summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/x86.c
blob: 72ac6bf05c8b4836d164ba2c61c18cd2826f6f41 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
12194
12195
12196
12197
12198
12199
12200
12201
12202
12203
12204
12205
12206
12207
12208
12209
12210
12211
12212
12213
12214
12215
12216
12217
12218
12219
12220
12221
12222
12223
12224
12225
12226
12227
12228
12229
12230
12231
12232
12233
12234
12235
12236
12237
12238
12239
12240
12241
12242
12243
12244
12245
12246
12247
12248
12249
12250
12251
12252
12253
12254
12255
12256
12257
12258
12259
12260
12261
12262
12263
12264
12265
12266
12267
12268
12269
12270
12271
12272
12273
12274
12275
12276
12277
12278
12279
12280
12281
12282
12283
12284
12285
12286
12287
12288
12289
12290
12291
12292
12293
12294
12295
12296
12297
12298
12299
12300
12301
12302
12303
12304
12305
12306
12307
12308
12309
12310
12311
12312
12313
12314
12315
12316
12317
12318
12319
12320
12321
12322
12323
12324
12325
12326
12327
12328
12329
12330
12331
12332
12333
12334
12335
12336
12337
12338
12339
12340
12341
12342
12343
12344
12345
12346
12347
12348
12349
12350
12351
12352
12353
12354
12355
12356
12357
12358
12359
12360
12361
12362
12363
12364
12365
12366
12367
12368
12369
12370
12371
12372
12373
12374
12375
12376
12377
12378
12379
12380
12381
12382
12383
12384
12385
12386
12387
12388
12389
12390
12391
12392
12393
12394
12395
12396
12397
12398
12399
12400
12401
12402
12403
12404
12405
12406
12407
12408
12409
12410
12411
12412
12413
12414
12415
12416
12417
12418
12419
12420
12421
12422
12423
12424
12425
12426
12427
12428
12429
12430
12431
12432
12433
12434
12435
12436
12437
12438
12439
12440
12441
12442
12443
12444
12445
12446
12447
12448
12449
12450
12451
12452
12453
12454
12455
12456
12457
12458
12459
12460
12461
12462
12463
12464
12465
12466
12467
12468
12469
12470
12471
12472
12473
12474
12475
12476
12477
12478
12479
12480
12481
12482
12483
12484
12485
12486
12487
12488
12489
12490
12491
12492
12493
12494
12495
12496
12497
12498
12499
12500
12501
12502
12503
12504
12505
12506
12507
12508
12509
12510
12511
12512
12513
12514
12515
12516
12517
12518
12519
12520
12521
12522
12523
12524
12525
12526
12527
12528
12529
12530
12531
12532
12533
12534
12535
12536
12537
12538
12539
12540
12541
12542
12543
12544
12545
12546
12547
12548
12549
12550
12551
12552
12553
12554
12555
12556
12557
12558
12559
12560
12561
12562
12563
12564
12565
12566
12567
12568
12569
12570
12571
12572
12573
12574
12575
12576
12577
12578
12579
12580
12581
12582
12583
12584
12585
12586
12587
12588
12589
12590
12591
12592
12593
12594
12595
12596
12597
12598
12599
12600
12601
12602
12603
12604
12605
12606
12607
12608
12609
12610
12611
12612
12613
12614
12615
12616
12617
12618
12619
12620
12621
12622
12623
12624
12625
12626
12627
12628
12629
12630
12631
12632
12633
12634
12635
12636
12637
12638
12639
12640
12641
12642
12643
12644
12645
12646
12647
12648
12649
12650
12651
12652
12653
12654
12655
12656
12657
12658
12659
12660
12661
12662
12663
12664
12665
12666
12667
12668
12669
12670
12671
12672
12673
12674
12675
12676
12677
12678
12679
12680
12681
12682
12683
12684
12685
12686
12687
12688
12689
12690
12691
12692
12693
12694
12695
12696
12697
12698
12699
12700
12701
12702
12703
12704
12705
12706
12707
12708
12709
12710
12711
12712
12713
12714
12715
12716
12717
12718
12719
12720
12721
12722
12723
12724
12725
12726
12727
12728
12729
12730
12731
12732
12733
12734
12735
12736
12737
12738
12739
12740
12741
12742
12743
12744
12745
12746
12747
12748
12749
12750
12751
12752
12753
12754
12755
12756
12757
12758
12759
12760
12761
12762
12763
12764
12765
12766
12767
12768
12769
12770
12771
12772
12773
12774
12775
12776
12777
12778
12779
12780
12781
12782
12783
12784
12785
12786
12787
12788
12789
12790
12791
12792
12793
12794
12795
12796
12797
12798
12799
12800
12801
12802
12803
12804
12805
12806
12807
12808
12809
12810
12811
12812
12813
12814
12815
12816
12817
12818
12819
12820
12821
12822
12823
12824
12825
12826
12827
12828
12829
12830
12831
12832
12833
12834
12835
12836
12837
12838
12839
12840
12841
12842
12843
12844
12845
12846
12847
12848
12849
12850
12851
12852
12853
12854
12855
12856
12857
12858
12859
12860
12861
12862
12863
12864
12865
12866
12867
12868
12869
12870
12871
12872
12873
12874
12875
12876
12877
12878
12879
12880
12881
12882
12883
12884
12885
12886
12887
12888
12889
12890
12891
12892
12893
12894
12895
12896
12897
12898
12899
12900
12901
12902
12903
12904
12905
12906
12907
12908
12909
12910
12911
12912
12913
12914
12915
12916
12917
12918
12919
12920
12921
12922
12923
12924
12925
12926
12927
12928
12929
12930
12931
12932
12933
12934
12935
12936
12937
12938
12939
12940
12941
12942
12943
12944
12945
12946
12947
12948
12949
12950
12951
12952
12953
12954
12955
12956
12957
12958
12959
12960
12961
12962
12963
12964
12965
12966
12967
12968
12969
12970
12971
12972
12973
12974
12975
12976
12977
12978
12979
12980
12981
12982
12983
12984
12985
12986
12987
12988
12989
12990
12991
12992
12993
12994
12995
12996
12997
12998
12999
13000
13001
13002
13003
13004
13005
13006
13007
13008
13009
13010
13011
13012
13013
13014
13015
13016
13017
13018
13019
13020
13021
13022
13023
13024
13025
13026
13027
13028
13029
13030
13031
13032
13033
13034
13035
13036
13037
13038
13039
13040
13041
13042
13043
13044
13045
13046
13047
13048
13049
13050
13051
13052
13053
13054
13055
13056
13057
13058
13059
13060
13061
13062
13063
13064
13065
13066
13067
13068
13069
13070
13071
13072
13073
13074
13075
13076
13077
13078
13079
13080
13081
13082
13083
13084
13085
13086
13087
13088
13089
13090
13091
13092
13093
13094
13095
13096
13097
13098
13099
13100
13101
13102
13103
13104
13105
13106
13107
13108
13109
13110
13111
13112
13113
13114
13115
13116
13117
13118
13119
13120
13121
13122
13123
13124
13125
13126
13127
13128
13129
13130
13131
13132
13133
13134
13135
13136
13137
13138
13139
13140
13141
13142
13143
13144
13145
13146
13147
13148
13149
13150
13151
13152
13153
13154
13155
13156
13157
13158
13159
13160
13161
13162
13163
13164
13165
13166
13167
13168
13169
13170
13171
13172
13173
13174
13175
13176
13177
13178
13179
13180
13181
13182
13183
13184
13185
13186
13187
13188
13189
13190
13191
13192
13193
13194
13195
13196
13197
13198
13199
13200
13201
13202
13203
13204
13205
13206
13207
13208
13209
13210
13211
13212
13213
13214
13215
13216
13217
13218
13219
13220
13221
13222
13223
13224
13225
13226
13227
13228
13229
13230
13231
13232
13233
13234
13235
13236
13237
13238
13239
13240
13241
13242
13243
13244
13245
13246
13247
13248
13249
13250
13251
13252
13253
13254
13255
13256
13257
13258
13259
13260
13261
13262
13263
13264
13265
13266
13267
13268
13269
13270
13271
13272
13273
13274
13275
13276
13277
13278
13279
13280
13281
13282
13283
13284
13285
13286
13287
13288
13289
13290
13291
13292
13293
13294
13295
13296
13297
13298
13299
13300
13301
13302
13303
13304
13305
13306
13307
13308
13309
13310
13311
13312
13313
13314
13315
13316
13317
13318
13319
13320
13321
13322
13323
13324
13325
13326
13327
13328
13329
13330
13331
13332
13333
13334
13335
13336
13337
13338
13339
13340
13341
13342
13343
13344
13345
13346
13347
13348
13349
13350
13351
13352
13353
13354
13355
13356
13357
13358
13359
13360
13361
13362
13363
13364
13365
13366
13367
13368
13369
13370
13371
13372
13373
13374
13375
13376
13377
13378
13379
13380
13381
13382
13383
13384
13385
13386
13387
13388
13389
13390
13391
13392
13393
13394
13395
13396
13397
13398
13399
13400
13401
13402
13403
13404
13405
13406
13407
13408
13409
13410
13411
13412
13413
13414
13415
13416
13417
13418
13419
13420
13421
13422
13423
13424
13425
13426
13427
13428
13429
13430
13431
13432
13433
13434
13435
13436
13437
13438
13439
13440
13441
13442
13443
13444
13445
13446
13447
13448
13449
13450
13451
13452
13453
13454
13455
13456
13457
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * derived from drivers/kvm/kvm_main.c
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2008 Qumranet, Inc.
 * Copyright IBM Corporation, 2008
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 */

#include <linux/kvm_host.h>
#include "irq.h"
#include "ioapic.h"
#include "mmu.h"
#include "i8254.h"
#include "tss.h"
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"
#include "x86.h"
#include "cpuid.h"
#include "pmu.h"
#include "hyperv.h"
#include "lapic.h"
#include "xen.h"
#include "smm.h"

#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <linux/moduleparam.h>
#include <linux/mman.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/cpufreq.h>
#include <linux/user-return-notifier.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/pci.h>
#include <linux/timekeeper_internal.h>
#include <linux/pvclock_gtod.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
#include <linux/sched/stat.h>
#include <linux/sched/isolation.h>
#include <linux/mem_encrypt.h>
#include <linux/entry-kvm.h>
#include <linux/suspend.h>

#include <trace/events/kvm.h>

#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mce.h>
#include <asm/pkru.h>
#include <linux/kernel_stat.h>
#include <asm/fpu/api.h>
#include <asm/fpu/xcr.h>
#include <asm/fpu/xstate.h>
#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
#include <asm/mshyperv.h>
#include <asm/hypervisor.h>
#include <asm/tlbflush.h>
#include <asm/intel_pt.h>
#include <asm/emulate_prefix.h>
#include <asm/sgx.h>
#include <clocksource/hyperv_timer.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32

struct kvm_caps kvm_caps __read_mostly = {
	.supported_mce_cap = MCG_CTL_P | MCG_SER_P,
};
EXPORT_SYMBOL_GPL(kvm_caps);

#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))

#define emul_to_vcpu(ctxt) \
	((struct kvm_vcpu *)(ctxt)->vcpu)

/* EFER defaults:
 * - enable syscall per default because its emulated by KVM
 * - enable LME and LMA per default on 64 bit KVM
 */
#ifdef CONFIG_X86_64
static
u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
#else
static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
#endif

static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;

#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE)

#define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE

#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                    KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)

static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
static void store_regs(struct kvm_vcpu *vcpu);
static int sync_regs(struct kvm_vcpu *vcpu);
static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu);

static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2);
static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2);

struct kvm_x86_ops kvm_x86_ops __read_mostly;

#define KVM_X86_OP(func)					     \
	DEFINE_STATIC_CALL_NULL(kvm_x86_##func,			     \
				*(((struct kvm_x86_ops *)0)->func));
#define KVM_X86_OP_OPTIONAL KVM_X86_OP
#define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP
#include <asm/kvm-x86-ops.h>
EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits);
EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg);

static bool __read_mostly ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);

bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
EXPORT_SYMBOL_GPL(report_ignored_msrs);

unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);

static bool __read_mostly kvmclock_periodic_sync = true;
module_param(kvmclock_periodic_sync, bool, S_IRUGO);

/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);

/*
 * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
 * adaptive tuning starting from default advancement of 1000ns.  '0' disables
 * advancement entirely.  Any other value is used as-is and disables adaptive
 * tuning, i.e. allows privileged userspace to set an exact advancement time.
 */
static int __read_mostly lapic_timer_advance_ns = -1;
module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);

static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, S_IRUGO);

bool __read_mostly enable_vmware_backdoor = false;
module_param(enable_vmware_backdoor, bool, S_IRUGO);
EXPORT_SYMBOL_GPL(enable_vmware_backdoor);

/*
 * Flags to manipulate forced emulation behavior (any non-zero value will
 * enable forced emulation).
 */
#define KVM_FEP_CLEAR_RFLAGS_RF	BIT(1)
static int __read_mostly force_emulation_prefix;
module_param(force_emulation_prefix, int, 0644);

int __read_mostly pi_inject_timer = -1;
module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);

/* Enable/disable PMU virtualization */
bool __read_mostly enable_pmu = true;
EXPORT_SYMBOL_GPL(enable_pmu);
module_param(enable_pmu, bool, 0444);

bool __read_mostly eager_page_split = true;
module_param(eager_page_split, bool, 0644);

/*
 * Restoring the host value for MSRs that are only consumed when running in
 * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
 * returns to userspace, i.e. the kernel can run with the guest's value.
 */
#define KVM_MAX_NR_USER_RETURN_MSRS 16

struct kvm_user_return_msrs {
	struct user_return_notifier urn;
	bool registered;
	struct kvm_user_return_msr_values {
		u64 host;
		u64 curr;
	} values[KVM_MAX_NR_USER_RETURN_MSRS];
};

u32 __read_mostly kvm_nr_uret_msrs;
EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs);
static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS];
static struct kvm_user_return_msrs __percpu *user_return_msrs;

#define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
				| XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \
				| XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE)

u64 __read_mostly host_efer;
EXPORT_SYMBOL_GPL(host_efer);

bool __read_mostly allow_smaller_maxphyaddr = 0;
EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);

bool __read_mostly enable_apicv = true;
EXPORT_SYMBOL_GPL(enable_apicv);

u64 __read_mostly host_xss;
EXPORT_SYMBOL_GPL(host_xss);

const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
	KVM_GENERIC_VM_STATS(),
	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
	STATS_DESC_COUNTER(VM, mmu_pte_write),
	STATS_DESC_COUNTER(VM, mmu_pde_zapped),
	STATS_DESC_COUNTER(VM, mmu_flooded),
	STATS_DESC_COUNTER(VM, mmu_recycled),
	STATS_DESC_COUNTER(VM, mmu_cache_miss),
	STATS_DESC_ICOUNTER(VM, mmu_unsync),
	STATS_DESC_ICOUNTER(VM, pages_4k),
	STATS_DESC_ICOUNTER(VM, pages_2m),
	STATS_DESC_ICOUNTER(VM, pages_1g),
	STATS_DESC_ICOUNTER(VM, nx_lpage_splits),
	STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size),
	STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions)
};

const struct kvm_stats_header kvm_vm_stats_header = {
	.name_size = KVM_STATS_NAME_SIZE,
	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
	.id_offset = sizeof(struct kvm_stats_header),
	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
		       sizeof(kvm_vm_stats_desc),
};

const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
	KVM_GENERIC_VCPU_STATS(),
	STATS_DESC_COUNTER(VCPU, pf_taken),
	STATS_DESC_COUNTER(VCPU, pf_fixed),
	STATS_DESC_COUNTER(VCPU, pf_emulate),
	STATS_DESC_COUNTER(VCPU, pf_spurious),
	STATS_DESC_COUNTER(VCPU, pf_fast),
	STATS_DESC_COUNTER(VCPU, pf_mmio_spte_created),
	STATS_DESC_COUNTER(VCPU, pf_guest),
	STATS_DESC_COUNTER(VCPU, tlb_flush),
	STATS_DESC_COUNTER(VCPU, invlpg),
	STATS_DESC_COUNTER(VCPU, exits),
	STATS_DESC_COUNTER(VCPU, io_exits),
	STATS_DESC_COUNTER(VCPU, mmio_exits),
	STATS_DESC_COUNTER(VCPU, signal_exits),
	STATS_DESC_COUNTER(VCPU, irq_window_exits),
	STATS_DESC_COUNTER(VCPU, nmi_window_exits),
	STATS_DESC_COUNTER(VCPU, l1d_flush),
	STATS_DESC_COUNTER(VCPU, halt_exits),
	STATS_DESC_COUNTER(VCPU, request_irq_exits),
	STATS_DESC_COUNTER(VCPU, irq_exits),
	STATS_DESC_COUNTER(VCPU, host_state_reload),
	STATS_DESC_COUNTER(VCPU, fpu_reload),
	STATS_DESC_COUNTER(VCPU, insn_emulation),
	STATS_DESC_COUNTER(VCPU, insn_emulation_fail),
	STATS_DESC_COUNTER(VCPU, hypercalls),
	STATS_DESC_COUNTER(VCPU, irq_injections),
	STATS_DESC_COUNTER(VCPU, nmi_injections),
	STATS_DESC_COUNTER(VCPU, req_event),
	STATS_DESC_COUNTER(VCPU, nested_run),
	STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
	STATS_DESC_COUNTER(VCPU, preemption_reported),
	STATS_DESC_COUNTER(VCPU, preemption_other),
	STATS_DESC_IBOOLEAN(VCPU, guest_mode),
	STATS_DESC_COUNTER(VCPU, notify_window_exits),
};

const struct kvm_stats_header kvm_vcpu_stats_header = {
	.name_size = KVM_STATS_NAME_SIZE,
	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
	.id_offset = sizeof(struct kvm_stats_header),
	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
		       sizeof(kvm_vcpu_stats_desc),
};

u64 __read_mostly host_xcr0;

static struct kmem_cache *x86_emulator_cache;

/*
 * When called, it means the previous get/set msr reached an invalid msr.
 * Return true if we want to ignore/silent this failed msr access.
 */
static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write)
{
	const char *op = write ? "wrmsr" : "rdmsr";

	if (ignore_msrs) {
		if (report_ignored_msrs)
			kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
				      op, msr, data);
		/* Mask the error */
		return true;
	} else {
		kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
				      op, msr, data);
		return false;
	}
}

static struct kmem_cache *kvm_alloc_emulator_cache(void)
{
	unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src);
	unsigned int size = sizeof(struct x86_emulate_ctxt);

	return kmem_cache_create_usercopy("x86_emulator", size,
					  __alignof__(struct x86_emulate_ctxt),
					  SLAB_ACCOUNT, useroffset,
					  size - useroffset, NULL);
}

static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);

static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
{
	int i;
	for (i = 0; i < ASYNC_PF_PER_VCPU; i++)
		vcpu->arch.apf.gfns[i] = ~0;
}

static void kvm_on_user_return(struct user_return_notifier *urn)
{
	unsigned slot;
	struct kvm_user_return_msrs *msrs
		= container_of(urn, struct kvm_user_return_msrs, urn);
	struct kvm_user_return_msr_values *values;
	unsigned long flags;

	/*
	 * Disabling irqs at this point since the following code could be
	 * interrupted and executed through kvm_arch_hardware_disable()
	 */
	local_irq_save(flags);
	if (msrs->registered) {
		msrs->registered = false;
		user_return_notifier_unregister(urn);
	}
	local_irq_restore(flags);
	for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) {
		values = &msrs->values[slot];
		if (values->host != values->curr) {
			wrmsrl(kvm_uret_msrs_list[slot], values->host);
			values->curr = values->host;
		}
	}
}

static int kvm_probe_user_return_msr(u32 msr)
{
	u64 val;
	int ret;

	preempt_disable();
	ret = rdmsrl_safe(msr, &val);
	if (ret)
		goto out;
	ret = wrmsrl_safe(msr, val);
out:
	preempt_enable();
	return ret;
}

int kvm_add_user_return_msr(u32 msr)
{
	BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS);

	if (kvm_probe_user_return_msr(msr))
		return -1;

	kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr;
	return kvm_nr_uret_msrs++;
}
EXPORT_SYMBOL_GPL(kvm_add_user_return_msr);

int kvm_find_user_return_msr(u32 msr)
{
	int i;

	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
		if (kvm_uret_msrs_list[i] == msr)
			return i;
	}
	return -1;
}
EXPORT_SYMBOL_GPL(kvm_find_user_return_msr);

static void kvm_user_return_msr_cpu_online(void)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
	u64 value;
	int i;

	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
		rdmsrl_safe(kvm_uret_msrs_list[i], &value);
		msrs->values[i].host = value;
		msrs->values[i].curr = value;
	}
}

int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
	int err;

	value = (value & mask) | (msrs->values[slot].host & ~mask);
	if (value == msrs->values[slot].curr)
		return 0;
	err = wrmsrl_safe(kvm_uret_msrs_list[slot], value);
	if (err)
		return 1;

	msrs->values[slot].curr = value;
	if (!msrs->registered) {
		msrs->urn.on_user_return = kvm_on_user_return;
		user_return_notifier_register(&msrs->urn);
		msrs->registered = true;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);

static void drop_user_return_notifiers(void)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);

	if (msrs->registered)
		kvm_on_user_return(&msrs->urn);
}

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);

enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
{
	return kvm_apic_mode(kvm_get_apic_base(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_get_apic_mode);

int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
	enum lapic_mode new_mode = kvm_apic_mode(msr_info->data);
	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);

	if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
		return 1;
	if (!msr_info->host_initiated) {
		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
			return 1;
		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
			return 1;
	}

	kvm_lapic_set_base(vcpu, msr_info->data);
	kvm_recalculate_apic_map(vcpu->kvm);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

/*
 * Handle a fault on a hardware virtualization (VMX or SVM) instruction.
 *
 * Hardware virtualization extension instructions may fault if a reboot turns
 * off virtualization while processes are running.  Usually after catching the
 * fault we just panic; during reboot instead the instruction is ignored.
 */
noinstr void kvm_spurious_fault(void)
{
	/* Fault while not rebooting.  We want the trace. */
	BUG_ON(!kvm_rebooting);
}
EXPORT_SYMBOL_GPL(kvm_spurious_fault);

#define EXCPT_BENIGN		0
#define EXCPT_CONTRIBUTORY	1
#define EXCPT_PF		2

static int exception_class(int vector)
{
	switch (vector) {
	case PF_VECTOR:
		return EXCPT_PF;
	case DE_VECTOR:
	case TS_VECTOR:
	case NP_VECTOR:
	case SS_VECTOR:
	case GP_VECTOR:
		return EXCPT_CONTRIBUTORY;
	default:
		break;
	}
	return EXCPT_BENIGN;
}

#define EXCPT_FAULT		0
#define EXCPT_TRAP		1
#define EXCPT_ABORT		2
#define EXCPT_INTERRUPT		3
#define EXCPT_DB		4

static int exception_type(int vector)
{
	unsigned int mask;

	if (WARN_ON(vector > 31 || vector == NMI_VECTOR))
		return EXCPT_INTERRUPT;

	mask = 1 << vector;

	/*
	 * #DBs can be trap-like or fault-like, the caller must check other CPU
	 * state, e.g. DR6, to determine whether a #DB is a trap or fault.
	 */
	if (mask & (1 << DB_VECTOR))
		return EXCPT_DB;

	if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR)))
		return EXCPT_TRAP;

	if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR)))
		return EXCPT_ABORT;

	/* Reserved exceptions will result in fault */
	return EXCPT_FAULT;
}

void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu,
				   struct kvm_queued_exception *ex)
{
	if (!ex->has_payload)
		return;

	switch (ex->vector) {
	case DB_VECTOR:
		/*
		 * "Certain debug exceptions may clear bit 0-3.  The
		 * remaining contents of the DR6 register are never
		 * cleared by the processor".
		 */
		vcpu->arch.dr6 &= ~DR_TRAP_BITS;
		/*
		 * In order to reflect the #DB exception payload in guest
		 * dr6, three components need to be considered: active low
		 * bit, FIXED_1 bits and active high bits (e.g. DR6_BD,
		 * DR6_BS and DR6_BT)
		 * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits.
		 * In the target guest dr6:
		 * FIXED_1 bits should always be set.
		 * Active low bits should be cleared if 1-setting in payload.
		 * Active high bits should be set if 1-setting in payload.
		 *
		 * Note, the payload is compatible with the pending debug
		 * exceptions/exit qualification under VMX, that active_low bits
		 * are active high in payload.
		 * So they need to be flipped for DR6.
		 */
		vcpu->arch.dr6 |= DR6_ACTIVE_LOW;
		vcpu->arch.dr6 |= ex->payload;
		vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW;

		/*
		 * The #DB payload is defined as compatible with the 'pending
		 * debug exceptions' field under VMX, not DR6. While bit 12 is
		 * defined in the 'pending debug exceptions' field (enabled
		 * breakpoint), it is reserved and must be zero in DR6.
		 */
		vcpu->arch.dr6 &= ~BIT(12);
		break;
	case PF_VECTOR:
		vcpu->arch.cr2 = ex->payload;
		break;
	}

	ex->has_payload = false;
	ex->payload = 0;
}
EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);

static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector,
				       bool has_error_code, u32 error_code,
				       bool has_payload, unsigned long payload)
{
	struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit;

	ex->vector = vector;
	ex->injected = false;
	ex->pending = true;
	ex->has_error_code = has_error_code;
	ex->error_code = error_code;
	ex->has_payload = has_payload;
	ex->payload = payload;
}

/* Forcibly leave the nested mode in cases like a vCPU reset */
static void kvm_leave_nested(struct kvm_vcpu *vcpu)
{
	kvm_x86_ops.nested_ops->leave_nested(vcpu);
}

static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
		unsigned nr, bool has_error, u32 error_code,
	        bool has_payload, unsigned long payload, bool reinject)
{
	u32 prev_nr;
	int class1, class2;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	/*
	 * If the exception is destined for L2 and isn't being reinjected,
	 * morph it to a VM-Exit if L1 wants to intercept the exception.  A
	 * previously injected exception is not checked because it was checked
	 * when it was original queued, and re-checking is incorrect if _L1_
	 * injected the exception, in which case it's exempt from interception.
	 */
	if (!reinject && is_guest_mode(vcpu) &&
	    kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) {
		kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code,
					   has_payload, payload);
		return;
	}

	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
	queue:
		if (reinject) {
			/*
			 * On VM-Entry, an exception can be pending if and only
			 * if event injection was blocked by nested_run_pending.
			 * In that case, however, vcpu_enter_guest() requests an
			 * immediate exit, and the guest shouldn't proceed far
			 * enough to need reinjection.
			 */
			WARN_ON_ONCE(kvm_is_exception_pending(vcpu));
			vcpu->arch.exception.injected = true;
			if (WARN_ON_ONCE(has_payload)) {
				/*
				 * A reinjected event has already
				 * delivered its payload.
				 */
				has_payload = false;
				payload = 0;
			}
		} else {
			vcpu->arch.exception.pending = true;
			vcpu->arch.exception.injected = false;
		}
		vcpu->arch.exception.has_error_code = has_error;
		vcpu->arch.exception.vector = nr;
		vcpu->arch.exception.error_code = error_code;
		vcpu->arch.exception.has_payload = has_payload;
		vcpu->arch.exception.payload = payload;
		if (!is_guest_mode(vcpu))
			kvm_deliver_exception_payload(vcpu,
						      &vcpu->arch.exception);
		return;
	}

	/* to check exception */
	prev_nr = vcpu->arch.exception.vector;
	if (prev_nr == DF_VECTOR) {
		/* triple fault -> shutdown */
		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}
	class1 = exception_class(prev_nr);
	class2 = exception_class(nr);
	if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) ||
	    (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
		/*
		 * Synthesize #DF.  Clear the previously injected or pending
		 * exception so as not to incorrectly trigger shutdown.
		 */
		vcpu->arch.exception.injected = false;
		vcpu->arch.exception.pending = false;

		kvm_queue_exception_e(vcpu, DF_VECTOR, 0);
	} else {
		/* replace previous exception with a new one in a hope
		   that instruction re-execution will regenerate lost
		   exception */
		goto queue;
	}
}

void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);

void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);

void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
			   unsigned long payload)
{
	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_p);

static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
				    u32 error_code, unsigned long payload)
{
	kvm_multiple_exception(vcpu, nr, true, error_code,
			       true, payload, false);
}

int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
	if (err)
		kvm_inject_gp(vcpu, 0);
	else
		return kvm_skip_emulated_instruction(vcpu);

	return 1;
}
EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);

static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err)
{
	if (err) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP |
				       EMULTYPE_COMPLETE_USER_EXIT);
}

void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
	++vcpu->stat.pf_guest;

	/*
	 * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of
	 * whether or not L1 wants to intercept "regular" #PF.
	 */
	if (is_guest_mode(vcpu) && fault->async_page_fault)
		kvm_queue_exception_vmexit(vcpu, PF_VECTOR,
					   true, fault->error_code,
					   true, fault->address);
	else
		kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
					fault->address);
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);

void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
				    struct x86_exception *fault)
{
	struct kvm_mmu *fault_mmu;
	WARN_ON_ONCE(fault->vector != PF_VECTOR);

	fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu :
					       vcpu->arch.walk_mmu;

