&efx->flush_wq);
}

static void efx_farch_handle_generated_event(struct efx_channel *channel,
					     efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	struct efx_rx_queue *rx_queue =
		efx_channel_has_rx_queue(channel) ?
		efx_channel_get_rx_queue(channel) : NULL;
	unsigned magic, code;

	magic = EFX_QWORD_FIELD(*event, FSF_AZ_DRV_GEN_EV_MAGIC);
	code = _EFX_CHANNEL_MAGIC_CODE(magic);

	if (magic == EFX_CHANNEL_MAGIC_TEST(channel)) {
		channel->event_test_cpu = raw_smp_processor_id();
	} else if (rx_queue && magic == EFX_CHANNEL_MAGIC_FILL(rx_queue)) {
		/* The queue must be empty, so we won't receive any rx
		 * events, so efx_process_channel() won't refill the
		 * queue. Refill it here */
		efx_fast_push_rx_descriptors(rx_queue, true);
	} else if (rx_queue && magic == EFX_CHANNEL_MAGIC_RX_DRAIN(rx_queue)) {
		efx_farch_handle_drain_event(channel);
	} else if (code == _EFX_CHANNEL_MAGIC_TX_DRAIN) {
		efx_farch_handle_drain_event(channel);
	} else {
		netif_dbg(efx, hw, efx->net_dev, "channel %d received "
			  "generated event "EFX_QWORD_FMT"\n",
			  channel->channel, EFX_QWORD_VAL(*event));
	}
}

static void
efx_farch_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
{
	struct efx_nic *efx = channel->efx;
	unsigned int ev_sub_code;
	unsigned int ev_sub_data;

	ev_sub_code = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBCODE);
	ev_sub_data = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);

	switch (ev_sub_code) {
	case FSE_AZ_TX_DESCQ_FLS_DONE_EV:
		netif_vdbg(efx, hw, efx->net_dev, "channel %d TXQ %d flushed\n",
			   channel->channel, ev_sub_data);
		efx_farch_handle_tx_flush_done(efx, event);
#ifdef CONFIG_SFC_SRIOV
		efx_siena_sriov_tx_flush_done(efx, event);
#endif
		break;
	case FSE_AZ_RX_DESCQ_FLS_DONE_EV:
		netif_vdbg(efx, hw, efx->net_dev, "channel %d RXQ %d flushed\n",
			   channel->channel, ev_sub_data);
		efx_farch_handle_rx_flush_done(efx, event);
#ifdef CONFIG_SFC_SRIOV
		efx_siena_sriov_rx_flush_done(efx, event);
#endif
		break;
	case FSE_AZ_EVQ_INIT_DONE_EV:
		netif_dbg(efx, hw, efx->net_dev,
			  "channel %d EVQ %d initialised\n",
			  channel->channel, ev_sub_data);
		break;
	case FSE_AZ_SRM_UPD_DONE_EV:
		netif_vdbg(efx, hw, efx->net_dev,
			   "channel %d SRAM update done\n", channel->channel);
		break;
	case FSE_AZ_WAKE_UP_EV:
		netif_vdbg(efx, hw, efx->net_dev,
			   "channel %d RXQ %d wakeup event\n",
			   channel->channel, ev_sub_data);
		break;
	case FSE_AZ_TIMER_EV:
		netif_vdbg(efx, hw, efx->net_dev,
			   "channel %d RX queue %d timer expired\n",
			   channel->channel, ev_sub_data);
		break;
	case FSE_AA_RX_RECOVER_EV:
		netif_err(efx, rx_err, efx->net_dev,
			  "channel %d seen DRIVER RX_RESET event. "
			"Resetting.\n", channel->channel);
		atomic_inc(&efx->rx_reset);
		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
		break;
	case FSE_BZ_RX_DSC_ERROR_EV:
		if (ev_sub_data < EFX_VI_BASE) {
			netif_err(efx, rx_err, efx->net_dev,
				  "RX DMA Q %d reports descriptor fetch error."
				  " RX Q %d is disabled.\n", ev_sub_data,
				  ev_sub_data);
			efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
		}
#ifdef CONFIG_SFC_SRIOV
		else
			efx_siena_sriov_desc_fetch_err(efx, ev_sub_data);
#endif
		break;
	case FSE_BZ_TX_DSC_ERROR_EV:
		if (ev_sub_data < EFX_VI_BASE) {
			netif_err(efx, tx_err, efx->net_dev,
				  "TX DMA Q %d reports descriptor fetch error."
				  " TX Q %d is disabled.\n", ev_sub_data,
				  ev_sub_data);
			efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
		}
#ifdef CONFIG_SFC_SRIOV
		else
			efx_siena_sriov_desc_fetch_err(efx, ev_sub_data);
#endif
		break;
	default:
		netif_vdbg(efx, hw, efx->net_dev,
			   "channel %d unknown driver event code %d "
			   "data %04x\n", channel->channel, ev_sub_code,
			   ev_sub_data);
		break;
	}
}

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

	if (budget <= 0)
		return spent;

	read_ptr = channel->eventq_read_ptr;

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

		if (!efx_event_present(&event))
			/* End of events */
			break;

		netif_vdbg(channel->efx, intr, channel->efx->net_dev,
			   "channel %d event is "EFX_QWORD_FMT"\n",
			   channel->channel, EFX_QWORD_VAL(event));

		/* Clear this event by marking it all ones */
		EFX_SET_QWORD(*p_event);

		++read_ptr;

		ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE);

		switch (ev_code) {
		case FSE_AZ_EV_CODE_RX_EV:
			efx_farch_handle_rx_event(channel, &event);
			if (++spent == budget)
				goto out;
			break;
		case FSE_AZ_EV_CODE_TX_EV:
			efx_farch_handle_tx_event(channel, &event);
			break;
		case FSE_AZ_EV_CODE_DRV_GEN_EV:
			efx_farch_handle_generated_event(channel, &event);
			break;
		case FSE_AZ_EV_CODE_DRIVER_EV:
			efx_farch_handle_driver_event(channel, &event);
			break;
#ifdef CONFIG_SFC_SRIOV
		case FSE_CZ_EV_CODE_USER_EV:
			efx_siena_sriov_event(channel, &event);
			break;
#endif
		case FSE_CZ_EV_CODE_MCDI_EV:
			efx_mcdi_process_event(channel, &event);
			break;
		case FSE_AZ_EV_CODE_GLOBAL_EV:
			if (efx->type->handle_global_event &&
			    efx->type->handle_global_event(channel, &event))
				break;
			/* else fall through */
		default:
			netif_err(channel->efx, hw, channel->efx->net_dev,
				  "channel %d unknown event type %d (data "
				  EFX_QWORD_FMT ")\n", channel->channel,
				  ev_code, EFX_QWORD_VAL(event));
		}
	}

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

/* Allocate buffer table entries for event queue */
int efx_farch_ev_probe(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;
	unsigned entries;

	entries = channel->eventq_mask + 1;
	return efx_alloc_special_buffer(efx, &channel->eventq,
					entries * sizeof(efx_qword_t));
}

int efx_farch_ev_init(struct efx_channel *channel)
{
	efx_oword_t reg;
	struct efx_nic *efx = channel->efx;

	netif_dbg(efx, hw, efx->net_dev,
		  "channel %d event queue in special buffers %d-%d\n",
		  channel->channel, channel->eventq.index,
		  channel->eventq.index + channel->eventq.entries - 1);

	EFX_POPULATE_OWORD_3(reg,
			     FRF_CZ_TIMER_Q_EN, 1,
			     FRF_CZ_HOST_NOTIFY_MODE, 0,
			     FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
	efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);

	/* Pin event queue buffer */
	efx_init_special_buffer(efx, &channel->eventq);

	/* Fill event queue with all ones (i.e. empty events) */
	memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);

