summaryrefslogtreecommitdiff
path: root/arch/mips/kvm/vz.c
blob: dde20887a70dfc643c5bb1005599055d019e2eb5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * KVM/MIPS: Support for hardware virtualization extensions
 *
 * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
 * Authors: Yann Le Du <ledu@kymasys.com>
 */

#include <linux/errno.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/preempt.h>
#include <linux/vmalloc.h>
#include <asm/cacheflush.h>
#include <asm/cacheops.h>
#include <asm/cmpxchg.h>
#include <asm/fpu.h>
#include <asm/hazards.h>
#include <asm/inst.h>
#include <asm/mmu_context.h>
#include <asm/r4kcache.h>
#include <asm/time.h>
#include <asm/tlb.h>
#include <asm/tlbex.h>

#include <linux/kvm_host.h>

#include "interrupt.h"

#include "trace.h"

/* Pointers to last VCPU loaded on each physical CPU */
static struct kvm_vcpu *last_vcpu[NR_CPUS];
/* Pointers to last VCPU executed on each physical CPU */
static struct kvm_vcpu *last_exec_vcpu[NR_CPUS];

/*
 * Number of guest VTLB entries to use, so we can catch inconsistency between
 * CPUs.
 */
static unsigned int kvm_vz_guest_vtlb_size;

static inline long kvm_vz_read_gc0_ebase(void)
{
	if (sizeof(long) == 8 && cpu_has_ebase_wg)
		return read_gc0_ebase_64();
	else
		return read_gc0_ebase();
}

static inline void kvm_vz_write_gc0_ebase(long v)
{
	/*
	 * First write with WG=1 to write upper bits, then write again in case
	 * WG should be left at 0.
	 * write_gc0_ebase_64() is no longer UNDEFINED since R6.
	 */
	if (sizeof(long) == 8 &&
	    (cpu_has_mips64r6 || cpu_has_ebase_wg)) {
		write_gc0_ebase_64(v | MIPS_EBASE_WG);
		write_gc0_ebase_64(v);
	} else {
		write_gc0_ebase(v | MIPS_EBASE_WG);
		write_gc0_ebase(v);
	}
}

/*
 * These Config bits may be writable by the guest:
 * Config:	[K23, KU] (!TLB), K0
 * Config1:	(none)
 * Config2:	[TU, SU] (impl)
 * Config3:	ISAOnExc
 * Config4:	FTLBPageSize
 * Config5:	K, CV, MSAEn, UFE, FRE, SBRI, UFR
 */

static inline unsigned int kvm_vz_config_guest_wrmask(struct kvm_vcpu *vcpu)
{
	return CONF_CM_CMASK;
}

static inline unsigned int kvm_vz_config1_guest_wrmask(struct kvm_vcpu *vcpu)
{
	return 0;
}

static inline unsigned int kvm_vz_config2_guest_wrmask(struct kvm_vcpu *vcpu)
{
	return 0;
}

static inline unsigned int kvm_vz_config3_guest_wrmask(struct kvm_vcpu *vcpu)
{
	return MIPS_CONF3_ISA_OE;
}

static inline unsigned int kvm_vz_config4_guest_wrmask(struct kvm_vcpu *vcpu)
{
	/* no need to be exact */
	return MIPS_CONF4_VFTLBPAGESIZE;
}

static inline unsigned int kvm_vz_config5_guest_wrmask(struct kvm_vcpu *vcpu)
{
	unsigned int mask = MIPS_CONF5_K | MIPS_CONF5_CV | MIPS_CONF5_SBRI;

	/* Permit MSAEn changes if MSA supported and enabled */
	if (kvm_mips_guest_has_msa(&vcpu->arch))
		mask |= MIPS_CONF5_MSAEN;

	/*
	 * Permit guest FPU mode changes if FPU is enabled and the relevant
	 * feature exists according to FIR register.
	 */
	if (kvm_mips_guest_has_fpu(&vcpu->arch)) {
		if (cpu_has_ufr)
			mask |= MIPS_CONF5_UFR;
		if (cpu_has_fre)
			mask |= MIPS_CONF5_FRE | MIPS_CONF5_UFE;
	}

	return mask;
}

/*
 * VZ optionally allows these additional Config bits to be written by root:
 * Config:	M, [MT]
 * Config1:	M, [MMUSize-1, C2, MD, PC, WR, CA], FP
 * Config2:	M
 * Config3:	M, MSAP, [BPG], ULRI, [DSP2P, DSPP], CTXTC, [ITL, LPA, VEIC,
 *		VInt, SP, CDMM, MT, SM, TL]
 * Config4:	M, [VTLBSizeExt, MMUSizeExt]
 * Config5:	MRP
 */

static inline unsigned int kvm_vz_config_user_wrmask(struct kvm_vcpu *vcpu)
{
	return kvm_vz_config_guest_wrmask(vcpu) | MIPS_CONF_M;
}

static inline unsigned int kvm_vz_config1_user_wrmask(struct kvm_vcpu *vcpu)
{
	unsigned int mask = kvm_vz_config1_guest_wrmask(vcpu) | MIPS_CONF_M;

	/* Permit FPU to be present if FPU is supported */
	if (kvm_mips_guest_can_have_fpu(&vcpu->arch))
		mask |= MIPS_CONF1_FP;

	return mask;
}

static inline unsigned int kvm_vz_config2_user_wrmask(struct kvm_vcpu *vcpu)
{
	return kvm_vz_config2_guest_wrmask(vcpu) | MIPS_CONF_M;
}

static inline unsigned int kvm_vz_config3_user_wrmask(struct kvm_vcpu *vcpu)
{
	unsigned int mask = kvm_vz_config3_guest_wrmask(vcpu) | MIPS_CONF_M |
		MIPS_CONF3_ULRI | MIPS_CONF3_CTXTC;

	/* Permit MSA to be present if MSA is supported */
	if (kvm_mips_guest_can_have_msa(&vcpu->arch))
		mask |= MIPS_CONF3_MSA;

	return mask;
}

static inline unsigned int kvm_vz_config4_user_wrmask(struct kvm_vcpu *vcpu)
{
	return kvm_vz_config4_guest_wrmask(vcpu) | MIPS_CONF_M;
}

static inline unsigned int kvm_vz_config5_user_wrmask(struct kvm_vcpu *vcpu)
{
	return kvm_vz_config5_guest_wrmask(vcpu) | MIPS_CONF5_MRP;
}

static gpa_t kvm_vz_gva_to_gpa_cb(gva_t gva)
{
	/* VZ guest has already converted gva to gpa */
	return gva;
}

static void kvm_vz_queue_irq(struct kvm_vcpu *vcpu, unsigned int priority)
{
	set_bit(priority, &vcpu->arch.pending_exceptions);
	clear_bit(priority, &vcpu->arch.pending_exceptions_clr);
}

static void kvm_vz_dequeue_irq(struct kvm_vcpu *vcpu, unsigned int priority)
{
	clear_bit(priority, &vcpu->arch.pending_exceptions);
	set_bit(priority, &vcpu->arch.pending_exceptions_clr);
}

static void kvm_vz_queue_timer_int_cb(struct kvm_vcpu *vcpu)
{
	/*
	 * timer expiry is asynchronous to vcpu execution therefore defer guest
	 * cp0 accesses
	 */
	kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_TIMER);
}

static void kvm_vz_dequeue_timer_int_cb(struct kvm_vcpu *vcpu)
{
	/*
	 * timer expiry is asynchronous to vcpu execution therefore defer guest
	 * cp0 accesses
	 */
	kvm_vz_dequeue_irq(vcpu, MIPS_EXC_INT_TIMER);
}

static void kvm_vz_queue_io_int_cb(struct kvm_vcpu *vcpu,
				   struct kvm_mips_interrupt *irq)
{
	int intr = (int)irq->irq;

	/*
	 * interrupts are asynchronous to vcpu execution therefore defer guest
	 * cp0 accesses
	 */
	switch (intr) {
	case 2:
		kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_IO);
		break;

	case 3:
		kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_IPI_1);
		break;

	case 4:
		kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_IPI_2);
		break;

	default:
		break;
	}

}

static void kvm_vz_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
				     struct kvm_mips_interrupt *irq)
{
	int intr = (int)irq->irq;

	/*
	 * interrupts are asynchronous to vcpu execution therefore defer guest
	 * cp0 accesses
	 */
	switch (intr) {
	case -2:
		kvm_vz_dequeue_irq(vcpu, MIPS_EXC_INT_IO);
		break;

	case -3:
		kvm_vz_dequeue_irq(vcpu, MIPS_EXC_INT_IPI_1);
		break;

	case -4:
		kvm_vz_dequeue_irq(vcpu, MIPS_EXC_INT_IPI_2);
		break;

	default:
		break;
	}

}

static u32 kvm_vz_priority_to_irq[MIPS_EXC_MAX] = {
	[MIPS_EXC_INT_TIMER] = C_IRQ5,
	[MIPS_EXC_INT_IO]    = C_IRQ0,
	[MIPS_EXC_INT_IPI_1] = C_IRQ1,
	[MIPS_EXC_INT_IPI_2] = C_IRQ2,
};

static int kvm_vz_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
				 u32 cause)
{
	u32 irq = (priority < MIPS_EXC_MAX) ?
		kvm_vz_priority_to_irq[priority] : 0;

	switch (priority) {
	case MIPS_EXC_INT_TIMER:
		set_gc0_cause(C_TI);
		break;

	case MIPS_EXC_INT_IO:
	case MIPS_EXC_INT_IPI_1:
	case MIPS_EXC_INT_IPI_2:
		if (cpu_has_guestctl2)
			set_c0_guestctl2(irq);
		else
			set_gc0_cause(irq);
		break;

	default:
		break;
	}

	clear_bit(priority, &vcpu->arch.pending_exceptions);
	return 1;
}

static int kvm_vz_irq_clear_cb(struct kvm_vcpu *vcpu, unsigned int priority,
			       u32 cause)
{
	u32 irq = (priority < MIPS_EXC_MAX) ?
		kvm_vz_priority_to_irq[priority] : 0;

	switch (priority) {
	case MIPS_EXC_INT_TIMER:
		/*
		 * Call to kvm_write_c0_guest_compare() clears Cause.TI in
		 * kvm_mips_emulate_CP0(). Explicitly clear irq associated with
		 * Cause.IP[IPTI] if GuestCtl2 virtual interrupt register not
		 * supported or if not using GuestCtl2 Hardware Clear.
		 */
		if (cpu_has_guestctl2) {
			if (!(read_c0_guestctl2() & (irq << 14)))
				clear_c0_guestctl2(irq);
		} else {
			clear_gc0_cause(irq);
		}
		break;

	case MIPS_EXC_INT_IO:
	case MIPS_EXC_INT_IPI_1:
	case MIPS_EXC_INT_IPI_2:
		/* Clear GuestCtl2.VIP irq if not using Hardware Clear */
		if (cpu_has_guestctl2) {
			if (!(read_c0_guestctl2() & (irq << 14)))
				clear_c0_guestctl2(irq);
		} else {
			clear_gc0_cause(irq);
		}
		break;

	default:
		break;
	}

	clear_bit(priority, &vcpu->arch.pending_exceptions_clr);
	return 1;
}

/*
 * VZ guest timer handling.
 */

/**
 * kvm_vz_should_use_htimer() - Find whether to use the VZ hard guest timer.
 * @vcpu:	Virtual CPU.
 *
 * Returns:	true if the VZ GTOffset & real guest CP0_Count should be used
 *		instead of software emulation of guest timer.
 *		false otherwise.
 */
static bool kvm_vz_should_use_htimer(struct kvm_vcpu *vcpu)
{
	if (kvm_mips_count_disabled(vcpu))
		return false;

	/* Chosen frequency must match real frequency */
	if (mips_hpt_frequency != vcpu->arch.count_hz)
		return false;

	/* We don't support a CP0_GTOffset with fewer bits than CP0_Count */
	if (current_cpu_data.gtoffset_mask != 0xffffffff)
		return false;

	return true;
}

/**
 * _kvm_vz_restore_stimer() - Restore soft timer state.
 * @vcpu:	Virtual CPU.
 * @compare:	CP0_Compare register value, restored by caller.
 * @cause:	CP0_Cause register to restore.
 *
 * Restore VZ state relating to the soft timer. The hard timer can be enabled
 * later.
 */
static void _kvm_vz_restore_stimer(struct kvm_vcpu *vcpu, u32 compare,
				   u32 cause)
{
	/*
	 * Avoid spurious counter interrupts by setting Guest CP0_Count to just
	 * after Guest CP0_Compare.
	 */
	write_c0_gtoffset(compare - read_c0_count());

	back_to_back_c0_hazard();
	write_gc0_cause(cause);
}

/**
 * _kvm_vz_restore_htimer() - Restore hard timer state.
 * @vcpu:	Virtual CPU.
 * @compare:	CP0_Compare register value, restored by caller.
 * @cause:	CP0_Cause register to restore.
 *
 * Restore hard timer Guest.Count & Guest.Cause taking care to preserve the
 * value of Guest.CP0_Cause.TI while restoring Guest.CP0_Cause.
 */
static void _kvm_vz_restore_htimer(struct kvm_vcpu *vcpu,
				   u32 compare, u32 cause)
{
	u32 start_count, after_count;
	ktime_t freeze_time;
	unsigned long flags;

	/*
	 * Freeze the soft-timer and sync the guest CP0_Count with it. We do
	 * this with interrupts disabled to avoid latency.
	 */
	local_irq_save(flags);
	freeze_time = kvm_mips_freeze_hrtimer(vcpu, &start_count);
	write_c0_gtoffset(start_count - read_c0_count());
	local_irq_restore(flags);

	/* restore guest CP0_Cause, as TI may already be set */
	back_to_back_c0_hazard();
	write_gc0_cause(cause);

	/*
	 * The above sequence isn't atomic and would result in lost timer
	 * interrupts if we're not careful. Detect if a timer interrupt is due
	 * and assert it.
	 */
	back_to_back_c0_hazard();
	after_count = read_gc0_count();
	if (after_count - start_count > compare - start_count - 1)
		kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_TIMER);
}