	/*
	 * Invalidate the TLB entry for the faulting address, if it exists,
	 * else the access will fault indefinitely (and to emulate hardware).
	 */
	if ((fault->error_code & PFERR_PRESENT_MASK) &&
	    !(fault->error_code & PFERR_RSVD_MASK))
		kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address,
				       fault_mmu->root.hpa);

	fault_mmu->inject_page_fault(vcpu, fault);
}
EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault);

void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
	atomic_inc(&vcpu->arch.nmi_queued);
	kvm_make_request(KVM_REQ_NMI, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);

void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);

void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);

/*
 * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
 * a #GP and return false.
 */
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
{
	if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl)
		return true;
	kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
	return false;
}
EXPORT_SYMBOL_GPL(kvm_require_cpl);

bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr)
{
	if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE))
		return true;

	kvm_queue_exception(vcpu, UD_VECTOR);
	return false;
}
EXPORT_SYMBOL_GPL(kvm_require_dr);

static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2);
}

/*
 * Load the pae pdptrs.  Return 1 if they are all valid, 0 otherwise.
 */
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
	gpa_t real_gpa;
	int i;
	int ret;
	u64 pdpte[ARRAY_SIZE(mmu->pdptrs)];

	/*
	 * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated
	 * to an L1 GPA.
	 */
	real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn),
				     PFERR_USER_MASK | PFERR_WRITE_MASK, NULL);
	if (real_gpa == INVALID_GPA)
		return 0;

	/* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */
	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte,
				       cr3 & GENMASK(11, 5), sizeof(pdpte));
	if (ret < 0)
		return 0;

	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
		if ((pdpte[i] & PT_PRESENT_MASK) &&
		    (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
			return 0;
		}
	}

	/*
	 * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled.
	 * Shadow page roots need to be reconstructed instead.
	 */
	if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)))
		kvm_mmu_free_roots(vcpu->kvm, mmu, KVM_MMU_ROOT_CURRENT);

	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
	kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu);
	vcpu->arch.pdptrs_from_userspace = false;

	return 1;
}
EXPORT_SYMBOL_GPL(load_pdptrs);

void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0)
{
	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_async_pf_hash_reset(vcpu);

		/*
		 * Clearing CR0.PG is defined to flush the TLB from the guest's
		 * perspective.
		 */
		if (!(cr0 & X86_CR0_PG))
			kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
	}

	if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS)
		kvm_mmu_reset_context(vcpu);

	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
}
EXPORT_SYMBOL_GPL(kvm_post_set_cr0);

int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	unsigned long old_cr0 = kvm_read_cr0(vcpu);

	cr0 |= X86_CR0_ET;

#ifdef CONFIG_X86_64
	if (cr0 & 0xffffffff00000000UL)
		return 1;
#endif

	cr0 &= ~CR0_RESERVED_BITS;

	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD))
		return 1;

	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE))
		return 1;

#ifdef CONFIG_X86_64
	if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) &&
	    (cr0 & X86_CR0_PG)) {
		int cs_db, cs_l;

		if (!is_pae(vcpu))
			return 1;
		static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
		if (cs_l)
			return 1;
	}
#endif
	if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) &&
	    is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) &&
	    !load_pdptrs(vcpu, kvm_read_cr3(vcpu)))
		return 1;

	if (!(cr0 & X86_CR0_PG) &&
	    (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)))
		return 1;

	static_call(kvm_x86_set_cr0)(vcpu, cr0);

	kvm_post_set_cr0(vcpu, old_cr0, cr0);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);

void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
	(void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);

void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.guest_state_protected)
		return;

	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {

		if (vcpu->arch.xcr0 != host_xcr0)
			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);

		if (vcpu->arch.xsaves_enabled &&
		    vcpu->arch.ia32_xss != host_xss)
			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
	}

#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
	if (static_cpu_has(X86_FEATURE_PKU) &&
	    vcpu->arch.pkru != vcpu->arch.host_pkru &&
	    ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
	     kvm_read_cr4_bits(vcpu, X86_CR4_PKE)))
		write_pkru(vcpu->arch.pkru);
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
}
EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);

void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.guest_state_protected)
		return;

#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
	if (static_cpu_has(X86_FEATURE_PKU) &&
	    ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
	     kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) {
		vcpu->arch.pkru = rdpkru();
		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
			write_pkru(vcpu->arch.host_pkru);
	}
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */

	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {

		if (vcpu->arch.xcr0 != host_xcr0)
			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);

		if (vcpu->arch.xsaves_enabled &&
		    vcpu->arch.ia32_xss != host_xss)
			wrmsrl(MSR_IA32_XSS, host_xss);
	}

}
EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);

#ifdef CONFIG_X86_64
static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC;
}
#endif

static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	u64 xcr0 = xcr;
	u64 old_xcr0 = vcpu->arch.xcr0;
	u64 valid_bits;

	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
	if (index != XCR_XFEATURE_ENABLED_MASK)
		return 1;
	if (!(xcr0 & XFEATURE_MASK_FP))
		return 1;
	if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE))
		return 1;

	/*
	 * Do not allow the guest to set bits that we do not support
	 * saving.  However, xcr0 bit 0 is always set, even if the
	 * emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
	 */
	valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
	if (xcr0 & ~valid_bits)
		return 1;

	if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) !=
	    (!(xcr0 & XFEATURE_MASK_BNDCSR)))
		return 1;

	if (xcr0 & XFEATURE_MASK_AVX512) {
		if (!(xcr0 & XFEATURE_MASK_YMM))
			return 1;
		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
			return 1;
	}

	if ((xcr0 & XFEATURE_MASK_XTILE) &&
	    ((xcr0 & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE))
		return 1;

	vcpu->arch.xcr0 = xcr0;

	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
		kvm_update_cpuid_runtime(vcpu);
	return 0;
}

int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
{
	/* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */
	if (static_call(kvm_x86_get_cpl)(vcpu) != 0 ||
	    __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv);

bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	if (cr4 & cr4_reserved_bits)
		return false;

	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
		return false;

	return true;
}
EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4);

static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	return __kvm_is_valid_cr4(vcpu, cr4) &&
	       static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
}

void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
{
	if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS)
		kvm_mmu_reset_context(vcpu);

	/*
	 * If CR4.PCIDE is changed 0 -> 1, there is no need to flush the TLB
	 * according to the SDM; however, stale prev_roots could be reused
	 * incorrectly in the future after a MOV to CR3 with NOFLUSH=1, so we
	 * free them all.  This is *not* a superset of KVM_REQ_TLB_FLUSH_GUEST
	 * or KVM_REQ_TLB_FLUSH_CURRENT, because the hardware TLB is not flushed,
	 * so fall through.
	 */
	if (!tdp_enabled &&
	    (cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE))
		kvm_mmu_unload(vcpu);

	/*
	 * The TLB has to be flushed for all PCIDs if any of the following
	 * (architecturally required) changes happen:
	 * - CR4.PCIDE is changed from 1 to 0
	 * - CR4.PGE is toggled
	 *
	 * This is a superset of KVM_REQ_TLB_FLUSH_CURRENT.
	 */
	if (((cr4 ^ old_cr4) & X86_CR4_PGE) ||
	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);

	/*
	 * The TLB has to be flushed for the current PCID if any of the
	 * following (architecturally required) changes happen:
	 * - CR4.SMEP is changed from 0 to 1
	 * - CR4.PAE is toggled
	 */
	else if (((cr4 ^ old_cr4) & X86_CR4_PAE) ||
		 ((cr4 & X86_CR4_SMEP) && !(old_cr4 & X86_CR4_SMEP)))
		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);

}
EXPORT_SYMBOL_GPL(kvm_post_set_cr4);

int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	unsigned long old_cr4 = kvm_read_cr4(vcpu);

	if (!kvm_is_valid_cr4(vcpu, cr4))
		return 1;

	if (is_long_mode(vcpu)) {
		if (!(cr4 & X86_CR4_PAE))
			return 1;
		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
			return 1;
	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
		   && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS)
		   && !load_pdptrs(vcpu, kvm_read_cr3(vcpu)))
		return 1;

	if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
		if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
			return 1;

		/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
		if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
			return 1;
	}

	static_call(kvm_x86_set_cr4)(vcpu, cr4);

	kvm_post_set_cr4(vcpu, old_cr4, cr4);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid)
{
	struct kvm_mmu *mmu = vcpu->arch.mmu;
	unsigned long roots_to_free = 0;
	int i;

	/*
	 * MOV CR3 and INVPCID are usually not intercepted when using TDP, but
	 * this is reachable when running EPT=1 and unrestricted_guest=0,  and
	 * also via the emulator.  KVM's TDP page tables are not in the scope of
	 * the invalidation, but the guest's TLB entries need to be flushed as
	 * the CPU may have cached entries in its TLB for the target PCID.
	 */
	if (unlikely(tdp_enabled)) {
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
		return;
	}

	/*
	 * If neither the current CR3 nor any of the prev_roots use the given
	 * PCID, then nothing needs to be done here because a resync will
	 * happen anyway before switching to any other CR3.
	 */
	if (kvm_get_active_pcid(vcpu) == pcid) {
		kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
	}

	/*
	 * If PCID is disabled, there is no need to free prev_roots even if the
	 * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB
	 * with PCIDE=0.
	 */
	if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
		return;

	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
		if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid)
			roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);

	kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free);
}

int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	bool skip_tlb_flush = false;
	unsigned long pcid = 0;
#ifdef CONFIG_X86_64
	bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);

	if (pcid_enabled) {
		skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH;
		cr3 &= ~X86_CR3_PCID_NOFLUSH;
		pcid = cr3 & X86_CR3_PCID_MASK;
	}
#endif

	/* PDPTRs are always reloaded for PAE paging. */
	if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu))
		goto handle_tlb_flush;

	/*
	 * Do not condition the GPA check on long mode, this helper is used to
	 * stuff CR3, e.g. for RSM emulation, and there is no guarantee that
	 * the current vCPU mode is accurate.
	 */
	if (kvm_vcpu_is_illegal_gpa(vcpu, cr3))
		return 1;

	if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3))
		return 1;

	if (cr3 != kvm_read_cr3(vcpu))
		kvm_mmu_new_pgd(vcpu, cr3);

	vcpu->arch.cr3 = cr3;
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
	/* Do not call post_set_cr3, we do not get here for confidential guests.  */

handle_tlb_flush:
	/*
	 * A load of CR3 that flushes the TLB flushes only the current PCID,
	 * even if PCID is disabled, in which case PCID=0 is flushed.  It's a
	 * moot point in the end because _disabling_ PCID will flush all PCIDs,
	 * and it's impossible to use a non-zero PCID when PCID is disabled,
	 * i.e. only PCID=0 can be relevant.
	 */
	if (!skip_tlb_flush)
		kvm_invalidate_pcid(vcpu, pcid);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);

int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	if (cr8 & CR8_RESERVED_BITS)
		return 1;
	if (lapic_in_kernel(vcpu))
		kvm_lapic_set_tpr(vcpu, cr8);
	else
		vcpu->arch.cr8 = cr8;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr8);

unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
{
	if (lapic_in_kernel(vcpu))
		return kvm_lapic_get_cr8(vcpu);
	else
		return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);

static void kvm_update_dr0123(struct kvm_vcpu *vcpu)
{
	int i;

	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
		for (i = 0; i < KVM_NR_DB_REGS; i++)
			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
	}
}

void kvm_update_dr7(struct kvm_vcpu *vcpu)
{
	unsigned long dr7;

	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
		dr7 = vcpu->arch.guest_debug_dr7;
	else
		dr7 = vcpu->arch.dr7;
	static_call(kvm_x86_set_dr7)(vcpu, dr7);
	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED;
	if (dr7 & DR7_BP_EN_MASK)
		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
}
EXPORT_SYMBOL_GPL(kvm_update_dr7);

static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
{
	u64 fixed = DR6_FIXED_1;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM))
		fixed |= DR6_RTM;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
		fixed |= DR6_BUS_LOCK;
	return fixed;
}

int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	size_t size = ARRAY_SIZE(vcpu->arch.db);

	switch (dr) {
	case 0 ... 3:
		vcpu->arch.db[array_index_nospec(dr, size)] = val;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
			vcpu->arch.eff_db[dr] = val;
		break;
	case 4:
	case 6:
		if (!kvm_dr6_valid(val))
			return 1; /* #GP */
		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
		break;
	case 5:
	default: /* 7 */
		if (!kvm_dr7_valid(val))
			return 1; /* #GP */
		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
		kvm_update_dr7(vcpu);
		break;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_dr);

void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	size_t size = ARRAY_SIZE(vcpu->arch.db);

	switch (dr) {
	case 0 ... 3:
		*val = vcpu->arch.db[array_index_nospec(dr, size)];
		break;
	case 4:
	case 6:
		*val = vcpu->arch.dr6;
		break;
	case 5:
	default: /* 7 */
		*val = vcpu->arch.dr7;
		break;
	}
}
EXPORT_SYMBOL_GPL(kvm_get_dr);

int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data;

	if (kvm_pmu_rdpmc(vcpu, ecx, &data)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	kvm_rax_write(vcpu, (u32)data);
	kvm_rdx_write(vcpu, data >> 32);
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
 * extract the supported MSRs from the related const lists.
 * msrs_to_save is selected from the msrs_to_save_all to reflect the
 * capabilities of the host cpu. This capabilities test skips MSRs that are
 * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
 * may depend on host virtualization features rather than host cpu features.
 */

static const u32 msrs_to_save_all[] = {
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_STAR,
#ifdef CONFIG_X86_64
	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
	MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
	MSR_IA32_SPEC_CTRL,
	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
	MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
	MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
	MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
	MSR_IA32_UMWAIT_CONTROL,

	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,

	/* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */
	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
	MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
	MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
	MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7,
	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
	MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7,

	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,

	/* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */
	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,

	MSR_IA32_XFD, MSR_IA32_XFD_ERR,
};

static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
static unsigned num_msrs_to_save;

static const u32 emulated_msrs_all[] = {
	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
	HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
	HV_X64_MSR_RESET,
	HV_X64_MSR_VP_INDEX,
	HV_X64_MSR_VP_RUNTIME,
	HV_X64_MSR_SCONTROL,
	HV_X64_MSR_STIMER0_CONFIG,
	HV_X64_MSR_VP_ASSIST_PAGE,
	HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL,
	HV_X64_MSR_TSC_EMULATION_STATUS,
	HV_X64_MSR_SYNDBG_OPTIONS,
	HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
	HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
	HV_X64_MSR_SYNDBG_PENDING_BUFFER,

	MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
	MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK,

	MSR_IA32_TSC_ADJUST,
	MSR_IA32_TSC_DEADLINE,
	MSR_IA32_ARCH_CAPABILITIES,
	MSR_IA32_PERF_CAPABILITIES,
	MSR_IA32_MISC_ENABLE,
	MSR_IA32_MCG_STATUS,
	MSR_IA32_MCG_CTL,
	MSR_IA32_MCG_EXT_CTL,
	MSR_IA32_SMBASE,
	MSR_SMI_COUNT,
	MSR_PLATFORM_INFO,
	MSR_MISC_FEATURES_ENABLES,
	MSR_AMD64_VIRT_SPEC_CTRL,
	MSR_AMD64_TSC_RATIO,
	MSR_IA32_POWER_CTL,
	MSR_IA32_UCODE_REV,

	/*
	 * The following list leaves out MSRs whose values are determined
	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
	 * We always support the "true" VMX control MSRs, even if the host
	 * processor does not, so I am putting these registers here rather
	 * than in msrs_to_save_all.
	 */
	MSR_IA32_VMX_BASIC,
	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
	MSR_IA32_VMX_TRUE_EXIT_CTLS,
	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
	MSR_IA32_VMX_MISC,
	MSR_IA32_VMX_CR0_FIXED0,
	MSR_IA32_VMX_CR4_FIXED0,
	MSR_IA32_VMX_VMCS_ENUM,
	MSR_IA32_VMX_PROCBASED_CTLS2,
	MSR_IA32_VMX_EPT_VPID_CAP,
	MSR_IA32_VMX_VMFUNC,

	MSR_K7_HWCR,
	MSR_KVM_POLL_CONTROL,
};

static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
static unsigned num_emulated_msrs;

/*
 * List of msr numbers which are used to expose MSR-based features that
 * can be used by a hypervisor to validate requested CPU features.
 */
static const u32 msr_based_features_all[] = {
	MSR_IA32_VMX_BASIC,
	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
	MSR_IA32_VMX_PINBASED_CTLS,
	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
	MSR_IA32_VMX_PROCBASED_CTLS,
	MSR_IA32_VMX_TRUE_EXIT_CTLS,
	MSR_IA32_VMX_EXIT_CTLS,
	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
	MSR_IA32_VMX_ENTRY_CTLS,
	MSR_IA32_VMX_MISC,
	MSR_IA32_VMX_CR0_FIXED0,
	MSR_IA32_VMX_CR0_FIXED1,
	MSR_IA32_VMX_CR4_FIXED0,
	MSR_IA32_VMX_CR4_FIXED1,
	MSR_IA32_VMX_VMCS_ENUM,
	MSR_IA32_VMX_PROCBASED_CTLS2,
	MSR_IA32_VMX_EPT_VPID_CAP,
	MSR_IA32_VMX_VMFUNC,

	MSR_F10H_DECFG,
	MSR_IA32_UCODE_REV,
	MSR_IA32_ARCH_CAPABILITIES,
	MSR_IA32_PERF_CAPABILITIES,
};

static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
static unsigned int num_msr_based_features;

/*
 * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
 * does not yet virtualize. These include:
 *   10 - MISC_PACKAGE_CTRLS
 *   11 - ENERGY_FILTERING_CTL
 *   12 - DOITM
 *   18 - FB_CLEAR_CTRL
 *   21 - XAPIC_DISABLE_STATUS
 *   23 - OVERCLOCKING_STATUS
 */

#define KVM_SUPPORTED_ARCH_CAP \
	(ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \
	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)

static u64 kvm_get_arch_capabilities(void)
{
	u64 data = 0;

	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
		data &= KVM_SUPPORTED_ARCH_CAP;
	}

	/*
	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
	 * the nested hypervisor runs with NX huge pages.  If it is not,
	 * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other
	 * L1 guests, so it need not worry about its own (L2) guests.
	 */
	data |= ARCH_CAP_PSCHANGE_MC_NO;

	/*
	 * If we're doing cache flushes (either "always" or "cond")
	 * we will do one whenever the guest does a vmlaunch/vmresume.
	 * If an outer hypervisor is doing the cache flush for us
	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
	 * capability to the guest too, and if EPT is disabled we're not
	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
	 * require a nested hypervisor to do a flush of its own.
	 */
	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;

	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
		data |= ARCH_CAP_RDCL_NO;
	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
		data |= ARCH_CAP_SSB_NO;
	if (!boot_cpu_has_bug(X86_BUG_MDS))
		data |= ARCH_CAP_MDS_NO;

	if (!boot_cpu_has(X86_FEATURE_RTM)) {
		/*
		 * If RTM=0 because the kernel has disabled TSX, the host might
		 * have TAA_NO or TSX_CTRL.  Clear TAA_NO (the guest sees RTM=0
		 * and therefore knows that there cannot be TAA) but keep
		 * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts,
		 * and we want to allow migrating those guests to tsx=off hosts.
		 */
		data &= ~ARCH_CAP_TAA_NO;
	} else if (!boot_cpu_has_bug(X86_BUG_TAA)) {
		data |= ARCH_CAP_TAA_NO;
	} else {
		/*
		 * Nothing to do here; we emulate TSX_CTRL if present on the
		 * host so the guest can choose between disabling TSX or
		 * using VERW to clear CPU buffers.
		 */
	}

	return data;
}

static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
{
	switch (msr->index) {
	case MSR_IA32_ARCH_CAPABILITIES:
		msr->data = kvm_get_arch_capabilities();
		break;
	case MSR_IA32_PERF_CAPABILITIES:
		msr->data = kvm_caps.supported_perf_cap;
		break;
	case MSR_IA32_UCODE_REV:
		rdmsrl_safe(msr->index, &msr->data);
		break;
	default:
		return static_call(kvm_x86_get_msr_feature)(msr);
	}
	return 0;
}

static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	struct kvm_msr_entry msr;
	int r;

	msr.index = index;
	r = kvm_get_msr_feature(&msr);

	if (r == KVM_MSR_RET_INVALID) {
		/* Unconditionally clear the output for simplicity */
		*data = 0;
		if (kvm_msr_ignored_check(index, 0, false))
			r = 0;
	}

	if (r)
		return r;

	*data = msr.data;

	return 0;
}

static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
		return false;

	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
		return false;

	if (efer & (EFER_LME | EFER_LMA) &&
	    !guest_cpuid_has(vcpu, X86_FEATURE_LM))
		return false;

	if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX))
		return false;

	return true;

}
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	if (efer & efer_reserved_bits)
		return false;

	return __kvm_valid_efer(vcpu, efer);
}
EXPORT_SYMBOL_GPL(kvm_valid_efer);

static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	u64 old_efer = vcpu->arch.efer;
	u64 efer = msr_info->data;
	int r;

	if (efer & efer_reserved_bits)
		return 1;

	if (!msr_info->host_initiated) {
		if (!__kvm_valid_efer(vcpu, efer))
			return 1;

		if (is_paging(vcpu) &&
		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
			return 1;
	}

	efer &= ~EFER_LMA;
	efer |= vcpu->arch.efer & EFER_LMA;

	r = static_call(kvm_x86_set_efer)(vcpu, efer);
	if (r) {
		WARN_ON(r > 0);
		return r;
	}

	if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
		kvm_mmu_reset_context(vcpu);

	return 0;
}

void kvm_enable_efer_bits(u64 mask)
{
       efer_reserved_bits &= ~mask;
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);

bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
{
	struct kvm_x86_msr_filter *msr_filter;
	struct msr_bitmap_range *ranges;
	struct kvm *kvm = vcpu->kvm;
	bool allowed;
	int idx;
	u32 i;

	/* x2APIC MSRs do not support filtering. */
	if (index >= 0x800 && index <= 0x8ff)
		return true;

	idx = srcu_read_lock(&kvm->srcu);

	msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
	if (!msr_filter) {
		allowed = true;
		goto out;
	}

	allowed = msr_filter->default_allow;
	ranges = msr_filter->ranges;

	for (i = 0; i < msr_filter->count; i++) {
		u32 start = ranges[i].base;
		u32 end = start + ranges[i].nmsrs;
		u32 flags = ranges[i].flags;
		unsigned long *bitmap = ranges[i].bitmap;

		if ((index >= start) && (index < end) && (flags & type)) {
			allowed = !!test_bit(index - start, bitmap);
			break;
		}
	}

out:
	srcu_read_unlock(&kvm->srcu, idx);

	return allowed;
}
EXPORT_SYMBOL_GPL(kvm_msr_allowed);

/*
 * Write @data into the MSR specified by @index.  Select MSR specific fault
 * checks are bypassed if @host_initiated is %true.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
			 bool host_initiated)
{
	struct msr_data msr;

	switch (index) {
	case MSR_FS_BASE:
	case MSR_GS_BASE:
	case MSR_KERNEL_GS_BASE:
	case MSR_CSTAR:
	case MSR_LSTAR:
		if (is_noncanonical_address(data, vcpu))
			return 1;
		break;
	case MSR_IA32_SYSENTER_EIP:
	case MSR_IA32_SYSENTER_ESP:
		/*
		 * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
		 * non-canonical address is written on Intel but not on
		 * AMD (which ignores the top 32-bits, because it does
		 * not implement 64-bit SYSENTER).
		 *
		 * 64-bit code should hence be able to write a non-canonical
		 * value on AMD.  Making the address canonical ensures that
		 * vmentry does not fail on Intel after writing a non-canonical
		 * value, and that something deterministic happens if the guest
		 * invokes 64-bit SYSENTER.
		 */
		data = __canonical_address(data, vcpu_virt_addr_bits(vcpu));
		break;
	case MSR_TSC_AUX:
		if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
			return 1;

		if (!host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDPID))
			return 1;

		/*
		 * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has
		 * incomplete and conflicting architectural behavior.  Current
		 * AMD CPUs completely ignore bits 63:32, i.e. they aren't
		 * reserved and always read as zeros.  Enforce Intel's reserved
		 * bits check if and only if the guest CPU is Intel, and clear
		 * the bits in all other cases.  This ensures cross-vendor
		 * migration will provide consistent behavior for the guest.
		 */
		if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0)
			return 1;

		data = (u32)data;
		break;
	}

	msr.data = data;
	msr.index = index;
	msr.host_initiated = host_initiated;

	return static_call(kvm_x86_set_msr)(vcpu, &msr);
}

static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
				     u32 index, u64 data, bool host_initiated)
{
	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);

	if (ret == KVM_MSR_RET_INVALID)
		if (kvm_msr_ignored_check(index, data, true))
			ret = 0;

	return ret;
}

/*
 * Read the MSR specified by @index into @data.  Select MSR specific fault
 * checks are bypassed if @host_initiated is %true.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
		  bool host_initiated)
{
	struct msr_data msr;
	int ret;

	switch (index) {
	case MSR_TSC_AUX:
		if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
			return 1;

		if (!host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDPID))
			return 1;
		break;
	}

	msr.index = index;
	msr.host_initiated = host_initiated;

	ret = static_call(kvm_x86_get_msr)(vcpu, &msr);
	if (!ret)
		*data = msr.data;
	return ret;
}

static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
				     u32 index, u64 *data, bool host_initiated)
{
	int ret = __kvm_get_msr(vcpu, index, data, host_initiated);

	if (ret == KVM_MSR_RET_INVALID) {
		/* Unconditionally clear *data for simplicity */
		*data = 0;
		if (kvm_msr_ignored_check(index, 0, false))
			ret = 0;
	}

	return ret;
}

static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data)
{
	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
		return KVM_MSR_RET_FILTERED;
	return kvm_get_msr_ignored_check(vcpu, index, data, false);
}

static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data)
{
	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
		return KVM_MSR_RET_FILTERED;
	return kvm_set_msr_ignored_check(vcpu, index, data, false);
}

int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
{
	return kvm_get_msr_ignored_check(vcpu, index, data, false);
}
EXPORT_SYMBOL_GPL(kvm_get_msr);

int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
{
	return kvm_set_msr_ignored_check(vcpu, index, data, false);
}
EXPORT_SYMBOL_GPL(kvm_set_msr);

static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu)
{
	if (!vcpu->run->msr.error) {
		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
	}
}

static int complete_emulated_msr_access(struct kvm_vcpu *vcpu)
{
	return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error);
}

static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
{
	complete_userspace_rdmsr(vcpu);
	return complete_emulated_msr_access(vcpu);
}

static int complete_fast_msr_access(struct kvm_vcpu *vcpu)
{
	return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error);
}

static int complete_fast_rdmsr(struct kvm_vcpu *vcpu)
{
	complete_userspace_rdmsr(vcpu);
	return complete_fast_msr_access(vcpu);
}

static u64 kvm_msr_reason(int r)
{
	switch (r) {
	case KVM_MSR_RET_INVALID:
		return KVM_MSR_EXIT_REASON_UNKNOWN;
	case KVM_MSR_RET_FILTERED:
		return KVM_MSR_EXIT_REASON_FILTER;
	default:
		return KVM_MSR_EXIT_REASON_INVAL;
	}
}

static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
			      u32 exit_reason, u64 data,
			      int (*completion)(struct kvm_vcpu *vcpu),
			      int r)
{
	u64 msr_reason = kvm_msr_reason(r);

	/* Check if the user wanted to know about this MSR fault */
	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
		return 0;

	vcpu->run->exit_reason = exit_reason;
	vcpu->run->msr.error = 0;
	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
	vcpu->run->msr.reason = msr_reason;
	vcpu->run->msr.index = index;
	vcpu->run->msr.data = data;
	vcpu->arch.complete_userspace_io = completion;

	return 1;
}

int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data;
	int r;

	r = kvm_get_msr_with_filter(vcpu, ecx, &data);

	if (!r) {
		trace_kvm_msr_read(ecx, data);

		kvm_rax_write(vcpu, data & -1u);
		kvm_rdx_write(vcpu, (data >> 32) & -1u);
	} else {
		/* MSR read failed? See if we should ask user space */
		if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0,
				       complete_fast_rdmsr, r))
			return 0;
		trace_kvm_msr_read_ex(ecx);
	}

	return static_call(kvm_x86_complete_emulated_msr)(vcpu, r);
}
EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);

int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data = kvm_read_edx_eax(vcpu);
	int r;

	r = kvm_set_msr_with_filter(vcpu, ecx, data);

	if (!r) {
		trace_kvm_msr_write(ecx, data);
	} else {
		/* MSR write failed? See if we should ask user space */
		if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data,
				       complete_fast_msr_access, r))
			return 0;
		/* Signal all other negative errors to userspace */
		if (r < 0)
			return r;
		trace_kvm_msr_write_ex(ecx, data);
	}

	return static_call(kvm_x86_complete_emulated_msr)(vcpu, r);
}
EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);

int kvm_emulate_as_nop(struct kvm_vcpu *vcpu)
{
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_as_nop);

int kvm_emulate_invd(struct kvm_vcpu *vcpu)
{
	/* Treat an INVD instruction as a NOP and just skip it. */
	return kvm_emulate_as_nop(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_invd);

int kvm_handle_invalid_op(struct kvm_vcpu *vcpu)
{
	kvm_queue_exception(vcpu, UD_VECTOR);
	return 1;
}
EXPORT_SYMBOL_GPL(kvm_handle_invalid_op);


static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn)
{
	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) &&
	    !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT))
		return kvm_handle_invalid_op(vcpu);

	pr_warn_once("kvm: %s instruction emulated as NOP!\n", insn);
	return kvm_emulate_as_nop(vcpu);
}
int kvm_emulate_mwait(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_monitor_mwait(vcpu, "MWAIT");
}
EXPORT_SYMBOL_GPL(kvm_emulate_mwait);

int kvm_emulate_monitor(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_monitor_mwait(vcpu, "MONITOR");
}
EXPORT_SYMBOL_GPL(kvm_emulate_monitor);

static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
{
	xfer_to_guest_mode_prepare();
	return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) ||
		xfer_to_guest_mode_work_pending();
}