	/* Push event queue to card */
	EFX_POPULATE_OWORD_3(reg,
			     FRF_AZ_EVQ_EN, 1,
			     FRF_AZ_EVQ_SIZE, __ffs(channel->eventq.entries),
			     FRF_AZ_EVQ_BUF_BASE_ID, channel->eventq.index);
	efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
			 channel->channel);

	return 0;
}

void efx_farch_ev_fini(struct efx_channel *channel)
{
	efx_oword_t reg;
	struct efx_nic *efx = channel->efx;

	/* Remove event queue from card */
	EFX_ZERO_OWORD(reg);
	efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
			 channel->channel);
	efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);

	/* Unpin event queue */
	efx_fini_special_buffer(efx, &channel->eventq);
}

/* Free buffers backing event queue */
void efx_farch_ev_remove(struct efx_channel *channel)
{
	efx_free_special_buffer(channel->efx, &channel->eventq);
}


void efx_farch_ev_test_generate(struct efx_channel *channel)
{
	efx_farch_magic_event(channel, EFX_CHANNEL_MAGIC_TEST(channel));
}

void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue)
{
	efx_farch_magic_event(efx_rx_queue_channel(rx_queue),
			      EFX_CHANNEL_MAGIC_FILL(rx_queue));
}

/**************************************************************************
 *
 * Hardware interrupts
 * The hardware interrupt handler does very little work; all the event
 * queue processing is carried out by per-channel tasklets.
 *
 **************************************************************************/

/* Enable/disable/generate interrupts */
static inline void efx_farch_interrupts(struct efx_nic *efx,
				      bool enabled, bool force)
{
	efx_oword_t int_en_reg_ker;

	EFX_POPULATE_OWORD_3(int_en_reg_ker,
			     FRF_AZ_KER_INT_LEVE_SEL, efx->irq_level,
			     FRF_AZ_KER_INT_KER, force,
			     FRF_AZ_DRV_INT_EN_KER, enabled);
	efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER);
}

void efx_farch_irq_enable_master(struct efx_nic *efx)
{
	EFX_ZERO_OWORD(*((efx_oword_t *) efx->irq_status.addr));
	wmb(); /* Ensure interrupt vector is clear before interrupts enabled */

	efx_farch_interrupts(efx, true, false);
}

void efx_farch_irq_disable_master(struct efx_nic *efx)
{
	/* Disable interrupts */
	efx_farch_interrupts(efx, false, false);
}

/* Generate a test interrupt
 * Interrupt must already have been enabled, otherwise nasty things
 * may happen.
 */
int efx_farch_irq_test_generate(struct efx_nic *efx)
{
	efx_farch_interrupts(efx, true, true);
	return 0;
}

/* Process a fatal interrupt
 * Disable bus mastering ASAP and schedule a reset
 */
irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx)
{
	efx_oword_t *int_ker = efx->irq_status.addr;
	efx_oword_t fatal_intr;
	int error, mem_perr;

	efx_reado(efx, &fatal_intr, FR_AZ_FATAL_INTR_KER);
	error = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_FATAL_INTR);

	netif_err(efx, hw, efx->net_dev, "SYSTEM ERROR "EFX_OWORD_FMT" status "
		  EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker),
		  EFX_OWORD_VAL(fatal_intr),
		  error ? "disabling bus mastering" : "no recognised error");

	/* If this is a memory parity error dump which blocks are offending */
	mem_perr = (EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER) ||
		    EFX_OWORD_FIELD(fatal_intr, FRF_AZ_SRM_PERR_INT_KER));
	if (mem_perr) {
		efx_oword_t reg;
		efx_reado(efx, &reg, FR_AZ_MEM_STAT);
		netif_err(efx, hw, efx->net_dev,
			  "SYSTEM ERROR: memory parity error "EFX_OWORD_FMT"\n",
			  EFX_OWORD_VAL(reg));
	}

	/* Disable both devices */
	pci_clear_master(efx->pci_dev);
	efx_farch_irq_disable_master(efx);

	/* Count errors and reset or disable the NIC accordingly */
	if (efx->int_error_count == 0 ||
	    time_after(jiffies, efx->int_error_expire)) {
		efx->int_error_count = 0;
		efx->int_error_expire =
			jiffies + EFX_INT_ERROR_EXPIRE * HZ;
	}
	if (++efx->int_error_count < EFX_MAX_INT_ERRORS) {
		netif_err(efx, hw, efx->net_dev,
			  "SYSTEM ERROR - reset scheduled\n");
		efx_schedule_reset(efx, RESET_TYPE_INT_ERROR);
	} else {
		netif_err(efx, hw, efx->net_dev,
			  "SYSTEM ERROR - max number of errors seen."
			  "NIC will be disabled\n");
		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
	}

	return IRQ_HANDLED;
}

/* Handle a legacy interrupt
 * Acknowledges the interrupt and schedule event queue processing.
 */
irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id)
{
	struct efx_nic *efx = dev_id;
	bool soft_enabled = READ_ONCE(efx->irq_soft_enabled);
	efx_oword_t *int_ker = efx->irq_status.addr;
	irqreturn_t result = IRQ_NONE;
	struct efx_channel *channel;
	efx_dword_t reg;
	u32 queues;
	int syserr;

	/* Read the ISR which also ACKs the interrupts */
	efx_readd(efx, &reg, FR_BZ_INT_ISR0);
	queues = EFX_EXTRACT_DWORD(reg, 0, 31);

	/* Legacy interrupts are disabled too late by the EEH kernel
	 * code. Disable them earlier.
	 * If an EEH error occurred, the read will have returned all ones.
	 */
	if (EFX_DWORD_IS_ALL_ONES(reg) && efx_try_recovery(efx) &&
	    !efx->eeh_disabled_legacy_irq) {
		disable_irq_nosync(efx->legacy_irq);
		efx->eeh_disabled_legacy_irq = true;
	}

	/* Handle non-event-queue sources */
	if (queues & (1U << efx->irq_level) && soft_enabled) {
		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
		if (unlikely(syserr))
			return efx_farch_fatal_interrupt(efx);
		efx->last_irq_cpu = raw_smp_processor_id();
	}

	if (queues != 0) {
		efx->irq_zero_count = 0;

		/* Schedule processing of any interrupting queues */
		if (likely(soft_enabled)) {
			efx_for_each_channel(channel, efx) {
				if (queues & 1)
					efx_schedule_channel_irq(channel);
				queues >>= 1;
			}
		}
		result = IRQ_HANDLED;

	} else {
		efx_qword_t *event;

		/* Legacy ISR read can return zero once (SF bug 15783) */

		/* We can't return IRQ_HANDLED more than once on seeing ISR=0
		 * because this might be a shared interrupt. */
		if (efx->irq_zero_count++ == 0)
			result = IRQ_HANDLED;

		/* Ensure we schedule or rearm all event queues */
		if (likely(soft_enabled)) {
			efx_for_each_channel(channel, efx) {
				event = efx_event(channel,
						  channel->eventq_read_ptr);
				if (efx_event_present(event))
					efx_schedule_channel_irq(channel);
				else
					efx_farch_ev_read_ack(channel);
			}
		}
	}

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

	return result;
}

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

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

	if (!likely(READ_ONCE(efx->irq_soft_enabled)))
		return IRQ_HANDLED;

	/* Handle non-event-queue sources */
	if (context->index == efx->irq_level) {
		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
		if (unlikely(syserr))
			return efx_farch_fatal_interrupt(efx);
		efx->last_irq_cpu = raw_smp_processor_id();
	}

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

	return IRQ_HANDLED;
}

/* Setup RSS indirection table.
 * This maps from the hash value of the packet to RXQ
 */
void efx_farch_rx_push_indir_table(struct efx_nic *efx)
{
	size_t i = 0;
	efx_dword_t dword;