/**
 * kvm_vz_restore_timer() - Restore timer state.
 * @vcpu:	Virtual CPU.
 *
 * Restore soft timer state from saved context.
 */
static void kvm_vz_restore_timer(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	u32 cause, compare;

	compare = kvm_read_sw_gc0_compare(cop0);
	cause = kvm_read_sw_gc0_cause(cop0);

	write_gc0_compare(compare);
	_kvm_vz_restore_stimer(vcpu, compare, cause);
}

/**
 * kvm_vz_acquire_htimer() - Switch to hard timer state.
 * @vcpu:	Virtual CPU.
 *
 * Restore hard timer state on top of existing soft timer state if possible.
 *
 * Since hard timer won't remain active over preemption, preemption should be
 * disabled by the caller.
 */
void kvm_vz_acquire_htimer(struct kvm_vcpu *vcpu)
{
	u32 gctl0;

	gctl0 = read_c0_guestctl0();
	if (!(gctl0 & MIPS_GCTL0_GT) && kvm_vz_should_use_htimer(vcpu)) {
		/* enable guest access to hard timer */
		write_c0_guestctl0(gctl0 | MIPS_GCTL0_GT);

		_kvm_vz_restore_htimer(vcpu, read_gc0_compare(),
				       read_gc0_cause());
	}
}

/**
 * _kvm_vz_save_htimer() - Switch to software emulation of guest timer.
 * @vcpu:	Virtual CPU.
 * @compare:	Pointer to write compare value to.
 * @cause:	Pointer to write cause value to.
 *
 * Save VZ guest timer state and switch to software emulation of guest CP0
 * timer. The hard timer must already be in use, so preemption should be
 * disabled.
 */
static void _kvm_vz_save_htimer(struct kvm_vcpu *vcpu,
				u32 *out_compare, u32 *out_cause)
{
	u32 cause, compare, before_count, end_count;
	ktime_t before_time;

	compare = read_gc0_compare();
	*out_compare = compare;

	before_time = ktime_get();

	/*
	 * Record the CP0_Count *prior* to saving CP0_Cause, so we have a time
	 * at which no pending timer interrupt is missing.
	 */
	before_count = read_gc0_count();
	back_to_back_c0_hazard();
	cause = read_gc0_cause();
	*out_cause = cause;

	/*
	 * Record a final CP0_Count which we will transfer to the soft-timer.
	 * This is recorded *after* saving CP0_Cause, so we don't get any timer
	 * interrupts from just after the final CP0_Count point.
	 */
	back_to_back_c0_hazard();
	end_count = read_gc0_count();

	/*
	 * The above sequence isn't atomic, so we could miss a timer interrupt
	 * between reading CP0_Cause and end_count. Detect and record any timer
	 * interrupt due between before_count and end_count.
	 */
	if (end_count - before_count > compare - before_count - 1)
		kvm_vz_queue_irq(vcpu, MIPS_EXC_INT_TIMER);

	/*
	 * Restore soft-timer, ignoring a small amount of negative drift due to
	 * delay between freeze_hrtimer and setting CP0_GTOffset.
	 */
	kvm_mips_restore_hrtimer(vcpu, before_time, end_count, -0x10000);
}

/**
 * kvm_vz_save_timer() - Save guest timer state.
 * @vcpu:	Virtual CPU.
 *
 * Save VZ guest timer state and switch to soft guest timer if hard timer was in
 * use.
 */
static void kvm_vz_save_timer(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	u32 gctl0, compare, cause;

	gctl0 = read_c0_guestctl0();
	if (gctl0 & MIPS_GCTL0_GT) {
		/* disable guest use of hard timer */
		write_c0_guestctl0(gctl0 & ~MIPS_GCTL0_GT);

		/* save hard timer state */
		_kvm_vz_save_htimer(vcpu, &compare, &cause);
	} else {
		compare = read_gc0_compare();
		cause = read_gc0_cause();
	}

	/* save timer-related state to VCPU context */
	kvm_write_sw_gc0_cause(cop0, cause);
	kvm_write_sw_gc0_compare(cop0, compare);
}

/**
 * kvm_vz_lose_htimer() - Ensure hard guest timer is not in use.
 * @vcpu:	Virtual CPU.
 *
 * Transfers the state of the hard guest timer to the soft guest timer, leaving
 * guest state intact so it can continue to be used with the soft timer.
 */
void kvm_vz_lose_htimer(struct kvm_vcpu *vcpu)
{
	u32 gctl0, compare, cause;

	preempt_disable();
	gctl0 = read_c0_guestctl0();
	if (gctl0 & MIPS_GCTL0_GT) {
		/* disable guest use of timer */
		write_c0_guestctl0(gctl0 & ~MIPS_GCTL0_GT);

		/* switch to soft timer */
		_kvm_vz_save_htimer(vcpu, &compare, &cause);

		/* leave soft timer in usable state */
		_kvm_vz_restore_stimer(vcpu, compare, cause);
	}
	preempt_enable();
}

/**
 * is_eva_access() - Find whether an instruction is an EVA memory accessor.
 * @inst:	32-bit instruction encoding.
 *
 * Finds whether @inst encodes an EVA memory access instruction, which would
 * indicate that emulation of it should access the user mode address space
 * instead of the kernel mode address space. This matters for MUSUK segments
 * which are TLB mapped for user mode but unmapped for kernel mode.
 *
 * Returns:	Whether @inst encodes an EVA accessor instruction.
 */
static bool is_eva_access(union mips_instruction inst)
{
	if (inst.spec3_format.opcode != spec3_op)
		return false;

	switch (inst.spec3_format.func) {
	case lwle_op:
	case lwre_op:
	case cachee_op:
	case sbe_op:
	case she_op:
	case sce_op:
	case swe_op:
	case swle_op:
	case swre_op:
	case prefe_op:
	case lbue_op:
	case lhue_op:
	case lbe_op:
	case lhe_op:
	case lle_op:
	case lwe_op:
		return true;
	default:
		return false;
	}
}

/**
 * is_eva_am_mapped() - Find whether an access mode is mapped.
 * @vcpu:	KVM VCPU state.
 * @am:		3-bit encoded access mode.
 * @eu:		Segment becomes unmapped and uncached when Status.ERL=1.
 *
 * Decode @am to find whether it encodes a mapped segment for the current VCPU
 * state. Where necessary @eu and the actual instruction causing the fault are
 * taken into account to make the decision.
 *
 * Returns:	Whether the VCPU faulted on a TLB mapped address.
 */
static bool is_eva_am_mapped(struct kvm_vcpu *vcpu, unsigned int am, bool eu)
{
	u32 am_lookup;
	int err;

	/*
	 * Interpret access control mode. We assume address errors will already
	 * have been caught by the guest, leaving us with:
	 *      AM      UM  SM  KM  31..24 23..16
	 * UK    0 000          Unm   0      0
	 * MK    1 001          TLB   1
	 * MSK   2 010      TLB TLB   1
	 * MUSK  3 011  TLB TLB TLB   1
	 * MUSUK 4 100  TLB TLB Unm   0      1
	 * USK   5 101      Unm Unm   0      0
	 * -     6 110                0      0
	 * UUSK  7 111  Unm Unm Unm   0      0
	 *
	 * We shift a magic value by AM across the sign bit to find if always
	 * TLB mapped, and if not shift by 8 again to find if it depends on KM.
	 */
	am_lookup = 0x70080000 << am;
	if ((s32)am_lookup < 0) {
		/*
		 * MK, MSK, MUSK
		 * Always TLB mapped, unless SegCtl.EU && ERL
		 */
		if (!eu || !(read_gc0_status() & ST0_ERL))
			return true;
	} else {
		am_lookup <<= 8;
		if ((s32)am_lookup < 0) {
			union mips_instruction inst;
			unsigned int status;
			u32 *opc;

			/*
			 * MUSUK
			 * TLB mapped if not in kernel mode
			 */
			status = read_gc0_status();
			if (!(status & (ST0_EXL | ST0_ERL)) &&
			    (status & ST0_KSU))
				return true;
			/*
			 * EVA access instructions in kernel
			 * mode access user address space.
			 */
			opc = (u32 *)vcpu->arch.pc;
			if (vcpu->arch.host_cp0_cause & CAUSEF_BD)
				opc += 1;
			err = kvm_get_badinstr(opc, vcpu, &inst.word);
			if (!err && is_eva_access(inst))
				return true;
		}
	}

	return false;
}

/**
 * kvm_vz_gva_to_gpa() - Convert valid GVA to GPA.
 * @vcpu:	KVM VCPU state.
 * @gva:	Guest virtual address to convert.
 * @gpa:	Output guest physical address.
 *
 * Convert a guest virtual address (GVA) which is valid according to the guest
 * context, to a guest physical address (GPA).
 *
 * Returns:	0 on success.
 *		-errno on failure.
 */
static int kvm_vz_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
			     unsigned long *gpa)
{
	u32 gva32 = gva;
	unsigned long segctl;

	if ((long)gva == (s32)gva32) {
		/* Handle canonical 32-bit virtual address */
		if (cpu_guest_has_segments) {
			unsigned long mask, pa;

			switch (gva32 >> 29) {
			case 0:
			case 1: /* CFG5 (1GB) */
				segctl = read_gc0_segctl2() >> 16;
				mask = (unsigned long)0xfc0000000ull;
				break;
			case 2:
			case 3: /* CFG4 (1GB) */
				segctl = read_gc0_segctl2();
				mask = (unsigned long)0xfc0000000ull;
				break;
			case 4: /* CFG3 (512MB) */
				segctl = read_gc0_segctl1() >> 16;
				mask = (unsigned long)0xfe0000000ull;
				break;
			case 5: /* CFG2 (512MB) */
				segctl = read_gc0_segctl1();
				mask = (unsigned long)0xfe0000000ull;
				break;
			case 6: /* CFG1 (512MB) */
				segctl = read_gc0_segctl0() >> 16;
				mask = (unsigned long)0xfe0000000ull;
				break;
			case 7: /* CFG0 (512MB) */
				segctl = read_gc0_segctl0();
				mask = (unsigned long)0xfe0000000ull;
				break;
			default:
				/*
				 * GCC 4.9 isn't smart enough to figure out that
				 * segctl and mask are always initialised.
				 */
				unreachable();
			}

			if (is_eva_am_mapped(vcpu, (segctl >> 4) & 0x7,
					     segctl & 0x0008))
				goto tlb_mapped;

			/* Unmapped, find guest physical address */
			pa = (segctl << 20) & mask;
			pa |= gva32 & ~mask;
			*gpa = pa;
			return 0;
		} else if ((s32)gva32 < (s32)0xc0000000) {
			/* legacy unmapped KSeg0 or KSeg1 */
			*gpa = gva32 & 0x1fffffff;
			return 0;
		}
#ifdef CONFIG_64BIT
	} else if ((gva & 0xc000000000000000) == 0x8000000000000000) {
		/* XKPHYS */
		if (cpu_guest_has_segments) {
			/*
			 * Each of the 8 regions can be overridden by SegCtl2.XR
			 * to use SegCtl1.XAM.
			 */
			segctl = read_gc0_segctl2();
			if (segctl & (1ull << (56 + ((gva >> 59) & 0x7)))) {
				segctl = read_gc0_segctl1();
				if (is_eva_am_mapped(vcpu, (segctl >> 59) & 0x7,
						     0))
					goto tlb_mapped;
			}

		}
		/*
		 * Traditionally fully unmapped.
		 * Bits 61:59 specify the CCA, which we can just mask off here.
		 * Bits 58:PABITS should be zero, but we shouldn't have got here
		 * if it wasn't.
		 */
		*gpa = gva & 0x07ffffffffffffff;
		return 0;
#endif
	}

tlb_mapped:
	return kvm_vz_guest_tlb_lookup(vcpu, gva, gpa);
}

/**
 * kvm_vz_badvaddr_to_gpa() - Convert GVA BadVAddr from root exception to GPA.
 * @vcpu:	KVM VCPU state.
 * @badvaddr:	Root BadVAddr.
 * @gpa:	Output guest physical address.
 *
 * VZ implementations are permitted to report guest virtual addresses (GVA) in
 * BadVAddr on a root exception during guest execution, instead of the more
 * convenient guest physical addresses (GPA). When we get a GVA, this function
 * converts it to a GPA, taking into account guest segmentation and guest TLB
 * state.
 *
 * Returns:	0 on success.
 *		-errno on failure.
 */
static int kvm_vz_badvaddr_to_gpa(struct kvm_vcpu *vcpu, unsigned long badvaddr,
				  unsigned long *gpa)
{
	unsigned int gexccode = (vcpu->arch.host_cp0_guestctl0 &
				 MIPS_GCTL0_GEXC) >> MIPS_GCTL0_GEXC_SHIFT;

	/* If BadVAddr is GPA, then all is well in the world */
	if (likely(gexccode == MIPS_GCTL0_GEXC_GPA)) {
		*gpa = badvaddr;
		return 0;
	}

	/* Otherwise we'd expect it to be GVA ... */
	if (WARN(gexccode != MIPS_GCTL0_GEXC_GVA,
		 "Unexpected gexccode %#x\n", gexccode))
		return -EINVAL;

	/* ... and we need to perform the GVA->GPA translation in software */
	return kvm_vz_gva_to_gpa(vcpu, badvaddr, gpa);
}

static int kvm_trap_vz_no_handler(struct kvm_vcpu *vcpu)
{
	u32 *opc = (u32 *) vcpu->arch.pc;
	u32 cause = vcpu->arch.host_cp0_cause;
	u32 exccode = (cause & CAUSEF_EXCCODE) >> CAUSEB_EXCCODE;
	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
	u32 inst = 0;

	/*
	 *  Fetch the instruction.
	 */
	if (cause & CAUSEF_BD)
		opc += 1;
	kvm_get_badinstr(opc, vcpu, &inst);

	kvm_err("Exception Code: %d not handled @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#x\n",
		exccode, opc, inst, badvaddr,
		read_gc0_status());
	kvm_arch_vcpu_dump_regs(vcpu);
	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
	return RESUME_HOST;
}

static unsigned long mips_process_maar(unsigned int op, unsigned long val)
{
	/* Mask off unused bits */
	unsigned long mask = 0xfffff000 | MIPS_MAAR_S | MIPS_MAAR_VL;

	if (read_gc0_pagegrain() & PG_ELPA)
		mask |= 0x00ffffff00000000ull;
	if (cpu_guest_has_mvh)
		mask |= MIPS_MAAR_VH;