/*
 * The fast path for frequent and performance sensitive wrmsr emulation,
 * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces
 * the latency of virtual IPI by avoiding the expensive bits of transitioning
 * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the
 * other cases which must be called after interrupts are enabled on the host.
 */
static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data)
{
	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic))
		return 1;

	if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) &&
	    ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
	    ((data & APIC_MODE_MASK) == APIC_DM_FIXED) &&
	    ((u32)(data >> 32) != X2APIC_BROADCAST))
		return kvm_x2apic_icr_write(vcpu->arch.apic, data);

	return 1;
}

static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data)
{
	if (!kvm_can_use_hv_timer(vcpu))
		return 1;

	kvm_set_lapic_tscdeadline_msr(vcpu, data);
	return 0;
}

fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu)
{
	u32 msr = kvm_rcx_read(vcpu);
	u64 data;
	fastpath_t ret = EXIT_FASTPATH_NONE;

	switch (msr) {
	case APIC_BASE_MSR + (APIC_ICR >> 4):
		data = kvm_read_edx_eax(vcpu);
		if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) {
			kvm_skip_emulated_instruction(vcpu);
			ret = EXIT_FASTPATH_EXIT_HANDLED;
		}
		break;
	case MSR_IA32_TSC_DEADLINE:
		data = kvm_read_edx_eax(vcpu);
		if (!handle_fastpath_set_tscdeadline(vcpu, data)) {
			kvm_skip_emulated_instruction(vcpu);
			ret = EXIT_FASTPATH_REENTER_GUEST;
		}
		break;
	default:
		break;
	}

	if (ret != EXIT_FASTPATH_NONE)
		trace_kvm_msr_write(msr, data);

	return ret;
}
EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff);

/*
 * Adapt set_msr() to msr_io()'s calling convention
 */
static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_get_msr_ignored_check(vcpu, index, data, true);
}

static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_set_msr_ignored_check(vcpu, index, *data, true);
}

#ifdef CONFIG_X86_64
struct pvclock_clock {
	int vclock_mode;
	u64 cycle_last;
	u64 mask;
	u32 mult;
	u32 shift;
	u64 base_cycles;
	u64 offset;
};

struct pvclock_gtod_data {
	seqcount_t	seq;

	struct pvclock_clock clock; /* extract of a clocksource struct */
	struct pvclock_clock raw_clock; /* extract of a clocksource struct */

	ktime_t		offs_boot;
	u64		wall_time_sec;
};

static struct pvclock_gtod_data pvclock_gtod_data;

static void update_pvclock_gtod(struct timekeeper *tk)
{
	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;

	write_seqcount_begin(&vdata->seq);

	/* copy pvclock gtod data */
	vdata->clock.vclock_mode	= tk->tkr_mono.clock->vdso_clock_mode;
	vdata->clock.cycle_last		= tk->tkr_mono.cycle_last;
	vdata->clock.mask		= tk->tkr_mono.mask;
	vdata->clock.mult		= tk->tkr_mono.mult;
	vdata->clock.shift		= tk->tkr_mono.shift;
	vdata->clock.base_cycles	= tk->tkr_mono.xtime_nsec;
	vdata->clock.offset		= tk->tkr_mono.base;

	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->vdso_clock_mode;
	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
	vdata->raw_clock.mask		= tk->tkr_raw.mask;
	vdata->raw_clock.mult		= tk->tkr_raw.mult;
	vdata->raw_clock.shift		= tk->tkr_raw.shift;
	vdata->raw_clock.base_cycles	= tk->tkr_raw.xtime_nsec;
	vdata->raw_clock.offset		= tk->tkr_raw.base;

	vdata->wall_time_sec            = tk->xtime_sec;

	vdata->offs_boot		= tk->offs_boot;

	write_seqcount_end(&vdata->seq);
}

static s64 get_kvmclock_base_ns(void)
{
	/* Count up from boot time, but with the frequency of the raw clock.  */
	return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot));
}
#else
static s64 get_kvmclock_base_ns(void)
{
	/* Master clock not used, so we can just use CLOCK_BOOTTIME.  */
	return ktime_get_boottime_ns();
}
#endif

static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs)
{
	int version;
	int r;
	struct pvclock_wall_clock wc;
	u32 wc_sec_hi;
	u64 wall_nsec;

	if (!wall_clock)
		return;

	r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
	if (r)
		return;

	if (version & 1)
		++version;  /* first time write, random junk */

	++version;

	if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version)))
		return;

	/*
	 * The guest calculates current wall clock time by adding
	 * system time (updated by kvm_guest_time_update below) to the
	 * wall clock specified here.  We do the reverse here.
	 */
	wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm);

	wc.nsec = do_div(wall_nsec, 1000000000);
	wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */
	wc.version = version;

	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));

	if (sec_hi_ofs) {
		wc_sec_hi = wall_nsec >> 32;
		kvm_write_guest(kvm, wall_clock + sec_hi_ofs,
				&wc_sec_hi, sizeof(wc_sec_hi));
	}

	version++;
	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
}

static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
				  bool old_msr, bool host_initiated)
{
	struct kvm_arch *ka = &vcpu->kvm->arch;

	if (vcpu->vcpu_id == 0 && !host_initiated) {
		if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);

		ka->boot_vcpu_runs_old_kvmclock = old_msr;
	}

	vcpu->arch.time = system_time;
	kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);

	/* we verify if the enable bit is set... */
	if (system_time & 1) {
		kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
				 KVM_HOST_USES_PFN, system_time & ~1ULL,
				 sizeof(struct pvclock_vcpu_time_info));
	} else {
		kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
	}

	return;
}

static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
	do_shl32_div32(dividend, divisor);
	return dividend;
}

static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
			       s8 *pshift, u32 *pmultiplier)
{
	uint64_t scaled64;
	int32_t  shift = 0;
	uint64_t tps64;
	uint32_t tps32;

	tps64 = base_hz;
	scaled64 = scaled_hz;
	while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
		tps64 >>= 1;
		shift--;
	}

	tps32 = (uint32_t)tps64;
	while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
		if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
			scaled64 >>= 1;
		else
			tps32 <<= 1;
		shift++;
	}

	*pshift = shift;
	*pmultiplier = div_frac(scaled64, tps32);
}

#ifdef CONFIG_X86_64
static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
#endif

static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
static unsigned long max_tsc_khz;

static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
	u64 v = (u64)khz * (1000000 + ppm);
	do_div(v, 1000000);
	return v;
}

static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier);

static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
{
	u64 ratio;

	/* Guest TSC same frequency as host TSC? */
	if (!scale) {
		kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio);
		return 0;
	}

	/* TSC scaling supported? */
	if (!kvm_caps.has_tsc_control) {
		if (user_tsc_khz > tsc_khz) {
			vcpu->arch.tsc_catchup = 1;
			vcpu->arch.tsc_always_catchup = 1;
			return 0;
		} else {
			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
			return -1;
		}
	}

	/* TSC scaling required  - calculate ratio */
	ratio = mul_u64_u32_div(1ULL << kvm_caps.tsc_scaling_ratio_frac_bits,
				user_tsc_khz, tsc_khz);

	if (ratio == 0 || ratio >= kvm_caps.max_tsc_scaling_ratio) {
		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
			            user_tsc_khz);
		return -1;
	}

	kvm_vcpu_write_tsc_multiplier(vcpu, ratio);
	return 0;
}

static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
{
	u32 thresh_lo, thresh_hi;
	int use_scaling = 0;

	/* tsc_khz can be zero if TSC calibration fails */
	if (user_tsc_khz == 0) {
		/* set tsc_scaling_ratio to a safe value */
		kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio);
		return -1;
	}

	/* Compute a scale to convert nanoseconds in TSC cycles */
	kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
			   &vcpu->arch.virtual_tsc_shift,
			   &vcpu->arch.virtual_tsc_mult);
	vcpu->arch.virtual_tsc_khz = user_tsc_khz;

	/*
	 * Compute the variation in TSC rate which is acceptable
	 * within the range of tolerance and decide if the
	 * rate being applied is within that bounds of the hardware
	 * rate.  If so, no scaling or compensation need be done.
	 */
	thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
	thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
	if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
		pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
		use_scaling = 1;
	}
	return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
}

static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
{
	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
				      vcpu->arch.virtual_tsc_mult,
				      vcpu->arch.virtual_tsc_shift);
	tsc += vcpu->arch.this_tsc_write;
	return tsc;
}

#ifdef CONFIG_X86_64
static inline int gtod_is_based_on_tsc(int mode)
{
	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
}
#endif

static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
	bool vcpus_matched;
	struct kvm_arch *ka = &vcpu->kvm->arch;
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;

	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
			 atomic_read(&vcpu->kvm->online_vcpus));

	/*
	 * Once the masterclock is enabled, always perform request in
	 * order to update it.
	 *
	 * In order to enable masterclock, the host clocksource must be TSC
	 * and the vcpus need to have matched TSCs.  When that happens,
	 * perform request to enable masterclock.
	 */
	if (ka->use_master_clock ||
	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);

	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
			    atomic_read(&vcpu->kvm->online_vcpus),
		            ka->use_master_clock, gtod->clock.vclock_mode);
#endif
}

/*
 * Multiply tsc by a fixed point number represented by ratio.
 *
 * The most significant 64-N bits (mult) of ratio represent the
 * integral part of the fixed point number; the remaining N bits
 * (frac) represent the fractional part, ie. ratio represents a fixed
 * point number (mult + frac * 2^(-N)).
 *
 * N equals to kvm_caps.tsc_scaling_ratio_frac_bits.
 */
static inline u64 __scale_tsc(u64 ratio, u64 tsc)
{
	return mul_u64_u64_shr(tsc, ratio, kvm_caps.tsc_scaling_ratio_frac_bits);
}

u64 kvm_scale_tsc(u64 tsc, u64 ratio)
{
	u64 _tsc = tsc;

	if (ratio != kvm_caps.default_tsc_scaling_ratio)
		_tsc = __scale_tsc(ratio, tsc);

	return _tsc;
}
EXPORT_SYMBOL_GPL(kvm_scale_tsc);

static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
{
	u64 tsc;

	tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio);

	return target_tsc - tsc;
}

u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
	return vcpu->arch.l1_tsc_offset +
		kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);

u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier)
{
	u64 nested_offset;

	if (l2_multiplier == kvm_caps.default_tsc_scaling_ratio)
		nested_offset = l1_offset;
	else
		nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier,
						kvm_caps.tsc_scaling_ratio_frac_bits);

	nested_offset += l2_offset;
	return nested_offset;
}
EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset);

u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier)
{
	if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio)
		return mul_u64_u64_shr(l1_multiplier, l2_multiplier,
				       kvm_caps.tsc_scaling_ratio_frac_bits);

	return l1_multiplier;
}
EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier);

static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset)
{
	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
				   vcpu->arch.l1_tsc_offset,
				   l1_offset);

	vcpu->arch.l1_tsc_offset = l1_offset;

	/*
	 * If we are here because L1 chose not to trap WRMSR to TSC then
	 * according to the spec this should set L1's TSC (as opposed to
	 * setting L1's offset for L2).
	 */
	if (is_guest_mode(vcpu))
		vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset(
			l1_offset,
			static_call(kvm_x86_get_l2_tsc_offset)(vcpu),
			static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu));
	else
		vcpu->arch.tsc_offset = l1_offset;

	static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset);
}

static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier)
{
	vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier;

	/* Userspace is changing the multiplier while L2 is active */
	if (is_guest_mode(vcpu))
		vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(
			l1_multiplier,
			static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu));
	else
		vcpu->arch.tsc_scaling_ratio = l1_multiplier;

	if (kvm_caps.has_tsc_control)
		static_call(kvm_x86_write_tsc_multiplier)(
			vcpu, vcpu->arch.tsc_scaling_ratio);
}

static inline bool kvm_check_tsc_unstable(void)
{
#ifdef CONFIG_X86_64
	/*
	 * TSC is marked unstable when we're running on Hyper-V,
	 * 'TSC page' clocksource is good.
	 */
	if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK)
		return false;
#endif
	return check_tsc_unstable();
}

/*
 * Infers attempts to synchronize the guest's tsc from host writes. Sets the
 * offset for the vcpu and tracks the TSC matching generation that the vcpu
 * participates in.
 */
static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
				  u64 ns, bool matched)
{
	struct kvm *kvm = vcpu->kvm;

	lockdep_assert_held(&kvm->arch.tsc_write_lock);

	/*
	 * We also track th most recent recorded KHZ, write and time to
	 * allow the matching interval to be extended at each write.
	 */
	kvm->arch.last_tsc_nsec = ns;
	kvm->arch.last_tsc_write = tsc;
	kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
	kvm->arch.last_tsc_offset = offset;

	vcpu->arch.last_guest_tsc = tsc;

	kvm_vcpu_write_tsc_offset(vcpu, offset);

	if (!matched) {
		/*
		 * We split periods of matched TSC writes into generations.
		 * For each generation, we track the original measured
		 * nanosecond time, offset, and write, so if TSCs are in
		 * sync, we can match exact offset, and if not, we can match
		 * exact software computation in compute_guest_tsc()
		 *
		 * These values are tracked in kvm->arch.cur_xxx variables.
		 */
		kvm->arch.cur_tsc_generation++;
		kvm->arch.cur_tsc_nsec = ns;
		kvm->arch.cur_tsc_write = tsc;
		kvm->arch.cur_tsc_offset = offset;
		kvm->arch.nr_vcpus_matched_tsc = 0;
	} else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) {
		kvm->arch.nr_vcpus_matched_tsc++;
	}

	/* Keep track of which generation this VCPU has synchronized to */
	vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;

	kvm_track_tsc_matching(vcpu);
}

static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u64 offset, ns, elapsed;
	unsigned long flags;
	bool matched = false;
	bool synchronizing = false;

	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
	offset = kvm_compute_l1_tsc_offset(vcpu, data);
	ns = get_kvmclock_base_ns();
	elapsed = ns - kvm->arch.last_tsc_nsec;

	if (vcpu->arch.virtual_tsc_khz) {
		if (data == 0) {
			/*
			 * detection of vcpu initialization -- need to sync
			 * with other vCPUs. This particularly helps to keep
			 * kvm_clock stable after CPU hotplug
			 */
			synchronizing = true;
		} else {
			u64 tsc_exp = kvm->arch.last_tsc_write +
						nsec_to_cycles(vcpu, elapsed);
			u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL;
			/*
			 * Special case: TSC write with a small delta (1 second)
			 * of virtual cycle time against real time is
			 * interpreted as an attempt to synchronize the CPU.
			 */
			synchronizing = data < tsc_exp + tsc_hz &&
					data + tsc_hz > tsc_exp;
		}
	}

	/*
	 * For a reliable TSC, we can match TSC offsets, and for an unstable
	 * TSC, we add elapsed time in this computation.  We could let the
	 * compensation code attempt to catch up if we fall behind, but
	 * it's better to try to match offsets from the beginning.
         */
	if (synchronizing &&
	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
		if (!kvm_check_tsc_unstable()) {
			offset = kvm->arch.cur_tsc_offset;
		} else {
			u64 delta = nsec_to_cycles(vcpu, elapsed);
			data += delta;
			offset = kvm_compute_l1_tsc_offset(vcpu, data);
		}
		matched = true;
	}

	__kvm_synchronize_tsc(vcpu, offset, data, ns, matched);
	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
}

static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
					   s64 adjustment)
{
	u64 tsc_offset = vcpu->arch.l1_tsc_offset;
	kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment);
}

static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
{
	if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio)
		WARN_ON(adjustment < 0);
	adjustment = kvm_scale_tsc((u64) adjustment,
				   vcpu->arch.l1_tsc_scaling_ratio);
	adjust_tsc_offset_guest(vcpu, adjustment);
}

#ifdef CONFIG_X86_64

static u64 read_tsc(void)
{
	u64 ret = (u64)rdtsc_ordered();
	u64 last = pvclock_gtod_data.clock.cycle_last;

	if (likely(ret >= last))
		return ret;

	/*
	 * GCC likes to generate cmov here, but this branch is extremely
	 * predictable (it's just a function of time and the likely is
	 * very likely) and there's a data dependence, so force GCC
	 * to generate a branch instead.  I don't barrier() because
	 * we don't actually need a barrier, and if this function
	 * ever gets inlined it will generate worse code.
	 */
	asm volatile ("");
	return last;
}

static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
			  int *mode)
{
	long v;
	u64 tsc_pg_val;

	switch (clock->vclock_mode) {
	case VDSO_CLOCKMODE_HVCLOCK:
		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
						  tsc_timestamp);
		if (tsc_pg_val != U64_MAX) {
			/* TSC page valid */
			*mode = VDSO_CLOCKMODE_HVCLOCK;
			v = (tsc_pg_val - clock->cycle_last) &
				clock->mask;
		} else {
			/* TSC page invalid */
			*mode = VDSO_CLOCKMODE_NONE;
		}
		break;
	case VDSO_CLOCKMODE_TSC:
		*mode = VDSO_CLOCKMODE_TSC;
		*tsc_timestamp = read_tsc();
		v = (*tsc_timestamp - clock->cycle_last) &
			clock->mask;
		break;
	default:
		*mode = VDSO_CLOCKMODE_NONE;
	}

	if (*mode == VDSO_CLOCKMODE_NONE)
		*tsc_timestamp = v = 0;

	return v * clock->mult;
}

static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
{
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
	unsigned long seq;
	int mode;
	u64 ns;

	do {
		seq = read_seqcount_begin(&gtod->seq);
		ns = gtod->raw_clock.base_cycles;
		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
		ns >>= gtod->raw_clock.shift;
		ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot));
	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
	*t = ns;

	return mode;
}

static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
{
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
	unsigned long seq;
	int mode;
	u64 ns;

	do {
		seq = read_seqcount_begin(&gtod->seq);
		ts->tv_sec = gtod->wall_time_sec;
		ns = gtod->clock.base_cycles;
		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
		ns >>= gtod->clock.shift;
	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));

	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
	ts->tv_nsec = ns;

	return mode;
}

/* returns true if host is using TSC based clocksource */
static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
{
	/* checked again under seqlock below */
	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
		return false;

	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
						      tsc_timestamp));
}

/* returns true if host is using TSC based clocksource */
static bool kvm_get_walltime_and_clockread(struct timespec64 *ts,
					   u64 *tsc_timestamp)
{
	/* checked again under seqlock below */
	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
		return false;

	return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
}
#endif

/*
 *
 * Assuming a stable TSC across physical CPUS, and a stable TSC
 * across virtual CPUs, the following condition is possible.
 * Each numbered line represents an event visible to both
 * CPUs at the next numbered event.
 *
 * "timespecX" represents host monotonic time. "tscX" represents
 * RDTSC value.
 *
 * 		VCPU0 on CPU0		|	VCPU1 on CPU1
 *
 * 1.  read timespec0,tsc0
 * 2.					| timespec1 = timespec0 + N
 * 					| tsc1 = tsc0 + M
 * 3. transition to guest		| transition to guest
 * 4. ret0 = timespec0 + (rdtsc - tsc0) |
 * 5.				        | ret1 = timespec1 + (rdtsc - tsc1)
 * 				        | ret1 = timespec0 + N + (rdtsc - (tsc0 + M))
 *
 * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity:
 *
 * 	- ret0 < ret1
 *	- timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M))
 *		...
 *	- 0 < N - M => M < N
 *
 * That is, when timespec0 != timespec1, M < N. Unfortunately that is not
 * always the case (the difference between two distinct xtime instances
 * might be smaller then the difference between corresponding TSC reads,
 * when updating guest vcpus pvclock areas).
 *
 * To avoid that problem, do not allow visibility of distinct
 * system_timestamp/tsc_timestamp values simultaneously: use a master
 * copy of host monotonic time values. Update that master copy
 * in lockstep.
 *
 * Rely on synchronization of host TSCs and guest TSCs for monotonicity.
 *
 */

static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
{
#ifdef CONFIG_X86_64
	struct kvm_arch *ka = &kvm->arch;
	int vclock_mode;
	bool host_tsc_clocksource, vcpus_matched;

	lockdep_assert_held(&kvm->arch.tsc_write_lock);
	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
			atomic_read(&kvm->online_vcpus));

	/*
	 * If the host uses TSC clock, then passthrough TSC as stable
	 * to the guest.
	 */
	host_tsc_clocksource = kvm_get_time_and_clockread(
					&ka->master_kernel_ns,
					&ka->master_cycle_now);

	ka->use_master_clock = host_tsc_clocksource && vcpus_matched
				&& !ka->backwards_tsc_observed
				&& !ka->boot_vcpu_runs_old_kvmclock;

	if (ka->use_master_clock)
		atomic_set(&kvm_guest_has_master_clock, 1);

	vclock_mode = pvclock_gtod_data.clock.vclock_mode;
	trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode,
					vcpus_matched);
#endif
}

static void kvm_make_mclock_inprogress_request(struct kvm *kvm)
{
	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
}

static void __kvm_start_pvclock_update(struct kvm *kvm)
{
	raw_spin_lock_irq(&kvm->arch.tsc_write_lock);
	write_seqcount_begin(&kvm->arch.pvclock_sc);
}

static void kvm_start_pvclock_update(struct kvm *kvm)
{
	kvm_make_mclock_inprogress_request(kvm);

	/* no guest entries from this point */
	__kvm_start_pvclock_update(kvm);
}

static void kvm_end_pvclock_update(struct kvm *kvm)
{
	struct kvm_arch *ka = &kvm->arch;
	struct kvm_vcpu *vcpu;
	unsigned long i;

	write_seqcount_end(&ka->pvclock_sc);
	raw_spin_unlock_irq(&ka->tsc_write_lock);
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

	/* guest entries allowed */
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
}

static void kvm_update_masterclock(struct kvm *kvm)
{
	kvm_hv_request_tsc_page_update(kvm);
	kvm_start_pvclock_update(kvm);
	pvclock_update_vm_gtod_copy(kvm);
	kvm_end_pvclock_update(kvm);
}

/* Called within read_seqcount_begin/retry for kvm->pvclock_sc.  */
static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
{
	struct kvm_arch *ka = &kvm->arch;
	struct pvclock_vcpu_time_info hv_clock;

	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
	get_cpu();

	data->flags = 0;
	if (ka->use_master_clock && __this_cpu_read(cpu_tsc_khz)) {
#ifdef CONFIG_X86_64
		struct timespec64 ts;

		if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) {
			data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec;
			data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC;
		} else
#endif
		data->host_tsc = rdtsc();

		data->flags |= KVM_CLOCK_TSC_STABLE;
		hv_clock.tsc_timestamp = ka->master_cycle_now;
		hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
				   &hv_clock.tsc_shift,
				   &hv_clock.tsc_to_system_mul);
		data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc);
	} else {
		data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset;
	}

	put_cpu();
}

static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
{
	struct kvm_arch *ka = &kvm->arch;
	unsigned seq;

	do {
		seq = read_seqcount_begin(&ka->pvclock_sc);
		__get_kvmclock(kvm, data);
	} while (read_seqcount_retry(&ka->pvclock_sc, seq));
}

u64 get_kvmclock_ns(struct kvm *kvm)
{
	struct kvm_clock_data data;

	get_kvmclock(kvm, &data);
	return data.clock;
}

static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
				    struct gfn_to_pfn_cache *gpc,
				    unsigned int offset)
{
	struct kvm_vcpu_arch *vcpu = &v->arch;
	struct pvclock_vcpu_time_info *guest_hv_clock;
	unsigned long flags;

	read_lock_irqsave(&gpc->lock, flags);
	while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa,
					   offset + sizeof(*guest_hv_clock))) {
		read_unlock_irqrestore(&gpc->lock, flags);

		if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa,
						 offset + sizeof(*guest_hv_clock)))
			return;

		read_lock_irqsave(&gpc->lock, flags);
	}

	guest_hv_clock = (void *)(gpc->khva + offset);

	/*
	 * This VCPU is paused, but it's legal for a guest to read another
	 * VCPU's kvmclock, so we really have to follow the specification where
	 * it says that version is odd if data is being modified, and even after
	 * it is consistent.
	 */

	guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1;
	smp_wmb();

	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
	vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);

	if (vcpu->pvclock_set_guest_stopped_request) {
		vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
		vcpu->pvclock_set_guest_stopped_request = false;
	}

	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
	smp_wmb();

	guest_hv_clock->version = ++vcpu->hv_clock.version;

	mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
	read_unlock_irqrestore(&gpc->lock, flags);

	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
}

static int kvm_guest_time_update(struct kvm_vcpu *v)
{
	unsigned long flags, tgt_tsc_khz;
	unsigned seq;
	struct kvm_vcpu_arch *vcpu = &v->arch;
	struct kvm_arch *ka = &v->kvm->arch;
	s64 kernel_ns;
	u64 tsc_timestamp, host_tsc;
	u8 pvclock_flags;
	bool use_master_clock;

	kernel_ns = 0;
	host_tsc = 0;

	/*
	 * If the host uses TSC clock, then passthrough TSC as stable
	 * to the guest.
	 */
	do {
		seq = read_seqcount_begin(&ka->pvclock_sc);
		use_master_clock = ka->use_master_clock;
		if (use_master_clock) {
			host_tsc = ka->master_cycle_now;
			kernel_ns = ka->master_kernel_ns;
		}
	} while (read_seqcount_retry(&ka->pvclock_sc, seq));

	/* Keep irq disabled to prevent changes to the clock */
	local_irq_save(flags);
	tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
	if (unlikely(tgt_tsc_khz == 0)) {
		local_irq_restore(flags);
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
		return 1;
	}
	if (!use_master_clock) {
		host_tsc = rdtsc();
		kernel_ns = get_kvmclock_base_ns();
	}

	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);

	/*
	 * We may have to catch up the TSC to match elapsed wall clock
	 * time for two reasons, even if kvmclock is used.
	 *   1) CPU could have been running below the maximum TSC rate
	 *   2) Broken TSC compensation resets the base at each VCPU
	 *      entry to avoid unknown leaps of TSC even when running
	 *      again on the same CPU.  This may cause apparent elapsed
	 *      time to disappear, and the guest to stand still or run
	 *	very slowly.
	 */
	if (vcpu->tsc_catchup) {
		u64 tsc = compute_guest_tsc(v, kernel_ns);
		if (tsc > tsc_timestamp) {
			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
			tsc_timestamp = tsc;
		}
	}

	local_irq_restore(flags);

	/* With all the info we got, fill in the values */

	if (kvm_caps.has_tsc_control)
		tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
					    v->arch.l1_tsc_scaling_ratio);

	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
				   &vcpu->hv_clock.tsc_shift,
				   &vcpu->hv_clock.tsc_to_system_mul);
		vcpu->hw_tsc_khz = tgt_tsc_khz;
	}

	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	vcpu->last_guest_tsc = tsc_timestamp;

	/* If the host uses TSC clocksource, then it is stable */
	pvclock_flags = 0;
	if (use_master_clock)
		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;

	vcpu->hv_clock.flags = pvclock_flags;

	if (vcpu->pv_time.active)
		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
	if (vcpu->xen.vcpu_info_cache.active)
		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
					offsetof(struct compat_vcpu_info, time));
	if (vcpu->xen.vcpu_time_info_cache.active)
		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
	return 0;
}

/*
 * kvmclock updates which are isolated to a given vcpu, such as
 * vcpu->cpu migration, should not allow system_timestamp from
 * the rest of the vcpus to remain static. Otherwise ntp frequency
 * correction applies to one vcpu's system_timestamp but not
 * the others.
 *
 * So in those cases, request a kvmclock update for all vcpus.
 * We need to rate-limit these requests though, as they can
 * considerably slow guests that have a large number of vcpus.
 * The time for a remote vcpu to update its kvmclock is bound
 * by the delay we use to rate-limit the updates.
 */