	BUILD_BUG_ON(ARRAY_SIZE(efx->rss_context.rx_indir_table) !=
		     FR_BZ_RX_INDIRECTION_TBL_ROWS);

	for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
		EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
				     efx->rss_context.rx_indir_table[i]);
		efx_writed(efx, &dword,
			   FR_BZ_RX_INDIRECTION_TBL +
			   FR_BZ_RX_INDIRECTION_TBL_STEP * i);
	}
}

void efx_farch_rx_pull_indir_table(struct efx_nic *efx)
{
	size_t i = 0;
	efx_dword_t dword;

	BUILD_BUG_ON(ARRAY_SIZE(efx->rss_context.rx_indir_table) !=
		     FR_BZ_RX_INDIRECTION_TBL_ROWS);

	for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
		efx_readd(efx, &dword,
			   FR_BZ_RX_INDIRECTION_TBL +
			   FR_BZ_RX_INDIRECTION_TBL_STEP * i);
		efx->rss_context.rx_indir_table[i] = EFX_DWORD_FIELD(dword, FRF_BZ_IT_QUEUE);
	}
}

/* Looks at available SRAM resources and works out how many queues we
 * can support, and where things like descriptor caches should live.
 *
 * SRAM is split up as follows:
 * 0                          buftbl entries for channels
 * efx->vf_buftbl_base        buftbl entries for SR-IOV
 * efx->rx_dc_base            RX descriptor caches
 * efx->tx_dc_base            TX descriptor caches
 */
void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
{
	unsigned vi_count, buftbl_min, total_tx_channels;

#ifdef CONFIG_SFC_SRIOV
	struct siena_nic_data *nic_data = efx->nic_data;
#endif

	total_tx_channels = efx->n_tx_channels + efx->n_extra_tx_channels;
	/* Account for the buffer table entries backing the datapath channels
	 * and the descriptor caches for those channels.
	 */
	buftbl_min = ((efx->n_rx_channels * EFX_MAX_DMAQ_SIZE +
		       total_tx_channels * EFX_TXQ_TYPES * EFX_MAX_DMAQ_SIZE +
		       efx->n_channels * EFX_MAX_EVQ_SIZE)
		      * sizeof(efx_qword_t) / EFX_BUF_SIZE);
	vi_count = max(efx->n_channels, total_tx_channels * EFX_TXQ_TYPES);

#ifdef CONFIG_SFC_SRIOV
	if (efx->type->sriov_wanted) {
		if (efx->type->sriov_wanted(efx)) {
			unsigned vi_dc_entries, buftbl_free;
			unsigned entries_per_vf, vf_limit;

			nic_data->vf_buftbl_base = buftbl_min;

			vi_dc_entries = RX_DC_ENTRIES + TX_DC_ENTRIES;
			vi_count = max(vi_count, EFX_VI_BASE);
			buftbl_free = (sram_lim_qw - buftbl_min -
				       vi_count * vi_dc_entries);

			entries_per_vf = ((vi_dc_entries +
					   EFX_VF_BUFTBL_PER_VI) *
					  efx_vf_size(efx));
			vf_limit = min(buftbl_free / entries_per_vf,
				       (1024U - EFX_VI_BASE) >> efx->vi_scale);

			if (efx->vf_count > vf_limit) {
				netif_err(efx, probe, efx->net_dev,
					  "Reducing VF count from from %d to %d\n",
					  efx->vf_count, vf_limit);
				efx->vf_count = vf_limit;
			}
			vi_count += efx->vf_count * efx_vf_size(efx);
		}
	}
#endif

	efx->tx_dc_base = sram_lim_qw - vi_count * TX_DC_ENTRIES;
	efx->rx_dc_base = efx->tx_dc_base - vi_count * RX_DC_ENTRIES;
}

u32 efx_farch_fpga_ver(struct efx_nic *efx)
{
	efx_oword_t altera_build;
	efx_reado(efx, &altera_build, FR_AZ_ALTERA_BUILD);
	return EFX_OWORD_FIELD(altera_build, FRF_AZ_ALTERA_BUILD_VER);
}

void efx_farch_init_common(struct efx_nic *efx)
{
	efx_oword_t temp;

	/* Set positions of descriptor caches in SRAM. */
	EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_TX_DC_BASE_ADR, efx->tx_dc_base);
	efx_writeo(efx, &temp, FR_AZ_SRM_TX_DC_CFG);
	EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_RX_DC_BASE_ADR, efx->rx_dc_base);
	efx_writeo(efx, &temp, FR_AZ_SRM_RX_DC_CFG);

	/* Set TX descriptor cache size. */
	BUILD_BUG_ON(TX_DC_ENTRIES != (8 << TX_DC_ENTRIES_ORDER));
	EFX_POPULATE_OWORD_1(temp, FRF_AZ_TX_DC_SIZE, TX_DC_ENTRIES_ORDER);
	efx_writeo(efx, &temp, FR_AZ_TX_DC_CFG);

	/* Set RX descriptor cache size.  Set low watermark to size-8, as
	 * this allows most efficient prefetching.
	 */
	BUILD_BUG_ON(RX_DC_ENTRIES != (8 << RX_DC_ENTRIES_ORDER));
	EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_SIZE, RX_DC_ENTRIES_ORDER);
	efx_writeo(efx, &temp, FR_AZ_RX_DC_CFG);
	EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_PF_LWM, RX_DC_ENTRIES - 8);
	efx_writeo(efx, &temp, FR_AZ_RX_DC_PF_WM);

	/* Program INT_KER address */
	EFX_POPULATE_OWORD_2(temp,
			     FRF_AZ_NORM_INT_VEC_DIS_KER,
			     EFX_INT_MODE_USE_MSI(efx),
			     FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr);
	efx_writeo(efx, &temp, FR_AZ_INT_ADR_KER);

	if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx))
		/* Use an interrupt level unused by event queues */
		efx->irq_level = 0x1f;
	else
		/* Use a valid MSI-X vector */
		efx->irq_level = 0;

	/* Enable all the genuinely fatal interrupts.  (They are still
	 * masked by the overall interrupt mask, controlled by
	 * falcon_interrupts()).
	 *
	 * Note: All other fatal interrupts are enabled
	 */
	EFX_POPULATE_OWORD_3(temp,
			     FRF_AZ_ILL_ADR_INT_KER_EN, 1,
			     FRF_AZ_RBUF_OWN_INT_KER_EN, 1,
			     FRF_AZ_TBUF_OWN_INT_KER_EN, 1);
	EFX_SET_OWORD_FIELD(temp, FRF_CZ_SRAM_PERR_INT_P_KER_EN, 1);
	EFX_INVERT_OWORD(temp);
	efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER);

	/* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be
	 * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q.
	 */
	efx_reado(efx, &temp, FR_AZ_TX_RESERVED);
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER, 0xfe);
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER_EN, 1);
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_ONE_PKT_PER_Q, 1);
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PUSH_EN, 1);
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_DIS_NON_IP_EV, 1);
	/* Enable SW_EV to inherit in char driver - assume harmless here */
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_SOFT_EVT_EN, 1);
	/* Prefetch threshold 2 => fetch when descriptor cache half empty */
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_THRESHOLD, 2);
	/* Disable hardware watchdog which can misfire */
	EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_WD_TMR, 0x3fffff);
	/* Squash TX of packets of 16 bytes or less */
	EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1);
	efx_writeo(efx, &temp, FR_AZ_TX_RESERVED);

	EFX_POPULATE_OWORD_4(temp,
			     /* Default values */
			     FRF_BZ_TX_PACE_SB_NOT_AF, 0x15,
			     FRF_BZ_TX_PACE_SB_AF, 0xb,
			     FRF_BZ_TX_PACE_FB_BASE, 0,
			     /* Allow large pace values in the fast bin. */
			     FRF_BZ_TX_PACE_BIN_TH,
			     FFE_BZ_TX_PACE_RESERVED);
	efx_writeo(efx, &temp, FR_BZ_TX_PACE);
}