	/* Set or clear VH */
	if (op == mtc_op) {
		/* clear VH */
		val &= ~MIPS_MAAR_VH;
	} else if (op == dmtc_op) {
		/* set VH to match VL */
		val &= ~MIPS_MAAR_VH;
		if (val & MIPS_MAAR_VL)
			val |= MIPS_MAAR_VH;
	}

	return val & mask;
}

static void kvm_write_maari(struct kvm_vcpu *vcpu, unsigned long val)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;

	val &= MIPS_MAARI_INDEX;
	if (val == MIPS_MAARI_INDEX)
		kvm_write_sw_gc0_maari(cop0, ARRAY_SIZE(vcpu->arch.maar) - 1);
	else if (val < ARRAY_SIZE(vcpu->arch.maar))
		kvm_write_sw_gc0_maari(cop0, val);
}

static enum emulation_result kvm_vz_gpsi_cop0(union mips_instruction inst,
					      u32 *opc, u32 cause,
					      struct kvm_run *run,
					      struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	enum emulation_result er = EMULATE_DONE;
	u32 rt, rd, sel;
	unsigned long curr_pc;
	unsigned long val;

	/*
	 * Update PC and hold onto current PC in case there is
	 * an error and we want to rollback the PC
	 */
	curr_pc = vcpu->arch.pc;
	er = update_pc(vcpu, cause);
	if (er == EMULATE_FAIL)
		return er;

	if (inst.co_format.co) {
		switch (inst.co_format.func) {
		case wait_op:
			er = kvm_mips_emul_wait(vcpu);
			break;
		default:
			er = EMULATE_FAIL;
		}
	} else {
		rt = inst.c0r_format.rt;
		rd = inst.c0r_format.rd;
		sel = inst.c0r_format.sel;

		switch (inst.c0r_format.rs) {
		case dmfc_op:
		case mfc_op:
#ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
			cop0->stat[rd][sel]++;
#endif
			if (rd == MIPS_CP0_COUNT &&
			    sel == 0) {			/* Count */
				val = kvm_mips_read_count(vcpu);
			} else if (rd == MIPS_CP0_COMPARE &&
				   sel == 0) {		/* Compare */
				val = read_gc0_compare();
			} else if (rd == MIPS_CP0_LLADDR &&
				   sel == 0) {		/* LLAddr */
				if (cpu_guest_has_rw_llb)
					val = read_gc0_lladdr() &
						MIPS_LLADDR_LLB;
				else
					val = 0;
			} else if (rd == MIPS_CP0_LLADDR &&
				   sel == 1 &&		/* MAAR */
				   cpu_guest_has_maar &&
				   !cpu_guest_has_dyn_maar) {
				/* MAARI must be in range */
				BUG_ON(kvm_read_sw_gc0_maari(cop0) >=
						ARRAY_SIZE(vcpu->arch.maar));
				val = vcpu->arch.maar[
					kvm_read_sw_gc0_maari(cop0)];
			} else if ((rd == MIPS_CP0_PRID &&
				    (sel == 0 ||	/* PRid */
				     sel == 2 ||	/* CDMMBase */
				     sel == 3)) ||	/* CMGCRBase */
				   (rd == MIPS_CP0_STATUS &&
				    (sel == 2 ||	/* SRSCtl */
				     sel == 3)) ||	/* SRSMap */
				   (rd == MIPS_CP0_CONFIG &&
				    (sel == 7)) ||	/* Config7 */
				   (rd == MIPS_CP0_LLADDR &&
				    (sel == 2) &&	/* MAARI */
				    cpu_guest_has_maar &&
				    !cpu_guest_has_dyn_maar) ||
				   (rd == MIPS_CP0_ERRCTL &&
				    (sel == 0))) {	/* ErrCtl */
				val = cop0->reg[rd][sel];
			} else {
				val = 0;
				er = EMULATE_FAIL;
			}

			if (er != EMULATE_FAIL) {
				/* Sign extend */
				if (inst.c0r_format.rs == mfc_op)
					val = (int)val;
				vcpu->arch.gprs[rt] = val;
			}

			trace_kvm_hwr(vcpu, (inst.c0r_format.rs == mfc_op) ?
					KVM_TRACE_MFC0 : KVM_TRACE_DMFC0,
				      KVM_TRACE_COP0(rd, sel), val);
			break;

		case dmtc_op:
		case mtc_op:
#ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
			cop0->stat[rd][sel]++;
#endif
			val = vcpu->arch.gprs[rt];
			trace_kvm_hwr(vcpu, (inst.c0r_format.rs == mtc_op) ?
					KVM_TRACE_MTC0 : KVM_TRACE_DMTC0,
				      KVM_TRACE_COP0(rd, sel), val);

			if (rd == MIPS_CP0_COUNT &&
			    sel == 0) {			/* Count */
				kvm_vz_lose_htimer(vcpu);
				kvm_mips_write_count(vcpu, vcpu->arch.gprs[rt]);
			} else if (rd == MIPS_CP0_COMPARE &&
				   sel == 0) {		/* Compare */
				kvm_mips_write_compare(vcpu,
						       vcpu->arch.gprs[rt],
						       true);
			} else if (rd == MIPS_CP0_LLADDR &&
				   sel == 0) {		/* LLAddr */
				/*
				 * P5600 generates GPSI on guest MTC0 LLAddr.
				 * Only allow the guest to clear LLB.
				 */
				if (cpu_guest_has_rw_llb &&
				    !(val & MIPS_LLADDR_LLB))
					write_gc0_lladdr(0);
			} else if (rd == MIPS_CP0_LLADDR &&
				   sel == 1 &&		/* MAAR */
				   cpu_guest_has_maar &&
				   !cpu_guest_has_dyn_maar) {
				val = mips_process_maar(inst.c0r_format.rs,
							val);

				/* MAARI must be in range */
				BUG_ON(kvm_read_sw_gc0_maari(cop0) >=
						ARRAY_SIZE(vcpu->arch.maar));
				vcpu->arch.maar[kvm_read_sw_gc0_maari(cop0)] =
									val;
			} else if (rd == MIPS_CP0_LLADDR &&
				   (sel == 2) &&	/* MAARI */
				   cpu_guest_has_maar &&
				   !cpu_guest_has_dyn_maar) {
				kvm_write_maari(vcpu, val);
			} else if (rd == MIPS_CP0_ERRCTL &&
				   (sel == 0)) {	/* ErrCtl */
				/* ignore the written value */
			} else {
				er = EMULATE_FAIL;
			}
			break;

		default:
			er = EMULATE_FAIL;
			break;
		}
	}
	/* Rollback PC only if emulation was unsuccessful */
	if (er == EMULATE_FAIL) {
		kvm_err("[%#lx]%s: unsupported cop0 instruction 0x%08x\n",
			curr_pc, __func__, inst.word);

		vcpu->arch.pc = curr_pc;
	}

	return er;
}

static enum emulation_result kvm_vz_gpsi_cache(union mips_instruction inst,
					       u32 *opc, u32 cause,
					       struct kvm_run *run,
					       struct kvm_vcpu *vcpu)
{
	enum emulation_result er = EMULATE_DONE;
	u32 cache, op_inst, op, base;
	s16 offset;
	struct kvm_vcpu_arch *arch = &vcpu->arch;
	unsigned long va, curr_pc;

	/*
	 * Update PC and hold onto current PC in case there is
	 * an error and we want to rollback the PC
	 */
	curr_pc = vcpu->arch.pc;
	er = update_pc(vcpu, cause);
	if (er == EMULATE_FAIL)
		return er;

	base = inst.i_format.rs;
	op_inst = inst.i_format.rt;
	if (cpu_has_mips_r6)
		offset = inst.spec3_format.simmediate;
	else
		offset = inst.i_format.simmediate;
	cache = op_inst & CacheOp_Cache;
	op = op_inst & CacheOp_Op;

	va = arch->gprs[base] + offset;

	kvm_debug("CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
		  cache, op, base, arch->gprs[base], offset);

	/* Secondary or tirtiary cache ops ignored */
	if (cache != Cache_I && cache != Cache_D)
		return EMULATE_DONE;

	switch (op_inst) {
	case Index_Invalidate_I:
		flush_icache_line_indexed(va);
		return EMULATE_DONE;
	case Index_Writeback_Inv_D:
		flush_dcache_line_indexed(va);
		return EMULATE_DONE;
	case Hit_Invalidate_I:
	case Hit_Invalidate_D:
	case Hit_Writeback_Inv_D:
		if (boot_cpu_type() == CPU_CAVIUM_OCTEON3) {
			/* We can just flush entire icache */
			local_flush_icache_range(0, 0);
			return EMULATE_DONE;
		}

		/* So far, other platforms support guest hit cache ops */
		break;
	default:
		break;
	};

	kvm_err("@ %#lx/%#lx CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
		curr_pc, vcpu->arch.gprs[31], cache, op, base, arch->gprs[base],
		offset);
	/* Rollback PC */
	vcpu->arch.pc = curr_pc;

	return EMULATE_FAIL;
}

static enum emulation_result kvm_trap_vz_handle_gpsi(u32 cause, u32 *opc,
						     struct kvm_vcpu *vcpu)
{
	enum emulation_result er = EMULATE_DONE;
	struct kvm_vcpu_arch *arch = &vcpu->arch;
	struct kvm_run *run = vcpu->run;
	union mips_instruction inst;
	int rd, rt, sel;
	int err;

	/*
	 *  Fetch the instruction.
	 */
	if (cause & CAUSEF_BD)
		opc += 1;
	err = kvm_get_badinstr(opc, vcpu, &inst.word);
	if (err)
		return EMULATE_FAIL;

	switch (inst.r_format.opcode) {
	case cop0_op:
		er = kvm_vz_gpsi_cop0(inst, opc, cause, run, vcpu);
		break;
#ifndef CONFIG_CPU_MIPSR6
	case cache_op:
		trace_kvm_exit(vcpu, KVM_TRACE_EXIT_CACHE);
		er = kvm_vz_gpsi_cache(inst, opc, cause, run, vcpu);
		break;
#endif
	case spec3_op:
		switch (inst.spec3_format.func) {
#ifdef CONFIG_CPU_MIPSR6
		case cache6_op:
			trace_kvm_exit(vcpu, KVM_TRACE_EXIT_CACHE);
			er = kvm_vz_gpsi_cache(inst, opc, cause, run, vcpu);
			break;
#endif
		case rdhwr_op:
			if (inst.r_format.rs || (inst.r_format.re >> 3))
				goto unknown;

			rd = inst.r_format.rd;
			rt = inst.r_format.rt;
			sel = inst.r_format.re & 0x7;

			switch (rd) {
			case MIPS_HWR_CC:	/* Read count register */
				arch->gprs[rt] =
					(long)(int)kvm_mips_read_count(vcpu);
				break;
			default:
				trace_kvm_hwr(vcpu, KVM_TRACE_RDHWR,
					      KVM_TRACE_HWR(rd, sel), 0);
				goto unknown;
			};

			trace_kvm_hwr(vcpu, KVM_TRACE_RDHWR,
				      KVM_TRACE_HWR(rd, sel), arch->gprs[rt]);

			er = update_pc(vcpu, cause);
			break;
		default:
			goto unknown;
		};
		break;
unknown:

	default:
		kvm_err("GPSI exception not supported (%p/%#x)\n",
				opc, inst.word);
		kvm_arch_vcpu_dump_regs(vcpu);
		er = EMULATE_FAIL;
		break;
	}

	return er;
}

static enum emulation_result kvm_trap_vz_handle_gsfc(u32 cause, u32 *opc,
						     struct kvm_vcpu *vcpu)
{
	enum emulation_result er = EMULATE_DONE;
	struct kvm_vcpu_arch *arch = &vcpu->arch;
	union mips_instruction inst;
	int err;

	/*
	 *  Fetch the instruction.
	 */
	if (cause & CAUSEF_BD)
		opc += 1;
	err = kvm_get_badinstr(opc, vcpu, &inst.word);
	if (err)
		return EMULATE_FAIL;

	/* complete MTC0 on behalf of guest and advance EPC */
	if (inst.c0r_format.opcode == cop0_op &&
	    inst.c0r_format.rs == mtc_op &&
	    inst.c0r_format.z == 0) {
		int rt = inst.c0r_format.rt;
		int rd = inst.c0r_format.rd;
		int sel = inst.c0r_format.sel;
		unsigned int val = arch->gprs[rt];
		unsigned int old_val, change;

		trace_kvm_hwr(vcpu, KVM_TRACE_MTC0, KVM_TRACE_COP0(rd, sel),
			      val);

		if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
			/* FR bit should read as zero if no FPU */
			if (!kvm_mips_guest_has_fpu(&vcpu->arch))
				val &= ~(ST0_CU1 | ST0_FR);

			/*
			 * Also don't allow FR to be set if host doesn't support
			 * it.
			 */
			if (!(boot_cpu_data.fpu_id & MIPS_FPIR_F64))
				val &= ~ST0_FR;

			old_val = read_gc0_status();
			change = val ^ old_val;

			if (change & ST0_FR) {
				/*
				 * FPU and Vector register state is made
				 * UNPREDICTABLE by a change of FR, so don't
				 * even bother saving it.
				 */
				kvm_drop_fpu(vcpu);
			}

			/*
			 * If MSA state is already live, it is undefined how it
			 * interacts with FR=0 FPU state, and we don't want to
			 * hit reserved instruction exceptions trying to save
			 * the MSA state later when CU=1 && FR=1, so play it
			 * safe and save it first.
			 */
			if (change & ST0_CU1 && !(val & ST0_FR) &&
			    vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA)
				kvm_lose_fpu(vcpu);

			write_gc0_status(val);
		} else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) {
			u32 old_cause = read_gc0_cause();
			u32 change = old_cause ^ val;

			/* DC bit enabling/disabling timer? */
			if (change & CAUSEF_DC) {
				if (val & CAUSEF_DC) {
					kvm_vz_lose_htimer(vcpu);
					kvm_mips_count_disable_cause(vcpu);
				} else {
					kvm_mips_count_enable_cause(vcpu);
				}
			}