#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100)

static void kvmclock_update_fn(struct work_struct *work)
{
	unsigned long i;
	struct delayed_work *dwork = to_delayed_work(work);
	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
					   kvmclock_update_work);
	struct kvm *kvm = container_of(ka, struct kvm, arch);
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
		kvm_vcpu_kick(vcpu);
	}
}

static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
{
	struct kvm *kvm = v->kvm;

	kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
					KVMCLOCK_UPDATE_DELAY);
}

#define KVMCLOCK_SYNC_PERIOD (300 * HZ)

static void kvmclock_sync_fn(struct work_struct *work)
{
	struct delayed_work *dwork = to_delayed_work(work);
	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
					   kvmclock_sync_work);
	struct kvm *kvm = container_of(ka, struct kvm, arch);

	if (!kvmclock_periodic_sync)
		return;

	schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
					KVMCLOCK_SYNC_PERIOD);
}

/* These helpers are safe iff @msr is known to be an MCx bank MSR. */
static bool is_mci_control_msr(u32 msr)
{
	return (msr & 3) == 0;
}
static bool is_mci_status_msr(u32 msr)
{
	return (msr & 3) == 1;
}

/*
 * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP.
 */
static bool can_set_mci_status(struct kvm_vcpu *vcpu)
{
	/* McStatusWrEn enabled? */
	if (guest_cpuid_is_amd_or_hygon(vcpu))
		return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));

	return false;
}

static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;
	u32 msr = msr_info->index;
	u64 data = msr_info->data;
	u32 offset, last_msr;

	switch (msr) {
	case MSR_IA32_MCG_STATUS:
		vcpu->arch.mcg_status = data;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P) &&
		    (data || !msr_info->host_initiated))
			return 1;
		if (data != 0 && data != ~(u64)0)
			return 1;
		vcpu->arch.mcg_ctl = data;
		break;
	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
		last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1;
		if (msr > last_msr)
			return 1;

		if (!(mcg_cap & MCG_CMCI_P) && (data || !msr_info->host_initiated))
			return 1;
		/* An attempt to write a 1 to a reserved bit raises #GP */
		if (data & ~(MCI_CTL2_CMCI_EN | MCI_CTL2_CMCI_THRESHOLD_MASK))
			return 1;
		offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2,
					    last_msr + 1 - MSR_IA32_MC0_CTL2);
		vcpu->arch.mci_ctl2_banks[offset] = data;
		break;
	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
		last_msr = MSR_IA32_MCx_CTL(bank_num) - 1;
		if (msr > last_msr)
			return 1;

		/*
		 * Only 0 or all 1s can be written to IA32_MCi_CTL, all other
		 * values are architecturally undefined.  But, some Linux
		 * kernels clear bit 10 in bank 4 to workaround a BIOS/GART TLB
		 * issue on AMD K8s, allow bit 10 to be clear when setting all
		 * other bits in order to avoid an uncaught #GP in the guest.
		 *
		 * UNIXWARE clears bit 0 of MC1_CTL to ignore correctable,
		 * single-bit ECC data errors.
		 */
		if (is_mci_control_msr(msr) &&
		    data != 0 && (data | (1 << 10) | 1) != ~(u64)0)
			return 1;

		/*
		 * All CPUs allow writing 0 to MCi_STATUS MSRs to clear the MSR.
		 * AMD-based CPUs allow non-zero values, but if and only if
		 * HWCR[McStatusWrEn] is set.
		 */
		if (!msr_info->host_initiated && is_mci_status_msr(msr) &&
		    data != 0 && !can_set_mci_status(vcpu))
			return 1;

		offset = array_index_nospec(msr - MSR_IA32_MC0_CTL,
					    last_msr + 1 - MSR_IA32_MC0_CTL);
		vcpu->arch.mce_banks[offset] = data;
		break;
	default:
		return 1;
	}
	return 0;
}

static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu)
{
	u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT;

	return (vcpu->arch.apf.msr_en_val & mask) == mask;
}

static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
	gpa_t gpa = data & ~0x3f;

	/* Bits 4:5 are reserved, Should be zero */
	if (data & 0x30)
		return 1;

	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) &&
	    (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT))
		return 1;

	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) &&
	    (data & KVM_ASYNC_PF_DELIVERY_AS_INT))
		return 1;

	if (!lapic_in_kernel(vcpu))
		return data ? 1 : 0;

	vcpu->arch.apf.msr_en_val = data;

	if (!kvm_pv_async_pf_enabled(vcpu)) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_async_pf_hash_reset(vcpu);
		return 0;
	}

	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
					sizeof(u64)))
		return 1;

	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;

	kvm_async_pf_wakeup_all(vcpu);

	return 0;
}

static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
{
	/* Bits 8-63 are reserved */
	if (data >> 8)
		return 1;

	if (!lapic_in_kernel(vcpu))
		return 1;

	vcpu->arch.apf.msr_int_val = data;

	vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK;

	return 0;
}

static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
	kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
	vcpu->arch.time = 0;
}

static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.tlb_flush;
	static_call(kvm_x86_flush_tlb_all)(vcpu);

	/* Flushing all ASIDs flushes the current ASID... */
	kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}

static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.tlb_flush;

	if (!tdp_enabled) {
		/*
		 * A TLB flush on behalf of the guest is equivalent to
		 * INVPCID(all), toggling CR4.PGE, etc., which requires
		 * a forced sync of the shadow page tables.  Ensure all the
		 * roots are synced and the guest TLB in hardware is clean.
		 */
		kvm_mmu_sync_roots(vcpu);
		kvm_mmu_sync_prev_roots(vcpu);
	}

	static_call(kvm_x86_flush_tlb_guest)(vcpu);

	/*
	 * Flushing all "guest" TLB is always a superset of Hyper-V's fine
	 * grained flushing.
	 */
	kvm_hv_vcpu_purge_flush_tlb(vcpu);
}


static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.tlb_flush;
	static_call(kvm_x86_flush_tlb_current)(vcpu);
}

/*
 * Service "local" TLB flush requests, which are specific to the current MMU
 * context.  In addition to the generic event handling in vcpu_enter_guest(),
 * TLB flushes that are targeted at an MMU context also need to be serviced
 * prior before nested VM-Enter/VM-Exit.
 */
void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
{
	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
		kvm_vcpu_flush_tlb_current(vcpu);

	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
		kvm_vcpu_flush_tlb_guest(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);

static void record_steal_time(struct kvm_vcpu *vcpu)
{
	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
	struct kvm_steal_time __user *st;
	struct kvm_memslots *slots;
	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
	u64 steal;
	u32 version;

	if (kvm_xen_msr_enabled(vcpu->kvm)) {
		kvm_xen_runstate_set_running(vcpu);
		return;
	}

	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
		return;

	if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm))
		return;

	slots = kvm_memslots(vcpu->kvm);

	if (unlikely(slots->generation != ghc->generation ||
		     gpa != ghc->gpa ||
		     kvm_is_error_hva(ghc->hva) || !ghc->memslot)) {
		/* We rely on the fact that it fits in a single page. */
		BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS);

		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) ||
		    kvm_is_error_hva(ghc->hva) || !ghc->memslot)
			return;
	}

	st = (struct kvm_steal_time __user *)ghc->hva;
	/*
	 * Doing a TLB flush here, on the guest's behalf, can avoid
	 * expensive IPIs.
	 */
	if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) {
		u8 st_preempted = 0;
		int err = -EFAULT;

		if (!user_access_begin(st, sizeof(*st)))
			return;

		asm volatile("1: xchgb %0, %2\n"
			     "xor %1, %1\n"
			     "2:\n"
			     _ASM_EXTABLE_UA(1b, 2b)
			     : "+q" (st_preempted),
			       "+&r" (err),
			       "+m" (st->preempted));
		if (err)
			goto out;

		user_access_end();

		vcpu->arch.st.preempted = 0;

		trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
				       st_preempted & KVM_VCPU_FLUSH_TLB);
		if (st_preempted & KVM_VCPU_FLUSH_TLB)
			kvm_vcpu_flush_tlb_guest(vcpu);

		if (!user_access_begin(st, sizeof(*st)))
			goto dirty;
	} else {
		if (!user_access_begin(st, sizeof(*st)))
			return;

		unsafe_put_user(0, &st->preempted, out);
		vcpu->arch.st.preempted = 0;
	}

	unsafe_get_user(version, &st->version, out);
	if (version & 1)
		version += 1;  /* first time write, random junk */

	version += 1;
	unsafe_put_user(version, &st->version, out);

	smp_wmb();

	unsafe_get_user(steal, &st->steal, out);
	steal += current->sched_info.run_delay -
		vcpu->arch.st.last_steal;
	vcpu->arch.st.last_steal = current->sched_info.run_delay;
	unsafe_put_user(steal, &st->steal, out);

	version += 1;
	unsafe_put_user(version, &st->version, out);

 out:
	user_access_end();
 dirty:
	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
}

int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	bool pr = false;
	u32 msr = msr_info->index;
	u64 data = msr_info->data;

	if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr)
		return kvm_xen_write_hypercall_page(vcpu, data);

	switch (msr) {
	case MSR_AMD64_NB_CFG:
	case MSR_IA32_UCODE_WRITE:
	case MSR_VM_HSAVE_PA:
	case MSR_AMD64_PATCH_LOADER:
	case MSR_AMD64_BU_CFG2:
	case MSR_AMD64_DC_CFG:
	case MSR_F15H_EX_CFG:
		break;

	case MSR_IA32_UCODE_REV:
		if (msr_info->host_initiated)
			vcpu->arch.microcode_version = data;
		break;
	case MSR_IA32_ARCH_CAPABILITIES:
		if (!msr_info->host_initiated)
			return 1;
		vcpu->arch.arch_capabilities = data;
		break;
	case MSR_IA32_PERF_CAPABILITIES:
		if (!msr_info->host_initiated)
			return 1;
		if (data & ~kvm_caps.supported_perf_cap)
			return 1;

		vcpu->arch.perf_capabilities = data;
		kvm_pmu_refresh(vcpu);
		return 0;
	case MSR_EFER:
		return set_efer(vcpu, msr_info);
	case MSR_K7_HWCR:
		data &= ~(u64)0x40;	/* ignore flush filter disable */
		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
		data &= ~(u64)0x8;	/* ignore TLB cache disable */

		/* Handle McStatusWrEn */
		if (data == BIT_ULL(18)) {
			vcpu->arch.msr_hwcr = data;
		} else if (data != 0) {
			vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
				    data);
			return 1;
		}
		break;
	case MSR_FAM10H_MMIO_CONF_BASE:
		if (data != 0) {
			vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: "
				    "0x%llx\n", data);
			return 1;
		}
		break;
	case 0x200 ... MSR_IA32_MC0_CTL2 - 1:
	case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff:
		return kvm_mtrr_set_msr(vcpu, msr, data);
	case MSR_IA32_APICBASE:
		return kvm_set_apic_base(vcpu, msr_info);
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
		return kvm_x2apic_msr_write(vcpu, msr, data);
	case MSR_IA32_TSC_DEADLINE:
		kvm_set_lapic_tscdeadline_msr(vcpu, data);
		break;
	case MSR_IA32_TSC_ADJUST:
		if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) {
			if (!msr_info->host_initiated) {
				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
				adjust_tsc_offset_guest(vcpu, adj);
				/* Before back to guest, tsc_timestamp must be adjusted
				 * as well, otherwise guest's percpu pvclock time could jump.
				 */
				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
			}
			vcpu->arch.ia32_tsc_adjust_msr = data;
		}
		break;
	case MSR_IA32_MISC_ENABLE: {
		u64 old_val = vcpu->arch.ia32_misc_enable_msr;

		if (!msr_info->host_initiated) {
			/* RO bits */
			if ((old_val ^ data) & MSR_IA32_MISC_ENABLE_PMU_RO_MASK)
				return 1;

			/* R bits, i.e. writes are ignored, but don't fault. */
			data = data & ~MSR_IA32_MISC_ENABLE_EMON;
			data |= old_val & MSR_IA32_MISC_ENABLE_EMON;
		}

		if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) &&
		    ((old_val ^ data)  & MSR_IA32_MISC_ENABLE_MWAIT)) {
			if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3))
				return 1;
			vcpu->arch.ia32_misc_enable_msr = data;
			kvm_update_cpuid_runtime(vcpu);
		} else {
			vcpu->arch.ia32_misc_enable_msr = data;
		}
		break;
	}
	case MSR_IA32_SMBASE:
		if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
			return 1;
		vcpu->arch.smbase = data;
		break;
	case MSR_IA32_POWER_CTL:
		vcpu->arch.msr_ia32_power_ctl = data;
		break;
	case MSR_IA32_TSC:
		if (msr_info->host_initiated) {
			kvm_synchronize_tsc(vcpu, data);
		} else {
			u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset;
			adjust_tsc_offset_guest(vcpu, adj);
			vcpu->arch.ia32_tsc_adjust_msr += adj;
		}
		break;
	case MSR_IA32_XSS:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
			return 1;
		/*
		 * KVM supports exposing PT to the guest, but does not support
		 * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than
		 * XSAVES/XRSTORS to save/restore PT MSRs.
		 */
		if (data & ~kvm_caps.supported_xss)
			return 1;
		vcpu->arch.ia32_xss = data;
		kvm_update_cpuid_runtime(vcpu);
		break;
	case MSR_SMI_COUNT:
		if (!msr_info->host_initiated)
			return 1;
		vcpu->arch.smi_count = data;
		break;
	case MSR_KVM_WALL_CLOCK_NEW:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
			return 1;

		vcpu->kvm->arch.wall_clock = data;
		kvm_write_wall_clock(vcpu->kvm, data, 0);
		break;
	case MSR_KVM_WALL_CLOCK:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
			return 1;

		vcpu->kvm->arch.wall_clock = data;
		kvm_write_wall_clock(vcpu->kvm, data, 0);
		break;
	case MSR_KVM_SYSTEM_TIME_NEW:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
			return 1;

		kvm_write_system_time(vcpu, data, false, msr_info->host_initiated);
		break;
	case MSR_KVM_SYSTEM_TIME:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
			return 1;

		kvm_write_system_time(vcpu, data, true,  msr_info->host_initiated);
		break;
	case MSR_KVM_ASYNC_PF_EN:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
			return 1;

		if (kvm_pv_enable_async_pf(vcpu, data))
			return 1;
		break;
	case MSR_KVM_ASYNC_PF_INT:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
			return 1;

		if (kvm_pv_enable_async_pf_int(vcpu, data))
			return 1;
		break;
	case MSR_KVM_ASYNC_PF_ACK:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
			return 1;
		if (data & 0x1) {
			vcpu->arch.apf.pageready_pending = false;
			kvm_check_async_pf_completion(vcpu);
		}
		break;
	case MSR_KVM_STEAL_TIME:
		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
			return 1;

		if (unlikely(!sched_info_on()))
			return 1;

		if (data & KVM_STEAL_RESERVED_MASK)
			return 1;

		vcpu->arch.st.msr_val = data;

		if (!(data & KVM_MSR_ENABLED))
			break;

		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);

		break;
	case MSR_KVM_PV_EOI_EN:
		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
			return 1;

		if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8)))
			return 1;
		break;

	case MSR_KVM_POLL_CONTROL:
		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
			return 1;

		/* only enable bit supported */
		if (data & (-1ULL << 1))
			return 1;

		vcpu->arch.msr_kvm_poll_control = data;
		break;

	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
		return set_msr_mce(vcpu, msr_info);

	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
	case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
		pr = true;
		fallthrough;
	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
	case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
		if (kvm_pmu_is_valid_msr(vcpu, msr))
			return kvm_pmu_set_msr(vcpu, msr_info);

		if (pr || data != 0)
			vcpu_unimpl(vcpu, "disabled perfctr wrmsr: "
				    "0x%x data 0x%llx\n", msr, data);
		break;
	case MSR_K7_CLK_CTL:
		/*
		 * Ignore all writes to this no longer documented MSR.
		 * Writes are only relevant for old K7 processors,
		 * all pre-dating SVM, but a recommended workaround from
		 * AMD for these chips. It is possible to specify the
		 * affected processor models on the command line, hence
		 * the need to ignore the workaround.
		 */
		break;
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
	case HV_X64_MSR_SYNDBG_OPTIONS:
	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
	case HV_X64_MSR_CRASH_CTL:
	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
	case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
	case HV_X64_MSR_TSC_EMULATION_CONTROL:
	case HV_X64_MSR_TSC_EMULATION_STATUS:
		return kvm_hv_set_msr_common(vcpu, msr, data,
					     msr_info->host_initiated);
	case MSR_IA32_BBL_CR_CTL3:
		/* Drop writes to this legacy MSR -- see rdmsr
		 * counterpart for further detail.
		 */
		if (report_ignored_msrs)
			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
				msr, data);
		break;
	case MSR_AMD64_OSVW_ID_LENGTH:
		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
			return 1;
		vcpu->arch.osvw.length = data;
		break;
	case MSR_AMD64_OSVW_STATUS:
		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
			return 1;
		vcpu->arch.osvw.status = data;
		break;
	case MSR_PLATFORM_INFO:
		if (!msr_info->host_initiated ||
		    (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
		     cpuid_fault_enabled(vcpu)))
			return 1;
		vcpu->arch.msr_platform_info = data;
		break;
	case MSR_MISC_FEATURES_ENABLES:
		if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT ||
		    (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT &&
		     !supports_cpuid_fault(vcpu)))
			return 1;
		vcpu->arch.msr_misc_features_enables = data;
		break;
#ifdef CONFIG_X86_64
	case MSR_IA32_XFD:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
			return 1;

		if (data & ~kvm_guest_supported_xfd(vcpu))
			return 1;

		fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data);
		break;
	case MSR_IA32_XFD_ERR:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
			return 1;

		if (data & ~kvm_guest_supported_xfd(vcpu))
			return 1;

		vcpu->arch.guest_fpu.xfd_err = data;
		break;
#endif
	case MSR_IA32_PEBS_ENABLE:
	case MSR_IA32_DS_AREA:
	case MSR_PEBS_DATA_CFG:
	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
		if (kvm_pmu_is_valid_msr(vcpu, msr))
			return kvm_pmu_set_msr(vcpu, msr_info);
		/*
		 * Userspace is allowed to write '0' to MSRs that KVM reports
		 * as to-be-saved, even if an MSRs isn't fully supported.
		 */
		return !msr_info->host_initiated || data;
	default:
		if (kvm_pmu_is_valid_msr(vcpu, msr))
			return kvm_pmu_set_msr(vcpu, msr_info);
		return KVM_MSR_RET_INVALID;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);

static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
{
	u64 data;
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;
	u32 offset, last_msr;

	switch (msr) {
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
		data = 0;
		break;
	case MSR_IA32_MCG_CAP:
		data = vcpu->arch.mcg_cap;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P) && !host)
			return 1;
		data = vcpu->arch.mcg_ctl;
		break;
	case MSR_IA32_MCG_STATUS:
		data = vcpu->arch.mcg_status;
		break;
	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
		last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1;
		if (msr > last_msr)
			return 1;

		if (!(mcg_cap & MCG_CMCI_P) && !host)
			return 1;
		offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2,
					    last_msr + 1 - MSR_IA32_MC0_CTL2);
		data = vcpu->arch.mci_ctl2_banks[offset];
		break;
	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
		last_msr = MSR_IA32_MCx_CTL(bank_num) - 1;
		if (msr > last_msr)
			return 1;

		offset = array_index_nospec(msr - MSR_IA32_MC0_CTL,
					    last_msr + 1 - MSR_IA32_MC0_CTL);
		data = vcpu->arch.mce_banks[offset];
		break;
	default:
		return 1;
	}
	*pdata = data;
	return 0;
}

int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	switch (msr_info->index) {
	case MSR_IA32_PLATFORM_ID:
	case MSR_IA32_EBL_CR_POWERON:
	case MSR_IA32_LASTBRANCHFROMIP:
	case MSR_IA32_LASTBRANCHTOIP:
	case MSR_IA32_LASTINTFROMIP:
	case MSR_IA32_LASTINTTOIP:
	case MSR_AMD64_SYSCFG:
	case MSR_K8_TSEG_ADDR:
	case MSR_K8_TSEG_MASK:
	case MSR_VM_HSAVE_PA:
	case MSR_K8_INT_PENDING_MSG:
	case MSR_AMD64_NB_CFG:
	case MSR_FAM10H_MMIO_CONF_BASE:
	case MSR_AMD64_BU_CFG2:
	case MSR_IA32_PERF_CTL:
	case MSR_AMD64_DC_CFG:
	case MSR_F15H_EX_CFG:
	/*
	 * Intel Sandy Bridge CPUs must support the RAPL (running average power
	 * limit) MSRs. Just return 0, as we do not want to expose the host
	 * data here. Do not conditionalize this on CPUID, as KVM does not do
	 * so for existing CPU-specific MSRs.
	 */
	case MSR_RAPL_POWER_UNIT:
	case MSR_PP0_ENERGY_STATUS:	/* Power plane 0 (core) */
	case MSR_PP1_ENERGY_STATUS:	/* Power plane 1 (graphics uncore) */
	case MSR_PKG_ENERGY_STATUS:	/* Total package */
	case MSR_DRAM_ENERGY_STATUS:	/* DRAM controller */
		msr_info->data = 0;
		break;
	case MSR_IA32_PEBS_ENABLE:
	case MSR_IA32_DS_AREA:
	case MSR_PEBS_DATA_CFG:
	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
			return kvm_pmu_get_msr(vcpu, msr_info);
		/*
		 * Userspace is allowed to read MSRs that KVM reports as
		 * to-be-saved, even if an MSR isn't fully supported.
		 */
		if (!msr_info->host_initiated)
			return 1;
		msr_info->data = 0;
		break;
	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
	case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
	case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
			return kvm_pmu_get_msr(vcpu, msr_info);
		msr_info->data = 0;
		break;
	case MSR_IA32_UCODE_REV:
		msr_info->data = vcpu->arch.microcode_version;
		break;
	case MSR_IA32_ARCH_CAPABILITIES:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
			return 1;
		msr_info->data = vcpu->arch.arch_capabilities;
		break;
	case MSR_IA32_PERF_CAPABILITIES:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
			return 1;
		msr_info->data = vcpu->arch.perf_capabilities;
		break;
	case MSR_IA32_POWER_CTL:
		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
		break;
	case MSR_IA32_TSC: {
		/*
		 * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
		 * even when not intercepted. AMD manual doesn't explicitly
		 * state this but appears to behave the same.
		 *
		 * On userspace reads and writes, however, we unconditionally
		 * return L1's TSC value to ensure backwards-compatible
		 * behavior for migration.
		 */
		u64 offset, ratio;

		if (msr_info->host_initiated) {
			offset = vcpu->arch.l1_tsc_offset;
			ratio = vcpu->arch.l1_tsc_scaling_ratio;
		} else {
			offset = vcpu->arch.tsc_offset;
			ratio = vcpu->arch.tsc_scaling_ratio;
		}

		msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset;
		break;
	}
	case MSR_MTRRcap:
	case 0x200 ... MSR_IA32_MC0_CTL2 - 1:
	case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff:
		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
	case 0xcd: /* fsb frequency */
		msr_info->data = 3;
		break;
		/*
		 * MSR_EBC_FREQUENCY_ID
		 * Conservative value valid for even the basic CPU models.
		 * Models 0,1: 000 in bits 23:21 indicating a bus speed of
		 * 100MHz, model 2 000 in bits 18:16 indicating 100MHz,
		 * and 266MHz for model 3, or 4. Set Core Clock
		 * Frequency to System Bus Frequency Ratio to 1 (bits
		 * 31:24) even though these are only valid for CPU
		 * models > 2, however guests may end up dividing or
		 * multiplying by zero otherwise.
		 */
	case MSR_EBC_FREQUENCY_ID:
		msr_info->data = 1 << 24;
		break;
	case MSR_IA32_APICBASE:
		msr_info->data = kvm_get_apic_base(vcpu);
		break;
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
	case MSR_IA32_TSC_DEADLINE:
		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
		break;
	case MSR_IA32_TSC_ADJUST:
		msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr;
		break;
	case MSR_IA32_MISC_ENABLE:
		msr_info->data = vcpu->arch.ia32_misc_enable_msr;
		break;
	case MSR_IA32_SMBASE:
		if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
			return 1;
		msr_info->data = vcpu->arch.smbase;
		break;
	case MSR_SMI_COUNT:
		msr_info->data = vcpu->arch.smi_count;
		break;
	case MSR_IA32_PERF_STATUS:
		/* TSC increment by tick */
		msr_info->data = 1000ULL;
		/* CPU multiplier */
		msr_info->data |= (((uint64_t)4ULL) << 40);
		break;
	case MSR_EFER:
		msr_info->data = vcpu->arch.efer;
		break;
	case MSR_KVM_WALL_CLOCK:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
			return 1;

		msr_info->data = vcpu->kvm->arch.wall_clock;
		break;
	case MSR_KVM_WALL_CLOCK_NEW:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
			return 1;

		msr_info->data = vcpu->kvm->arch.wall_clock;
		break;
	case MSR_KVM_SYSTEM_TIME:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
			return 1;

		msr_info->data = vcpu->arch.time;
		break;
	case MSR_KVM_SYSTEM_TIME_NEW:
		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
			return 1;

		msr_info->data = vcpu->arch.time;
		break;
	case MSR_KVM_ASYNC_PF_EN:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
			return 1;

		msr_info->data = vcpu->arch.apf.msr_en_val;
		break;
	case MSR_KVM_ASYNC_PF_INT:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
			return 1;

		msr_info->data = vcpu->arch.apf.msr_int_val;
		break;
	case MSR_KVM_ASYNC_PF_ACK:
		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
			return 1;

		msr_info->data = 0;
		break;
	case MSR_KVM_STEAL_TIME:
		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
			return 1;

		msr_info->data = vcpu->arch.st.msr_val;
		break;
	case MSR_KVM_PV_EOI_EN:
		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
			return 1;

		msr_info->data = vcpu->arch.pv_eoi.msr_val;
		break;
	case MSR_KVM_POLL_CONTROL:
		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
			return 1;

		msr_info->data = vcpu->arch.msr_kvm_poll_control;
		break;
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
	case MSR_IA32_MCG_CAP:
	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
		return get_msr_mce(vcpu, msr_info->index, &msr_info->data,
				   msr_info->host_initiated);
	case MSR_IA32_XSS:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
			return 1;
		msr_info->data = vcpu->arch.ia32_xss;
		break;
	case MSR_K7_CLK_CTL:
		/*
		 * Provide expected ramp-up count for K7. All other
		 * are set to zero, indicating minimum divisors for
		 * every field.
		 *
		 * This prevents guest kernels on AMD host with CPU
		 * type 6, model 8 and higher from exploding due to
		 * the rdmsr failing.
		 */
		msr_info->data = 0x20000000;
		break;
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
	case HV_X64_MSR_SYNDBG_OPTIONS:
	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
	case HV_X64_MSR_CRASH_CTL:
	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
	case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
	case HV_X64_MSR_TSC_EMULATION_CONTROL:
	case HV_X64_MSR_TSC_EMULATION_STATUS:
		return kvm_hv_get_msr_common(vcpu,
					     msr_info->index, &msr_info->data,
					     msr_info->host_initiated);
	case MSR_IA32_BBL_CR_CTL3:
		/* This legacy MSR exists but isn't fully documented in current
		 * silicon.  It is however accessed by winxp in very narrow
		 * scenarios where it sets bit #19, itself documented as
		 * a "reserved" bit.  Best effort attempt to source coherent
		 * read data here should the balance of the register be
		 * interpreted by the guest:
		 *
		 * L2 cache control register 3: 64GB range, 256KB size,
		 * enabled, latency 0x1, configured
		 */
		msr_info->data = 0xbe702111;
		break;
	case MSR_AMD64_OSVW_ID_LENGTH:
		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
			return 1;
		msr_info->data = vcpu->arch.osvw.length;
		break;
	case MSR_AMD64_OSVW_STATUS:
		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
			return 1;
		msr_info->data = vcpu->arch.osvw.status;
		break;
	case MSR_PLATFORM_INFO:
		if (!msr_info->host_initiated &&
		    !vcpu->kvm->arch.guest_can_read_msr_platform_info)
			return 1;
		msr_info->data = vcpu->arch.msr_platform_info;
		break;
	case MSR_MISC_FEATURES_ENABLES:
		msr_info->data = vcpu->arch.msr_misc_features_enables;
		break;
	case MSR_K7_HWCR:
		msr_info->data = vcpu->arch.msr_hwcr;
		break;
#ifdef CONFIG_X86_64
	case MSR_IA32_XFD:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
			return 1;

		msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd;
		break;
	case MSR_IA32_XFD_ERR:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
			return 1;

		msr_info->data = vcpu->arch.guest_fpu.xfd_err;
		break;
#endif
	default:
		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
			return kvm_pmu_get_msr(vcpu, msr_info);
		return KVM_MSR_RET_INVALID;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);