/**************************************************************************
 *
 * Filter tables
 *
 **************************************************************************
 */

/* "Fudge factors" - difference between programmed value and actual depth.
 * Due to pipelined implementation we need to program H/W with a value that
 * is larger than the hop limit we want.
 */
#define EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD 3
#define EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL 1

/* Hard maximum search limit.  Hardware will time-out beyond 200-something.
 * We also need to avoid infinite loops in efx_farch_filter_search() when the
 * table is full.
 */
#define EFX_FARCH_FILTER_CTL_SRCH_MAX 200

/* Don't try very hard to find space for performance hints, as this is
 * counter-productive. */
#define EFX_FARCH_FILTER_CTL_SRCH_HINT_MAX 5

enum efx_farch_filter_type {
	EFX_FARCH_FILTER_TCP_FULL = 0,
	EFX_FARCH_FILTER_TCP_WILD,
	EFX_FARCH_FILTER_UDP_FULL,
	EFX_FARCH_FILTER_UDP_WILD,
	EFX_FARCH_FILTER_MAC_FULL = 4,
	EFX_FARCH_FILTER_MAC_WILD,
	EFX_FARCH_FILTER_UC_DEF = 8,
	EFX_FARCH_FILTER_MC_DEF,
	EFX_FARCH_FILTER_TYPE_COUNT,		/* number of specific types */
};

enum efx_farch_filter_table_id {
	EFX_FARCH_FILTER_TABLE_RX_IP = 0,
	EFX_FARCH_FILTER_TABLE_RX_MAC,
	EFX_FARCH_FILTER_TABLE_RX_DEF,
	EFX_FARCH_FILTER_TABLE_TX_MAC,
	EFX_FARCH_FILTER_TABLE_COUNT,
};

enum efx_farch_filter_index {
	EFX_FARCH_FILTER_INDEX_UC_DEF,
	EFX_FARCH_FILTER_INDEX_MC_DEF,
	EFX_FARCH_FILTER_SIZE_RX_DEF,
};

struct efx_farch_filter_spec {
	u8	type:4;
	u8	priority:4;
	u8	flags;
	u16	dmaq_id;
	u32	data[3];
};

struct efx_farch_filter_table {
	enum efx_farch_filter_table_id id;
	u32		offset;		/* address of table relative to BAR */
	unsigned	size;		/* number of entries */
	unsigned	step;		/* step between entries */
	unsigned	used;		/* number currently used */
	unsigned long	*used_bitmap;
	struct efx_farch_filter_spec *spec;
	unsigned	search_limit[EFX_FARCH_FILTER_TYPE_COUNT];
};

struct efx_farch_filter_state {
	struct rw_semaphore lock; /* Protects table contents */
	struct efx_farch_filter_table table[EFX_FARCH_FILTER_TABLE_COUNT];
};

static void
efx_farch_filter_table_clear_entry(struct efx_nic *efx,
				   struct efx_farch_filter_table *table,
				   unsigned int filter_idx);

/* The filter hash function is LFSR polynomial x^16 + x^3 + 1 of a 32-bit
 * key derived from the n-tuple.  The initial LFSR state is 0xffff. */
static u16 efx_farch_filter_hash(u32 key)
{
	u16 tmp;

	/* First 16 rounds */
	tmp = 0x1fff ^ key >> 16;
	tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
	tmp = tmp ^ tmp >> 9;
	/* Last 16 rounds */
	tmp = tmp ^ tmp << 13 ^ key;
	tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
	return tmp ^ tmp >> 9;
}

/* To allow for hash collisions, filter search continues at these
 * increments from the first possible entry selected by the hash. */
static u16 efx_farch_filter_increment(u32 key)
{
	return key * 2 - 1;
}

static enum efx_farch_filter_table_id
efx_farch_filter_spec_table_id(const struct efx_farch_filter_spec *spec)
{
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
		     (EFX_FARCH_FILTER_TCP_FULL >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
		     (EFX_FARCH_FILTER_TCP_WILD >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
		     (EFX_FARCH_FILTER_UDP_FULL >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
		     (EFX_FARCH_FILTER_UDP_WILD >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_MAC !=
		     (EFX_FARCH_FILTER_MAC_FULL >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_MAC !=
		     (EFX_FARCH_FILTER_MAC_WILD >> 2));
	BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_TX_MAC !=
		     EFX_FARCH_FILTER_TABLE_RX_MAC + 2);
	return (spec->type >> 2) + ((spec->flags & EFX_FILTER_FLAG_TX) ? 2 : 0);
}

static void efx_farch_filter_push_rx_config(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	struct efx_farch_filter_table *table;
	efx_oword_t filter_ctl;

	efx_reado(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
	EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_FULL_SRCH_LIMIT,
			    table->search_limit[EFX_FARCH_FILTER_TCP_FULL] +
			    EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
	EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_WILD_SRCH_LIMIT,
			    table->search_limit[EFX_FARCH_FILTER_TCP_WILD] +
			    EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
	EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_FULL_SRCH_LIMIT,
			    table->search_limit[EFX_FARCH_FILTER_UDP_FULL] +
			    EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
	EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_WILD_SRCH_LIMIT,
			    table->search_limit[EFX_FARCH_FILTER_UDP_WILD] +
			    EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_MAC];
	if (table->size) {
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT,
			table->search_limit[EFX_FARCH_FILTER_MAC_FULL] +
			EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT,
			table->search_limit[EFX_FARCH_FILTER_MAC_WILD] +
			EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
	}

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
	if (table->size) {
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_UNICAST_NOMATCH_Q_ID,
			table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].dmaq_id);
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_UNICAST_NOMATCH_RSS_ENABLED,
			!!(table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].flags &
			   EFX_FILTER_FLAG_RX_RSS));
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_MULTICAST_NOMATCH_Q_ID,
			table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].dmaq_id);
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED,
			!!(table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].flags &
			   EFX_FILTER_FLAG_RX_RSS));

		/* There is a single bit to enable RX scatter for all
		 * unmatched packets.  Only set it if scatter is
		 * enabled in both filter specs.
		 */
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_BZ_SCATTER_ENBL_NO_MATCH_Q,
			!!(table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].flags &
			   table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].flags &
			   EFX_FILTER_FLAG_RX_SCATTER));
	} else {
		/* We don't expose 'default' filters because unmatched
		 * packets always go to the queue number found in the
		 * RSS table.  But we still need to set the RX scatter
		 * bit here.
		 */
		EFX_SET_OWORD_FIELD(
			filter_ctl, FRF_BZ_SCATTER_ENBL_NO_MATCH_Q,
			efx->rx_scatter);
	}

	efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
}

static void efx_farch_filter_push_tx_limits(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	struct efx_farch_filter_table *table;
	efx_oword_t tx_cfg;

	efx_reado(efx, &tx_cfg, FR_AZ_TX_CFG);

	table = &state->table[EFX_FARCH_FILTER_TABLE_TX_MAC];
	if (table->size) {
		EFX_SET_OWORD_FIELD(
			tx_cfg, FRF_CZ_TX_ETH_FILTER_FULL_SEARCH_RANGE,
			table->search_limit[EFX_FARCH_FILTER_MAC_FULL] +
			EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
		EFX_SET_OWORD_FIELD(
			tx_cfg, FRF_CZ_TX_ETH_FILTER_WILD_SEARCH_RANGE,
			table->search_limit[EFX_FARCH_FILTER_MAC_WILD] +
			EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
	}

	efx_writeo(efx, &tx_cfg, FR_AZ_TX_CFG);
}

static int
efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec,
			       const struct efx_filter_spec *gen_spec)
{
	bool is_full = false;

	if ((gen_spec->flags & EFX_FILTER_FLAG_RX_RSS) && gen_spec->rss_context)
		return -EINVAL;

	spec->priority = gen_spec->priority;
	spec->flags = gen_spec->flags;
	spec->dmaq_id = gen_spec->dmaq_id;

	switch (gen_spec->match_flags) {
	case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
	      EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
	      EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT):
		is_full = true;
		/* fall through */
	case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
	      EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT): {
		__be32 rhost, host1, host2;
		__be16 rport, port1, port2;