			/* Only certain bits are RW to the guest */
			change &= (CAUSEF_DC | CAUSEF_IV | CAUSEF_WP |
				   CAUSEF_IP0 | CAUSEF_IP1);

			/* WP can only be cleared */
			change &= ~CAUSEF_WP | old_cause;

			write_gc0_cause(old_cause ^ change);
		} else if ((rd == MIPS_CP0_STATUS) && (sel == 1)) { /* IntCtl */
			write_gc0_intctl(val);
		} else if ((rd == MIPS_CP0_CONFIG) && (sel == 5)) {
			old_val = read_gc0_config5();
			change = val ^ old_val;
			/* Handle changes in FPU/MSA modes */
			preempt_disable();

			/*
			 * Propagate FRE changes immediately if the FPU
			 * context is already loaded.
			 */
			if (change & MIPS_CONF5_FRE &&
			    vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)
				change_c0_config5(MIPS_CONF5_FRE, val);

			preempt_enable();

			val = old_val ^
				(change & kvm_vz_config5_guest_wrmask(vcpu));
			write_gc0_config5(val);
		} else {
			kvm_err("Handle GSFC, unsupported field change @ %p: %#x\n",
			    opc, inst.word);
			er = EMULATE_FAIL;
		}

		if (er != EMULATE_FAIL)
			er = update_pc(vcpu, cause);
	} else {
		kvm_err("Handle GSFC, unrecognized instruction @ %p: %#x\n",
			opc, inst.word);
		er = EMULATE_FAIL;
	}

	return er;
}

static enum emulation_result kvm_trap_vz_handle_ghfc(u32 cause, u32 *opc,
						     struct kvm_vcpu *vcpu)
{
	/*
	 * Presumably this is due to MC (guest mode change), so lets trace some
	 * relevant info.
	 */
	trace_kvm_guest_mode_change(vcpu);

	return EMULATE_DONE;
}

static enum emulation_result kvm_trap_vz_handle_hc(u32 cause, u32 *opc,
						   struct kvm_vcpu *vcpu)
{
	enum emulation_result er;
	union mips_instruction inst;
	unsigned long curr_pc;
	int err;

	if (cause & CAUSEF_BD)
		opc += 1;
	err = kvm_get_badinstr(opc, vcpu, &inst.word);
	if (err)
		return EMULATE_FAIL;

	/*
	 * Update PC and hold onto current PC in case there is
	 * an error and we want to rollback the PC
	 */
	curr_pc = vcpu->arch.pc;
	er = update_pc(vcpu, cause);
	if (er == EMULATE_FAIL)
		return er;

	er = kvm_mips_emul_hypcall(vcpu, inst);
	if (er == EMULATE_FAIL)
		vcpu->arch.pc = curr_pc;

	return er;
}

static enum emulation_result kvm_trap_vz_no_handler_guest_exit(u32 gexccode,
							u32 cause,
							u32 *opc,
							struct kvm_vcpu *vcpu)
{
	u32 inst;

	/*
	 *  Fetch the instruction.
	 */
	if (cause & CAUSEF_BD)
		opc += 1;
	kvm_get_badinstr(opc, vcpu, &inst);

	kvm_err("Guest Exception Code: %d not yet handled @ PC: %p, inst: 0x%08x  Status: %#x\n",
		gexccode, opc, inst, read_gc0_status());

	return EMULATE_FAIL;
}

static int kvm_trap_vz_handle_guest_exit(struct kvm_vcpu *vcpu)
{
	u32 *opc = (u32 *) vcpu->arch.pc;
	u32 cause = vcpu->arch.host_cp0_cause;
	enum emulation_result er = EMULATE_DONE;
	u32 gexccode = (vcpu->arch.host_cp0_guestctl0 &
			MIPS_GCTL0_GEXC) >> MIPS_GCTL0_GEXC_SHIFT;
	int ret = RESUME_GUEST;

	trace_kvm_exit(vcpu, KVM_TRACE_EXIT_GEXCCODE_BASE + gexccode);
	switch (gexccode) {
	case MIPS_GCTL0_GEXC_GPSI:
		++vcpu->stat.vz_gpsi_exits;
		er = kvm_trap_vz_handle_gpsi(cause, opc, vcpu);
		break;
	case MIPS_GCTL0_GEXC_GSFC:
		++vcpu->stat.vz_gsfc_exits;
		er = kvm_trap_vz_handle_gsfc(cause, opc, vcpu);
		break;
	case MIPS_GCTL0_GEXC_HC:
		++vcpu->stat.vz_hc_exits;
		er = kvm_trap_vz_handle_hc(cause, opc, vcpu);
		break;
	case MIPS_GCTL0_GEXC_GRR:
		++vcpu->stat.vz_grr_exits;
		er = kvm_trap_vz_no_handler_guest_exit(gexccode, cause, opc,
						       vcpu);
		break;
	case MIPS_GCTL0_GEXC_GVA:
		++vcpu->stat.vz_gva_exits;
		er = kvm_trap_vz_no_handler_guest_exit(gexccode, cause, opc,
						       vcpu);
		break;
	case MIPS_GCTL0_GEXC_GHFC:
		++vcpu->stat.vz_ghfc_exits;
		er = kvm_trap_vz_handle_ghfc(cause, opc, vcpu);
		break;
	case MIPS_GCTL0_GEXC_GPA:
		++vcpu->stat.vz_gpa_exits;
		er = kvm_trap_vz_no_handler_guest_exit(gexccode, cause, opc,
						       vcpu);
		break;
	default:
		++vcpu->stat.vz_resvd_exits;
		er = kvm_trap_vz_no_handler_guest_exit(gexccode, cause, opc,
						       vcpu);
		break;

	}

	if (er == EMULATE_DONE) {
		ret = RESUME_GUEST;
	} else if (er == EMULATE_HYPERCALL) {
		ret = kvm_mips_handle_hypcall(vcpu);
	} else {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		ret = RESUME_HOST;
	}
	return ret;
}

/**
 * kvm_trap_vz_handle_cop_unusuable() - Guest used unusable coprocessor.
 * @vcpu:	Virtual CPU context.
 *
 * Handle when the guest attempts to use a coprocessor which hasn't been allowed
 * by the root context.
 */
static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	u32 cause = vcpu->arch.host_cp0_cause;
	enum emulation_result er = EMULATE_FAIL;
	int ret = RESUME_GUEST;

	if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) {
		/*
		 * If guest FPU not present, the FPU operation should have been
		 * treated as a reserved instruction!
		 * If FPU already in use, we shouldn't get this at all.
		 */
		if (WARN_ON(!kvm_mips_guest_has_fpu(&vcpu->arch) ||
			    vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)) {
			preempt_enable();
			return EMULATE_FAIL;
		}

		kvm_own_fpu(vcpu);
		er = EMULATE_DONE;
	}
	/* other coprocessors not handled */

	switch (er) {
	case EMULATE_DONE:
		ret = RESUME_GUEST;
		break;

	case EMULATE_FAIL:
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		ret = RESUME_HOST;
		break;

	default:
		BUG();
	}
	return ret;
}

/**
 * kvm_trap_vz_handle_msa_disabled() - Guest used MSA while disabled in root.
 * @vcpu:	Virtual CPU context.
 *
 * Handle when the guest attempts to use MSA when it is disabled in the root
 * context.
 */
static int kvm_trap_vz_handle_msa_disabled(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;

	/*
	 * If MSA not present or not exposed to guest or FR=0, the MSA operation
	 * should have been treated as a reserved instruction!
	 * Same if CU1=1, FR=0.
	 * If MSA already in use, we shouldn't get this at all.
	 */
	if (!kvm_mips_guest_has_msa(&vcpu->arch) ||
	    (read_gc0_status() & (ST0_CU1 | ST0_FR)) == ST0_CU1 ||
	    !(read_gc0_config5() & MIPS_CONF5_MSAEN) ||
	    vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA) {
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		return RESUME_HOST;
	}

	kvm_own_msa(vcpu);

	return RESUME_GUEST;
}

static int kvm_trap_vz_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	u32 *opc = (u32 *) vcpu->arch.pc;
	u32 cause = vcpu->arch.host_cp0_cause;
	ulong badvaddr = vcpu->arch.host_cp0_badvaddr;
	union mips_instruction inst;
	enum emulation_result er = EMULATE_DONE;
	int err, ret = RESUME_GUEST;

	if (kvm_mips_handle_vz_root_tlb_fault(badvaddr, vcpu, false)) {
		/* A code fetch fault doesn't count as an MMIO */
		if (kvm_is_ifetch_fault(&vcpu->arch)) {
			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
			return RESUME_HOST;
		}

		/* Fetch the instruction */
		if (cause & CAUSEF_BD)
			opc += 1;
		err = kvm_get_badinstr(opc, vcpu, &inst.word);
		if (err) {
			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
			return RESUME_HOST;
		}

		/* Treat as MMIO */
		er = kvm_mips_emulate_load(inst, cause, run, vcpu);
		if (er == EMULATE_FAIL) {
			kvm_err("Guest Emulate Load from MMIO space failed: PC: %p, BadVaddr: %#lx\n",
				opc, badvaddr);
			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		}
	}

	if (er == EMULATE_DONE) {
		ret = RESUME_GUEST;
	} else if (er == EMULATE_DO_MMIO) {
		run->exit_reason = KVM_EXIT_MMIO;
		ret = RESUME_HOST;
	} else {
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		ret = RESUME_HOST;
	}
	return ret;
}

static int kvm_trap_vz_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	u32 *opc = (u32 *) vcpu->arch.pc;
	u32 cause = vcpu->arch.host_cp0_cause;
	ulong badvaddr = vcpu->arch.host_cp0_badvaddr;
	union mips_instruction inst;
	enum emulation_result er = EMULATE_DONE;
	int err;
	int ret = RESUME_GUEST;

	/* Just try the access again if we couldn't do the translation */
	if (kvm_vz_badvaddr_to_gpa(vcpu, badvaddr, &badvaddr))
		return RESUME_GUEST;
	vcpu->arch.host_cp0_badvaddr = badvaddr;

	if (kvm_mips_handle_vz_root_tlb_fault(badvaddr, vcpu, true)) {
		/* Fetch the instruction */
		if (cause & CAUSEF_BD)
			opc += 1;
		err = kvm_get_badinstr(opc, vcpu, &inst.word);
		if (err) {
			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
			return RESUME_HOST;
		}

		/* Treat as MMIO */
		er = kvm_mips_emulate_store(inst, cause, run, vcpu);
		if (er == EMULATE_FAIL) {
			kvm_err("Guest Emulate Store to MMIO space failed: PC: %p, BadVaddr: %#lx\n",
				opc, badvaddr);
			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		}
	}

	if (er == EMULATE_DONE) {
		ret = RESUME_GUEST;
	} else if (er == EMULATE_DO_MMIO) {
		run->exit_reason = KVM_EXIT_MMIO;
		ret = RESUME_HOST;
	} else {
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		ret = RESUME_HOST;
	}
	return ret;
}

static u64 kvm_vz_get_one_regs[] = {
	KVM_REG_MIPS_CP0_INDEX,
	KVM_REG_MIPS_CP0_ENTRYLO0,
	KVM_REG_MIPS_CP0_ENTRYLO1,
	KVM_REG_MIPS_CP0_CONTEXT,
	KVM_REG_MIPS_CP0_PAGEMASK,
	KVM_REG_MIPS_CP0_PAGEGRAIN,
	KVM_REG_MIPS_CP0_WIRED,
	KVM_REG_MIPS_CP0_HWRENA,
	KVM_REG_MIPS_CP0_BADVADDR,
	KVM_REG_MIPS_CP0_COUNT,
	KVM_REG_MIPS_CP0_ENTRYHI,
	KVM_REG_MIPS_CP0_COMPARE,
	KVM_REG_MIPS_CP0_STATUS,
	KVM_REG_MIPS_CP0_INTCTL,
	KVM_REG_MIPS_CP0_CAUSE,
	KVM_REG_MIPS_CP0_EPC,
	KVM_REG_MIPS_CP0_PRID,
	KVM_REG_MIPS_CP0_EBASE,
	KVM_REG_MIPS_CP0_CONFIG,
	KVM_REG_MIPS_CP0_CONFIG1,
	KVM_REG_MIPS_CP0_CONFIG2,
	KVM_REG_MIPS_CP0_CONFIG3,
	KVM_REG_MIPS_CP0_CONFIG4,
	KVM_REG_MIPS_CP0_CONFIG5,
#ifdef CONFIG_64BIT
	KVM_REG_MIPS_CP0_XCONTEXT,
#endif
	KVM_REG_MIPS_CP0_ERROREPC,