/*
 * Read or write a bunch of msrs. All parameters are kernel addresses.
 *
 * @return number of msrs set successfully.
 */
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
		    struct kvm_msr_entry *entries,
		    int (*do_msr)(struct kvm_vcpu *vcpu,
				  unsigned index, u64 *data))
{
	int i;

	for (i = 0; i < msrs->nmsrs; ++i)
		if (do_msr(vcpu, entries[i].index, &entries[i].data))
			break;

	return i;
}

/*
 * Read or write a bunch of msrs. Parameters are user addresses.
 *
 * @return number of msrs set successfully.
 */
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
		  int (*do_msr)(struct kvm_vcpu *vcpu,
				unsigned index, u64 *data),
		  int writeback)
{
	struct kvm_msrs msrs;
	struct kvm_msr_entry *entries;
	int r, n;
	unsigned size;

	r = -EFAULT;
	if (copy_from_user(&msrs, user_msrs, sizeof(msrs)))
		goto out;

	r = -E2BIG;
	if (msrs.nmsrs >= MAX_IO_MSRS)
		goto out;

	size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
	entries = memdup_user(user_msrs->entries, size);
	if (IS_ERR(entries)) {
		r = PTR_ERR(entries);
		goto out;
	}

	r = n = __msr_io(vcpu, &msrs, entries, do_msr);
	if (r < 0)
		goto out_free;

	r = -EFAULT;
	if (writeback && copy_to_user(user_msrs->entries, entries, size))
		goto out_free;

	r = n;

out_free:
	kfree(entries);
out:
	return r;
}

static inline bool kvm_can_mwait_in_guest(void)
{
	return boot_cpu_has(X86_FEATURE_MWAIT) &&
		!boot_cpu_has_bug(X86_BUG_MONITOR) &&
		boot_cpu_has(X86_FEATURE_ARAT);
}

static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
					    struct kvm_cpuid2 __user *cpuid_arg)
{
	struct kvm_cpuid2 cpuid;
	int r;

	r = -EFAULT;
	if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
		return r;

	r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries);
	if (r)
		return r;

	r = -EFAULT;
	if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
		return r;

	return 0;
}

int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
	int r = 0;

	switch (ext) {
	case KVM_CAP_IRQCHIP:
	case KVM_CAP_HLT:
	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
	case KVM_CAP_SET_TSS_ADDR:
	case KVM_CAP_EXT_CPUID:
	case KVM_CAP_EXT_EMUL_CPUID:
	case KVM_CAP_CLOCKSOURCE:
	case KVM_CAP_PIT:
	case KVM_CAP_NOP_IO_DELAY:
	case KVM_CAP_MP_STATE:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_USER_NMI:
	case KVM_CAP_REINJECT_CONTROL:
	case KVM_CAP_IRQ_INJECT_STATUS:
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_IOEVENTFD_NO_LENGTH:
	case KVM_CAP_PIT2:
	case KVM_CAP_PIT_STATE2:
	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
	case KVM_CAP_VCPU_EVENTS:
	case KVM_CAP_HYPERV:
	case KVM_CAP_HYPERV_VAPIC:
	case KVM_CAP_HYPERV_SPIN:
	case KVM_CAP_HYPERV_SYNIC:
	case KVM_CAP_HYPERV_SYNIC2:
	case KVM_CAP_HYPERV_VP_INDEX:
	case KVM_CAP_HYPERV_EVENTFD:
	case KVM_CAP_HYPERV_TLBFLUSH:
	case KVM_CAP_HYPERV_SEND_IPI:
	case KVM_CAP_HYPERV_CPUID:
	case KVM_CAP_HYPERV_ENFORCE_CPUID:
	case KVM_CAP_SYS_HYPERV_CPUID:
	case KVM_CAP_PCI_SEGMENT:
	case KVM_CAP_DEBUGREGS:
	case KVM_CAP_X86_ROBUST_SINGLESTEP:
	case KVM_CAP_XSAVE:
	case KVM_CAP_ASYNC_PF:
	case KVM_CAP_ASYNC_PF_INT:
	case KVM_CAP_GET_TSC_KHZ:
	case KVM_CAP_KVMCLOCK_CTRL:
	case KVM_CAP_READONLY_MEM:
	case KVM_CAP_HYPERV_TIME:
	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
	case KVM_CAP_TSC_DEADLINE_TIMER:
	case KVM_CAP_DISABLE_QUIRKS:
	case KVM_CAP_SET_BOOT_CPU_ID:
 	case KVM_CAP_SPLIT_IRQCHIP:
	case KVM_CAP_IMMEDIATE_EXIT:
	case KVM_CAP_PMU_EVENT_FILTER:
	case KVM_CAP_GET_MSR_FEATURES:
	case KVM_CAP_MSR_PLATFORM_INFO:
	case KVM_CAP_EXCEPTION_PAYLOAD:
	case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
	case KVM_CAP_SET_GUEST_DEBUG:
	case KVM_CAP_LAST_CPU:
	case KVM_CAP_X86_USER_SPACE_MSR:
	case KVM_CAP_X86_MSR_FILTER:
	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
#ifdef CONFIG_X86_SGX_KVM
	case KVM_CAP_SGX_ATTRIBUTE:
#endif
	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
	case KVM_CAP_SREGS2:
	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
	case KVM_CAP_VCPU_ATTRIBUTES:
	case KVM_CAP_SYS_ATTRIBUTES:
	case KVM_CAP_VAPIC:
	case KVM_CAP_ENABLE_CAP:
	case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
		r = 1;
		break;
	case KVM_CAP_EXIT_HYPERCALL:
		r = KVM_EXIT_HYPERCALL_VALID_MASK;
		break;
	case KVM_CAP_SET_GUEST_DEBUG2:
		return KVM_GUESTDBG_VALID_MASK;
#ifdef CONFIG_KVM_XEN
	case KVM_CAP_XEN_HVM:
		r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR |
		    KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
		    KVM_XEN_HVM_CONFIG_SHARED_INFO |
		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
		if (sched_info_on())
			r |= KVM_XEN_HVM_CONFIG_RUNSTATE;
		break;
#endif
	case KVM_CAP_SYNC_REGS:
		r = KVM_SYNC_X86_VALID_FIELDS;
		break;
	case KVM_CAP_ADJUST_CLOCK:
		r = KVM_CLOCK_VALID_FLAGS;
		break;
	case KVM_CAP_X86_DISABLE_EXITS:
		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
		      KVM_X86_DISABLE_EXITS_CSTATE;
		if(kvm_can_mwait_in_guest())
			r |= KVM_X86_DISABLE_EXITS_MWAIT;
		break;
	case KVM_CAP_X86_SMM:
		if (!IS_ENABLED(CONFIG_KVM_SMM))
			break;

		/* SMBASE is usually relocated above 1M on modern chipsets,
		 * and SMM handlers might indeed rely on 4G segment limits,
		 * so do not report SMM to be available if real mode is
		 * emulated via vm86 mode.  Still, do not go to great lengths
		 * to avoid userspace's usage of the feature, because it is a
		 * fringe case that is not enabled except via specific settings
		 * of the module parameters.
		 */
		r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE);
		break;
	case KVM_CAP_NR_VCPUS:
		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
		break;
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
	case KVM_CAP_MAX_VCPU_ID:
		r = KVM_MAX_VCPU_IDS;
		break;
	case KVM_CAP_PV_MMU:	/* obsolete */
		r = 0;
		break;
	case KVM_CAP_MCE:
		r = KVM_MAX_MCE_BANKS;
		break;
	case KVM_CAP_XCRS:
		r = boot_cpu_has(X86_FEATURE_XSAVE);
		break;
	case KVM_CAP_TSC_CONTROL:
	case KVM_CAP_VM_TSC_CONTROL:
		r = kvm_caps.has_tsc_control;
		break;
	case KVM_CAP_X2APIC_API:
		r = KVM_X2APIC_API_VALID_FLAGS;
		break;
	case KVM_CAP_NESTED_STATE:
		r = kvm_x86_ops.nested_ops->get_state ?
			kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
		break;
	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
		r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
		break;
	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
		r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
		break;
	case KVM_CAP_SMALLER_MAXPHYADDR:
		r = (int) allow_smaller_maxphyaddr;
		break;
	case KVM_CAP_STEAL_TIME:
		r = sched_info_on();
		break;
	case KVM_CAP_X86_BUS_LOCK_EXIT:
		if (kvm_caps.has_bus_lock_exit)
			r = KVM_BUS_LOCK_DETECTION_OFF |
			    KVM_BUS_LOCK_DETECTION_EXIT;
		else
			r = 0;
		break;
	case KVM_CAP_XSAVE2: {
		u64 guest_perm = xstate_get_guest_group_perm();

		r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false);
		if (r < sizeof(struct kvm_xsave))
			r = sizeof(struct kvm_xsave);
		break;
	}
	case KVM_CAP_PMU_CAPABILITY:
		r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0;
		break;
	case KVM_CAP_DISABLE_QUIRKS2:
		r = KVM_X86_VALID_QUIRKS;
		break;
	case KVM_CAP_X86_NOTIFY_VMEXIT:
		r = kvm_caps.has_notify_vmexit;
		break;
	default:
		break;
	}
	return r;
}

static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr)
{
	void __user *uaddr = (void __user*)(unsigned long)attr->addr;

	if ((u64)(unsigned long)uaddr != attr->addr)
		return ERR_PTR_USR(-EFAULT);
	return uaddr;
}

static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
{
	u64 __user *uaddr = kvm_get_attr_addr(attr);

	if (attr->group)
		return -ENXIO;

	if (IS_ERR(uaddr))
		return PTR_ERR(uaddr);

	switch (attr->attr) {
	case KVM_X86_XCOMP_GUEST_SUPP:
		if (put_user(kvm_caps.supported_xcr0, uaddr))
			return -EFAULT;
		return 0;
	default:
		return -ENXIO;
		break;
	}
}

static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr)
{
	if (attr->group)
		return -ENXIO;

	switch (attr->attr) {
	case KVM_X86_XCOMP_GUEST_SUPP:
		return 0;
	default:
		return -ENXIO;
	}
}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	long r;

	switch (ioctl) {
	case KVM_GET_MSR_INDEX_LIST: {
		struct kvm_msr_list __user *user_msr_list = argp;
		struct kvm_msr_list msr_list;
		unsigned n;

		r = -EFAULT;
		if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
			goto out;
		n = msr_list.nmsrs;
		msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs;
		if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
			goto out;
		r = -E2BIG;
		if (n < msr_list.nmsrs)
			goto out;
		r = -EFAULT;
		if (copy_to_user(user_msr_list->indices, &msrs_to_save,
				 num_msrs_to_save * sizeof(u32)))
			goto out;
		if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
				 &emulated_msrs,
				 num_emulated_msrs * sizeof(u32)))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_SUPPORTED_CPUID:
	case KVM_GET_EMULATED_CPUID: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
			goto out;

		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
					    ioctl);
		if (r)
			goto out;

		r = -EFAULT;
		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
			goto out;
		r = 0;
		break;
	}
	case KVM_X86_GET_MCE_CAP_SUPPORTED:
		r = -EFAULT;
		if (copy_to_user(argp, &kvm_caps.supported_mce_cap,
				 sizeof(kvm_caps.supported_mce_cap)))
			goto out;
		r = 0;
		break;
	case KVM_GET_MSR_FEATURE_INDEX_LIST: {
		struct kvm_msr_list __user *user_msr_list = argp;
		struct kvm_msr_list msr_list;
		unsigned int n;

		r = -EFAULT;
		if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
			goto out;
		n = msr_list.nmsrs;
		msr_list.nmsrs = num_msr_based_features;
		if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
			goto out;
		r = -E2BIG;
		if (n < msr_list.nmsrs)
			goto out;
		r = -EFAULT;
		if (copy_to_user(user_msr_list->indices, &msr_based_features,
				 num_msr_based_features * sizeof(u32)))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_MSRS:
		r = msr_io(NULL, argp, do_get_msr_feature, 1);
		break;
	case KVM_GET_SUPPORTED_HV_CPUID:
		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
		break;
	case KVM_GET_DEVICE_ATTR: {
		struct kvm_device_attr attr;
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_x86_dev_get_attr(&attr);
		break;
	}
	case KVM_HAS_DEVICE_ATTR: {
		struct kvm_device_attr attr;
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_x86_dev_has_attr(&attr);
		break;
	}
	default:
		r = -EINVAL;
		break;
	}
out:
	return r;
}

static void wbinvd_ipi(void *garbage)
{
	wbinvd();
}

static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
{
	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	/* Address WBINVD may be executed by guest */
	if (need_emulate_wbinvd(vcpu)) {
		if (static_call(kvm_x86_has_wbinvd_exit)())
			cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
		else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
			smp_call_function_single(vcpu->cpu,
					wbinvd_ipi, NULL, 1);
	}

	static_call(kvm_x86_vcpu_load)(vcpu, cpu);

	/* Save host pkru register if supported */
	vcpu->arch.host_pkru = read_pkru();

	/* Apply any externally detected TSC adjustments (due to suspend) */
	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
		vcpu->arch.tsc_offset_adjustment = 0;
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
	}

	if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
		s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
				rdtsc() - vcpu->arch.last_host_tsc;
		if (tsc_delta < 0)
			mark_tsc_unstable("KVM discovered backwards TSC");

		if (kvm_check_tsc_unstable()) {
			u64 offset = kvm_compute_l1_tsc_offset(vcpu,
						vcpu->arch.last_guest_tsc);
			kvm_vcpu_write_tsc_offset(vcpu, offset);
			vcpu->arch.tsc_catchup = 1;
		}

		if (kvm_lapic_hv_timer_in_use(vcpu))
			kvm_lapic_restart_hv_timer(vcpu);

		/*
		 * On a host with synchronized TSC, there is no need to update
		 * kvmclock on vcpu->cpu migration
		 */
		if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
			kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
		if (vcpu->cpu != cpu)
			kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu);
		vcpu->cpu = cpu;
	}

	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
}

static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
{
	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
	struct kvm_steal_time __user *st;
	struct kvm_memslots *slots;
	static const u8 preempted = KVM_VCPU_PREEMPTED;
	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;

	/*
	 * The vCPU can be marked preempted if and only if the VM-Exit was on
	 * an instruction boundary and will not trigger guest emulation of any
	 * kind (see vcpu_run).  Vendor specific code controls (conservatively)
	 * when this is true, for example allowing the vCPU to be marked
	 * preempted if and only if the VM-Exit was due to a host interrupt.
	 */
	if (!vcpu->arch.at_instruction_boundary) {
		vcpu->stat.preemption_other++;
		return;
	}

	vcpu->stat.preemption_reported++;
	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
		return;

	if (vcpu->arch.st.preempted)
		return;

	/* This happens on process exit */
	if (unlikely(current->mm != vcpu->kvm->mm))
		return;

	slots = kvm_memslots(vcpu->kvm);

	if (unlikely(slots->generation != ghc->generation ||
		     gpa != ghc->gpa ||
		     kvm_is_error_hva(ghc->hva) || !ghc->memslot))
		return;

	st = (struct kvm_steal_time __user *)ghc->hva;
	BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted));

	if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted)))
		vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;

	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	int idx;

	if (vcpu->preempted) {
		if (!vcpu->arch.guest_state_protected)
			vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);

		/*
		 * Take the srcu lock as memslots will be accessed to check the gfn
		 * cache generation against the memslots generation.
		 */
		idx = srcu_read_lock(&vcpu->kvm->srcu);
		if (kvm_xen_msr_enabled(vcpu->kvm))
			kvm_xen_runstate_set_preempted(vcpu);
		else
			kvm_steal_time_set_preempted(vcpu);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
	}

	static_call(kvm_x86_vcpu_put)(vcpu);
	vcpu->arch.last_host_tsc = rdtsc();
}

static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);

	return kvm_apic_get_state(vcpu, s);
}

static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	int r;

	r = kvm_apic_set_state(vcpu, s);
	if (r)
		return r;
	update_cr8_intercept(vcpu);

	return 0;
}

static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
{
	/*
	 * We can accept userspace's request for interrupt injection
	 * as long as we have a place to store the interrupt number.
	 * The actual injection will happen when the CPU is able to
	 * deliver the interrupt.
	 */
	if (kvm_cpu_has_extint(vcpu))
		return false;

	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
	return (!lapic_in_kernel(vcpu) ||
		kvm_apic_accept_pic_intr(vcpu));
}

static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
{
	/*
	 * Do not cause an interrupt window exit if an exception
	 * is pending or an event needs reinjection; userspace
	 * might want to inject the interrupt manually using KVM_SET_REGS
	 * or KVM_SET_SREGS.  For that to work, we must be at an
	 * instruction boundary and with no events half-injected.
	 */
	return (kvm_arch_interrupt_allowed(vcpu) &&
		kvm_cpu_accept_dm_intr(vcpu) &&
		!kvm_event_needs_reinjection(vcpu) &&
		!kvm_is_exception_pending(vcpu));
}

static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
				    struct kvm_interrupt *irq)
{
	if (irq->irq >= KVM_NR_INTERRUPTS)
		return -EINVAL;

	if (!irqchip_in_kernel(vcpu->kvm)) {
		kvm_queue_interrupt(vcpu, irq->irq, false);
		kvm_make_request(KVM_REQ_EVENT, vcpu);
		return 0;
	}

	/*
	 * With in-kernel LAPIC, we only use this to inject EXTINT, so
	 * fail for in-kernel 8259.
	 */
	if (pic_in_kernel(vcpu->kvm))
		return -ENXIO;

	if (vcpu->arch.pending_external_vector != -1)
		return -EEXIST;

	vcpu->arch.pending_external_vector = irq->irq;
	kvm_make_request(KVM_REQ_EVENT, vcpu);
	return 0;
}

static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
{
	kvm_inject_nmi(vcpu);

	return 0;
}

static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
					   struct kvm_tpr_access_ctl *tac)
{
	if (tac->flags)
		return -EINVAL;
	vcpu->arch.tpr_access_reporting = !!tac->enabled;
	return 0;
}

static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
					u64 mcg_cap)
{
	int r;
	unsigned bank_num = mcg_cap & 0xff, bank;

	r = -EINVAL;
	if (!bank_num || bank_num > KVM_MAX_MCE_BANKS)
		goto out;
	if (mcg_cap & ~(kvm_caps.supported_mce_cap | 0xff | 0xff0000))
		goto out;
	r = 0;
	vcpu->arch.mcg_cap = mcg_cap;
	/* Init IA32_MCG_CTL to all 1s */
	if (mcg_cap & MCG_CTL_P)
		vcpu->arch.mcg_ctl = ~(u64)0;
	/* Init IA32_MCi_CTL to all 1s, IA32_MCi_CTL2 to all 0s */
	for (bank = 0; bank < bank_num; bank++) {
		vcpu->arch.mce_banks[bank*4] = ~(u64)0;
		if (mcg_cap & MCG_CMCI_P)
			vcpu->arch.mci_ctl2_banks[bank] = 0;
	}

	kvm_apic_after_set_mcg_cap(vcpu);

	static_call(kvm_x86_setup_mce)(vcpu);
out:
	return r;
}

/*
 * Validate this is an UCNA (uncorrectable no action) error by checking the
 * MCG_STATUS and MCi_STATUS registers:
 * - none of the bits for Machine Check Exceptions are set
 * - both the VAL (valid) and UC (uncorrectable) bits are set
 * MCI_STATUS_PCC - Processor Context Corrupted
 * MCI_STATUS_S - Signaled as a Machine Check Exception
 * MCI_STATUS_AR - Software recoverable Action Required
 */
static bool is_ucna(struct kvm_x86_mce *mce)
{
	return	!mce->mcg_status &&
		!(mce->status & (MCI_STATUS_PCC | MCI_STATUS_S | MCI_STATUS_AR)) &&
		(mce->status & MCI_STATUS_VAL) &&
		(mce->status & MCI_STATUS_UC);
}

static int kvm_vcpu_x86_set_ucna(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce, u64* banks)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;

	banks[1] = mce->status;
	banks[2] = mce->addr;
	banks[3] = mce->misc;
	vcpu->arch.mcg_status = mce->mcg_status;

	if (!(mcg_cap & MCG_CMCI_P) ||
	    !(vcpu->arch.mci_ctl2_banks[mce->bank] & MCI_CTL2_CMCI_EN))
		return 0;

	if (lapic_in_kernel(vcpu))
		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTCMCI);

	return 0;
}

static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
				      struct kvm_x86_mce *mce)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;
	u64 *banks = vcpu->arch.mce_banks;

	if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL))
		return -EINVAL;

	banks += array_index_nospec(4 * mce->bank, 4 * bank_num);

	if (is_ucna(mce))
		return kvm_vcpu_x86_set_ucna(vcpu, mce, banks);

	/*
	 * if IA32_MCG_CTL is not all 1s, the uncorrected error
	 * reporting is disabled
	 */
	if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) &&
	    vcpu->arch.mcg_ctl != ~(u64)0)
		return 0;
	/*
	 * if IA32_MCi_CTL is not all 1s, the uncorrected error
	 * reporting is disabled for the bank
	 */
	if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0)
		return 0;
	if (mce->status & MCI_STATUS_UC) {
		if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
		    !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
			return 0;
		}
		if (banks[1] & MCI_STATUS_VAL)
			mce->status |= MCI_STATUS_OVER;
		banks[2] = mce->addr;
		banks[3] = mce->misc;
		vcpu->arch.mcg_status = mce->mcg_status;
		banks[1] = mce->status;
		kvm_queue_exception(vcpu, MC_VECTOR);
	} else if (!(banks[1] & MCI_STATUS_VAL)
		   || !(banks[1] & MCI_STATUS_UC)) {
		if (banks[1] & MCI_STATUS_VAL)
			mce->status |= MCI_STATUS_OVER;
		banks[2] = mce->addr;
		banks[3] = mce->misc;
		banks[1] = mce->status;
	} else
		banks[1] |= MCI_STATUS_OVER;
	return 0;
}

static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
					       struct kvm_vcpu_events *events)
{
	struct kvm_queued_exception *ex;

	process_nmi(vcpu);

#ifdef CONFIG_KVM_SMM
	if (kvm_check_request(KVM_REQ_SMI, vcpu))
		process_smi(vcpu);
#endif

	/*
	 * KVM's ABI only allows for one exception to be migrated.  Luckily,
	 * the only time there can be two queued exceptions is if there's a
	 * non-exiting _injected_ exception, and a pending exiting exception.
	 * In that case, ignore the VM-Exiting exception as it's an extension
	 * of the injected exception.
	 */
	if (vcpu->arch.exception_vmexit.pending &&
	    !vcpu->arch.exception.pending &&
	    !vcpu->arch.exception.injected)
		ex = &vcpu->arch.exception_vmexit;
	else
		ex = &vcpu->arch.exception;

	/*
	 * In guest mode, payload delivery should be deferred if the exception
	 * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1
	 * intercepts #PF, ditto for DR6 and #DBs.  If the per-VM capability,
	 * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not
	 * propagate the payload and so it cannot be safely deferred.  Deliver
	 * the payload if the capability hasn't been requested.
	 */
	if (!vcpu->kvm->arch.exception_payload_enabled &&
	    ex->pending && ex->has_payload)
		kvm_deliver_exception_payload(vcpu, ex);

	memset(events, 0, sizeof(*events));

	/*
	 * The API doesn't provide the instruction length for software
	 * exceptions, so don't report them. As long as the guest RIP
	 * isn't advanced, we should expect to encounter the exception
	 * again.
	 */
	if (!kvm_exception_is_soft(ex->vector)) {
		events->exception.injected = ex->injected;
		events->exception.pending = ex->pending;
		/*
		 * For ABI compatibility, deliberately conflate
		 * pending and injected exceptions when
		 * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
		 */
		if (!vcpu->kvm->arch.exception_payload_enabled)
			events->exception.injected |= ex->pending;
	}
	events->exception.nr = ex->vector;
	events->exception.has_error_code = ex->has_error_code;
	events->exception.error_code = ex->error_code;
	events->exception_has_payload = ex->has_payload;
	events->exception_payload = ex->payload;

	events->interrupt.injected =
		vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
	events->interrupt.nr = vcpu->arch.interrupt.nr;
	events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);

	events->nmi.injected = vcpu->arch.nmi_injected;
	events->nmi.pending = vcpu->arch.nmi_pending != 0;
	events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu);

	/* events->sipi_vector is never valid when reporting to user space */

#ifdef CONFIG_KVM_SMM
	events->smi.smm = is_smm(vcpu);
	events->smi.pending = vcpu->arch.smi_pending;
	events->smi.smm_inside_nmi =
		!!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
#endif
	events->smi.latched_init = kvm_lapic_latched_init(vcpu);

	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
			 | KVM_VCPUEVENT_VALID_SHADOW
			 | KVM_VCPUEVENT_VALID_SMM);
	if (vcpu->kvm->arch.exception_payload_enabled)
		events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
	if (vcpu->kvm->arch.triple_fault_event) {
		events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
	}
}

static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
					      struct kvm_vcpu_events *events)
{
	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
			      | KVM_VCPUEVENT_VALID_SHADOW
			      | KVM_VCPUEVENT_VALID_SMM
			      | KVM_VCPUEVENT_VALID_PAYLOAD
			      | KVM_VCPUEVENT_VALID_TRIPLE_FAULT))
		return -EINVAL;

	if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
		if (!vcpu->kvm->arch.exception_payload_enabled)
			return -EINVAL;
		if (events->exception.pending)
			events->exception.injected = 0;
		else
			events->exception_has_payload = 0;
	} else {
		events->exception.pending = 0;
		events->exception_has_payload = 0;
	}

	if ((events->exception.injected || events->exception.pending) &&
	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
		return -EINVAL;

	/* INITs are latched while in SMM */
	if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
	    (events->smi.smm || events->smi.pending) &&
	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
		return -EINVAL;

	process_nmi(vcpu);

	/*
	 * Flag that userspace is stuffing an exception, the next KVM_RUN will
	 * morph the exception to a VM-Exit if appropriate.  Do this only for
	 * pending exceptions, already-injected exceptions are not subject to
	 * intercpetion.  Note, userspace that conflates pending and injected
	 * is hosed, and will incorrectly convert an injected exception into a
	 * pending exception, which in turn may cause a spurious VM-Exit.
	 */
	vcpu->arch.exception_from_userspace = events->exception.pending;

	vcpu->arch.exception_vmexit.pending = false;

	vcpu->arch.exception.injected = events->exception.injected;
	vcpu->arch.exception.pending = events->exception.pending;
	vcpu->arch.exception.vector = events->exception.nr;
	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
	vcpu->arch.exception.error_code = events->exception.error_code;
	vcpu->arch.exception.has_payload = events->exception_has_payload;
	vcpu->arch.exception.payload = events->exception_payload;

	vcpu->arch.interrupt.injected = events->interrupt.injected;
	vcpu->arch.interrupt.nr = events->interrupt.nr;
	vcpu->arch.interrupt.soft = events->interrupt.soft;
	if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
		static_call(kvm_x86_set_interrupt_shadow)(vcpu,
						events->interrupt.shadow);

	vcpu->arch.nmi_injected = events->nmi.injected;
	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
		vcpu->arch.nmi_pending = events->nmi.pending;
	static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);

	if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
	    lapic_in_kernel(vcpu))
		vcpu->arch.apic->sipi_vector = events->sipi_vector;

	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
#ifdef CONFIG_KVM_SMM
		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
			kvm_leave_nested(vcpu);
			kvm_smm_changed(vcpu, events->smi.smm);
		}

		vcpu->arch.smi_pending = events->smi.pending;

		if (events->smi.smm) {
			if (events->smi.smm_inside_nmi)
				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
			else
				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
		}

#else
		if (events->smi.smm || events->smi.pending ||
		    events->smi.smm_inside_nmi)
			return -EINVAL;
#endif

		if (lapic_in_kernel(vcpu)) {
			if (events->smi.latched_init)
				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
			else
				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
		}
	}

	if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) {
		if (!vcpu->kvm->arch.triple_fault_event)
			return -EINVAL;
		if (events->triple_fault.pending)
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		else
			kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
	}

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	return 0;
}

static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
					     struct kvm_debugregs *dbgregs)
{
	unsigned long val;

	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
	kvm_get_dr(vcpu, 6, &val);
	dbgregs->dr6 = val;
	dbgregs->dr7 = vcpu->arch.dr7;
	dbgregs->flags = 0;
	memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
}

static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
					    struct kvm_debugregs *dbgregs)
{
	if (dbgregs->flags)
		return -EINVAL;

	if (!kvm_dr6_valid(dbgregs->dr6))
		return -EINVAL;
	if (!kvm_dr7_valid(dbgregs->dr7))
		return -EINVAL;

	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
	kvm_update_dr0123(vcpu);
	vcpu->arch.dr6 = dbgregs->dr6;
	vcpu->arch.dr7 = dbgregs->dr7;
	kvm_update_dr7(vcpu);

	return 0;
}

static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
					 struct kvm_xsave *guest_xsave)
{
	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
		return;

	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
				       guest_xsave->region,
				       sizeof(guest_xsave->region),
				       vcpu->arch.pkru);
}

static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
					  u8 *state, unsigned int size)
{
	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
		return;

	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
				       state, size, vcpu->arch.pkru);
}

static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
					struct kvm_xsave *guest_xsave)
{
	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
		return 0;