		EFX_WARN_ON_PARANOID(!(gen_spec->flags & EFX_FILTER_FLAG_RX));

		if (gen_spec->ether_type != htons(ETH_P_IP))
			return -EPROTONOSUPPORT;
		if (gen_spec->loc_port == 0 ||
		    (is_full && gen_spec->rem_port == 0))
			return -EADDRNOTAVAIL;
		switch (gen_spec->ip_proto) {
		case IPPROTO_TCP:
			spec->type = (is_full ? EFX_FARCH_FILTER_TCP_FULL :
				      EFX_FARCH_FILTER_TCP_WILD);
			break;
		case IPPROTO_UDP:
			spec->type = (is_full ? EFX_FARCH_FILTER_UDP_FULL :
				      EFX_FARCH_FILTER_UDP_WILD);
			break;
		default:
			return -EPROTONOSUPPORT;
		}

		/* Filter is constructed in terms of source and destination,
		 * with the odd wrinkle that the ports are swapped in a UDP
		 * wildcard filter.  We need to convert from local and remote
		 * (= zero for wildcard) addresses.
		 */
		rhost = is_full ? gen_spec->rem_host[0] : 0;
		rport = is_full ? gen_spec->rem_port : 0;
		host1 = rhost;
		host2 = gen_spec->loc_host[0];
		if (!is_full && gen_spec->ip_proto == IPPROTO_UDP) {
			port1 = gen_spec->loc_port;
			port2 = rport;
		} else {
			port1 = rport;
			port2 = gen_spec->loc_port;
		}
		spec->data[0] = ntohl(host1) << 16 | ntohs(port1);
		spec->data[1] = ntohs(port2) << 16 | ntohl(host1) >> 16;
		spec->data[2] = ntohl(host2);

		break;
	}

	case EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_OUTER_VID:
		is_full = true;
		/* fall through */
	case EFX_FILTER_MATCH_LOC_MAC:
		spec->type = (is_full ? EFX_FARCH_FILTER_MAC_FULL :
			      EFX_FARCH_FILTER_MAC_WILD);
		spec->data[0] = is_full ? ntohs(gen_spec->outer_vid) : 0;
		spec->data[1] = (gen_spec->loc_mac[2] << 24 |
				 gen_spec->loc_mac[3] << 16 |
				 gen_spec->loc_mac[4] << 8 |
				 gen_spec->loc_mac[5]);
		spec->data[2] = (gen_spec->loc_mac[0] << 8 |
				 gen_spec->loc_mac[1]);
		break;

	case EFX_FILTER_MATCH_LOC_MAC_IG:
		spec->type = (is_multicast_ether_addr(gen_spec->loc_mac) ?
			      EFX_FARCH_FILTER_MC_DEF :
			      EFX_FARCH_FILTER_UC_DEF);
		memset(spec->data, 0, sizeof(spec->data)); /* ensure equality */
		break;

	default:
		return -EPROTONOSUPPORT;
	}

	return 0;
}

static void
efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec,
			     const struct efx_farch_filter_spec *spec)
{
	bool is_full = false;

	/* *gen_spec should be completely initialised, to be consistent
	 * with efx_filter_init_{rx,tx}() and in case we want to copy
	 * it back to userland.
	 */
	memset(gen_spec, 0, sizeof(*gen_spec));

	gen_spec->priority = spec->priority;
	gen_spec->flags = spec->flags;
	gen_spec->dmaq_id = spec->dmaq_id;

	switch (spec->type) {
	case EFX_FARCH_FILTER_TCP_FULL:
	case EFX_FARCH_FILTER_UDP_FULL:
		is_full = true;
		/* fall through */
	case EFX_FARCH_FILTER_TCP_WILD:
	case EFX_FARCH_FILTER_UDP_WILD: {
		__be32 host1, host2;
		__be16 port1, port2;

		gen_spec->match_flags =
			EFX_FILTER_MATCH_ETHER_TYPE |
			EFX_FILTER_MATCH_IP_PROTO |
			EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT;
		if (is_full)
			gen_spec->match_flags |= (EFX_FILTER_MATCH_REM_HOST |
						  EFX_FILTER_MATCH_REM_PORT);
		gen_spec->ether_type = htons(ETH_P_IP);
		gen_spec->ip_proto =
			(spec->type == EFX_FARCH_FILTER_TCP_FULL ||
			 spec->type == EFX_FARCH_FILTER_TCP_WILD) ?
			IPPROTO_TCP : IPPROTO_UDP;

		host1 = htonl(spec->data[0] >> 16 | spec->data[1] << 16);
		port1 = htons(spec->data[0]);
		host2 = htonl(spec->data[2]);
		port2 = htons(spec->data[1] >> 16);
		if (spec->flags & EFX_FILTER_FLAG_TX) {
			gen_spec->loc_host[0] = host1;
			gen_spec->rem_host[0] = host2;
		} else {
			gen_spec->loc_host[0] = host2;
			gen_spec->rem_host[0] = host1;
		}
		if (!!(gen_spec->flags & EFX_FILTER_FLAG_TX) ^
		    (!is_full && gen_spec->ip_proto == IPPROTO_UDP)) {
			gen_spec->loc_port = port1;
			gen_spec->rem_port = port2;
		} else {
			gen_spec->loc_port = port2;
			gen_spec->rem_port = port1;
		}

		break;
	}

	case EFX_FARCH_FILTER_MAC_FULL:
		is_full = true;
		/* fall through */
	case EFX_FARCH_FILTER_MAC_WILD:
		gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC;
		if (is_full)
			gen_spec->match_flags |= EFX_FILTER_MATCH_OUTER_VID;
		gen_spec->loc_mac[0] = spec->data[2] >> 8;
		gen_spec->loc_mac[1] = spec->data[2];
		gen_spec->loc_mac[2] = spec->data[1] >> 24;
		gen_spec->loc_mac[3] = spec->data[1] >> 16;
		gen_spec->loc_mac[4] = spec->data[1] >> 8;
		gen_spec->loc_mac[5] = spec->data[1];
		gen_spec->outer_vid = htons(spec->data[0]);
		break;

	case EFX_FARCH_FILTER_UC_DEF:
	case EFX_FARCH_FILTER_MC_DEF:
		gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC_IG;
		gen_spec->loc_mac[0] = spec->type == EFX_FARCH_FILTER_MC_DEF;
		break;

	default:
		WARN_ON(1);
		break;
	}
}

static void
efx_farch_filter_init_rx_auto(struct efx_nic *efx,
			      struct efx_farch_filter_spec *spec)
{
	/* If there's only one channel then disable RSS for non VF
	 * traffic, thereby allowing VFs to use RSS when the PF can't.
	 */
	spec->priority = EFX_FILTER_PRI_AUTO;
	spec->flags = (EFX_FILTER_FLAG_RX |
		       (efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0) |
		       (efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0));
	spec->dmaq_id = 0;
}