	KVM_REG_MIPS_COUNT_CTL,
	KVM_REG_MIPS_COUNT_RESUME,
	KVM_REG_MIPS_COUNT_HZ,
};

static u64 kvm_vz_get_one_regs_contextconfig[] = {
	KVM_REG_MIPS_CP0_CONTEXTCONFIG,
#ifdef CONFIG_64BIT
	KVM_REG_MIPS_CP0_XCONTEXTCONFIG,
#endif
};

static u64 kvm_vz_get_one_regs_segments[] = {
	KVM_REG_MIPS_CP0_SEGCTL0,
	KVM_REG_MIPS_CP0_SEGCTL1,
	KVM_REG_MIPS_CP0_SEGCTL2,
};

static u64 kvm_vz_get_one_regs_htw[] = {
	KVM_REG_MIPS_CP0_PWBASE,
	KVM_REG_MIPS_CP0_PWFIELD,
	KVM_REG_MIPS_CP0_PWSIZE,
	KVM_REG_MIPS_CP0_PWCTL,
};

static u64 kvm_vz_get_one_regs_kscratch[] = {
	KVM_REG_MIPS_CP0_KSCRATCH1,
	KVM_REG_MIPS_CP0_KSCRATCH2,
	KVM_REG_MIPS_CP0_KSCRATCH3,
	KVM_REG_MIPS_CP0_KSCRATCH4,
	KVM_REG_MIPS_CP0_KSCRATCH5,
	KVM_REG_MIPS_CP0_KSCRATCH6,
};

static unsigned long kvm_vz_num_regs(struct kvm_vcpu *vcpu)
{
	unsigned long ret;

	ret = ARRAY_SIZE(kvm_vz_get_one_regs);
	if (cpu_guest_has_userlocal)
		++ret;
	if (cpu_guest_has_badinstr)
		++ret;
	if (cpu_guest_has_badinstrp)
		++ret;
	if (cpu_guest_has_contextconfig)
		ret += ARRAY_SIZE(kvm_vz_get_one_regs_contextconfig);
	if (cpu_guest_has_segments)
		ret += ARRAY_SIZE(kvm_vz_get_one_regs_segments);
	if (cpu_guest_has_htw)
		ret += ARRAY_SIZE(kvm_vz_get_one_regs_htw);
	if (cpu_guest_has_maar && !cpu_guest_has_dyn_maar)
		ret += 1 + ARRAY_SIZE(vcpu->arch.maar);
	ret += __arch_hweight8(cpu_data[0].guest.kscratch_mask);

	return ret;
}

static int kvm_vz_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices)
{
	u64 index;
	unsigned int i;

	if (copy_to_user(indices, kvm_vz_get_one_regs,
			 sizeof(kvm_vz_get_one_regs)))
		return -EFAULT;
	indices += ARRAY_SIZE(kvm_vz_get_one_regs);

	if (cpu_guest_has_userlocal) {
		index = KVM_REG_MIPS_CP0_USERLOCAL;
		if (copy_to_user(indices, &index, sizeof(index)))
			return -EFAULT;
		++indices;
	}
	if (cpu_guest_has_badinstr) {
		index = KVM_REG_MIPS_CP0_BADINSTR;
		if (copy_to_user(indices, &index, sizeof(index)))
			return -EFAULT;
		++indices;
	}
	if (cpu_guest_has_badinstrp) {
		index = KVM_REG_MIPS_CP0_BADINSTRP;
		if (copy_to_user(indices, &index, sizeof(index)))
			return -EFAULT;
		++indices;
	}
	if (cpu_guest_has_contextconfig) {
		if (copy_to_user(indices, kvm_vz_get_one_regs_contextconfig,
				 sizeof(kvm_vz_get_one_regs_contextconfig)))
			return -EFAULT;
		indices += ARRAY_SIZE(kvm_vz_get_one_regs_contextconfig);
	}
	if (cpu_guest_has_segments) {
		if (copy_to_user(indices, kvm_vz_get_one_regs_segments,
				 sizeof(kvm_vz_get_one_regs_segments)))
			return -EFAULT;
		indices += ARRAY_SIZE(kvm_vz_get_one_regs_segments);
	}
	if (cpu_guest_has_htw) {
		if (copy_to_user(indices, kvm_vz_get_one_regs_htw,
				 sizeof(kvm_vz_get_one_regs_htw)))
			return -EFAULT;
		indices += ARRAY_SIZE(kvm_vz_get_one_regs_htw);
	}
	if (cpu_guest_has_maar && !cpu_guest_has_dyn_maar) {
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.maar); ++i) {
			index = KVM_REG_MIPS_CP0_MAAR(i);
			if (copy_to_user(indices, &index, sizeof(index)))
				return -EFAULT;
			++indices;
		}

		index = KVM_REG_MIPS_CP0_MAARI;
		if (copy_to_user(indices, &index, sizeof(index)))
			return -EFAULT;
		++indices;
	}
	for (i = 0; i < 6; ++i) {
		if (!cpu_guest_has_kscr(i + 2))
			continue;

		if (copy_to_user(indices, &kvm_vz_get_one_regs_kscratch[i],
				 sizeof(kvm_vz_get_one_regs_kscratch[i])))
			return -EFAULT;
		++indices;
	}

	return 0;
}

static inline s64 entrylo_kvm_to_user(unsigned long v)
{
	s64 mask, ret = v;

	if (BITS_PER_LONG == 32) {
		/*
		 * KVM API exposes 64-bit version of the register, so move the
		 * RI/XI bits up into place.
		 */
		mask = MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI;
		ret &= ~mask;
		ret |= ((s64)v & mask) << 32;
	}
	return ret;
}

static inline unsigned long entrylo_user_to_kvm(s64 v)
{
	unsigned long mask, ret = v;

	if (BITS_PER_LONG == 32) {
		/*
		 * KVM API exposes 64-bit versiono of the register, so move the
		 * RI/XI bits down into place.
		 */
		mask = MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI;
		ret &= ~mask;
		ret |= (v >> 32) & mask;
	}
	return ret;
}

static int kvm_vz_get_one_reg(struct kvm_vcpu *vcpu,
			      const struct kvm_one_reg *reg,
			      s64 *v)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	unsigned int idx;

	switch (reg->id) {
	case KVM_REG_MIPS_CP0_INDEX:
		*v = (long)read_gc0_index();
		break;
	case KVM_REG_MIPS_CP0_ENTRYLO0:
		*v = entrylo_kvm_to_user(read_gc0_entrylo0());
		break;
	case KVM_REG_MIPS_CP0_ENTRYLO1:
		*v = entrylo_kvm_to_user(read_gc0_entrylo1());
		break;
	case KVM_REG_MIPS_CP0_CONTEXT:
		*v = (long)read_gc0_context();
		break;
	case KVM_REG_MIPS_CP0_CONTEXTCONFIG:
		if (!cpu_guest_has_contextconfig)
			return -EINVAL;
		*v = read_gc0_contextconfig();
		break;
	case KVM_REG_MIPS_CP0_USERLOCAL:
		if (!cpu_guest_has_userlocal)
			return -EINVAL;
		*v = read_gc0_userlocal();
		break;
#ifdef CONFIG_64BIT
	case KVM_REG_MIPS_CP0_XCONTEXTCONFIG:
		if (!cpu_guest_has_contextconfig)
			return -EINVAL;
		*v = read_gc0_xcontextconfig();
		break;
#endif
	case KVM_REG_MIPS_CP0_PAGEMASK:
		*v = (long)read_gc0_pagemask();
		break;
	case KVM_REG_MIPS_CP0_PAGEGRAIN:
		*v = (long)read_gc0_pagegrain();
		break;
	case KVM_REG_MIPS_CP0_SEGCTL0:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		*v = read_gc0_segctl0();
		break;
	case KVM_REG_MIPS_CP0_SEGCTL1:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		*v = read_gc0_segctl1();
		break;
	case KVM_REG_MIPS_CP0_SEGCTL2:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		*v = read_gc0_segctl2();
		break;
	case KVM_REG_MIPS_CP0_PWBASE:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		*v = read_gc0_pwbase();
		break;
	case KVM_REG_MIPS_CP0_PWFIELD:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		*v = read_gc0_pwfield();
		break;
	case KVM_REG_MIPS_CP0_PWSIZE:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		*v = read_gc0_pwsize();
		break;
	case KVM_REG_MIPS_CP0_WIRED:
		*v = (long)read_gc0_wired();
		break;
	case KVM_REG_MIPS_CP0_PWCTL:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		*v = read_gc0_pwctl();
		break;
	case KVM_REG_MIPS_CP0_HWRENA:
		*v = (long)read_gc0_hwrena();
		break;
	case KVM_REG_MIPS_CP0_BADVADDR:
		*v = (long)read_gc0_badvaddr();
		break;
	case KVM_REG_MIPS_CP0_BADINSTR:
		if (!cpu_guest_has_badinstr)
			return -EINVAL;
		*v = read_gc0_badinstr();
		break;
	case KVM_REG_MIPS_CP0_BADINSTRP:
		if (!cpu_guest_has_badinstrp)
			return -EINVAL;
		*v = read_gc0_badinstrp();
		break;
	case KVM_REG_MIPS_CP0_COUNT:
		*v = kvm_mips_read_count(vcpu);
		break;
	case KVM_REG_MIPS_CP0_ENTRYHI:
		*v = (long)read_gc0_entryhi();
		break;
	case KVM_REG_MIPS_CP0_COMPARE:
		*v = (long)read_gc0_compare();
		break;
	case KVM_REG_MIPS_CP0_STATUS:
		*v = (long)read_gc0_status();
		break;
	case KVM_REG_MIPS_CP0_INTCTL:
		*v = read_gc0_intctl();
		break;
	case KVM_REG_MIPS_CP0_CAUSE:
		*v = (long)read_gc0_cause();
		break;
	case KVM_REG_MIPS_CP0_EPC:
		*v = (long)read_gc0_epc();
		break;
	case KVM_REG_MIPS_CP0_PRID:
		switch (boot_cpu_type()) {
		case CPU_CAVIUM_OCTEON3:
			/* Octeon III has a read-only guest.PRid */
			*v = read_gc0_prid();
			break;
		default:
			*v = (long)kvm_read_c0_guest_prid(cop0);
			break;
		};
		break;
	case KVM_REG_MIPS_CP0_EBASE:
		*v = kvm_vz_read_gc0_ebase();
		break;
	case KVM_REG_MIPS_CP0_CONFIG:
		*v = read_gc0_config();
		break;
	case KVM_REG_MIPS_CP0_CONFIG1:
		if (!cpu_guest_has_conf1)
			return -EINVAL;
		*v = read_gc0_config1();
		break;
	case KVM_REG_MIPS_CP0_CONFIG2:
		if (!cpu_guest_has_conf2)
			return -EINVAL;
		*v = read_gc0_config2();
		break;
	case KVM_REG_MIPS_CP0_CONFIG3:
		if (!cpu_guest_has_conf3)
			return -EINVAL;
		*v = read_gc0_config3();
		break;
	case KVM_REG_MIPS_CP0_CONFIG4:
		if (!cpu_guest_has_conf4)
			return -EINVAL;
		*v = read_gc0_config4();
		break;
	case KVM_REG_MIPS_CP0_CONFIG5:
		if (!cpu_guest_has_conf5)
			return -EINVAL;
		*v = read_gc0_config5();
		break;
	case KVM_REG_MIPS_CP0_MAAR(0) ... KVM_REG_MIPS_CP0_MAAR(0x3f):
		if (!cpu_guest_has_maar || cpu_guest_has_dyn_maar)
			return -EINVAL;
		idx = reg->id - KVM_REG_MIPS_CP0_MAAR(0);
		if (idx >= ARRAY_SIZE(vcpu->arch.maar))
			return -EINVAL;
		*v = vcpu->arch.maar[idx];
		break;
	case KVM_REG_MIPS_CP0_MAARI:
		if (!cpu_guest_has_maar || cpu_guest_has_dyn_maar)
			return -EINVAL;
		*v = kvm_read_sw_gc0_maari(vcpu->arch.cop0);
		break;
#ifdef CONFIG_64BIT
	case KVM_REG_MIPS_CP0_XCONTEXT:
		*v = read_gc0_xcontext();
		break;
#endif
	case KVM_REG_MIPS_CP0_ERROREPC:
		*v = (long)read_gc0_errorepc();
		break;
	case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6:
		idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2;
		if (!cpu_guest_has_kscr(idx))
			return -EINVAL;
		switch (idx) {
		case 2:
			*v = (long)read_gc0_kscratch1();
			break;
		case 3:
			*v = (long)read_gc0_kscratch2();
			break;
		case 4:
			*v = (long)read_gc0_kscratch3();
			break;
		case 5:
			*v = (long)read_gc0_kscratch4();
			break;
		case 6:
			*v = (long)read_gc0_kscratch5();
			break;
		case 7:
			*v = (long)read_gc0_kscratch6();
			break;
		}
		break;
	case KVM_REG_MIPS_COUNT_CTL:
		*v = vcpu->arch.count_ctl;
		break;
	case KVM_REG_MIPS_COUNT_RESUME:
		*v = ktime_to_ns(vcpu->arch.count_resume);
		break;
	case KVM_REG_MIPS_COUNT_HZ:
		*v = vcpu->arch.count_hz;
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

static int kvm_vz_set_one_reg(struct kvm_vcpu *vcpu,
			      const struct kvm_one_reg *reg,
			      s64 v)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	unsigned int idx;
	int ret = 0;
	unsigned int cur, change;