	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
					      guest_xsave->region,
					      kvm_caps.supported_xcr0,
					      &vcpu->arch.pkru);
}

static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
					struct kvm_xcrs *guest_xcrs)
{
	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
		guest_xcrs->nr_xcrs = 0;
		return;
	}

	guest_xcrs->nr_xcrs = 1;
	guest_xcrs->flags = 0;
	guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
	guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
}

static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
				       struct kvm_xcrs *guest_xcrs)
{
	int i, r = 0;

	if (!boot_cpu_has(X86_FEATURE_XSAVE))
		return -EINVAL;

	if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
		return -EINVAL;

	for (i = 0; i < guest_xcrs->nr_xcrs; i++)
		/* Only support XCR0 currently */
		if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) {
			r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
				guest_xcrs->xcrs[i].value);
			break;
		}
	if (r)
		r = -EINVAL;
	return r;
}

/*
 * kvm_set_guest_paused() indicates to the guest kernel that it has been
 * stopped by the hypervisor.  This function will be called from the host only.
 * EINVAL is returned when the host attempts to set the flag for a guest that
 * does not support pv clocks.
 */
static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
{
	if (!vcpu->arch.pv_time.active)
		return -EINVAL;
	vcpu->arch.pvclock_set_guest_stopped_request = true;
	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
	return 0;
}

static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int r;

	switch (attr->attr) {
	case KVM_VCPU_TSC_OFFSET:
		r = 0;
		break;
	default:
		r = -ENXIO;
	}

	return r;
}

static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	u64 __user *uaddr = kvm_get_attr_addr(attr);
	int r;

	if (IS_ERR(uaddr))
		return PTR_ERR(uaddr);

	switch (attr->attr) {
	case KVM_VCPU_TSC_OFFSET:
		r = -EFAULT;
		if (put_user(vcpu->arch.l1_tsc_offset, uaddr))
			break;
		r = 0;
		break;
	default:
		r = -ENXIO;
	}

	return r;
}

static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	u64 __user *uaddr = kvm_get_attr_addr(attr);
	struct kvm *kvm = vcpu->kvm;
	int r;

	if (IS_ERR(uaddr))
		return PTR_ERR(uaddr);

	switch (attr->attr) {
	case KVM_VCPU_TSC_OFFSET: {
		u64 offset, tsc, ns;
		unsigned long flags;
		bool matched;

		r = -EFAULT;
		if (get_user(offset, uaddr))
			break;

		raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);

		matched = (vcpu->arch.virtual_tsc_khz &&
			   kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz &&
			   kvm->arch.last_tsc_offset == offset);

		tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset;
		ns = get_kvmclock_base_ns();

		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched);
		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);

		r = 0;
		break;
	}
	default:
		r = -ENXIO;
	}

	return r;
}

static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu,
				      unsigned int ioctl,
				      void __user *argp)
{
	struct kvm_device_attr attr;
	int r;

	if (copy_from_user(&attr, argp, sizeof(attr)))
		return -EFAULT;

	if (attr.group != KVM_VCPU_TSC_CTRL)
		return -ENXIO;

	switch (ioctl) {
	case KVM_HAS_DEVICE_ATTR:
		r = kvm_arch_tsc_has_attr(vcpu, &attr);
		break;
	case KVM_GET_DEVICE_ATTR:
		r = kvm_arch_tsc_get_attr(vcpu, &attr);
		break;
	case KVM_SET_DEVICE_ATTR:
		r = kvm_arch_tsc_set_attr(vcpu, &attr);
		break;
	}

	return r;
}

static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
				     struct kvm_enable_cap *cap)
{
	int r;
	uint16_t vmcs_version;
	void __user *user_ptr;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
	case KVM_CAP_HYPERV_SYNIC2:
		if (cap->args[0])
			return -EINVAL;
		fallthrough;

	case KVM_CAP_HYPERV_SYNIC:
		if (!irqchip_in_kernel(vcpu->kvm))
			return -EINVAL;
		return kvm_hv_activate_synic(vcpu, cap->cap ==
					     KVM_CAP_HYPERV_SYNIC2);
	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
		if (!kvm_x86_ops.nested_ops->enable_evmcs)
			return -ENOTTY;
		r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
		if (!r) {
			user_ptr = (void __user *)(uintptr_t)cap->args[0];
			if (copy_to_user(user_ptr, &vmcs_version,
					 sizeof(vmcs_version)))
				r = -EFAULT;
		}
		return r;
	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
		if (!kvm_x86_ops.enable_l2_tlb_flush)
			return -ENOTTY;

		return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu);

	case KVM_CAP_HYPERV_ENFORCE_CPUID:
		return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);

	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
		vcpu->arch.pv_cpuid.enforce = cap->args[0];
		if (vcpu->arch.pv_cpuid.enforce)
			kvm_update_pv_runtime(vcpu);

		return 0;
	default:
		return -EINVAL;
	}
}

long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;
	union {
		struct kvm_sregs2 *sregs2;
		struct kvm_lapic_state *lapic;
		struct kvm_xsave *xsave;
		struct kvm_xcrs *xcrs;
		void *buffer;
	} u;

	vcpu_load(vcpu);

	u.buffer = NULL;
	switch (ioctl) {
	case KVM_GET_LAPIC: {
		r = -EINVAL;
		if (!lapic_in_kernel(vcpu))
			goto out;
		u.lapic = kzalloc(sizeof(struct kvm_lapic_state),
				GFP_KERNEL_ACCOUNT);

		r = -ENOMEM;
		if (!u.lapic)
			goto out;
		r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_LAPIC: {
		r = -EINVAL;
		if (!lapic_in_kernel(vcpu))
			goto out;
		u.lapic = memdup_user(argp, sizeof(*u.lapic));
		if (IS_ERR(u.lapic)) {
			r = PTR_ERR(u.lapic);
			goto out_nofree;
		}

		r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
		break;
	}
	case KVM_INTERRUPT: {
		struct kvm_interrupt irq;

		r = -EFAULT;
		if (copy_from_user(&irq, argp, sizeof(irq)))
			goto out;
		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
		break;
	}
	case KVM_NMI: {
		r = kvm_vcpu_ioctl_nmi(vcpu);
		break;
	}
	case KVM_SMI: {
		r = kvm_inject_smi(vcpu);
		break;
	}
	case KVM_SET_CPUID: {
		struct kvm_cpuid __user *cpuid_arg = argp;
		struct kvm_cpuid cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
			goto out;
		r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
		break;
	}
	case KVM_SET_CPUID2: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
			goto out;
		r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
					      cpuid_arg->entries);
		break;
	}
	case KVM_GET_CPUID2: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
			goto out;
		r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
					      cpuid_arg->entries);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_MSRS: {
		int idx = srcu_read_lock(&vcpu->kvm->srcu);
		r = msr_io(vcpu, argp, do_get_msr, 1);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
		break;
	}
	case KVM_SET_MSRS: {
		int idx = srcu_read_lock(&vcpu->kvm->srcu);
		r = msr_io(vcpu, argp, do_set_msr, 0);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
		break;
	}
	case KVM_TPR_ACCESS_REPORTING: {
		struct kvm_tpr_access_ctl tac;

		r = -EFAULT;
		if (copy_from_user(&tac, argp, sizeof(tac)))
			goto out;
		r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &tac, sizeof(tac)))
			goto out;
		r = 0;
		break;
	};
	case KVM_SET_VAPIC_ADDR: {
		struct kvm_vapic_addr va;
		int idx;

		r = -EINVAL;
		if (!lapic_in_kernel(vcpu))
			goto out;
		r = -EFAULT;
		if (copy_from_user(&va, argp, sizeof(va)))
			goto out;
		idx = srcu_read_lock(&vcpu->kvm->srcu);
		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
		break;
	}
	case KVM_X86_SETUP_MCE: {
		u64 mcg_cap;

		r = -EFAULT;
		if (copy_from_user(&mcg_cap, argp, sizeof(mcg_cap)))
			goto out;
		r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap);
		break;
	}
	case KVM_X86_SET_MCE: {
		struct kvm_x86_mce mce;

		r = -EFAULT;
		if (copy_from_user(&mce, argp, sizeof(mce)))
			goto out;
		r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
		break;
	}
	case KVM_GET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events);

		r = -EFAULT;
		if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		r = -EFAULT;
		if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
			break;

		r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
		break;
	}
	case KVM_GET_DEBUGREGS: {
		struct kvm_debugregs dbgregs;

		kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);

		r = -EFAULT;
		if (copy_to_user(argp, &dbgregs,
				 sizeof(struct kvm_debugregs)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_DEBUGREGS: {
		struct kvm_debugregs dbgregs;

		r = -EFAULT;
		if (copy_from_user(&dbgregs, argp,
				   sizeof(struct kvm_debugregs)))
			break;

		r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
		break;
	}
	case KVM_GET_XSAVE: {
		r = -EINVAL;
		if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave))
			break;

		u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT);
		r = -ENOMEM;
		if (!u.xsave)
			break;

		kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);

		r = -EFAULT;
		if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_XSAVE: {
		int size = vcpu->arch.guest_fpu.uabi_size;

		u.xsave = memdup_user(argp, size);
		if (IS_ERR(u.xsave)) {
			r = PTR_ERR(u.xsave);
			goto out_nofree;
		}

		r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
		break;
	}

	case KVM_GET_XSAVE2: {
		int size = vcpu->arch.guest_fpu.uabi_size;

		u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT);
		r = -ENOMEM;
		if (!u.xsave)
			break;

		kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size);

		r = -EFAULT;
		if (copy_to_user(argp, u.xsave, size))
			break;

		r = 0;
		break;
	}

	case KVM_GET_XCRS: {
		u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT);
		r = -ENOMEM;
		if (!u.xcrs)
			break;

		kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);

		r = -EFAULT;
		if (copy_to_user(argp, u.xcrs,
				 sizeof(struct kvm_xcrs)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_XCRS: {
		u.xcrs = memdup_user(argp, sizeof(*u.xcrs));
		if (IS_ERR(u.xcrs)) {
			r = PTR_ERR(u.xcrs);
			goto out_nofree;
		}

		r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
		break;
	}
	case KVM_SET_TSC_KHZ: {
		u32 user_tsc_khz;

		r = -EINVAL;
		user_tsc_khz = (u32)arg;

		if (kvm_caps.has_tsc_control &&
		    user_tsc_khz >= kvm_caps.max_guest_tsc_khz)
			goto out;

		if (user_tsc_khz == 0)
			user_tsc_khz = tsc_khz;

		if (!kvm_set_tsc_khz(vcpu, user_tsc_khz))
			r = 0;

		goto out;
	}
	case KVM_GET_TSC_KHZ: {
		r = vcpu->arch.virtual_tsc_khz;
		goto out;
	}
	case KVM_KVMCLOCK_CTRL: {
		r = kvm_set_guest_paused(vcpu);
		goto out;
	}
	case KVM_ENABLE_CAP: {
		struct kvm_enable_cap cap;

		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			goto out;
		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
		break;
	}
	case KVM_GET_NESTED_STATE: {
		struct kvm_nested_state __user *user_kvm_nested_state = argp;
		u32 user_data_size;

		r = -EINVAL;
		if (!kvm_x86_ops.nested_ops->get_state)
			break;

		BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));
		r = -EFAULT;
		if (get_user(user_data_size, &user_kvm_nested_state->size))
			break;

		r = kvm_x86_ops.nested_ops->get_state(vcpu, user_kvm_nested_state,
						     user_data_size);
		if (r < 0)
			break;

		if (r > user_data_size) {
			if (put_user(r, &user_kvm_nested_state->size))
				r = -EFAULT;
			else
				r = -E2BIG;
			break;
		}

		r = 0;
		break;
	}
	case KVM_SET_NESTED_STATE: {
		struct kvm_nested_state __user *user_kvm_nested_state = argp;
		struct kvm_nested_state kvm_state;
		int idx;

		r = -EINVAL;
		if (!kvm_x86_ops.nested_ops->set_state)
			break;

		r = -EFAULT;
		if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state)))
			break;

		r = -EINVAL;
		if (kvm_state.size < sizeof(kvm_state))
			break;

		if (kvm_state.flags &
		    ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE
		      | KVM_STATE_NESTED_EVMCS | KVM_STATE_NESTED_MTF_PENDING
		      | KVM_STATE_NESTED_GIF_SET))
			break;

		/* nested_run_pending implies guest_mode.  */
		if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING)
		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
			break;

		idx = srcu_read_lock(&vcpu->kvm->srcu);
		r = kvm_x86_ops.nested_ops->set_state(vcpu, user_kvm_nested_state, &kvm_state);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
		break;
	}
	case KVM_GET_SUPPORTED_HV_CPUID:
		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
		break;
#ifdef CONFIG_KVM_XEN
	case KVM_XEN_VCPU_GET_ATTR: {
		struct kvm_xen_vcpu_attr xva;

		r = -EFAULT;
		if (copy_from_user(&xva, argp, sizeof(xva)))
			goto out;
		r = kvm_xen_vcpu_get_attr(vcpu, &xva);
		if (!r && copy_to_user(argp, &xva, sizeof(xva)))
			r = -EFAULT;
		break;
	}
	case KVM_XEN_VCPU_SET_ATTR: {
		struct kvm_xen_vcpu_attr xva;

		r = -EFAULT;
		if (copy_from_user(&xva, argp, sizeof(xva)))
			goto out;
		r = kvm_xen_vcpu_set_attr(vcpu, &xva);
		break;
	}
#endif
	case KVM_GET_SREGS2: {
		u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.sregs2)
			goto out;
		__get_sregs2(vcpu, u.sregs2);
		r = -EFAULT;
		if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_SREGS2: {
		u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2));
		if (IS_ERR(u.sregs2)) {
			r = PTR_ERR(u.sregs2);
			u.sregs2 = NULL;
			goto out;
		}
		r = __set_sregs2(vcpu, u.sregs2);
		break;
	}
	case KVM_HAS_DEVICE_ATTR:
	case KVM_GET_DEVICE_ATTR:
	case KVM_SET_DEVICE_ATTR:
		r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp);
		break;
	default:
		r = -EINVAL;
	}
out:
	kfree(u.buffer);
out_nofree:
	vcpu_put(vcpu);
	return r;
}

vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
	return VM_FAULT_SIGBUS;
}

static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
{
	int ret;

	if (addr > (unsigned int)(-3 * PAGE_SIZE))
		return -EINVAL;
	ret = static_call(kvm_x86_set_tss_addr)(kvm, addr);
	return ret;
}

static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
					      u64 ident_addr)
{
	return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr);
}

static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
					 unsigned long kvm_nr_mmu_pages)
{
	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
		return -EINVAL;

	mutex_lock(&kvm->slots_lock);

	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;

	mutex_unlock(&kvm->slots_lock);
	return 0;
}

static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
	return kvm->arch.n_max_mmu_pages;
}

static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	struct kvm_pic *pic = kvm->arch.vpic;
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		memcpy(&chip->chip.pic, &pic->pics[0],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		memcpy(&chip->chip.pic, &pic->pics[1],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_IOAPIC:
		kvm_get_ioapic(kvm, &chip->chip.ioapic);
		break;
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	struct kvm_pic *pic = kvm->arch.vpic;
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		spin_lock(&pic->lock);
		memcpy(&pic->pics[0], &chip->chip.pic,
			sizeof(struct kvm_pic_state));
		spin_unlock(&pic->lock);
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		spin_lock(&pic->lock);
		memcpy(&pic->pics[1], &chip->chip.pic,
			sizeof(struct kvm_pic_state));
		spin_unlock(&pic->lock);
		break;
	case KVM_IRQCHIP_IOAPIC:
		kvm_set_ioapic(kvm, &chip->chip.ioapic);
		break;
	default:
		r = -EINVAL;
		break;
	}
	kvm_pic_update_irq(pic);
	return r;
}

static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
	struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;

	BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));

	mutex_lock(&kps->lock);
	memcpy(ps, &kps->channels, sizeof(*ps));
	mutex_unlock(&kps->lock);
	return 0;
}

static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
	int i;
	struct kvm_pit *pit = kvm->arch.vpit;

	mutex_lock(&pit->pit_state.lock);
	memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
	for (i = 0; i < 3; i++)
		kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
	mutex_unlock(&pit->pit_state.lock);
	return 0;
}

static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
		sizeof(ps->channels));
	ps->flags = kvm->arch.vpit->pit_state.flags;
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	memset(&ps->reserved, 0, sizeof(ps->reserved));
	return 0;
}

static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	int start = 0;
	int i;
	u32 prev_legacy, cur_legacy;
	struct kvm_pit *pit = kvm->arch.vpit;

	mutex_lock(&pit->pit_state.lock);
	prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
	cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
	if (!prev_legacy && cur_legacy)
		start = 1;
	memcpy(&pit->pit_state.channels, &ps->channels,
	       sizeof(pit->pit_state.channels));
	pit->pit_state.flags = ps->flags;
	for (i = 0; i < 3; i++)
		kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
				   start && i == 0);
	mutex_unlock(&pit->pit_state.lock);
	return 0;
}

static int kvm_vm_ioctl_reinject(struct kvm *kvm,
				 struct kvm_reinject_control *control)
{
	struct kvm_pit *pit = kvm->arch.vpit;

	/* pit->pit_state.lock was overloaded to prevent userspace from getting
	 * an inconsistent state after running multiple KVM_REINJECT_CONTROL
	 * ioctls in parallel.  Use a separate lock if that ioctl isn't rare.
	 */
	mutex_lock(&pit->pit_state.lock);
	kvm_pit_set_reinject(pit, control->pit_reinject);
	mutex_unlock(&pit->pit_state.lock);

	return 0;
}

void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{

	/*
	 * Flush all CPUs' dirty log buffers to the  dirty_bitmap.  Called
	 * before reporting dirty_bitmap to userspace.  KVM flushes the buffers
	 * on all VM-Exits, thus we only need to kick running vCPUs to force a
	 * VM-Exit.
	 */
	struct kvm_vcpu *vcpu;
	unsigned long i;

	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_vcpu_kick(vcpu);
}

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
			bool line_status)
{
	if (!irqchip_in_kernel(kvm))
		return -ENXIO;

	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
					irq_event->irq, irq_event->level,
					line_status);
	return 0;
}

int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
			    struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
	case KVM_CAP_DISABLE_QUIRKS2:
		r = -EINVAL;
		if (cap->args[0] & ~KVM_X86_VALID_QUIRKS)
			break;
		fallthrough;
	case KVM_CAP_DISABLE_QUIRKS:
		kvm->arch.disabled_quirks = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_SPLIT_IRQCHIP: {
		mutex_lock(&kvm->lock);
		r = -EINVAL;
		if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS)
			goto split_irqchip_unlock;
		r = -EEXIST;
		if (irqchip_in_kernel(kvm))
			goto split_irqchip_unlock;
		if (kvm->created_vcpus)
			goto split_irqchip_unlock;
		r = kvm_setup_empty_irq_routing(kvm);
		if (r)
			goto split_irqchip_unlock;
		/* Pairs with irqchip_in_kernel. */
		smp_wmb();
		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT);
		r = 0;
split_irqchip_unlock:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_CAP_X2APIC_API:
		r = -EINVAL;
		if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS)
			break;

		if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS)
			kvm->arch.x2apic_format = true;
		if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
			kvm->arch.x2apic_broadcast_quirk_disabled = true;

		r = 0;
		break;
	case KVM_CAP_X86_DISABLE_EXITS:
		r = -EINVAL;
		if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS)
			break;

		if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
			kvm_can_mwait_in_guest())
			kvm->arch.mwait_in_guest = true;
		if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
			kvm->arch.hlt_in_guest = true;
		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
			kvm->arch.pause_in_guest = true;
		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
			kvm->arch.cstate_in_guest = true;
		r = 0;
		break;
	case KVM_CAP_MSR_PLATFORM_INFO:
		kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_EXCEPTION_PAYLOAD:
		kvm->arch.exception_payload_enabled = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
		kvm->arch.triple_fault_event = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_X86_USER_SPACE_MSR:
		r = -EINVAL;
		if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK)
			break;
		kvm->arch.user_space_msr_mask = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_X86_BUS_LOCK_EXIT:
		r = -EINVAL;
		if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE)
			break;

		if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) &&
		    (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT))
			break;

		if (kvm_caps.has_bus_lock_exit &&
		    cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)
			kvm->arch.bus_lock_detection_enabled = true;
		r = 0;
		break;
#ifdef CONFIG_X86_SGX_KVM
	case KVM_CAP_SGX_ATTRIBUTE: {
		unsigned long allowed_attributes = 0;

		r = sgx_set_attribute(&allowed_attributes, cap->args[0]);
		if (r)
			break;

		/* KVM only supports the PROVISIONKEY privileged attribute. */
		if ((allowed_attributes & SGX_ATTR_PROVISIONKEY) &&
		    !(allowed_attributes & ~SGX_ATTR_PROVISIONKEY))
			kvm->arch.sgx_provisioning_allowed = true;
		else
			r = -EINVAL;
		break;
	}
#endif
	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
		r = -EINVAL;
		if (!kvm_x86_ops.vm_copy_enc_context_from)
			break;

		r = static_call(kvm_x86_vm_copy_enc_context_from)(kvm, cap->args[0]);
		break;
	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
		r = -EINVAL;
		if (!kvm_x86_ops.vm_move_enc_context_from)
			break;

		r = static_call(kvm_x86_vm_move_enc_context_from)(kvm, cap->args[0]);
		break;
	case KVM_CAP_EXIT_HYPERCALL:
		if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) {
			r = -EINVAL;
			break;
		}
		kvm->arch.hypercall_exit_enabled = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
		r = -EINVAL;
		if (cap->args[0] & ~1)
			break;
		kvm->arch.exit_on_emulation_error = cap->args[0];
		r = 0;
		break;
	case KVM_CAP_PMU_CAPABILITY:
		r = -EINVAL;
		if (!enable_pmu || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK))
			break;

		mutex_lock(&kvm->lock);
		if (!kvm->created_vcpus) {
			kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE);
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_CAP_MAX_VCPU_ID:
		r = -EINVAL;
		if (cap->args[0] > KVM_MAX_VCPU_IDS)
			break;

		mutex_lock(&kvm->lock);
		if (kvm->arch.max_vcpu_ids == cap->args[0]) {
			r = 0;
		} else if (!kvm->arch.max_vcpu_ids) {
			kvm->arch.max_vcpu_ids = cap->args[0];
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_CAP_X86_NOTIFY_VMEXIT:
		r = -EINVAL;
		if ((u32)cap->args[0] & ~KVM_X86_NOTIFY_VMEXIT_VALID_BITS)
			break;
		if (!kvm_caps.has_notify_vmexit)
			break;
		if (!((u32)cap->args[0] & KVM_X86_NOTIFY_VMEXIT_ENABLED))
			break;
		mutex_lock(&kvm->lock);
		if (!kvm->created_vcpus) {
			kvm->arch.notify_window = cap->args[0] >> 32;
			kvm->arch.notify_vmexit_flags = (u32)cap->args[0];
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
		r = -EINVAL;

		/*
		 * Since the risk of disabling NX hugepages is a guest crashing
		 * the system, ensure the userspace process has permission to
		 * reboot the system.
		 *
		 * Note that unlike the reboot() syscall, the process must have
		 * this capability in the root namespace because exposing
		 * /dev/kvm into a container does not limit the scope of the
		 * iTLB multihit bug to that container. In other words,
		 * this must use capable(), not ns_capable().
		 */
		if (!capable(CAP_SYS_BOOT)) {
			r = -EPERM;
			break;
		}

		if (cap->args[0])
			break;

		mutex_lock(&kvm->lock);
		if (!kvm->created_vcpus) {
			kvm->arch.disable_nx_huge_pages = true;
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow)
{
	struct kvm_x86_msr_filter *msr_filter;

	msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT);
	if (!msr_filter)
		return NULL;

	msr_filter->default_allow = default_allow;
	return msr_filter;
}

static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
{
	u32 i;

	if (!msr_filter)
		return;

	for (i = 0; i < msr_filter->count; i++)
		kfree(msr_filter->ranges[i].bitmap);

	kfree(msr_filter);
}

static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
			      struct kvm_msr_filter_range *user_range)
{
	unsigned long *bitmap = NULL;
	size_t bitmap_size;

	if (!user_range->nmsrs)
		return 0;

	if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK)
		return -EINVAL;

	if (!user_range->flags)
		return -EINVAL;

	bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long);
	if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE)
		return -EINVAL;

	bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size);
	if (IS_ERR(bitmap))
		return PTR_ERR(bitmap);

	msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) {
		.flags = user_range->flags,
		.base = user_range->base,
		.nmsrs = user_range->nmsrs,
		.bitmap = bitmap,
	};

	msr_filter->count++;
	return 0;
}

static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
				       struct kvm_msr_filter *filter)
{
	struct kvm_x86_msr_filter *new_filter, *old_filter;
	bool default_allow;
	bool empty = true;
	int r = 0;
	u32 i;

	if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK)
		return -EINVAL;

	for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
		empty &= !filter->ranges[i].nmsrs;

	default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY);
	if (empty && !default_allow)
		return -EINVAL;

	new_filter = kvm_alloc_msr_filter(default_allow);
	if (!new_filter)
		return -ENOMEM;

	for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) {
		r = kvm_add_msr_filter(new_filter, &filter->ranges[i]);
		if (r) {
			kvm_free_msr_filter(new_filter);
			return r;
		}
	}

	mutex_lock(&kvm->lock);

	/* The per-VM filter is protected by kvm->lock... */
	old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1);

	rcu_assign_pointer(kvm->arch.msr_filter, new_filter);
	synchronize_srcu(&kvm->srcu);

	kvm_free_msr_filter(old_filter);

	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
	mutex_unlock(&kvm->lock);

	return 0;
}

#ifdef CONFIG_KVM_COMPAT
/* for KVM_X86_SET_MSR_FILTER */
struct kvm_msr_filter_range_compat {
	__u32 flags;
	__u32 nmsrs;
	__u32 base;
	__u32 bitmap;
};

struct kvm_msr_filter_compat {
	__u32 flags;
	struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES];
};

#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat)

long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
			      unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct kvm *kvm = filp->private_data;
	long r = -ENOTTY;

	switch (ioctl) {
	case KVM_X86_SET_MSR_FILTER_COMPAT: {
		struct kvm_msr_filter __user *user_msr_filter = argp;
		struct kvm_msr_filter_compat filter_compat;
		struct kvm_msr_filter filter;
		int i;

		if (copy_from_user(&filter_compat, user_msr_filter,
				   sizeof(filter_compat)))
			return -EFAULT;

		filter.flags = filter_compat.flags;
		for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
			struct kvm_msr_filter_range_compat *cr;

			cr = &filter_compat.ranges[i];
			filter.ranges[i] = (struct kvm_msr_filter_range) {
				.flags = cr->flags,
				.nmsrs = cr->nmsrs,
				.base = cr->base,
				.bitmap = (__u8 *)(ulong)cr->bitmap,
			};
		}

		r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
		break;
	}
	}

	return r;
}
#endif

#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
static int kvm_arch_suspend_notifier(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;
	int ret = 0;

	mutex_lock(&kvm->lock);
	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (!vcpu->arch.pv_time.active)
			continue;

		ret = kvm_set_guest_paused(vcpu);
		if (ret) {
			kvm_err("Failed to pause guest VCPU%d: %d\n",
				vcpu->vcpu_id, ret);
			break;
		}
	}
	mutex_unlock(&kvm->lock);

	return ret ? NOTIFY_BAD : NOTIFY_DONE;
}

int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state)
{
	switch (state) {
	case PM_HIBERNATION_PREPARE:
	case PM_SUSPEND_PREPARE:
		return kvm_arch_suspend_notifier(kvm);
	}

	return NOTIFY_DONE;
}
#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */

static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp)
{
	struct kvm_clock_data data = { 0 };

	get_kvmclock(kvm, &data);
	if (copy_to_user(argp, &data, sizeof(data)))
		return -EFAULT;

	return 0;
}

static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
{
	struct kvm_arch *ka = &kvm->arch;
	struct kvm_clock_data data;
	u64 now_raw_ns;

	if (copy_from_user(&data, argp, sizeof(data)))
		return -EFAULT;

	/*
	 * Only KVM_CLOCK_REALTIME is used, but allow passing the
	 * result of KVM_GET_CLOCK back to KVM_SET_CLOCK.
	 */
	if (data.flags & ~KVM_CLOCK_VALID_FLAGS)
		return -EINVAL;

	kvm_hv_request_tsc_page_update(kvm);
	kvm_start_pvclock_update(kvm);
	pvclock_update_vm_gtod_copy(kvm);

	/*
	 * This pairs with kvm_guest_time_update(): when masterclock is
	 * in use, we use master_kernel_ns + kvmclock_offset to set
	 * unsigned 'system_time' so if we use get_kvmclock_ns() (which
	 * is slightly ahead) here we risk going negative on unsigned
	 * 'system_time' when 'data.clock' is very small.
	 */
	if (data.flags & KVM_CLOCK_REALTIME) {
		u64 now_real_ns = ktime_get_real_ns();