/* Build a filter entry and return its n-tuple key. */
static u32 efx_farch_filter_build(efx_oword_t *filter,
				  struct efx_farch_filter_spec *spec)
{
	u32 data3;

	switch (efx_farch_filter_spec_table_id(spec)) {
	case EFX_FARCH_FILTER_TABLE_RX_IP: {
		bool is_udp = (spec->type == EFX_FARCH_FILTER_UDP_FULL ||
			       spec->type == EFX_FARCH_FILTER_UDP_WILD);
		EFX_POPULATE_OWORD_7(
			*filter,
			FRF_BZ_RSS_EN,
			!!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
			FRF_BZ_SCATTER_EN,
			!!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
			FRF_BZ_TCP_UDP, is_udp,
			FRF_BZ_RXQ_ID, spec->dmaq_id,
			EFX_DWORD_2, spec->data[2],
			EFX_DWORD_1, spec->data[1],
			EFX_DWORD_0, spec->data[0]);
		data3 = is_udp;
		break;
	}

	case EFX_FARCH_FILTER_TABLE_RX_MAC: {
		bool is_wild = spec->type == EFX_FARCH_FILTER_MAC_WILD;
		EFX_POPULATE_OWORD_7(
			*filter,
			FRF_CZ_RMFT_RSS_EN,
			!!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
			FRF_CZ_RMFT_SCATTER_EN,
			!!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
			FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id,
			FRF_CZ_RMFT_WILDCARD_MATCH, is_wild,
			FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2],
			FRF_CZ_RMFT_DEST_MAC_LO, spec->data[1],
			FRF_CZ_RMFT_VLAN_ID, spec->data[0]);
		data3 = is_wild;
		break;
	}

	case EFX_FARCH_FILTER_TABLE_TX_MAC: {
		bool is_wild = spec->type == EFX_FARCH_FILTER_MAC_WILD;
		EFX_POPULATE_OWORD_5(*filter,
				     FRF_CZ_TMFT_TXQ_ID, spec->dmaq_id,
				     FRF_CZ_TMFT_WILDCARD_MATCH, is_wild,
				     FRF_CZ_TMFT_SRC_MAC_HI, spec->data[2],
				     FRF_CZ_TMFT_SRC_MAC_LO, spec->data[1],
				     FRF_CZ_TMFT_VLAN_ID, spec->data[0]);
		data3 = is_wild | spec->dmaq_id << 1;
		break;
	}

	default:
		BUG();
	}

	return spec->data[0] ^ spec->data[1] ^ spec->data[2] ^ data3;
}

static bool efx_farch_filter_equal(const struct efx_farch_filter_spec *left,
				   const struct efx_farch_filter_spec *right)
{
	if (left->type != right->type ||
	    memcmp(left->data, right->data, sizeof(left->data)))
		return false;

	if (left->flags & EFX_FILTER_FLAG_TX &&
	    left->dmaq_id != right->dmaq_id)
		return false;

	return true;
}

/*
 * Construct/deconstruct external filter IDs.  At least the RX filter
 * IDs must be ordered by matching priority, for RX NFC semantics.
 *
 * Deconstruction needs to be robust against invalid IDs so that
 * efx_filter_remove_id_safe() and efx_filter_get_filter_safe() can
 * accept user-provided IDs.
 */

#define EFX_FARCH_FILTER_MATCH_PRI_COUNT	5

static const u8 efx_farch_filter_type_match_pri[EFX_FARCH_FILTER_TYPE_COUNT] = {
	[EFX_FARCH_FILTER_TCP_FULL]	= 0,
	[EFX_FARCH_FILTER_UDP_FULL]	= 0,
	[EFX_FARCH_FILTER_TCP_WILD]	= 1,
	[EFX_FARCH_FILTER_UDP_WILD]	= 1,
	[EFX_FARCH_FILTER_MAC_FULL]	= 2,
	[EFX_FARCH_FILTER_MAC_WILD]	= 3,
	[EFX_FARCH_FILTER_UC_DEF]	= 4,
	[EFX_FARCH_FILTER_MC_DEF]	= 4,
};

static const enum efx_farch_filter_table_id efx_farch_filter_range_table[] = {
	EFX_FARCH_FILTER_TABLE_RX_IP,	/* RX match pri 0 */
	EFX_FARCH_FILTER_TABLE_RX_IP,
	EFX_FARCH_FILTER_TABLE_RX_MAC,
	EFX_FARCH_FILTER_TABLE_RX_MAC,
	EFX_FARCH_FILTER_TABLE_RX_DEF,	/* RX match pri 4 */
	EFX_FARCH_FILTER_TABLE_TX_MAC,	/* TX match pri 0 */
	EFX_FARCH_FILTER_TABLE_TX_MAC,	/* TX match pri 1 */
};

#define EFX_FARCH_FILTER_INDEX_WIDTH 13
#define EFX_FARCH_FILTER_INDEX_MASK ((1 << EFX_FARCH_FILTER_INDEX_WIDTH) - 1)

static inline u32
efx_farch_filter_make_id(const struct efx_farch_filter_spec *spec,
			 unsigned int index)
{
	unsigned int range;

	range = efx_farch_filter_type_match_pri[spec->type];
	if (!(spec->flags & EFX_FILTER_FLAG_RX))
		range += EFX_FARCH_FILTER_MATCH_PRI_COUNT;

	return range << EFX_FARCH_FILTER_INDEX_WIDTH | index;
}

static inline enum efx_farch_filter_table_id
efx_farch_filter_id_table_id(u32 id)
{
	unsigned int range = id >> EFX_FARCH_FILTER_INDEX_WIDTH;

	if (range < ARRAY_SIZE(efx_farch_filter_range_table))
		return efx_farch_filter_range_table[range];
	else
		return EFX_FARCH_FILTER_TABLE_COUNT; /* invalid */
}

static inline unsigned int efx_farch_filter_id_index(u32 id)
{
	return id & EFX_FARCH_FILTER_INDEX_MASK;
}

u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	unsigned int range = EFX_FARCH_FILTER_MATCH_PRI_COUNT - 1;
	enum efx_farch_filter_table_id table_id;

	do {
		table_id = efx_farch_filter_range_table[range];
		if (state->table[table_id].size != 0)
			return range << EFX_FARCH_FILTER_INDEX_WIDTH |
				state->table[table_id].size;
	} while (range--);

	return 0;
}

s32 efx_farch_filter_insert(struct efx_nic *efx,
			    struct efx_filter_spec *gen_spec,
			    bool replace_equal)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	struct efx_farch_filter_table *table;
	struct efx_farch_filter_spec spec;
	efx_oword_t filter;
	int rep_index, ins_index;
	unsigned int depth = 0;
	int rc;

	rc = efx_farch_filter_from_gen_spec(&spec, gen_spec);
	if (rc)
		return rc;

	down_write(&state->lock);

	table = &state->table[efx_farch_filter_spec_table_id(&spec)];
	if (table->size == 0) {
		rc = -EINVAL;
		goto out_unlock;
	}

	netif_vdbg(efx, hw, efx->net_dev,
		   "%s: type %d search_limit=%d", __func__, spec.type,
		   table->search_limit[spec.type]);

	if (table->id == EFX_FARCH_FILTER_TABLE_RX_DEF) {
		/* One filter spec per type */
		BUILD_BUG_ON(EFX_FARCH_FILTER_INDEX_UC_DEF != 0);
		BUILD_BUG_ON(EFX_FARCH_FILTER_INDEX_MC_DEF !=
			     EFX_FARCH_FILTER_MC_DEF - EFX_FARCH_FILTER_UC_DEF);
		rep_index = spec.type - EFX_FARCH_FILTER_UC_DEF;
		ins_index = rep_index;
	} else {
		/* Search concurrently for
		 * (1) a filter to be replaced (rep_index): any filter
		 *     with the same match values, up to the current
		 *     search depth for this type, and
		 * (2) the insertion point (ins_index): (1) or any
		 *     free slot before it or up to the maximum search
		 *     depth for this priority
		 * We fail if we cannot find (2).
		 *
		 * We can stop once either
		 * (a) we find (1), in which case we have definitely
		 *     found (2) as well; or
		 * (b) we have searched exhaustively for (1), and have
		 *     either found (2) or searched exhaustively for it
		 */
		u32 key = efx_farch_filter_build(&filter, &spec);
		unsigned int hash = efx_farch_filter_hash(key);
		unsigned int incr = efx_farch_filter_increment(key);
		unsigned int max_rep_depth = table->search_limit[spec.type];
		unsigned int max_ins_depth =
			spec.priority <= EFX_FILTER_PRI_HINT ?
			EFX_FARCH_FILTER_CTL_SRCH_HINT_MAX :
			EFX_FARCH_FILTER_CTL_SRCH_MAX;
		unsigned int i = hash & (table->size - 1);