	switch (reg->id) {
	case KVM_REG_MIPS_CP0_INDEX:
		write_gc0_index(v);
		break;
	case KVM_REG_MIPS_CP0_ENTRYLO0:
		write_gc0_entrylo0(entrylo_user_to_kvm(v));
		break;
	case KVM_REG_MIPS_CP0_ENTRYLO1:
		write_gc0_entrylo1(entrylo_user_to_kvm(v));
		break;
	case KVM_REG_MIPS_CP0_CONTEXT:
		write_gc0_context(v);
		break;
	case KVM_REG_MIPS_CP0_CONTEXTCONFIG:
		if (!cpu_guest_has_contextconfig)
			return -EINVAL;
		write_gc0_contextconfig(v);
		break;
	case KVM_REG_MIPS_CP0_USERLOCAL:
		if (!cpu_guest_has_userlocal)
			return -EINVAL;
		write_gc0_userlocal(v);
		break;
#ifdef CONFIG_64BIT
	case KVM_REG_MIPS_CP0_XCONTEXTCONFIG:
		if (!cpu_guest_has_contextconfig)
			return -EINVAL;
		write_gc0_xcontextconfig(v);
		break;
#endif
	case KVM_REG_MIPS_CP0_PAGEMASK:
		write_gc0_pagemask(v);
		break;
	case KVM_REG_MIPS_CP0_PAGEGRAIN:
		write_gc0_pagegrain(v);
		break;
	case KVM_REG_MIPS_CP0_SEGCTL0:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		write_gc0_segctl0(v);
		break;
	case KVM_REG_MIPS_CP0_SEGCTL1:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		write_gc0_segctl1(v);
		break;
	case KVM_REG_MIPS_CP0_SEGCTL2:
		if (!cpu_guest_has_segments)
			return -EINVAL;
		write_gc0_segctl2(v);
		break;
	case KVM_REG_MIPS_CP0_PWBASE:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		write_gc0_pwbase(v);
		break;
	case KVM_REG_MIPS_CP0_PWFIELD:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		write_gc0_pwfield(v);
		break;
	case KVM_REG_MIPS_CP0_PWSIZE:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		write_gc0_pwsize(v);
		break;
	case KVM_REG_MIPS_CP0_WIRED:
		change_gc0_wired(MIPSR6_WIRED_WIRED, v);
		break;
	case KVM_REG_MIPS_CP0_PWCTL:
		if (!cpu_guest_has_htw)
			return -EINVAL;
		write_gc0_pwctl(v);
		break;
	case KVM_REG_MIPS_CP0_HWRENA:
		write_gc0_hwrena(v);
		break;
	case KVM_REG_MIPS_CP0_BADVADDR:
		write_gc0_badvaddr(v);
		break;
	case KVM_REG_MIPS_CP0_BADINSTR:
		if (!cpu_guest_has_badinstr)
			return -EINVAL;
		write_gc0_badinstr(v);
		break;
	case KVM_REG_MIPS_CP0_BADINSTRP:
		if (!cpu_guest_has_badinstrp)
			return -EINVAL;
		write_gc0_badinstrp(v);
		break;
	case KVM_REG_MIPS_CP0_COUNT:
		kvm_mips_write_count(vcpu, v);
		break;
	case KVM_REG_MIPS_CP0_ENTRYHI:
		write_gc0_entryhi(v);
		break;
	case KVM_REG_MIPS_CP0_COMPARE:
		kvm_mips_write_compare(vcpu, v, false);
		break;
	case KVM_REG_MIPS_CP0_STATUS:
		write_gc0_status(v);
		break;
	case KVM_REG_MIPS_CP0_INTCTL:
		write_gc0_intctl(v);
		break;
	case KVM_REG_MIPS_CP0_CAUSE:
		/*
		 * If the timer is stopped or started (DC bit) it must look
		 * atomic with changes to the timer interrupt pending bit (TI).
		 * A timer interrupt should not happen in between.
		 */
		if ((read_gc0_cause() ^ v) & CAUSEF_DC) {
			if (v & CAUSEF_DC) {
				/* disable timer first */
				kvm_mips_count_disable_cause(vcpu);
				change_gc0_cause((u32)~CAUSEF_DC, v);
			} else {
				/* enable timer last */
				change_gc0_cause((u32)~CAUSEF_DC, v);
				kvm_mips_count_enable_cause(vcpu);
			}
		} else {
			write_gc0_cause(v);
		}
		break;
	case KVM_REG_MIPS_CP0_EPC:
		write_gc0_epc(v);
		break;
	case KVM_REG_MIPS_CP0_PRID:
		switch (boot_cpu_type()) {
		case CPU_CAVIUM_OCTEON3:
			/* Octeon III has a guest.PRid, but its read-only */
			break;
		default:
			kvm_write_c0_guest_prid(cop0, v);
			break;
		};
		break;
	case KVM_REG_MIPS_CP0_EBASE:
		kvm_vz_write_gc0_ebase(v);
		break;
	case KVM_REG_MIPS_CP0_CONFIG:
		cur = read_gc0_config();
		change = (cur ^ v) & kvm_vz_config_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config(v);
		}
		break;
	case KVM_REG_MIPS_CP0_CONFIG1:
		if (!cpu_guest_has_conf1)
			break;
		cur = read_gc0_config1();
		change = (cur ^ v) & kvm_vz_config1_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config1(v);
		}
		break;
	case KVM_REG_MIPS_CP0_CONFIG2:
		if (!cpu_guest_has_conf2)
			break;
		cur = read_gc0_config2();
		change = (cur ^ v) & kvm_vz_config2_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config2(v);
		}
		break;
	case KVM_REG_MIPS_CP0_CONFIG3:
		if (!cpu_guest_has_conf3)
			break;
		cur = read_gc0_config3();
		change = (cur ^ v) & kvm_vz_config3_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config3(v);
		}
		break;
	case KVM_REG_MIPS_CP0_CONFIG4:
		if (!cpu_guest_has_conf4)
			break;
		cur = read_gc0_config4();
		change = (cur ^ v) & kvm_vz_config4_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config4(v);
		}
		break;
	case KVM_REG_MIPS_CP0_CONFIG5:
		if (!cpu_guest_has_conf5)
			break;
		cur = read_gc0_config5();
		change = (cur ^ v) & kvm_vz_config5_user_wrmask(vcpu);
		if (change) {
			v = cur ^ change;
			write_gc0_config5(v);
		}
		break;
	case KVM_REG_MIPS_CP0_MAAR(0) ... KVM_REG_MIPS_CP0_MAAR(0x3f):
		if (!cpu_guest_has_maar || cpu_guest_has_dyn_maar)
			return -EINVAL;
		idx = reg->id - KVM_REG_MIPS_CP0_MAAR(0);
		if (idx >= ARRAY_SIZE(vcpu->arch.maar))
			return -EINVAL;
		vcpu->arch.maar[idx] = mips_process_maar(dmtc_op, v);
		break;
	case KVM_REG_MIPS_CP0_MAARI:
		if (!cpu_guest_has_maar || cpu_guest_has_dyn_maar)
			return -EINVAL;
		kvm_write_maari(vcpu, v);
		break;
#ifdef CONFIG_64BIT
	case KVM_REG_MIPS_CP0_XCONTEXT:
		write_gc0_xcontext(v);
		break;
#endif
	case KVM_REG_MIPS_CP0_ERROREPC:
		write_gc0_errorepc(v);
		break;
	case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6:
		idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2;
		if (!cpu_guest_has_kscr(idx))
			return -EINVAL;
		switch (idx) {
		case 2:
			write_gc0_kscratch1(v);
			break;
		case 3:
			write_gc0_kscratch2(v);
			break;
		case 4:
			write_gc0_kscratch3(v);
			break;
		case 5:
			write_gc0_kscratch4(v);
			break;
		case 6:
			write_gc0_kscratch5(v);
			break;
		case 7:
			write_gc0_kscratch6(v);
			break;
		}
		break;
	case KVM_REG_MIPS_COUNT_CTL:
		ret = kvm_mips_set_count_ctl(vcpu, v);
		break;
	case KVM_REG_MIPS_COUNT_RESUME:
		ret = kvm_mips_set_count_resume(vcpu, v);
		break;
	case KVM_REG_MIPS_COUNT_HZ:
		ret = kvm_mips_set_count_hz(vcpu, v);
		break;
	default:
		return -EINVAL;
	}
	return ret;
}

#define guestid_cache(cpu)	(cpu_data[cpu].guestid_cache)
static void kvm_vz_get_new_guestid(unsigned long cpu, struct kvm_vcpu *vcpu)
{
	unsigned long guestid = guestid_cache(cpu);

	if (!(++guestid & GUESTID_MASK)) {
		if (cpu_has_vtag_icache)
			flush_icache_all();

		if (!guestid)		/* fix version if needed */
			guestid = GUESTID_FIRST_VERSION;

		++guestid;		/* guestid 0 reserved for root */

		/* start new guestid cycle */
		kvm_vz_local_flush_roottlb_all_guests();
		kvm_vz_local_flush_guesttlb_all();
	}

	guestid_cache(cpu) = guestid;
}

/* Returns 1 if the guest TLB may be clobbered */
static int kvm_vz_check_requests(struct kvm_vcpu *vcpu, int cpu)
{
	int ret = 0;
	int i;

	if (!kvm_request_pending(vcpu))
		return 0;

	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		if (cpu_has_guestid) {
			/* Drop all GuestIDs for this VCPU */
			for_each_possible_cpu(i)
				vcpu->arch.vzguestid[i] = 0;
			/* This will clobber guest TLB contents too */
			ret = 1;
		}
		/*
		 * For Root ASID Dealias (RAD) we don't do anything here, but we
		 * still need the request to ensure we recheck asid_flush_mask.
		 * We can still return 0 as only the root TLB will be affected
		 * by a root ASID flush.
		 */
	}

	return ret;
}

static void kvm_vz_vcpu_save_wired(struct kvm_vcpu *vcpu)
{
	unsigned int wired = read_gc0_wired();
	struct kvm_mips_tlb *tlbs;
	int i;

	/* Expand the wired TLB array if necessary */
	wired &= MIPSR6_WIRED_WIRED;
	if (wired > vcpu->arch.wired_tlb_limit) {
		tlbs = krealloc(vcpu->arch.wired_tlb, wired *
				sizeof(*vcpu->arch.wired_tlb), GFP_ATOMIC);
		if (WARN_ON(!tlbs)) {
			/* Save whatever we can */
			wired = vcpu->arch.wired_tlb_limit;
		} else {
			vcpu->arch.wired_tlb = tlbs;
			vcpu->arch.wired_tlb_limit = wired;
		}
	}

	if (wired)
		/* Save wired entries from the guest TLB */
		kvm_vz_save_guesttlb(vcpu->arch.wired_tlb, 0, wired);
	/* Invalidate any dropped entries since last time */
	for (i = wired; i < vcpu->arch.wired_tlb_used; ++i) {
		vcpu->arch.wired_tlb[i].tlb_hi = UNIQUE_GUEST_ENTRYHI(i);
		vcpu->arch.wired_tlb[i].tlb_lo[0] = 0;
		vcpu->arch.wired_tlb[i].tlb_lo[1] = 0;
		vcpu->arch.wired_tlb[i].tlb_mask = 0;
	}
	vcpu->arch.wired_tlb_used = wired;
}

static void kvm_vz_vcpu_load_wired(struct kvm_vcpu *vcpu)
{
	/* Load wired entries into the guest TLB */
	if (vcpu->arch.wired_tlb)
		kvm_vz_load_guesttlb(vcpu->arch.wired_tlb, 0,
				     vcpu->arch.wired_tlb_used);
}

static void kvm_vz_vcpu_load_tlb(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvm *kvm = vcpu->kvm;
	struct mm_struct *gpa_mm = &kvm->arch.gpa_mm;
	bool migrated;

	/*
	 * Are we entering guest context on a different CPU to last time?
	 * If so, the VCPU's guest TLB state on this CPU may be stale.
	 */
	migrated = (vcpu->arch.last_exec_cpu != cpu);
	vcpu->arch.last_exec_cpu = cpu;

	/*
	 * A vcpu's GuestID is set in GuestCtl1.ID when the vcpu is loaded and
	 * remains set until another vcpu is loaded in.  As a rule GuestRID
	 * remains zeroed when in root context unless the kernel is busy
	 * manipulating guest tlb entries.
	 */
	if (cpu_has_guestid) {
		/*
		 * Check if our GuestID is of an older version and thus invalid.
		 *
		 * We also discard the stored GuestID if we've executed on
		 * another CPU, as the guest mappings may have changed without
		 * hypervisor knowledge.
		 */
		if (migrated ||
		    (vcpu->arch.vzguestid[cpu] ^ guestid_cache(cpu)) &
					GUESTID_VERSION_MASK) {
			kvm_vz_get_new_guestid(cpu, vcpu);
			vcpu->arch.vzguestid[cpu] = guestid_cache(cpu);
			trace_kvm_guestid_change(vcpu,
						 vcpu->arch.vzguestid[cpu]);
		}

		/* Restore GuestID */
		change_c0_guestctl1(GUESTID_MASK, vcpu->arch.vzguestid[cpu]);
	} else {
		/*
		 * The Guest TLB only stores a single guest's TLB state, so
		 * flush it if another VCPU has executed on this CPU.
		 *
		 * We also flush if we've executed on another CPU, as the guest
		 * mappings may have changed without hypervisor knowledge.
		 */
		if (migrated || last_exec_vcpu[cpu] != vcpu)
			kvm_vz_local_flush_guesttlb_all();
		last_exec_vcpu[cpu] = vcpu;

		/*
		 * Root ASID dealiases guest GPA mappings in the root TLB.
		 * Allocate new root ASID if needed.
		 */
		if (cpumask_test_and_clear_cpu(cpu, &kvm->arch.asid_flush_mask))
			get_new_mmu_context(gpa_mm);
		else
			check_mmu_context(gpa_mm);
	}
}

static int kvm_vz_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	bool migrated, all;

	/*
	 * Have we migrated to a different CPU?
	 * If so, any old guest TLB state may be stale.
	 */
	migrated = (vcpu->arch.last_sched_cpu != cpu);

	/*
	 * Was this the last VCPU to run on this CPU?
	 * If not, any old guest state from this VCPU will have been clobbered.
	 */
	all = migrated || (last_vcpu[cpu] != vcpu);
	last_vcpu[cpu] = vcpu;

	/*
	 * Restore CP0_Wired unconditionally as we clear it after use, and
	 * restore wired guest TLB entries (while in guest context).
	 */
	kvm_restore_gc0_wired(cop0);
	if (current->flags & PF_VCPU) {
		tlbw_use_hazard();
		kvm_vz_vcpu_load_tlb(vcpu, cpu);
		kvm_vz_vcpu_load_wired(vcpu);
	}

	/*
	 * Restore timer state regardless, as e.g. Cause.TI can change over time
	 * if left unmaintained.
	 */
	kvm_vz_restore_timer(vcpu);

	/* Set MC bit if we want to trace guest mode changes */
	if (kvm_trace_guest_mode_change)
		set_c0_guestctl0(MIPS_GCTL0_MC);
	else
		clear_c0_guestctl0(MIPS_GCTL0_MC);

	/* Don't bother restoring registers multiple times unless necessary */
	if (!all)
		return 0;

	/*
	 * Restore config registers first, as some implementations restrict
	 * writes to other registers when the corresponding feature bits aren't
	 * set. For example Status.CU1 cannot be set unless Config1.FP is set.
	 */
	kvm_restore_gc0_config(cop0);
	if (cpu_guest_has_conf1)
		kvm_restore_gc0_config1(cop0);
	if (cpu_guest_has_conf2)
		kvm_restore_gc0_config2(cop0);
	if (cpu_guest_has_conf3)
		kvm_restore_gc0_config3(cop0);
	if (cpu_guest_has_conf4)
		kvm_restore_gc0_config4(cop0);
	if (cpu_guest_has_conf5)
		kvm_restore_gc0_config5(cop0);
	if (cpu_guest_has_conf6)
		kvm_restore_gc0_config6(cop0);
	if (cpu_guest_has_conf7)
		kvm_restore_gc0_config7(cop0);

	kvm_restore_gc0_index(cop0);
	kvm_restore_gc0_entrylo0(cop0);
	kvm_restore_gc0_entrylo1(cop0);
	kvm_restore_gc0_context(cop0);
	if (cpu_guest_has_contextconfig)
		kvm_restore_gc0_contextconfig(cop0);
#ifdef CONFIG_64BIT
	kvm_restore_gc0_xcontext(cop0);
	if (cpu_guest_has_contextconfig)
		kvm_restore_gc0_xcontextconfig(cop0);
#endif
	kvm_restore_gc0_pagemask(cop0);
	kvm_restore_gc0_pagegrain(cop0);
	kvm_restore_gc0_hwrena(cop0);
	kvm_restore_gc0_badvaddr(cop0);
	kvm_restore_gc0_entryhi(cop0);
	kvm_restore_gc0_status(cop0);
	kvm_restore_gc0_intctl(cop0);
	kvm_restore_gc0_epc(cop0);
	kvm_vz_write_gc0_ebase(kvm_read_sw_gc0_ebase(cop0));
	if (cpu_guest_has_userlocal)
		kvm_restore_gc0_userlocal(cop0);

	kvm_restore_gc0_errorepc(cop0);