		/*
		 * Avoid stepping the kvmclock backwards.
		 */
		if (now_real_ns > data.realtime)
			data.clock += now_real_ns - data.realtime;
	}

	if (ka->use_master_clock)
		now_raw_ns = ka->master_kernel_ns;
	else
		now_raw_ns = get_kvmclock_base_ns();
	ka->kvmclock_offset = data.clock - now_raw_ns;
	kvm_end_pvclock_update(kvm);
	return 0;
}

long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r = -ENOTTY;
	/*
	 * This union makes it completely explicit to gcc-3.x
	 * that these two variables' stack usage should be
	 * combined, not added together.
	 */
	union {
		struct kvm_pit_state ps;
		struct kvm_pit_state2 ps2;
		struct kvm_pit_config pit_config;
	} u;

	switch (ioctl) {
	case KVM_SET_TSS_ADDR:
		r = kvm_vm_ioctl_set_tss_addr(kvm, arg);
		break;
	case KVM_SET_IDENTITY_MAP_ADDR: {
		u64 ident_addr;

		mutex_lock(&kvm->lock);
		r = -EINVAL;
		if (kvm->created_vcpus)
			goto set_identity_unlock;
		r = -EFAULT;
		if (copy_from_user(&ident_addr, argp, sizeof(ident_addr)))
			goto set_identity_unlock;
		r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr);
set_identity_unlock:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_SET_NR_MMU_PAGES:
		r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
		break;
	case KVM_GET_NR_MMU_PAGES:
		r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
		break;
	case KVM_CREATE_IRQCHIP: {
		mutex_lock(&kvm->lock);

		r = -EEXIST;
		if (irqchip_in_kernel(kvm))
			goto create_irqchip_unlock;

		r = -EINVAL;
		if (kvm->created_vcpus)
			goto create_irqchip_unlock;

		r = kvm_pic_init(kvm);
		if (r)
			goto create_irqchip_unlock;

		r = kvm_ioapic_init(kvm);
		if (r) {
			kvm_pic_destroy(kvm);
			goto create_irqchip_unlock;
		}

		r = kvm_setup_default_irq_routing(kvm);
		if (r) {
			kvm_ioapic_destroy(kvm);
			kvm_pic_destroy(kvm);
			goto create_irqchip_unlock;
		}
		/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
		smp_wmb();
		kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT);
	create_irqchip_unlock:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_CREATE_PIT:
		u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY;
		goto create_pit;
	case KVM_CREATE_PIT2:
		r = -EFAULT;
		if (copy_from_user(&u.pit_config, argp,
				   sizeof(struct kvm_pit_config)))
			goto out;
	create_pit:
		mutex_lock(&kvm->lock);
		r = -EEXIST;
		if (kvm->arch.vpit)
			goto create_pit_unlock;
		r = -ENOMEM;
		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
		if (kvm->arch.vpit)
			r = 0;
	create_pit_unlock:
		mutex_unlock(&kvm->lock);
		break;
	case KVM_GET_IRQCHIP: {
		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
		struct kvm_irqchip *chip;

		chip = memdup_user(argp, sizeof(*chip));
		if (IS_ERR(chip)) {
			r = PTR_ERR(chip);
			goto out;
		}

		r = -ENXIO;
		if (!irqchip_kernel(kvm))
			goto get_irqchip_out;
		r = kvm_vm_ioctl_get_irqchip(kvm, chip);
		if (r)
			goto get_irqchip_out;
		r = -EFAULT;
		if (copy_to_user(argp, chip, sizeof(*chip)))
			goto get_irqchip_out;
		r = 0;
	get_irqchip_out:
		kfree(chip);
		break;
	}
	case KVM_SET_IRQCHIP: {
		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
		struct kvm_irqchip *chip;

		chip = memdup_user(argp, sizeof(*chip));
		if (IS_ERR(chip)) {
			r = PTR_ERR(chip);
			goto out;
		}

		r = -ENXIO;
		if (!irqchip_kernel(kvm))
			goto set_irqchip_out;
		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
	set_irqchip_out:
		kfree(chip);
		break;
	}
	case KVM_GET_PIT: {
		r = -EFAULT;
		if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state)))
			goto out;
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto out;
		r = kvm_vm_ioctl_get_pit(kvm, &u.ps);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_PIT: {
		r = -EFAULT;
		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
			goto out;
		mutex_lock(&kvm->lock);
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto set_pit_out;
		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
set_pit_out:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_GET_PIT2: {
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto out;
		r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &u.ps2, sizeof(u.ps2)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_PIT2: {
		r = -EFAULT;
		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
			goto out;
		mutex_lock(&kvm->lock);
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto set_pit2_out;
		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
set_pit2_out:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_REINJECT_CONTROL: {
		struct kvm_reinject_control control;
		r =  -EFAULT;
		if (copy_from_user(&control, argp, sizeof(control)))
			goto out;
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto out;
		r = kvm_vm_ioctl_reinject(kvm, &control);
		break;
	}
	case KVM_SET_BOOT_CPU_ID:
		r = 0;
		mutex_lock(&kvm->lock);
		if (kvm->created_vcpus)
			r = -EBUSY;
		else
			kvm->arch.bsp_vcpu_id = arg;
		mutex_unlock(&kvm->lock);
		break;
#ifdef CONFIG_KVM_XEN
	case KVM_XEN_HVM_CONFIG: {
		struct kvm_xen_hvm_config xhc;
		r = -EFAULT;
		if (copy_from_user(&xhc, argp, sizeof(xhc)))
			goto out;
		r = kvm_xen_hvm_config(kvm, &xhc);
		break;
	}
	case KVM_XEN_HVM_GET_ATTR: {
		struct kvm_xen_hvm_attr xha;

		r = -EFAULT;
		if (copy_from_user(&xha, argp, sizeof(xha)))
			goto out;
		r = kvm_xen_hvm_get_attr(kvm, &xha);
		if (!r && copy_to_user(argp, &xha, sizeof(xha)))
			r = -EFAULT;
		break;
	}
	case KVM_XEN_HVM_SET_ATTR: {
		struct kvm_xen_hvm_attr xha;

		r = -EFAULT;
		if (copy_from_user(&xha, argp, sizeof(xha)))
			goto out;
		r = kvm_xen_hvm_set_attr(kvm, &xha);
		break;
	}
	case KVM_XEN_HVM_EVTCHN_SEND: {
		struct kvm_irq_routing_xen_evtchn uxe;

		r = -EFAULT;
		if (copy_from_user(&uxe, argp, sizeof(uxe)))
			goto out;
		r = kvm_xen_hvm_evtchn_send(kvm, &uxe);
		break;
	}
#endif
	case KVM_SET_CLOCK:
		r = kvm_vm_ioctl_set_clock(kvm, argp);
		break;
	case KVM_GET_CLOCK:
		r = kvm_vm_ioctl_get_clock(kvm, argp);
		break;
	case KVM_SET_TSC_KHZ: {
		u32 user_tsc_khz;

		r = -EINVAL;
		user_tsc_khz = (u32)arg;

		if (kvm_caps.has_tsc_control &&
		    user_tsc_khz >= kvm_caps.max_guest_tsc_khz)
			goto out;

		if (user_tsc_khz == 0)
			user_tsc_khz = tsc_khz;

		WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
		r = 0;

		goto out;
	}
	case KVM_GET_TSC_KHZ: {
		r = READ_ONCE(kvm->arch.default_tsc_khz);
		goto out;
	}
	case KVM_MEMORY_ENCRYPT_OP: {
		r = -ENOTTY;
		if (!kvm_x86_ops.mem_enc_ioctl)
			goto out;

		r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp);
		break;
	}
	case KVM_MEMORY_ENCRYPT_REG_REGION: {
		struct kvm_enc_region region;

		r = -EFAULT;
		if (copy_from_user(&region, argp, sizeof(region)))
			goto out;

		r = -ENOTTY;
		if (!kvm_x86_ops.mem_enc_register_region)
			goto out;

		r = static_call(kvm_x86_mem_enc_register_region)(kvm, &region);
		break;
	}
	case KVM_MEMORY_ENCRYPT_UNREG_REGION: {
		struct kvm_enc_region region;

		r = -EFAULT;
		if (copy_from_user(&region, argp, sizeof(region)))
			goto out;

		r = -ENOTTY;
		if (!kvm_x86_ops.mem_enc_unregister_region)
			goto out;

		r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, &region);
		break;
	}
	case KVM_HYPERV_EVENTFD: {
		struct kvm_hyperv_eventfd hvevfd;

		r = -EFAULT;
		if (copy_from_user(&hvevfd, argp, sizeof(hvevfd)))
			goto out;
		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
		break;
	}
	case KVM_SET_PMU_EVENT_FILTER:
		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
		break;
	case KVM_X86_SET_MSR_FILTER: {
		struct kvm_msr_filter __user *user_msr_filter = argp;
		struct kvm_msr_filter filter;

		if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
			return -EFAULT;

		r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
		break;
	}
	default:
		r = -ENOTTY;
	}
out:
	return r;
}

static void kvm_init_msr_list(void)
{
	u32 dummy[2];
	unsigned i;

	BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3,
			 "Please update the fixed PMCs in msrs_to_saved_all[]");

	num_msrs_to_save = 0;
	num_emulated_msrs = 0;
	num_msr_based_features = 0;

	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
			continue;

		/*
		 * Even MSRs that are valid in the host may not be exposed
		 * to the guests in some cases.
		 */
		switch (msrs_to_save_all[i]) {
		case MSR_IA32_BNDCFGS:
			if (!kvm_mpx_supported())
				continue;
			break;
		case MSR_TSC_AUX:
			if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) &&
			    !kvm_cpu_cap_has(X86_FEATURE_RDPID))
				continue;
			break;
		case MSR_IA32_UMWAIT_CONTROL:
			if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG))
				continue;
			break;
		case MSR_IA32_RTIT_CTL:
		case MSR_IA32_RTIT_STATUS:
			if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT))
				continue;
			break;
		case MSR_IA32_RTIT_CR3_MATCH:
			if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) ||
			    !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering))
				continue;
			break;
		case MSR_IA32_RTIT_OUTPUT_BASE:
		case MSR_IA32_RTIT_OUTPUT_MASK:
			if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) ||
				(!intel_pt_validate_hw_cap(PT_CAP_topa_output) &&
				 !intel_pt_validate_hw_cap(PT_CAP_single_range_output)))
				continue;
			break;
		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
			if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) ||
				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
				continue;
			break;
		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX:
			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
			    min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
				continue;
			break;
		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX:
			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
			    min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
				continue;
			break;
		case MSR_IA32_XFD:
		case MSR_IA32_XFD_ERR:
			if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
				continue;
			break;
		default:
			break;
		}

		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
	}

	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
		if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i]))
			continue;

		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
	}

	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
		struct kvm_msr_entry msr;

		msr.index = msr_based_features_all[i];
		if (kvm_get_msr_feature(&msr))
			continue;

		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
	}
}

static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
			   const void *v)
{
	int handled = 0;
	int n;

	do {
		n = min(len, 8);
		if (!(lapic_in_kernel(vcpu) &&
		      !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
		    && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
			break;
		handled += n;
		addr += n;
		len -= n;
		v += n;
	} while (len);

	return handled;
}

static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
{
	int handled = 0;
	int n;

	do {
		n = min(len, 8);
		if (!(lapic_in_kernel(vcpu) &&
		      !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
					 addr, n, v))
		    && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
			break;
		trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v);
		handled += n;
		addr += n;
		len -= n;
		v += n;
	} while (len);

	return handled;
}

void kvm_set_segment(struct kvm_vcpu *vcpu,
		     struct kvm_segment *var, int seg)
{
	static_call(kvm_x86_set_segment)(vcpu, var, seg);
}

void kvm_get_segment(struct kvm_vcpu *vcpu,
		     struct kvm_segment *var, int seg)
{
	static_call(kvm_x86_get_segment)(vcpu, var, seg);
}

gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access,
			   struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.mmu;
	gpa_t t_gpa;

	BUG_ON(!mmu_is_nested(vcpu));

	/* NPT walks are always user-walks */
	access |= PFERR_USER_MASK;
	t_gpa  = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception);

	return t_gpa;
}

gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
			      struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
	return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);

gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
			       struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
	access |= PFERR_WRITE_MASK;
	return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write);

/* uses this to access any guest's mapped memory without checking CPL */
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
				struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception);
}

static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
				      struct kvm_vcpu *vcpu, u64 access,
				      struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	void *data = val;
	int r = X86EMUL_CONTINUE;

	while (bytes) {
		gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception);
		unsigned offset = addr & (PAGE_SIZE-1);
		unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
		int ret;

		if (gpa == INVALID_GPA)
			return X86EMUL_PROPAGATE_FAULT;
		ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data,
					       offset, toread);
		if (ret < 0) {
			r = X86EMUL_IO_NEEDED;
			goto out;
		}

		bytes -= toread;
		data += toread;
		addr += toread;
	}
out:
	return r;
}

/* used for instruction fetching */
static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
				gva_t addr, void *val, unsigned int bytes,
				struct x86_exception *exception)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
	unsigned offset;
	int ret;

	/* Inline kvm_read_guest_virt_helper for speed.  */
	gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK,
				    exception);
	if (unlikely(gpa == INVALID_GPA))
		return X86EMUL_PROPAGATE_FAULT;

	offset = addr & (PAGE_SIZE-1);
	if (WARN_ON(offset + bytes > PAGE_SIZE))
		bytes = (unsigned)PAGE_SIZE - offset;
	ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val,
				       offset, bytes);
	if (unlikely(ret < 0))
		return X86EMUL_IO_NEEDED;

	return X86EMUL_CONTINUE;
}

int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
			       gva_t addr, void *val, unsigned int bytes,
			       struct x86_exception *exception)
{
	u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;

	/*
	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
	 * is returned, but our callers are not ready for that and they blindly
	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
	 * uninitialized kernel stack memory into cr2 and error code.
	 */
	memset(exception, 0, sizeof(*exception));
	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
					  exception);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_virt);

static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
			     gva_t addr, void *val, unsigned int bytes,
			     struct x86_exception *exception, bool system)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	u64 access = 0;

	if (system)
		access |= PFERR_IMPLICIT_ACCESS;
	else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
		access |= PFERR_USER_MASK;

	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
}

static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
				      struct kvm_vcpu *vcpu, u64 access,
				      struct x86_exception *exception)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	void *data = val;
	int r = X86EMUL_CONTINUE;

	while (bytes) {
		gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception);
		unsigned offset = addr & (PAGE_SIZE-1);
		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
		int ret;

		if (gpa == INVALID_GPA)
			return X86EMUL_PROPAGATE_FAULT;
		ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite);
		if (ret < 0) {
			r = X86EMUL_IO_NEEDED;
			goto out;
		}

		bytes -= towrite;
		data += towrite;
		addr += towrite;
	}
out:
	return r;
}

static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val,
			      unsigned int bytes, struct x86_exception *exception,
			      bool system)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	u64 access = PFERR_WRITE_MASK;

	if (system)
		access |= PFERR_IMPLICIT_ACCESS;
	else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
		access |= PFERR_USER_MASK;

	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
					   access, exception);
}

int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
				unsigned int bytes, struct x86_exception *exception)
{
	/* kvm_write_guest_virt_system can pull in tons of pages. */
	vcpu->arch.l1tf_flush_l1d = true;

	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
					   PFERR_WRITE_MASK, exception);
}
EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);

static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type,
				void *insn, int insn_len)
{
	return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type,
							    insn, insn_len);
}

int handle_ud(struct kvm_vcpu *vcpu)
{
	static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX };
	int fep_flags = READ_ONCE(force_emulation_prefix);
	int emul_type = EMULTYPE_TRAP_UD;
	char sig[5]; /* ud2; .ascii "kvm" */
	struct x86_exception e;

	if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0)))
		return 1;

	if (fep_flags &&
	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
				sig, sizeof(sig), &e) == 0 &&
	    memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) {
		if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF)
			kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF);
		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
		emul_type = EMULTYPE_TRAP_UD_FORCED;
	}

	return kvm_emulate_instruction(vcpu, emul_type);
}
EXPORT_SYMBOL_GPL(handle_ud);

static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
			    gpa_t gpa, bool write)
{
	/* For APIC access vmexit */
	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
		return 1;

	if (vcpu_match_mmio_gpa(vcpu, gpa)) {
		trace_vcpu_match_mmio(gva, gpa, write, true);
		return 1;
	}

	return 0;
}

static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
				gpa_t *gpa, struct x86_exception *exception,
				bool write)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0)
		| (write ? PFERR_WRITE_MASK : 0);

	/*
	 * currently PKRU is only applied to ept enabled guest so
	 * there is no pkey in EPT page table for L1 guest or EPT
	 * shadow page table for L2 guest.
	 */
	if (vcpu_match_mmio_gva(vcpu, gva) && (!is_paging(vcpu) ||
	    !permission_fault(vcpu, vcpu->arch.walk_mmu,
			      vcpu->arch.mmio_access, 0, access))) {
		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
					(gva & (PAGE_SIZE - 1));
		trace_vcpu_match_mmio(gva, *gpa, write, false);
		return 1;
	}

	*gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);

	if (*gpa == INVALID_GPA)
		return -1;

	return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write);
}

int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
			const void *val, int bytes)
{
	int ret;

	ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
	if (ret < 0)
		return 0;
	kvm_page_track_write(vcpu, gpa, val, bytes);
	return 1;
}

struct read_write_emulator_ops {
	int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val,
				  int bytes);
	int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa,
				  void *val, int bytes);
	int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa,
			       int bytes, void *val);
	int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa,
				    void *val, int bytes);
	bool write;
};

static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
{
	if (vcpu->mmio_read_completed) {
		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
			       vcpu->mmio_fragments[0].gpa, val);
		vcpu->mmio_read_completed = 0;
		return 1;
	}

	return 0;
}

static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
			void *val, int bytes)
{
	return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes);
}

static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
			 void *val, int bytes)
{
	return emulator_write_phys(vcpu, gpa, val, bytes);
}

static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
{
	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val);
	return vcpu_mmio_write(vcpu, gpa, bytes, val);
}

static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
			  void *val, int bytes)
{
	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL);
	return X86EMUL_IO_NEEDED;
}

static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
			   void *val, int bytes)
{
	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];

	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
	return X86EMUL_CONTINUE;
}

static const struct read_write_emulator_ops read_emultor = {
	.read_write_prepare = read_prepare,
	.read_write_emulate = read_emulate,
	.read_write_mmio = vcpu_mmio_read,
	.read_write_exit_mmio = read_exit_mmio,
};

static const struct read_write_emulator_ops write_emultor = {
	.read_write_emulate = write_emulate,
	.read_write_mmio = write_mmio,
	.read_write_exit_mmio = write_exit_mmio,
	.write = true,
};

static int emulator_read_write_onepage(unsigned long addr, void *val,
				       unsigned int bytes,
				       struct x86_exception *exception,
				       struct kvm_vcpu *vcpu,
				       const struct read_write_emulator_ops *ops)
{
	gpa_t gpa;
	int handled, ret;
	bool write = ops->write;
	struct kvm_mmio_fragment *frag;
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;

	/*
	 * If the exit was due to a NPF we may already have a GPA.
	 * If the GPA is present, use it to avoid the GVA to GPA table walk.
	 * Note, this cannot be used on string operations since string
	 * operation using rep will only have the initial GPA from the NPF
	 * occurred.
	 */
	if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) &&
	    (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) {
		gpa = ctxt->gpa_val;
		ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write);
	} else {
		ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
		if (ret < 0)
			return X86EMUL_PROPAGATE_FAULT;
	}

	if (!ret && ops->read_write_emulate(vcpu, gpa, val, bytes))
		return X86EMUL_CONTINUE;

	/*
	 * Is this MMIO handled locally?
	 */
	handled = ops->read_write_mmio(vcpu, gpa, bytes, val);
	if (handled == bytes)
		return X86EMUL_CONTINUE;

	gpa += handled;
	bytes -= handled;
	val += handled;

	WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
	frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
	frag->gpa = gpa;
	frag->data = val;
	frag->len = bytes;
	return X86EMUL_CONTINUE;
}

static int emulator_read_write(struct x86_emulate_ctxt *ctxt,
			unsigned long addr,
			void *val, unsigned int bytes,
			struct x86_exception *exception,
			const struct read_write_emulator_ops *ops)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	gpa_t gpa;
	int rc;

	if (ops->read_write_prepare &&
		  ops->read_write_prepare(vcpu, val, bytes))
		return X86EMUL_CONTINUE;

	vcpu->mmio_nr_fragments = 0;

	/* Crossing a page boundary? */
	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
		int now;

		now = -addr & ~PAGE_MASK;
		rc = emulator_read_write_onepage(addr, val, now, exception,
						 vcpu, ops);

		if (rc != X86EMUL_CONTINUE)
			return rc;
		addr += now;
		if (ctxt->mode != X86EMUL_MODE_PROT64)
			addr = (u32)addr;
		val += now;
		bytes -= now;
	}

	rc = emulator_read_write_onepage(addr, val, bytes, exception,
					 vcpu, ops);
	if (rc != X86EMUL_CONTINUE)
		return rc;

	if (!vcpu->mmio_nr_fragments)
		return rc;

	gpa = vcpu->mmio_fragments[0].gpa;

	vcpu->mmio_needed = 1;
	vcpu->mmio_cur_fragment = 0;

	vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
	vcpu->run->exit_reason = KVM_EXIT_MMIO;
	vcpu->run->mmio.phys_addr = gpa;

	return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
}

static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
				  unsigned long addr,
				  void *val,
				  unsigned int bytes,
				  struct x86_exception *exception)
{
	return emulator_read_write(ctxt, addr, val, bytes,
				   exception, &read_emultor);
}

static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
			    unsigned long addr,
			    const void *val,
			    unsigned int bytes,
			    struct x86_exception *exception)
{
	return emulator_read_write(ctxt, addr, (void *)val, bytes,
				   exception, &write_emultor);
}

#define emulator_try_cmpxchg_user(t, ptr, old, new) \
	(__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t))

static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
				     unsigned long addr,
				     const void *old,
				     const void *new,
				     unsigned int bytes,
				     struct x86_exception *exception)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	u64 page_line_mask;
	unsigned long hva;
	gpa_t gpa;
	int r;

	/* guests cmpxchg8b have to be emulated atomically */
	if (bytes > 8 || (bytes & (bytes - 1)))
		goto emul_write;

	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);

	if (gpa == INVALID_GPA ||
	    (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
		goto emul_write;

	/*
	 * Emulate the atomic as a straight write to avoid #AC if SLD is
	 * enabled in the host and the access splits a cache line.
	 */
	if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
		page_line_mask = ~(cache_line_size() - 1);
	else
		page_line_mask = PAGE_MASK;

	if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask))
		goto emul_write;

	hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa));
	if (kvm_is_error_hva(hva))
		goto emul_write;

	hva += offset_in_page(gpa);

	switch (bytes) {
	case 1:
		r = emulator_try_cmpxchg_user(u8, hva, old, new);
		break;
	case 2:
		r = emulator_try_cmpxchg_user(u16, hva, old, new);
		break;
	case 4:
		r = emulator_try_cmpxchg_user(u32, hva, old, new);
		break;
	case 8:
		r = emulator_try_cmpxchg_user(u64, hva, old, new);
		break;
	default:
		BUG();
	}

	if (r < 0)
		return X86EMUL_UNHANDLEABLE;
	if (r)
		return X86EMUL_CMPXCHG_FAILED;

	kvm_page_track_write(vcpu, gpa, new, bytes);

	return X86EMUL_CONTINUE;

emul_write:
	printk_once(KERN_WARNING "kvm: emulating exchange as write\n");

	return emulator_write_emulated(ctxt, addr, new, bytes, exception);
}

static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
			       unsigned short port, void *data,
			       unsigned int count, bool in)
{
	unsigned i;
	int r;

	WARN_ON_ONCE(vcpu->arch.pio.count);
	for (i = 0; i < count; i++) {
		if (in)
			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, port, size, data);
		else
			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, port, size, data);

		if (r) {
			if (i == 0)
				goto userspace_io;

			/*
			 * Userspace must have unregistered the device while PIO
			 * was running.  Drop writes / read as 0.
			 */
			if (in)
				memset(data, 0, size * (count - i));
			break;
		}

		data += size;
	}
	return 1;

userspace_io:
	vcpu->arch.pio.port = port;
	vcpu->arch.pio.in = in;
	vcpu->arch.pio.count = count;
	vcpu->arch.pio.size = size;

	if (in)
		memset(vcpu->arch.pio_data, 0, size * count);
	else
		memcpy(vcpu->arch.pio_data, data, size * count);

	vcpu->run->exit_reason = KVM_EXIT_IO;
	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
	vcpu->run->io.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = count;
	vcpu->run->io.port = port;
	return 0;
}

static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
      			   unsigned short port, void *val, unsigned int count)
{
	int r = emulator_pio_in_out(vcpu, size, port, val, count, true);
	if (r)
		trace_kvm_pio(KVM_PIO_IN, port, size, count, val);

	return r;
}

static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
{
	int size = vcpu->arch.pio.size;
	unsigned int count = vcpu->arch.pio.count;
	memcpy(val, vcpu->arch.pio_data, size * count);
	trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
	vcpu->arch.pio.count = 0;
}

static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
				    int size, unsigned short port, void *val,
				    unsigned int count)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	if (vcpu->arch.pio.count) {
		/*
		 * Complete a previous iteration that required userspace I/O.
		 * Note, @count isn't guaranteed to match pio.count as userspace
		 * can modify ECX before rerunning the vCPU.  Ignore any such
		 * shenanigans as KVM doesn't support modifying the rep count,
		 * and the emulator ensures @count doesn't overflow the buffer.
		 */
		complete_emulator_pio_in(vcpu, val);
		return 1;
	}

	return emulator_pio_in(vcpu, size, port, val, count);
}

static int emulator_pio_out(struct kvm_vcpu *vcpu, int size,
			    unsigned short port, const void *val,
			    unsigned int count)
{
	trace_kvm_pio(KVM_PIO_OUT, port, size, count, val);
	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
}

static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
				     int size, unsigned short port,
				     const void *val, unsigned int count)
{
	return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count);
}

static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
	return static_call(kvm_x86_get_segment_base)(vcpu, seg);
}

static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address)
{
	kvm_mmu_invlpg(emul_to_vcpu(ctxt), address);
}

static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
{
	if (!need_emulate_wbinvd(vcpu))
		return X86EMUL_CONTINUE;

	if (static_call(kvm_x86_has_wbinvd_exit)()) {
		int cpu = get_cpu();