		ins_index = -1;
		depth = 1;

		for (;;) {
			if (!test_bit(i, table->used_bitmap)) {
				if (ins_index < 0)
					ins_index = i;
			} else if (efx_farch_filter_equal(&spec,
							  &table->spec[i])) {
				/* Case (a) */
				if (ins_index < 0)
					ins_index = i;
				rep_index = i;
				break;
			}

			if (depth >= max_rep_depth &&
			    (ins_index >= 0 || depth >= max_ins_depth)) {
				/* Case (b) */
				if (ins_index < 0) {
					rc = -EBUSY;
					goto out_unlock;
				}
				rep_index = -1;
				break;
			}

			i = (i + incr) & (table->size - 1);
			++depth;
		}
	}

	/* If we found a filter to be replaced, check whether we
	 * should do so
	 */
	if (rep_index >= 0) {
		struct efx_farch_filter_spec *saved_spec =
			&table->spec[rep_index];

		if (spec.priority == saved_spec->priority && !replace_equal) {
			rc = -EEXIST;
			goto out_unlock;
		}
		if (spec.priority < saved_spec->priority) {
			rc = -EPERM;
			goto out_unlock;
		}
		if (saved_spec->priority == EFX_FILTER_PRI_AUTO ||
		    saved_spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO)
			spec.flags |= EFX_FILTER_FLAG_RX_OVER_AUTO;
	}

	/* Insert the filter */
	if (ins_index != rep_index) {
		__set_bit(ins_index, table->used_bitmap);
		++table->used;
	}
	table->spec[ins_index] = spec;

	if (table->id == EFX_FARCH_FILTER_TABLE_RX_DEF) {
		efx_farch_filter_push_rx_config(efx);
	} else {
		if (table->search_limit[spec.type] < depth) {
			table->search_limit[spec.type] = depth;
			if (spec.flags & EFX_FILTER_FLAG_TX)
				efx_farch_filter_push_tx_limits(efx);
			else
				efx_farch_filter_push_rx_config(efx);
		}

		efx_writeo(efx, &filter,
			   table->offset + table->step * ins_index);

		/* If we were able to replace a filter by inserting
		 * at a lower depth, clear the replaced filter
		 */
		if (ins_index != rep_index && rep_index >= 0)
			efx_farch_filter_table_clear_entry(efx, table,
							   rep_index);
	}

	netif_vdbg(efx, hw, efx->net_dev,
		   "%s: filter type %d index %d rxq %u set",
		   __func__, spec.type, ins_index, spec.dmaq_id);
	rc = efx_farch_filter_make_id(&spec, ins_index);

out_unlock:
	up_write(&state->lock);
	return rc;
}

static void
efx_farch_filter_table_clear_entry(struct efx_nic *efx,
				   struct efx_farch_filter_table *table,
				   unsigned int filter_idx)
{
	static efx_oword_t filter;

	EFX_WARN_ON_PARANOID(!test_bit(filter_idx, table->used_bitmap));
	BUG_ON(table->offset == 0); /* can't clear MAC default filters */

	__clear_bit(filter_idx, table->used_bitmap);
	--table->used;
	memset(&table->spec[filter_idx], 0, sizeof(table->spec[0]));

	efx_writeo(efx, &filter, table->offset + table->step * filter_idx);

	/* If this filter required a greater search depth than
	 * any other, the search limit for its type can now be
	 * decreased.  However, it is hard to determine that
	 * unless the table has become completely empty - in
	 * which case, all its search limits can be set to 0.
	 */
	if (unlikely(table->used == 0)) {
		memset(table->search_limit, 0, sizeof(table->search_limit));
		if (table->id == EFX_FARCH_FILTER_TABLE_TX_MAC)
			efx_farch_filter_push_tx_limits(efx);
		else
			efx_farch_filter_push_rx_config(efx);
	}
}

static int efx_farch_filter_remove(struct efx_nic *efx,
				   struct efx_farch_filter_table *table,
				   unsigned int filter_idx,
				   enum efx_filter_priority priority)
{
	struct efx_farch_filter_spec *spec = &table->spec[filter_idx];

	if (!test_bit(filter_idx, table->used_bitmap) ||
	    spec->priority != priority)
		return -ENOENT;

	if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) {
		efx_farch_filter_init_rx_auto(efx, spec);
		efx_farch_filter_push_rx_config(efx);
	} else {
		efx_farch_filter_table_clear_entry(efx, table, filter_idx);
	}

	return 0;
}

int efx_farch_filter_remove_safe(struct efx_nic *efx,
				 enum efx_filter_priority priority,
				 u32 filter_id)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	unsigned int filter_idx;
	struct efx_farch_filter_spec *spec;
	int rc;

	table_id = efx_farch_filter_id_table_id(filter_id);
	if ((unsigned int)table_id >= EFX_FARCH_FILTER_TABLE_COUNT)
		return -ENOENT;
	table = &state->table[table_id];

	filter_idx = efx_farch_filter_id_index(filter_id);
	if (filter_idx >= table->size)
		return -ENOENT;
	down_write(&state->lock);
	spec = &table->spec[filter_idx];

	rc = efx_farch_filter_remove(efx, table, filter_idx, priority);
	up_write(&state->lock);

	return rc;
}

int efx_farch_filter_get_safe(struct efx_nic *efx,
			      enum efx_filter_priority priority,
			      u32 filter_id, struct efx_filter_spec *spec_buf)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	struct efx_farch_filter_spec *spec;
	unsigned int filter_idx;
	int rc = -ENOENT;

	down_read(&state->lock);

	table_id = efx_farch_filter_id_table_id(filter_id);
	if ((unsigned int)table_id >= EFX_FARCH_FILTER_TABLE_COUNT)
		goto out_unlock;
	table = &state->table[table_id];

	filter_idx = efx_farch_filter_id_index(filter_id);
	if (filter_idx >= table->size)
		goto out_unlock;
	spec = &table->spec[filter_idx];

	if (test_bit(filter_idx, table->used_bitmap) &&
	    spec->priority == priority) {
		efx_farch_filter_to_gen_spec(spec_buf, spec);
		rc = 0;
	}

out_unlock:
	up_read(&state->lock);
	return rc;
}

static void
efx_farch_filter_table_clear(struct efx_nic *efx,
			     enum efx_farch_filter_table_id table_id,
			     enum efx_filter_priority priority)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	struct efx_farch_filter_table *table = &state->table[table_id];
	unsigned int filter_idx;

	down_write(&state->lock);
	for (filter_idx = 0; filter_idx < table->size; ++filter_idx) {
		if (table->spec[filter_idx].priority != EFX_FILTER_PRI_AUTO)
			efx_farch_filter_remove(efx, table,
						filter_idx, priority);
	}
	up_write(&state->lock);
}

int efx_farch_filter_clear_rx(struct efx_nic *efx,
			       enum efx_filter_priority priority)
{
	efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_IP,
				     priority);
	efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_MAC,
				     priority);
	efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_DEF,
				     priority);
	return 0;
}

u32 efx_farch_filter_count_rx_used(struct efx_nic *efx,
				   enum efx_filter_priority priority)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	unsigned int filter_idx;
	u32 count = 0;

	down_read(&state->lock);

	for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
	     table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
	     table_id++) {
		table = &state->table[table_id];
		for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
			if (test_bit(filter_idx, table->used_bitmap) &&
			    table->spec[filter_idx].priority == priority)
				++count;
		}
	}

	up_read(&state->lock);

	return count;
}

s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx,
				enum efx_filter_priority priority,
				u32 *buf, u32 size)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	unsigned int filter_idx;
	s32 count = 0;

	down_read(&state->lock);

	for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
	     table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
	     table_id++) {
		table = &state->table[table_id];
		for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
			if (test_bit(filter_idx, table->used_bitmap) &&
			    table->spec[filter_idx].priority == priority) {
				if (count == size) {
					count = -EMSGSIZE;
					goto out;
				}
				buf[count++] = efx_farch_filter_make_id(
					&table->spec[filter_idx], filter_idx);
			}
		}
	}
out:
	up_read(&state->lock);

	return count;
}

/* Restore filter stater after reset */
void efx_farch_filter_table_restore(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	efx_oword_t filter;
	unsigned int filter_idx;

	down_write(&state->lock);

	for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
		table = &state->table[table_id];