	/* restore KScratch registers if enabled in guest */
	if (cpu_guest_has_conf4) {
		if (cpu_guest_has_kscr(2))
			kvm_restore_gc0_kscratch1(cop0);
		if (cpu_guest_has_kscr(3))
			kvm_restore_gc0_kscratch2(cop0);
		if (cpu_guest_has_kscr(4))
			kvm_restore_gc0_kscratch3(cop0);
		if (cpu_guest_has_kscr(5))
			kvm_restore_gc0_kscratch4(cop0);
		if (cpu_guest_has_kscr(6))
			kvm_restore_gc0_kscratch5(cop0);
		if (cpu_guest_has_kscr(7))
			kvm_restore_gc0_kscratch6(cop0);
	}

	if (cpu_guest_has_badinstr)
		kvm_restore_gc0_badinstr(cop0);
	if (cpu_guest_has_badinstrp)
		kvm_restore_gc0_badinstrp(cop0);

	if (cpu_guest_has_segments) {
		kvm_restore_gc0_segctl0(cop0);
		kvm_restore_gc0_segctl1(cop0);
		kvm_restore_gc0_segctl2(cop0);
	}

	/* restore HTW registers */
	if (cpu_guest_has_htw) {
		kvm_restore_gc0_pwbase(cop0);
		kvm_restore_gc0_pwfield(cop0);
		kvm_restore_gc0_pwsize(cop0);
		kvm_restore_gc0_pwctl(cop0);
	}

	/* restore Root.GuestCtl2 from unused Guest guestctl2 register */
	if (cpu_has_guestctl2)
		write_c0_guestctl2(
			cop0->reg[MIPS_CP0_GUESTCTL2][MIPS_CP0_GUESTCTL2_SEL]);

	/*
	 * We should clear linked load bit to break interrupted atomics. This
	 * prevents a SC on the next VCPU from succeeding by matching a LL on
	 * the previous VCPU.
	 */
	if (cpu_guest_has_rw_llb)
		write_gc0_lladdr(0);

	return 0;
}

static int kvm_vz_vcpu_put(struct kvm_vcpu *vcpu, int cpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;

	if (current->flags & PF_VCPU)
		kvm_vz_vcpu_save_wired(vcpu);

	kvm_lose_fpu(vcpu);

	kvm_save_gc0_index(cop0);
	kvm_save_gc0_entrylo0(cop0);
	kvm_save_gc0_entrylo1(cop0);
	kvm_save_gc0_context(cop0);
	if (cpu_guest_has_contextconfig)
		kvm_save_gc0_contextconfig(cop0);
#ifdef CONFIG_64BIT
	kvm_save_gc0_xcontext(cop0);
	if (cpu_guest_has_contextconfig)
		kvm_save_gc0_xcontextconfig(cop0);
#endif
	kvm_save_gc0_pagemask(cop0);
	kvm_save_gc0_pagegrain(cop0);
	kvm_save_gc0_wired(cop0);
	/* allow wired TLB entries to be overwritten */
	clear_gc0_wired(MIPSR6_WIRED_WIRED);
	kvm_save_gc0_hwrena(cop0);
	kvm_save_gc0_badvaddr(cop0);
	kvm_save_gc0_entryhi(cop0);
	kvm_save_gc0_status(cop0);
	kvm_save_gc0_intctl(cop0);
	kvm_save_gc0_epc(cop0);
	kvm_write_sw_gc0_ebase(cop0, kvm_vz_read_gc0_ebase());
	if (cpu_guest_has_userlocal)
		kvm_save_gc0_userlocal(cop0);

	/* only save implemented config registers */
	kvm_save_gc0_config(cop0);
	if (cpu_guest_has_conf1)
		kvm_save_gc0_config1(cop0);
	if (cpu_guest_has_conf2)
		kvm_save_gc0_config2(cop0);
	if (cpu_guest_has_conf3)
		kvm_save_gc0_config3(cop0);
	if (cpu_guest_has_conf4)
		kvm_save_gc0_config4(cop0);
	if (cpu_guest_has_conf5)
		kvm_save_gc0_config5(cop0);
	if (cpu_guest_has_conf6)
		kvm_save_gc0_config6(cop0);
	if (cpu_guest_has_conf7)
		kvm_save_gc0_config7(cop0);

	kvm_save_gc0_errorepc(cop0);

	/* save KScratch registers if enabled in guest */
	if (cpu_guest_has_conf4) {
		if (cpu_guest_has_kscr(2))
			kvm_save_gc0_kscratch1(cop0);
		if (cpu_guest_has_kscr(3))
			kvm_save_gc0_kscratch2(cop0);
		if (cpu_guest_has_kscr(4))
			kvm_save_gc0_kscratch3(cop0);
		if (cpu_guest_has_kscr(5))
			kvm_save_gc0_kscratch4(cop0);
		if (cpu_guest_has_kscr(6))
			kvm_save_gc0_kscratch5(cop0);
		if (cpu_guest_has_kscr(7))
			kvm_save_gc0_kscratch6(cop0);
	}

	if (cpu_guest_has_badinstr)
		kvm_save_gc0_badinstr(cop0);
	if (cpu_guest_has_badinstrp)
		kvm_save_gc0_badinstrp(cop0);

	if (cpu_guest_has_segments) {
		kvm_save_gc0_segctl0(cop0);
		kvm_save_gc0_segctl1(cop0);
		kvm_save_gc0_segctl2(cop0);
	}

	/* save HTW registers if enabled in guest */
	if (cpu_guest_has_htw &&
	    kvm_read_sw_gc0_config3(cop0) & MIPS_CONF3_PW) {
		kvm_save_gc0_pwbase(cop0);
		kvm_save_gc0_pwfield(cop0);
		kvm_save_gc0_pwsize(cop0);
		kvm_save_gc0_pwctl(cop0);
	}

	kvm_vz_save_timer(vcpu);

	/* save Root.GuestCtl2 in unused Guest guestctl2 register */
	if (cpu_has_guestctl2)
		cop0->reg[MIPS_CP0_GUESTCTL2][MIPS_CP0_GUESTCTL2_SEL] =
			read_c0_guestctl2();

	return 0;
}

/**
 * kvm_vz_resize_guest_vtlb() - Attempt to resize guest VTLB.
 * @size:	Number of guest VTLB entries (0 < @size <= root VTLB entries).
 *
 * Attempt to resize the guest VTLB by writing guest Config registers. This is
 * necessary for cores with a shared root/guest TLB to avoid overlap with wired
 * entries in the root VTLB.
 *
 * Returns:	The resulting guest VTLB size.
 */
static unsigned int kvm_vz_resize_guest_vtlb(unsigned int size)
{
	unsigned int config4 = 0, ret = 0, limit;

	/* Write MMUSize - 1 into guest Config registers */
	if (cpu_guest_has_conf1)
		change_gc0_config1(MIPS_CONF1_TLBS,
				   (size - 1) << MIPS_CONF1_TLBS_SHIFT);
	if (cpu_guest_has_conf4) {
		config4 = read_gc0_config4();
		if (cpu_has_mips_r6 || (config4 & MIPS_CONF4_MMUEXTDEF) ==
		    MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT) {
			config4 &= ~MIPS_CONF4_VTLBSIZEEXT;
			config4 |= ((size - 1) >> MIPS_CONF1_TLBS_SIZE) <<
				MIPS_CONF4_VTLBSIZEEXT_SHIFT;
		} else if ((config4 & MIPS_CONF4_MMUEXTDEF) ==
			   MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT) {
			config4 &= ~MIPS_CONF4_MMUSIZEEXT;
			config4 |= ((size - 1) >> MIPS_CONF1_TLBS_SIZE) <<
				MIPS_CONF4_MMUSIZEEXT_SHIFT;
		}
		write_gc0_config4(config4);
	}

	/*
	 * Set Guest.Wired.Limit = 0 (no limit up to Guest.MMUSize-1), unless it
	 * would exceed Root.Wired.Limit (clearing Guest.Wired.Wired so write
	 * not dropped)
	 */
	if (cpu_has_mips_r6) {
		limit = (read_c0_wired() & MIPSR6_WIRED_LIMIT) >>
						MIPSR6_WIRED_LIMIT_SHIFT;
		if (size - 1 <= limit)
			limit = 0;
		write_gc0_wired(limit << MIPSR6_WIRED_LIMIT_SHIFT);
	}

	/* Read back MMUSize - 1 */
	back_to_back_c0_hazard();
	if (cpu_guest_has_conf1)
		ret = (read_gc0_config1() & MIPS_CONF1_TLBS) >>
						MIPS_CONF1_TLBS_SHIFT;
	if (config4) {
		if (cpu_has_mips_r6 || (config4 & MIPS_CONF4_MMUEXTDEF) ==
		    MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT)
			ret |= ((config4 & MIPS_CONF4_VTLBSIZEEXT) >>
				MIPS_CONF4_VTLBSIZEEXT_SHIFT) <<
				MIPS_CONF1_TLBS_SIZE;
		else if ((config4 & MIPS_CONF4_MMUEXTDEF) ==
			 MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT)
			ret |= ((config4 & MIPS_CONF4_MMUSIZEEXT) >>
				MIPS_CONF4_MMUSIZEEXT_SHIFT) <<
				MIPS_CONF1_TLBS_SIZE;
	}
	return ret + 1;
}

static int kvm_vz_hardware_enable(void)
{
	unsigned int mmu_size, guest_mmu_size, ftlb_size;
	u64 guest_cvmctl, cvmvmconfig;

	switch (current_cpu_type()) {
	case CPU_CAVIUM_OCTEON3:
		/* Set up guest timer/perfcount IRQ lines */
		guest_cvmctl = read_gc0_cvmctl();
		guest_cvmctl &= ~CVMCTL_IPTI;
		guest_cvmctl |= 7ull << CVMCTL_IPTI_SHIFT;
		guest_cvmctl &= ~CVMCTL_IPPCI;
		guest_cvmctl |= 6ull << CVMCTL_IPPCI_SHIFT;
		write_gc0_cvmctl(guest_cvmctl);

		cvmvmconfig = read_c0_cvmvmconfig();
		/* No I/O hole translation. */
		cvmvmconfig |= CVMVMCONF_DGHT;
		/* Halve the root MMU size */
		mmu_size = ((cvmvmconfig & CVMVMCONF_MMUSIZEM1)
			    >> CVMVMCONF_MMUSIZEM1_S) + 1;
		guest_mmu_size = mmu_size / 2;
		mmu_size -= guest_mmu_size;
		cvmvmconfig &= ~CVMVMCONF_RMMUSIZEM1;
		cvmvmconfig |= mmu_size - 1;
		write_c0_cvmvmconfig(cvmvmconfig);

		/* Update our records */
		current_cpu_data.tlbsize = mmu_size;
		current_cpu_data.tlbsizevtlb = mmu_size;
		current_cpu_data.guest.tlbsize = guest_mmu_size;

		/* Flush moved entries in new (guest) context */
		kvm_vz_local_flush_guesttlb_all();
		break;
	default:
		/*
		 * ImgTec cores tend to use a shared root/guest TLB. To avoid
		 * overlap of root wired and guest entries, the guest TLB may
		 * need resizing.
		 */
		mmu_size = current_cpu_data.tlbsizevtlb;
		ftlb_size = current_cpu_data.tlbsize - mmu_size;

		/* Try switching to maximum guest VTLB size for flush */
		guest_mmu_size = kvm_vz_resize_guest_vtlb(mmu_size);
		current_cpu_data.guest.tlbsize = guest_mmu_size + ftlb_size;
		kvm_vz_local_flush_guesttlb_all();

		/*
		 * Reduce to make space for root wired entries and at least 2
		 * root non-wired entries. This does assume that long-term wired
		 * entries won't be added later.
		 */
		guest_mmu_size = mmu_size - num_wired_entries() - 2;
		guest_mmu_size = kvm_vz_resize_guest_vtlb(guest_mmu_size);
		current_cpu_data.guest.tlbsize = guest_mmu_size + ftlb_size;

		/*
		 * Write the VTLB size, but if another CPU has already written,
		 * check it matches or we won't provide a consistent view to the
		 * guest. If this ever happens it suggests an asymmetric number
		 * of wired entries.
		 */
		if (cmpxchg(&kvm_vz_guest_vtlb_size, 0, guest_mmu_size) &&
		    WARN(guest_mmu_size != kvm_vz_guest_vtlb_size,
			 "Available guest VTLB size mismatch"))
			return -EINVAL;
		break;
	}

	/*
	 * Enable virtualization features granting guest direct control of
	 * certain features:
	 * CP0=1:	Guest coprocessor 0 context.
	 * AT=Guest:	Guest MMU.
	 * CG=1:	Hit (virtual address) CACHE operations (optional).
	 * CF=1:	Guest Config registers.
	 * CGI=1:	Indexed flush CACHE operations (optional).
	 */
	write_c0_guestctl0(MIPS_GCTL0_CP0 |
			   (MIPS_GCTL0_AT_GUEST << MIPS_GCTL0_AT_SHIFT) |
			   MIPS_GCTL0_CG | MIPS_GCTL0_CF);
	if (cpu_has_guestctl0ext)
		set_c0_guestctl0ext(MIPS_GCTL0EXT_CGI);

	if (cpu_has_guestid) {
		write_c0_guestctl1(0);
		kvm_vz_local_flush_roottlb_all_guests();

		GUESTID_MASK = current_cpu_data.guestid_mask;
		GUESTID_FIRST_VERSION = GUESTID_MASK + 1;
		GUESTID_VERSION_MASK = ~GUESTID_MASK;

		current_cpu_data.guestid_cache = GUESTID_FIRST_VERSION;
	}

	/* clear any pending injected virtual guest interrupts */
	if (cpu_has_guestctl2)
		clear_c0_guestctl2(0x3f << 10);

	return 0;
}

static void kvm_vz_hardware_disable(void)
{
	u64 cvmvmconfig;
	unsigned int mmu_size;

	/* Flush any remaining guest TLB entries */
	kvm_vz_local_flush_guesttlb_all();

	switch (current_cpu_type()) {
	case CPU_CAVIUM_OCTEON3:
		/*
		 * Allocate whole TLB for root. Existing guest TLB entries will
		 * change ownership to the root TLB. We should be safe though as
		 * they've already been flushed above while in guest TLB.
		 */
		cvmvmconfig = read_c0_cvmvmconfig();
		mmu_size = ((cvmvmconfig & CVMVMCONF_MMUSIZEM1)
			    >> CVMVMCONF_MMUSIZEM1_S) + 1;
		cvmvmconfig &= ~CVMVMCONF_RMMUSIZEM1;
		cvmvmconfig |= mmu_size - 1;
		write_c0_cvmvmconfig(cvmvmconfig);

		/* Update our records */
		current_cpu_data.tlbsize = mmu_size;
		current_cpu_data.tlbsizevtlb = mmu_size;
		current_cpu_data.guest.tlbsize = 0;

		/* Flush moved entries in new (root) context */
		local_flush_tlb_all();
		break;
	}

	if (cpu_has_guestid) {
		write_c0_guestctl1(0);
		kvm_vz_local_flush_roottlb_all_guests();
	}
}

static int kvm_vz_check_extension(struct kvm *kvm, long ext)
{
	int r;

	switch (ext) {
	case KVM_CAP_MIPS_VZ:
		/* we wouldn't be here unless cpu_has_vz */
		r = 1;
		break;
#ifdef CONFIG_64BIT
	case KVM_CAP_MIPS_64BIT:
		/* We support 64-bit registers/operations and addresses */
		r = 2;
		break;
#endif
	default:
		r = 0;
		break;
	}

	return r;
}

static int kvm_vz_vcpu_init(struct kvm_vcpu *vcpu)
{
	int i;

	for_each_possible_cpu(i)
		vcpu->arch.vzguestid[i] = 0;

	return 0;
}

static void kvm_vz_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	int cpu;

	/*
	 * If the VCPU is freed and reused as another VCPU, we don't want the
	 * matching pointer wrongly hanging around in last_vcpu[] or
	 * last_exec_vcpu[].
	 */
	for_each_possible_cpu(cpu) {
		if (last_vcpu[cpu] == vcpu)
			last_vcpu[cpu] = NULL;
		if (last_exec_vcpu[cpu] == vcpu)
			last_exec_vcpu[cpu] = NULL;
	}
}

static int kvm_vz_vcpu_setup(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	unsigned long count_hz = 100*1000*1000; /* default to 100 MHz */

	/*
	 * Start off the timer at the same frequency as the host timer, but the
	 * soft timer doesn't handle frequencies greater than 1GHz yet.
	 */
	if (mips_hpt_frequency && mips_hpt_frequency <= NSEC_PER_SEC)
		count_hz = mips_hpt_frequency;
	kvm_mips_init_count(vcpu, count_hz);

	/*
	 * Initialize guest register state to valid architectural reset state.
	 */

	/* PageGrain */
	if (cpu_has_mips_r6)
		kvm_write_sw_gc0_pagegrain(cop0, PG_RIE | PG_XIE | PG_IEC);
	/* Wired */
	if (cpu_has_mips_r6)
		kvm_write_sw_gc0_wired(cop0,
				       read_gc0_wired() & MIPSR6_WIRED_LIMIT);
	/* Status */
	kvm_write_sw_gc0_status(cop0, ST0_BEV | ST0_ERL);
	if (cpu_has_mips_r6)
		kvm_change_sw_gc0_status(cop0, ST0_FR, read_gc0_status());
	/* IntCtl */
	kvm_write_sw_gc0_intctl(cop0, read_gc0_intctl() &
				(INTCTLF_IPFDC | INTCTLF_IPPCI | INTCTLF_IPTI));
	/* PRId */
	kvm_write_sw_gc0_prid(cop0, boot_cpu_data.processor_id);
	/* EBase */
	kvm_write_sw_gc0_ebase(cop0, (s32)0x80000000 | vcpu->vcpu_id);
	/* Config */
	kvm_save_gc0_config(cop0);
	/* architecturally writable (e.g. from guest) */
	kvm_change_sw_gc0_config(cop0, CONF_CM_CMASK,
				 _page_cachable_default >> _CACHE_SHIFT);
	/* architecturally read only, but maybe writable from root */
	kvm_change_sw_gc0_config(cop0, MIPS_CONF_MT, read_c0_config());
	if (cpu_guest_has_conf1) {
		kvm_set_sw_gc0_config(cop0, MIPS_CONF_M);
		/* Config1 */
		kvm_save_gc0_config1(cop0);
		/* architecturally read only, but maybe writable from root */
		kvm_clear_sw_gc0_config1(cop0, MIPS_CONF1_C2	|
					       MIPS_CONF1_MD	|
					       MIPS_CONF1_PC	|
					       MIPS_CONF1_WR	|
					       MIPS_CONF1_CA	|
					       MIPS_CONF1_FP);
	}
	if (cpu_guest_has_conf2) {
		kvm_set_sw_gc0_config1(cop0, MIPS_CONF_M);
		/* Config2 */
		kvm_save_gc0_config2(cop0);
	}
	if (cpu_guest_has_conf3) {
		kvm_set_sw_gc0_config2(cop0, MIPS_CONF_M);
		/* Config3 */
		kvm_save_gc0_config3(cop0);
		/* architecturally writable (e.g. from guest) */
		kvm_clear_sw_gc0_config3(cop0, MIPS_CONF3_ISA_OE);
		/* architecturally read only, but maybe writable from root */
		kvm_clear_sw_gc0_config3(cop0, MIPS_CONF3_MSA	|
					       MIPS_CONF3_BPG	|
					       MIPS_CONF3_ULRI	|
					       MIPS_CONF3_DSP	|
					       MIPS_CONF3_CTXTC	|
					       MIPS_CONF3_ITL	|
					       MIPS_CONF3_LPA	|
					       MIPS_CONF3_VEIC	|
					       MIPS_CONF3_VINT	|
					       MIPS_CONF3_SP	|
					       MIPS_CONF3_CDMM	|
					       MIPS_CONF3_MT	|
					       MIPS_CONF3_SM	|
					       MIPS_CONF3_TL);
	}
	if (cpu_guest_has_conf4) {
		kvm_set_sw_gc0_config3(cop0, MIPS_CONF_M);
		/* Config4 */
		kvm_save_gc0_config4(cop0);
	}
	if (cpu_guest_has_conf5) {
		kvm_set_sw_gc0_config4(cop0, MIPS_CONF_M);
		/* Config5 */
		kvm_save_gc0_config5(cop0);
		/* architecturally writable (e.g. from guest) */
		kvm_clear_sw_gc0_config5(cop0, MIPS_CONF5_K	|
					       MIPS_CONF5_CV	|
					       MIPS_CONF5_MSAEN	|
					       MIPS_CONF5_UFE	|
					       MIPS_CONF5_FRE	|
					       MIPS_CONF5_SBRI	|
					       MIPS_CONF5_UFR);
		/* architecturally read only, but maybe writable from root */
		kvm_clear_sw_gc0_config5(cop0, MIPS_CONF5_MRP);
	}

	if (cpu_guest_has_contextconfig) {
		/* ContextConfig */
		kvm_write_sw_gc0_contextconfig(cop0, 0x007ffff0);
#ifdef CONFIG_64BIT
		/* XContextConfig */
		/* bits SEGBITS-13+3:4 set */
		kvm_write_sw_gc0_xcontextconfig(cop0,
					((1ull << (cpu_vmbits - 13)) - 1) << 4);
#endif
	}

	/* Implementation dependent, use the legacy layout */
	if (cpu_guest_has_segments) {
		/* SegCtl0, SegCtl1, SegCtl2 */
		kvm_write_sw_gc0_segctl0(cop0, 0x00200010);
		kvm_write_sw_gc0_segctl1(cop0, 0x00000002 |
				(_page_cachable_default >> _CACHE_SHIFT) <<
						(16 + MIPS_SEGCFG_C_SHIFT));
		kvm_write_sw_gc0_segctl2(cop0, 0x00380438);
	}

	/* reset HTW registers */
	if (cpu_guest_has_htw && cpu_has_mips_r6) {
		/* PWField */
		kvm_write_sw_gc0_pwfield(cop0, 0x0c30c302);
		/* PWSize */
		kvm_write_sw_gc0_pwsize(cop0, 1 << MIPS_PWSIZE_PTW_SHIFT);
	}

	/* start with no pending virtual guest interrupts */
	if (cpu_has_guestctl2)
		cop0->reg[MIPS_CP0_GUESTCTL2][MIPS_CP0_GUESTCTL2_SEL] = 0;

	/* Put PC at reset vector */
	vcpu->arch.pc = CKSEG1ADDR(0x1fc00000);

	return 0;
}

static void kvm_vz_flush_shadow_all(struct kvm *kvm)
{
	if (cpu_has_guestid) {
		/* Flush GuestID for each VCPU individually */
		kvm_flush_remote_tlbs(kvm);
	} else {
		/*
		 * For each CPU there is a single GPA ASID used by all VCPUs in
		 * the VM, so it doesn't make sense for the VCPUs to handle
		 * invalidation of these ASIDs individually.
		 *
		 * Instead mark all CPUs as needing ASID invalidation in
		 * asid_flush_mask, and just use kvm_flush_remote_tlbs(kvm) to
		 * kick any running VCPUs so they check asid_flush_mask.
		 */
		cpumask_setall(&kvm->arch.asid_flush_mask);
		kvm_flush_remote_tlbs(kvm);
	}
}

static void kvm_vz_flush_shadow_memslot(struct kvm *kvm,
					const struct kvm_memory_slot *slot)
{
	kvm_vz_flush_shadow_all(kvm);
}

static void kvm_vz_vcpu_reenter(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	int cpu = smp_processor_id();
	int preserve_guest_tlb;

	preserve_guest_tlb = kvm_vz_check_requests(vcpu, cpu);

	if (preserve_guest_tlb)
		kvm_vz_vcpu_save_wired(vcpu);

	kvm_vz_vcpu_load_tlb(vcpu, cpu);

	if (preserve_guest_tlb)
		kvm_vz_vcpu_load_wired(vcpu);
}

static int kvm_vz_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	int cpu = smp_processor_id();
	int r;

	kvm_vz_acquire_htimer(vcpu);
	/* Check if we have any exceptions/interrupts pending */
	kvm_mips_deliver_interrupts(vcpu, read_gc0_cause());

	kvm_vz_check_requests(vcpu, cpu);
	kvm_vz_vcpu_load_tlb(vcpu, cpu);
	kvm_vz_vcpu_load_wired(vcpu);

	r = vcpu->arch.vcpu_run(run, vcpu);

	kvm_vz_vcpu_save_wired(vcpu);

	return r;
}

static struct kvm_mips_callbacks kvm_vz_callbacks = {
	.handle_cop_unusable = kvm_trap_vz_handle_cop_unusable,
	.handle_tlb_mod = kvm_trap_vz_handle_tlb_st_miss,
	.handle_tlb_ld_miss = kvm_trap_vz_handle_tlb_ld_miss,
	.handle_tlb_st_miss = kvm_trap_vz_handle_tlb_st_miss,
	.handle_addr_err_st = kvm_trap_vz_no_handler,
	.handle_addr_err_ld = kvm_trap_vz_no_handler,
	.handle_syscall = kvm_trap_vz_no_handler,
	.handle_res_inst = kvm_trap_vz_no_handler,
	.handle_break = kvm_trap_vz_no_handler,
	.handle_msa_disabled = kvm_trap_vz_handle_msa_disabled,
	.handle_guest_exit = kvm_trap_vz_handle_guest_exit,

	.hardware_enable = kvm_vz_hardware_enable,
	.hardware_disable = kvm_vz_hardware_disable,
	.check_extension = kvm_vz_check_extension,
	.vcpu_init = kvm_vz_vcpu_init,
	.vcpu_uninit = kvm_vz_vcpu_uninit,
	.vcpu_setup = kvm_vz_vcpu_setup,
	.flush_shadow_all = kvm_vz_flush_shadow_all,
	.flush_shadow_memslot = kvm_vz_flush_shadow_memslot,
	.gva_to_gpa = kvm_vz_gva_to_gpa_cb,
	.queue_timer_int = kvm_vz_queue_timer_int_cb,
	.dequeue_timer_int = kvm_vz_dequeue_timer_int_cb,
	.queue_io_int = kvm_vz_queue_io_int_cb,
	.dequeue_io_int = kvm_vz_dequeue_io_int_cb,
	.irq_deliver = kvm_vz_irq_deliver_cb,
	.irq_clear = kvm_vz_irq_clear_cb,
	.num_regs = kvm_vz_num_regs,
	.copy_reg_indices = kvm_vz_copy_reg_indices,
	.get_one_reg = kvm_vz_get_one_reg,
	.set_one_reg = kvm_vz_set_one_reg,
	.vcpu_load = kvm_vz_vcpu_load,
	.vcpu_put = kvm_vz_vcpu_put,
	.vcpu_run = kvm_vz_vcpu_run,
	.vcpu_reenter = kvm_vz_vcpu_reenter,
};

int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks)
{
	if (!cpu_has_vz)
		return -ENODEV;

	/*
	 * VZ requires at least 2 KScratch registers, so it should have been
	 * possible to allocate pgd_reg.
	 */
	if (WARN(pgd_reg == -1,
		 "pgd_reg not allocated even though cpu_has_vz\n"))
		return -ENODEV;

	pr_info("Starting KVM with MIPS VZ extensions\n");

	*install_callbacks = &kvm_vz_callbacks;
	return 0;
}