		/* Check whether this is a regular register table */
		if (table->step == 0)
			continue;

		for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
			if (!test_bit(filter_idx, table->used_bitmap))
				continue;
			efx_farch_filter_build(&filter, &table->spec[filter_idx]);
			efx_writeo(efx, &filter,
				   table->offset + table->step * filter_idx);
		}
	}

	efx_farch_filter_push_rx_config(efx);
	efx_farch_filter_push_tx_limits(efx);

	up_write(&state->lock);
}

void efx_farch_filter_table_remove(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;

	for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
		kfree(state->table[table_id].used_bitmap);
		vfree(state->table[table_id].spec);
	}
	kfree(state);
}

int efx_farch_filter_table_probe(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state;
	struct efx_farch_filter_table *table;
	unsigned table_id;

	state = kzalloc(sizeof(struct efx_farch_filter_state), GFP_KERNEL);
	if (!state)
		return -ENOMEM;
	efx->filter_state = state;

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
	table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
	table->offset = FR_BZ_RX_FILTER_TBL0;
	table->size = FR_BZ_RX_FILTER_TBL0_ROWS;
	table->step = FR_BZ_RX_FILTER_TBL0_STEP;

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_MAC];
	table->id = EFX_FARCH_FILTER_TABLE_RX_MAC;
	table->offset = FR_CZ_RX_MAC_FILTER_TBL0;
	table->size = FR_CZ_RX_MAC_FILTER_TBL0_ROWS;
	table->step = FR_CZ_RX_MAC_FILTER_TBL0_STEP;

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
	table->id = EFX_FARCH_FILTER_TABLE_RX_DEF;
	table->size = EFX_FARCH_FILTER_SIZE_RX_DEF;

	table = &state->table[EFX_FARCH_FILTER_TABLE_TX_MAC];
	table->id = EFX_FARCH_FILTER_TABLE_TX_MAC;
	table->offset = FR_CZ_TX_MAC_FILTER_TBL0;
	table->size = FR_CZ_TX_MAC_FILTER_TBL0_ROWS;
	table->step = FR_CZ_TX_MAC_FILTER_TBL0_STEP;

	for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
		table = &state->table[table_id];
		if (table->size == 0)
			continue;
		table->used_bitmap = kcalloc(BITS_TO_LONGS(table->size),
					     sizeof(unsigned long),
					     GFP_KERNEL);
		if (!table->used_bitmap)
			goto fail;
		table->spec = vzalloc(table->size * sizeof(*table->spec));
		if (!table->spec)
			goto fail;
	}

	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
	if (table->size) {
		/* RX default filters must always exist */
		struct efx_farch_filter_spec *spec;
		unsigned i;

		for (i = 0; i < EFX_FARCH_FILTER_SIZE_RX_DEF; i++) {
			spec = &table->spec[i];
			spec->type = EFX_FARCH_FILTER_UC_DEF + i;
			efx_farch_filter_init_rx_auto(efx, spec);
			__set_bit(i, table->used_bitmap);
		}
	}

	efx_farch_filter_push_rx_config(efx);

	return 0;

fail:
	efx_farch_filter_table_remove(efx);
	return -ENOMEM;
}

/* Update scatter enable flags for filters pointing to our own RX queues */
void efx_farch_filter_update_rx_scatter(struct efx_nic *efx)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	enum efx_farch_filter_table_id table_id;
	struct efx_farch_filter_table *table;
	efx_oword_t filter;
	unsigned int filter_idx;

	down_write(&state->lock);

	for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
	     table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
	     table_id++) {
		table = &state->table[table_id];

		for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
			if (!test_bit(filter_idx, table->used_bitmap) ||
			    table->spec[filter_idx].dmaq_id >=
			    efx->n_rx_channels)
				continue;

			if (efx->rx_scatter)
				table->spec[filter_idx].flags |=
					EFX_FILTER_FLAG_RX_SCATTER;
			else
				table->spec[filter_idx].flags &=
					~EFX_FILTER_FLAG_RX_SCATTER;

			if (table_id == EFX_FARCH_FILTER_TABLE_RX_DEF)
				/* Pushed by efx_farch_filter_push_rx_config() */
				continue;

			efx_farch_filter_build(&filter, &table->spec[filter_idx]);
			efx_writeo(efx, &filter,
				   table->offset + table->step * filter_idx);
		}
	}

	efx_farch_filter_push_rx_config(efx);

	up_write(&state->lock);
}

#ifdef CONFIG_RFS_ACCEL

bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
				     unsigned int index)
{
	struct efx_farch_filter_state *state = efx->filter_state;
	struct efx_farch_filter_table *table;
	bool ret = false, force = false;
	u16 arfs_id;

	down_write(&state->lock);
	spin_lock_bh(&efx->rps_hash_lock);
	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
	if (test_bit(index, table->used_bitmap) &&
	    table->spec[index].priority == EFX_FILTER_PRI_HINT) {
		struct efx_arfs_rule *rule = NULL;
		struct efx_filter_spec spec;

		efx_farch_filter_to_gen_spec(&spec, &table->spec[index]);
		if (!efx->rps_hash_table) {
			/* In the absence of the table, we always returned 0 to
			 * ARFS, so use the same to query it.
			 */
			arfs_id = 0;
		} else {
			rule = efx_rps_hash_find(efx, &spec);
			if (!rule) {
				/* ARFS table doesn't know of this filter, remove it */
				force = true;
			} else {
				arfs_id = rule->arfs_id;
				if (!efx_rps_check_rule(rule, index, &force))
					goto out_unlock;
			}
		}
		if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id,
						 flow_id, arfs_id)) {
			if (rule)
				rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
			efx_rps_hash_del(efx, &spec);
			efx_farch_filter_table_clear_entry(efx, table, index);
			ret = true;
		}
	}
out_unlock:
	spin_unlock_bh(&efx->rps_hash_lock);
	up_write(&state->lock);
	return ret;
}

#endif /* CONFIG_RFS_ACCEL */

void efx_farch_filter_sync_rx_mode(struct efx_nic *efx)
{
	struct net_device *net_dev = efx->net_dev;
	struct netdev_hw_addr *ha;
	union efx_multicast_hash *mc_hash = &efx->multicast_hash;
	u32 crc;
	int bit;

	if (!efx_dev_registered(efx))
		return;

	netif_addr_lock_bh(net_dev);

	efx->unicast_filter = !(net_dev->flags & IFF_PROMISC);

	/* Build multicast hash table */
	if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
		memset(mc_hash, 0xff, sizeof(*mc_hash));
	} else {
		memset(mc_hash, 0x00, sizeof(*mc_hash));
		netdev_for_each_mc_addr(ha, net_dev) {
			crc = ether_crc_le(ETH_ALEN, ha->addr);
			bit = crc & (EFX_MCAST_HASH_ENTRIES - 1);
			__set_bit_le(bit, mc_hash);
		}

		/* Broadcast packets go through the multicast hash filter.
		 * ether_crc_le() of the broadcast address is 0xbe2612ff
		 * so we always add bit 0xff to the mask.
		 */
		__set_bit_le(0xff, mc_hash);
	}

	netif_addr_unlock_bh(net_dev);
}