		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
		on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
				wbinvd_ipi, NULL, 1);
		put_cpu();
		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
	} else
		wbinvd();
	return X86EMUL_CONTINUE;
}

int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
{
	kvm_emulate_wbinvd_noskip(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);



static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt)
{
	kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt));
}

static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
			    unsigned long *dest)
{
	kvm_get_dr(emul_to_vcpu(ctxt), dr, dest);
}

static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
			   unsigned long value)
{

	return kvm_set_dr(emul_to_vcpu(ctxt), dr, value);
}

static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
}

static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	unsigned long value;

	switch (cr) {
	case 0:
		value = kvm_read_cr0(vcpu);
		break;
	case 2:
		value = vcpu->arch.cr2;
		break;
	case 3:
		value = kvm_read_cr3(vcpu);
		break;
	case 4:
		value = kvm_read_cr4(vcpu);
		break;
	case 8:
		value = kvm_get_cr8(vcpu);
		break;
	default:
		kvm_err("%s: unexpected cr %u\n", __func__, cr);
		return 0;
	}

	return value;
}

static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	int res = 0;

	switch (cr) {
	case 0:
		res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
		break;
	case 2:
		vcpu->arch.cr2 = val;
		break;
	case 3:
		res = kvm_set_cr3(vcpu, val);
		break;
	case 4:
		res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
		break;
	case 8:
		res = kvm_set_cr8(vcpu, val);
		break;
	default:
		kvm_err("%s: unexpected cr %u\n", __func__, cr);
		res = -1;
	}

	return res;
}

static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
{
	return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt));
}

static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
	static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt);
}

static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
	static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt);
}

static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
	static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt);
}

static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
	static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt);
}

static unsigned long emulator_get_cached_segment_base(
	struct x86_emulate_ctxt *ctxt, int seg)
{
	return get_segment_base(emul_to_vcpu(ctxt), seg);
}

static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
				 struct desc_struct *desc, u32 *base3,
				 int seg)
{
	struct kvm_segment var;

	kvm_get_segment(emul_to_vcpu(ctxt), &var, seg);
	*selector = var.selector;

	if (var.unusable) {
		memset(desc, 0, sizeof(*desc));
		if (base3)
			*base3 = 0;
		return false;
	}

	if (var.g)
		var.limit >>= 12;
	set_desc_limit(desc, var.limit);
	set_desc_base(desc, (unsigned long)var.base);
#ifdef CONFIG_X86_64
	if (base3)
		*base3 = var.base >> 32;
#endif
	desc->type = var.type;
	desc->s = var.s;
	desc->dpl = var.dpl;
	desc->p = var.present;
	desc->avl = var.avl;
	desc->l = var.l;
	desc->d = var.db;
	desc->g = var.g;

	return true;
}

static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
				 struct desc_struct *desc, u32 base3,
				 int seg)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	struct kvm_segment var;

	var.selector = selector;
	var.base = get_desc_base(desc);
#ifdef CONFIG_X86_64
	var.base |= ((u64)base3) << 32;
#endif
	var.limit = get_desc_limit(desc);
	if (desc->g)
		var.limit = (var.limit << 12) | 0xfff;
	var.type = desc->type;
	var.dpl = desc->dpl;
	var.db = desc->d;
	var.s = desc->s;
	var.l = desc->l;
	var.g = desc->g;
	var.avl = desc->avl;
	var.present = desc->p;
	var.unusable = !var.present;
	var.padding = 0;

	kvm_set_segment(vcpu, &var, seg);
	return;
}

static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt,
					u32 msr_index, u64 *pdata)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	int r;

	r = kvm_get_msr_with_filter(vcpu, msr_index, pdata);
	if (r < 0)
		return X86EMUL_UNHANDLEABLE;

	if (r) {
		if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0,
				       complete_emulated_rdmsr, r))
			return X86EMUL_IO_NEEDED;

		trace_kvm_msr_read_ex(msr_index);
		return X86EMUL_PROPAGATE_FAULT;
	}

	trace_kvm_msr_read(msr_index, *pdata);
	return X86EMUL_CONTINUE;
}

static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
					u32 msr_index, u64 data)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	int r;

	r = kvm_set_msr_with_filter(vcpu, msr_index, data);
	if (r < 0)
		return X86EMUL_UNHANDLEABLE;

	if (r) {
		if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data,
				       complete_emulated_msr_access, r))
			return X86EMUL_IO_NEEDED;

		trace_kvm_msr_write_ex(msr_index, data);
		return X86EMUL_PROPAGATE_FAULT;
	}

	trace_kvm_msr_write(msr_index, data);
	return X86EMUL_CONTINUE;
}

static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
			    u32 msr_index, u64 *pdata)
{
	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
}

static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
			      u32 pmc)
{
	if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc))
		return 0;
	return -EINVAL;
}

static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
			     u32 pmc, u64 *pdata)
{
	return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata);
}

static void emulator_halt(struct x86_emulate_ctxt *ctxt)
{
	emul_to_vcpu(ctxt)->arch.halt_request = 1;
}

static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
			      struct x86_instruction_info *info,
			      enum x86_intercept_stage stage)
{
	return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage,
					    &ctxt->exception);
}

static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
			      u32 *eax, u32 *ebx, u32 *ecx, u32 *edx,
			      bool exact_only)
{
	return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only);
}

static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt)
{
	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM);
}

static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt)
{
	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE);
}

static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt)
{
	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR);
}

static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt)
{
	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID);
}

static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
{
	return kvm_register_read_raw(emul_to_vcpu(ctxt), reg);
}

static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val)
{
	kvm_register_write_raw(emul_to_vcpu(ctxt), reg, val);
}

static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
{
	static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked);
}

static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
{
	return emul_to_vcpu(ctxt)->arch.hflags;
}

#ifndef CONFIG_KVM_SMM
static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
{
	WARN_ON_ONCE(1);
	return X86EMUL_UNHANDLEABLE;
}
#endif

static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
{
	kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt));
}

static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr)
{
	return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr);
}

static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt)
{
	struct kvm *kvm = emul_to_vcpu(ctxt)->kvm;

	if (!kvm->vm_bugged)
		kvm_vm_bugged(kvm);
}

static const struct x86_emulate_ops emulate_ops = {
	.vm_bugged           = emulator_vm_bugged,
	.read_gpr            = emulator_read_gpr,
	.write_gpr           = emulator_write_gpr,
	.read_std            = emulator_read_std,
	.write_std           = emulator_write_std,
	.fetch               = kvm_fetch_guest_virt,
	.read_emulated       = emulator_read_emulated,
	.write_emulated      = emulator_write_emulated,
	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
	.invlpg              = emulator_invlpg,
	.pio_in_emulated     = emulator_pio_in_emulated,
	.pio_out_emulated    = emulator_pio_out_emulated,
	.get_segment         = emulator_get_segment,
	.set_segment         = emulator_set_segment,
	.get_cached_segment_base = emulator_get_cached_segment_base,
	.get_gdt             = emulator_get_gdt,
	.get_idt	     = emulator_get_idt,
	.set_gdt             = emulator_set_gdt,
	.set_idt	     = emulator_set_idt,
	.get_cr              = emulator_get_cr,
	.set_cr              = emulator_set_cr,
	.cpl                 = emulator_get_cpl,
	.get_dr              = emulator_get_dr,
	.set_dr              = emulator_set_dr,
	.set_msr_with_filter = emulator_set_msr_with_filter,
	.get_msr_with_filter = emulator_get_msr_with_filter,
	.get_msr             = emulator_get_msr,
	.check_pmc	     = emulator_check_pmc,
	.read_pmc            = emulator_read_pmc,
	.halt                = emulator_halt,
	.wbinvd              = emulator_wbinvd,
	.fix_hypercall       = emulator_fix_hypercall,
	.intercept           = emulator_intercept,
	.get_cpuid           = emulator_get_cpuid,
	.guest_has_long_mode = emulator_guest_has_long_mode,
	.guest_has_movbe     = emulator_guest_has_movbe,
	.guest_has_fxsr      = emulator_guest_has_fxsr,
	.guest_has_rdpid     = emulator_guest_has_rdpid,
	.set_nmi_mask        = emulator_set_nmi_mask,
	.get_hflags          = emulator_get_hflags,
	.leave_smm           = emulator_leave_smm,
	.triple_fault        = emulator_triple_fault,
	.set_xcr             = emulator_set_xcr,
};

static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
{
	u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
	/*
	 * an sti; sti; sequence only disable interrupts for the first
	 * instruction. So, if the last instruction, be it emulated or
	 * not, left the system with the INT_STI flag enabled, it
	 * means that the last instruction is an sti. We should not
	 * leave the flag on in this case. The same goes for mov ss
	 */
	if (int_shadow & mask)
		mask = 0;
	if (unlikely(int_shadow || mask)) {
		static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask);
		if (!mask)
			kvm_make_request(KVM_REQ_EVENT, vcpu);
	}
}

static void inject_emulated_exception(struct kvm_vcpu *vcpu)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;

	if (ctxt->exception.vector == PF_VECTOR)
		kvm_inject_emulated_page_fault(vcpu, &ctxt->exception);
	else if (ctxt->exception.error_code_valid)
		kvm_queue_exception_e(vcpu, ctxt->exception.vector,
				      ctxt->exception.error_code);
	else
		kvm_queue_exception(vcpu, ctxt->exception.vector);
}

static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu)
{
	struct x86_emulate_ctxt *ctxt;

	ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT);
	if (!ctxt) {
		pr_err("kvm: failed to allocate vcpu's emulator\n");
		return NULL;
	}

	ctxt->vcpu = vcpu;
	ctxt->ops = &emulate_ops;
	vcpu->arch.emulate_ctxt = ctxt;

	return ctxt;
}

static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
	int cs_db, cs_l;

	static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);

	ctxt->gpa_available = false;
	ctxt->eflags = kvm_get_rflags(vcpu);
	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;

	ctxt->eip = kvm_rip_read(vcpu);
	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
		     (cs_l && is_long_mode(vcpu))	? X86EMUL_MODE_PROT64 :
		     cs_db				? X86EMUL_MODE_PROT32 :
							  X86EMUL_MODE_PROT16;
	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);

	ctxt->interruptibility = 0;
	ctxt->have_exception = false;
	ctxt->exception.vector = -1;
	ctxt->perm_ok = false;

	init_decode_cache(ctxt);
	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
}

void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
	int ret;

	init_emulate_ctxt(vcpu);

	ctxt->op_bytes = 2;
	ctxt->ad_bytes = 2;
	ctxt->_eip = ctxt->eip + inc_eip;
	ret = emulate_int_real(ctxt, irq);

	if (ret != X86EMUL_CONTINUE) {
		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
	} else {
		ctxt->eip = ctxt->_eip;
		kvm_rip_write(vcpu, ctxt->eip);
		kvm_set_rflags(vcpu, ctxt->eflags);
	}
}
EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);

static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data,
					   u8 ndata, u8 *insn_bytes, u8 insn_size)
{
	struct kvm_run *run = vcpu->run;
	u64 info[5];
	u8 info_start;

	/*
	 * Zero the whole array used to retrieve the exit info, as casting to
	 * u32 for select entries will leave some chunks uninitialized.
	 */
	memset(&info, 0, sizeof(info));

	static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1],
					   &info[2], (u32 *)&info[3],
					   (u32 *)&info[4]);

	run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
	run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION;

	/*
	 * There's currently space for 13 entries, but 5 are used for the exit
	 * reason and info.  Restrict to 4 to reduce the maintenance burden
	 * when expanding kvm_run.emulation_failure in the future.
	 */
	if (WARN_ON_ONCE(ndata > 4))
		ndata = 4;

	/* Always include the flags as a 'data' entry. */
	info_start = 1;
	run->emulation_failure.flags = 0;

	if (insn_size) {
		BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) +
			      sizeof(run->emulation_failure.insn_bytes) != 16));
		info_start += 2;
		run->emulation_failure.flags |=
			KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES;
		run->emulation_failure.insn_size = insn_size;
		memset(run->emulation_failure.insn_bytes, 0x90,
		       sizeof(run->emulation_failure.insn_bytes));
		memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size);
	}

	memcpy(&run->internal.data[info_start], info, sizeof(info));
	memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data,
	       ndata * sizeof(data[0]));

	run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata;
}

static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;

	prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data,
				       ctxt->fetch.end - ctxt->fetch.data);
}

void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data,
					  u8 ndata)
{
	prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0);
}
EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit);

void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu)
{
	__kvm_prepare_emulation_failure_exit(vcpu, NULL, 0);
}
EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit);

static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
{
	struct kvm *kvm = vcpu->kvm;

	++vcpu->stat.insn_emulation_fail;
	trace_kvm_emulate_insn_failed(vcpu);

	if (emulation_type & EMULTYPE_VMWARE_GP) {
		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
		return 1;
	}

	if (kvm->arch.exit_on_emulation_error ||
	    (emulation_type & EMULTYPE_SKIP)) {
		prepare_emulation_ctxt_failure_exit(vcpu);
		return 0;
	}

	kvm_queue_exception(vcpu, UD_VECTOR);

	if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) {
		prepare_emulation_ctxt_failure_exit(vcpu);
		return 0;
	}

	return 1;
}

static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
				  bool write_fault_to_shadow_pgtable,
				  int emulation_type)
{
	gpa_t gpa = cr2_or_gpa;
	kvm_pfn_t pfn;

	if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF))
		return false;

	if (WARN_ON_ONCE(is_guest_mode(vcpu)) ||
	    WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))
		return false;

	if (!vcpu->arch.mmu->root_role.direct) {
		/*
		 * Write permission should be allowed since only
		 * write access need to be emulated.
		 */
		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);

		/*
		 * If the mapping is invalid in guest, let cpu retry
		 * it to generate fault.
		 */
		if (gpa == INVALID_GPA)
			return true;
	}

	/*
	 * Do not retry the unhandleable instruction if it faults on the
	 * readonly host memory, otherwise it will goto a infinite loop:
	 * retry instruction -> write #PF -> emulation fail -> retry
	 * instruction -> ...
	 */
	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));

	/*
	 * If the instruction failed on the error pfn, it can not be fixed,
	 * report the error to userspace.
	 */
	if (is_error_noslot_pfn(pfn))
		return false;

	kvm_release_pfn_clean(pfn);

	/* The instructions are well-emulated on direct mmu. */
	if (vcpu->arch.mmu->root_role.direct) {
		unsigned int indirect_shadow_pages;

		write_lock(&vcpu->kvm->mmu_lock);
		indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages;
		write_unlock(&vcpu->kvm->mmu_lock);

		if (indirect_shadow_pages)
			kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));

		return true;
	}

	/*
	 * if emulation was due to access to shadowed page table
	 * and it failed try to unshadow page and re-enter the
	 * guest to let CPU execute the instruction.
	 */
	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));

	/*
	 * If the access faults on its page table, it can not
	 * be fixed by unprotecting shadow page and it should
	 * be reported to userspace.
	 */
	return !write_fault_to_shadow_pgtable;
}

static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
			      gpa_t cr2_or_gpa,  int emulation_type)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;

	last_retry_eip = vcpu->arch.last_retry_eip;
	last_retry_addr = vcpu->arch.last_retry_addr;

	/*
	 * If the emulation is caused by #PF and it is non-page_table
	 * writing instruction, it means the VM-EXIT is caused by shadow
	 * page protected, we can zap the shadow page and retry this
	 * instruction directly.
	 *
	 * Note: if the guest uses a non-page-table modifying instruction
	 * on the PDE that points to the instruction, then we will unmap
	 * the instruction and go to an infinite loop. So, we cache the
	 * last retried eip and the last fault address, if we meet the eip
	 * and the address again, we can break out of the potential infinite
	 * loop.
	 */
	vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;

	if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF))
		return false;

	if (WARN_ON_ONCE(is_guest_mode(vcpu)) ||
	    WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))
		return false;

	if (x86_page_table_writing_insn(ctxt))
		return false;

	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
		return false;

	vcpu->arch.last_retry_eip = ctxt->eip;
	vcpu->arch.last_retry_addr = cr2_or_gpa;

	if (!vcpu->arch.mmu->root_role.direct)
		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);

	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));

	return true;
}

static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
static int complete_emulated_pio(struct kvm_vcpu *vcpu);

static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
				unsigned long *db)
{
	u32 dr6 = 0;
	int i;
	u32 enable, rwlen;

	enable = dr7;
	rwlen = dr7 >> 16;
	for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4)
		if ((enable & 3) && (rwlen & 15) == type && db[i] == addr)
			dr6 |= (1 << i);
	return dr6;
}

static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu)
{
	struct kvm_run *kvm_run = vcpu->run;

	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
		kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW;
		kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu);
		kvm_run->debug.arch.exception = DB_VECTOR;
		kvm_run->exit_reason = KVM_EXIT_DEBUG;
		return 0;
	}
	kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS);
	return 1;
}

int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
	unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
	int r;

	r = static_call(kvm_x86_skip_emulated_instruction)(vcpu);
	if (unlikely(!r))
		return 0;

	kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);

	/*
	 * rflags is the old, "raw" value of the flags.  The new value has
	 * not been saved yet.
	 *
	 * This is correct even for TF set by the guest, because "the
	 * processor will not generate this exception after the instruction
	 * that sets the TF flag".
	 */
	if (unlikely(rflags & X86_EFLAGS_TF))
		r = kvm_vcpu_do_singlestep(vcpu);
	return r;
}
EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);

static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu)
{
	u32 shadow;

	if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF)
		return true;

	/*
	 * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active,
	 * but AMD CPUs do not.  MOV/POP SS blocking is rare, check that first
	 * to avoid the relatively expensive CPUID lookup.
	 */
	shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
	return (shadow & KVM_X86_SHADOW_INT_MOV_SS) &&
	       guest_cpuid_is_intel(vcpu);
}

static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu,
					   int emulation_type, int *r)
{
	WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE);

	/*
	 * Do not check for code breakpoints if hardware has already done the
	 * checks, as inferred from the emulation type.  On NO_DECODE and SKIP,
	 * the instruction has passed all exception checks, and all intercepted
	 * exceptions that trigger emulation have lower priority than code
	 * breakpoints, i.e. the fact that the intercepted exception occurred
	 * means any code breakpoints have already been serviced.
	 *
	 * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as
	 * hardware has checked the RIP of the magic prefix, but not the RIP of
	 * the instruction being emulated.  The intent of forced emulation is
	 * to behave as if KVM intercepted the instruction without an exception
	 * and without a prefix.
	 */
	if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP |
			      EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF))
		return false;

	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
	    (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
		struct kvm_run *kvm_run = vcpu->run;
		unsigned long eip = kvm_get_linear_rip(vcpu);
		u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0,
					   vcpu->arch.guest_debug_dr7,
					   vcpu->arch.eff_db);

		if (dr6 != 0) {
			kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW;
			kvm_run->debug.arch.pc = eip;
			kvm_run->debug.arch.exception = DB_VECTOR;
			kvm_run->exit_reason = KVM_EXIT_DEBUG;
			*r = 0;
			return true;
		}
	}

	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) &&
	    !kvm_is_code_breakpoint_inhibited(vcpu)) {
		unsigned long eip = kvm_get_linear_rip(vcpu);
		u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0,
					   vcpu->arch.dr7,
					   vcpu->arch.db);

		if (dr6 != 0) {
			kvm_queue_exception_p(vcpu, DB_VECTOR, dr6);
			*r = 1;
			return true;
		}
	}

	return false;
}

static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
{
	switch (ctxt->opcode_len) {
	case 1:
		switch (ctxt->b) {
		case 0xe4:	/* IN */
		case 0xe5:
		case 0xec:
		case 0xed:
		case 0xe6:	/* OUT */
		case 0xe7:
		case 0xee:
		case 0xef:
		case 0x6c:	/* INS */
		case 0x6d:
		case 0x6e:	/* OUTS */
		case 0x6f:
			return true;
		}
		break;
	case 2:
		switch (ctxt->b) {
		case 0x33:	/* RDPMC */
			return true;
		}
		break;
	}

	return false;
}

/*
 * Decode an instruction for emulation.  The caller is responsible for handling
 * code breakpoints.  Note, manually detecting code breakpoints is unnecessary
 * (and wrong) when emulating on an intercepted fault-like exception[*], as
 * code breakpoints have higher priority and thus have already been done by
 * hardware.
 *
 * [*] Except #MC, which is higher priority, but KVM should never emulate in
 *     response to a machine check.
 */
int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
				    void *insn, int insn_len)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
	int r;

	init_emulate_ctxt(vcpu);

	r = x86_decode_insn(ctxt, insn, insn_len, emulation_type);

	trace_kvm_emulate_insn_start(vcpu);
	++vcpu->stat.insn_emulation;

	return r;
}
EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction);

int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
			    int emulation_type, void *insn, int insn_len)
{
	int r;
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
	bool writeback = true;
	bool write_fault_to_spt;

	if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len)))
		return 1;

	vcpu->arch.l1tf_flush_l1d = true;

	/*
	 * Clear write_fault_to_shadow_pgtable here to ensure it is
	 * never reused.
	 */
	write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
	vcpu->arch.write_fault_to_shadow_pgtable = false;

	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
		kvm_clear_exception_queue(vcpu);

		/*
		 * Return immediately if RIP hits a code breakpoint, such #DBs
		 * are fault-like and are higher priority than any faults on
		 * the code fetch itself.
		 */
		if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r))
			return r;

		r = x86_decode_emulated_instruction(vcpu, emulation_type,
						    insn, insn_len);
		if (r != EMULATION_OK)  {
			if ((emulation_type & EMULTYPE_TRAP_UD) ||
			    (emulation_type & EMULTYPE_TRAP_UD_FORCED)) {
				kvm_queue_exception(vcpu, UD_VECTOR);
				return 1;
			}
			if (reexecute_instruction(vcpu, cr2_or_gpa,
						  write_fault_to_spt,
						  emulation_type))
				return 1;
			if (ctxt->have_exception) {
				/*
				 * #UD should result in just EMULATION_FAILED, and trap-like
				 * exception should not be encountered during decode.
				 */
				WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR ||
					     exception_type(ctxt->exception.vector) == EXCPT_TRAP);
				inject_emulated_exception(vcpu);
				return 1;
			}
			return handle_emulation_failure(vcpu, emulation_type);
		}
	}

	if ((emulation_type & EMULTYPE_VMWARE_GP) &&
	    !is_vmware_backdoor_opcode(ctxt)) {
		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
		return 1;
	}

	/*
	 * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for
	 * use *only* by vendor callbacks for kvm_skip_emulated_instruction().
	 * The caller is responsible for updating interruptibility state and
	 * injecting single-step #DBs.
	 */
	if (emulation_type & EMULTYPE_SKIP) {
		if (ctxt->mode != X86EMUL_MODE_PROT64)
			ctxt->eip = (u32)ctxt->_eip;
		else
			ctxt->eip = ctxt->_eip;

		if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) {
			r = 1;
			goto writeback;
		}

		kvm_rip_write(vcpu, ctxt->eip);
		if (ctxt->eflags & X86_EFLAGS_RF)
			kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF);
		return 1;
	}

	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
		return 1;

	/* this is needed for vmware backdoor interface to work since it
	   changes registers values  during IO operation */
	if (vcpu->arch.emulate_regs_need_sync_from_vcpu) {
		vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
		emulator_invalidate_register_cache(ctxt);
	}

restart:
	if (emulation_type & EMULTYPE_PF) {
		/* Save the faulting GPA (cr2) in the address field */
		ctxt->exception.address = cr2_or_gpa;

		/* With shadow page tables, cr2 contains a GVA or nGPA. */
		if (vcpu->arch.mmu->root_role.direct) {
			ctxt->gpa_available = true;
			ctxt->gpa_val = cr2_or_gpa;
		}
	} else {
		/* Sanitize the address out of an abundance of paranoia. */
		ctxt->exception.address = 0;
	}

	r = x86_emulate_insn(ctxt);

	if (r == EMULATION_INTERCEPTED)
		return 1;

	if (r == EMULATION_FAILED) {
		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
					emulation_type))
			return 1;

		return handle_emulation_failure(vcpu, emulation_type);
	}

	if (ctxt->have_exception) {
		r = 1;
		inject_emulated_exception(vcpu);
	} else if (vcpu->arch.pio.count) {
		if (!vcpu->arch.pio.in) {
			/* FIXME: return into emulator if single-stepping.  */
			vcpu->arch.pio.count = 0;
		} else {
			writeback = false;
			vcpu->arch.complete_userspace_io = complete_emulated_pio;
		}
		r = 0;
	} else if (vcpu->mmio_needed) {
		++vcpu->stat.mmio_exits;

		if (!vcpu->mmio_is_write)
			writeback = false;
		r = 0;
		vcpu->arch.complete_userspace_io = complete_emulated_mmio;
	} else if (vcpu->arch.complete_userspace_io) {
		writeback = false;
		r = 0;
	} else if (r == EMULATION_RESTART)
		goto restart;
	else
		r = 1;

writeback:
	if (writeback) {
		unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
		toggle_interruptibility(vcpu, ctxt->interruptibility);
		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;

		/*
		 * Note, EXCPT_DB is assumed to be fault-like as the emulator
		 * only supports code breakpoints and general detect #DB, both
		 * of which are fault-like.
		 */
		if (!ctxt->have_exception ||
		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
			kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);
			if (ctxt->is_branch)
				kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
			kvm_rip_write(vcpu, ctxt->eip);
			if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
				r = kvm_vcpu_do_singlestep(vcpu);
			static_call_cond(kvm_x86_update_emulated_instruction)(vcpu);
			__kvm_set_rflags(vcpu, ctxt->eflags);
		}

		/*
		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
		 * do nothing, and it will be requested again as soon as
		 * the shadow expires.  But we still need to check here,
		 * because POPF has no interrupt shadow.
		 */
		if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF))
			kvm_make_request(KVM_REQ_EVENT, vcpu);
	} else
		vcpu->arch.emulate_regs_need_sync_to_vcpu = true;

	return r;
}

int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type)
{
	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
}
EXPORT_SYMBOL_GPL(kvm_emulate_instruction);

int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
					void *insn, int insn_len)
{
	return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len);
}
EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);

static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
{
	vcpu->arch.pio.count = 0;
	return 1;
}

static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
{
	vcpu->arch.pio.count = 0;

	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
		return 1;

	return kvm_skip_emulated_instruction(vcpu);
}

static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
			    unsigned short port)
{
	unsigned long val = kvm_rax_read(vcpu);
	int ret = emulator_pio_out(vcpu, size, port, &val, 1);

	if (ret)
		return ret;

	/*
	 * Workaround userspace that relies on old KVM behavior of %rip being
	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
	 */
	if (port == 0x7e &&
	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
		vcpu->arch.complete_userspace_io =
			complete_fast_pio_out_port_0x7e;
		kvm_skip_emulated_instruction(vcpu);
	} else {
		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
	}
	return 0;
}

static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
{
	unsigned long val;

	/* We should only ever be called with arch.pio.count equal to 1 */
	BUG_ON(vcpu->arch.pio.count != 1);

	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
		vcpu->arch.pio.count = 0;
		return 1;
	}

	/* For size less than 4 we merge, else we zero extend */
	val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0;

	complete_emulator_pio_in(vcpu, &val);
	kvm_rax_write(vcpu, val);

	return kvm_skip_emulated_instruction(vcpu);
}

static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
			   unsigned short port)
{
	unsigned long val;
	int ret;

	/* For size less than 4 we merge, else we zero extend */
	val = (size < 4) ? kvm_rax_read(vcpu) : 0;

	ret = emulator_pio_in(vcpu, size, port, &val, 1);
	if (ret) {
		kvm_rax_write(vcpu, val);
		return ret;
	}

	vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
	vcpu->arch.complete_userspace_io = complete_fast_pio_in;

	return 0;
}

int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in)
{
	int ret;

	if (in)
		ret = kvm_fast_pio_in(vcpu, size, port);
	else
		ret = kvm_fast_pio_out(vcpu, size, port);
	return ret && kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_fast_pio);

static int kvmclock_cpu_down_prep(unsigned int cpu)
{
	__this_cpu_write(cpu_tsc_khz, 0);
	return 0;
}

static void tsc_khz_changed(void *data)
{
	struct cpufreq_freqs *freq = data;
	unsigned long khz = 0;

	if (data)
		khz = freq->new;
	else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
		khz = cpufreq_quick_get(raw_smp_processor_id());
	if (!khz)
		khz = tsc_khz;
	__this_cpu_write(cpu_tsc_khz, khz);
}

#ifdef CONFIG_X86_64
static void kvm_hyperv_tsc_notifier(void)
{
	struct kvm *kvm;
	int cpu;

	mutex_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list)
		kvm_make_mclock_inprogress_request(kvm);

	/* no guest entries from this point */
	hyperv_stop_tsc_emulation();

	/* TSC frequency always matches when on Hyper-V */
	for_each_present_cpu(cpu)
		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
	kvm_caps.max_guest_tsc_khz = tsc_khz;

	list_for_each_entry(kvm, &vm_list, vm_list) {
		__kvm_start_pvclock_update(kvm);
		pvclock_update_vm_gtod_copy(kvm);
		kvm_end_pvclock_update(kvm);
	}

	mutex_unlock(&kvm_lock);
}
#endif

static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	int send_ipi = 0;
	unsigned long i;

	/*
	 * We allow guests to temporarily run on slowing clocks,
	 * provided we notify them after, or to run on accelerating
	 * clocks, provided we notify them before.  Thus time never
	 * goes backwards.
	 *
	 * However, we have a problem.  We can't atomically update
	 * the frequency of a given CPU from this function; it is
	 * merely a notifier, which can be called from any CPU.
	 * Changing the TSC frequency at arbitrary points in time
	 * requires a recomputation of local variables related to
	 * the TSC for each VCPU.  We must flag these local variables
	 * to be updated and be sure the update takes place with the
	 * new frequency before any guests proceed.
	 *
	 * Unfortunately, the combination of hotplug CPU and frequency
	 * change creates an intractable locking scenario; the order
	 * of when these callouts happen is undefined with respect to
	 * CPU hotplug, and they can race with each other.  As such,
	 * merely setting per_cpu(cpu_tsc_khz) = X during a hotadd is
	 * undefined; you can actually have a CPU frequency change take
	 * place in between the computation of X and the setting of the
	 * variable.  To protect against this problem, all updates of
	 * the per_cpu tsc_khz variable are done in an interrupt
	 * protected IPI, and all callers wishing to update the value
	 * must wait for a synchronous IPI to complete (which is trivial
	 * if the caller is on the CPU already).  This establishes the
	 * necessary total order on variable updates.
	 *
	 * Note that because a guest time update may take place
	 * anytime after the setting of the VCPU's request bit, the
	 * correct TSC value must be set before the request.  However,
	 * to ensure the update actually makes it to any guest which
	 * starts running in hardware virtualization between the set
	 * and the acquisition of the spinlock, we must also ping the
	 * CPU after setting the request bit.
	 *
	 */

	smp_call_function_single(cpu, tsc_khz_changed, freq, 1);

	mutex_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list) {
		kvm_for_each_vcpu(i, vcpu, kvm) {
			if (vcpu->cpu != cpu)
				continue;
			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
			if (vcpu->cpu != raw_smp_processor_id())
				send_ipi = 1;
		}
	}
	mutex_unlock(&kvm_lock);

	if (freq->old < freq->new && send_ipi) {
		/*
		 * We upscale the frequency.  Must make the guest
		 * doesn't see old kvmclock values while running with
		 * the new frequency, otherwise we risk the guest sees
		 * time go backwards.
		 *
		 * In case we update the frequency for another cpu
		 * (which might be in guest context) send an interrupt
		 * to kick the cpu out of guest context.  Next time
		 * guest context is entered kvmclock will be updated,
		 * so the guest will not see stale values.
		 */
		smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
	}
}

static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
				     void *data)
{
	struct cpufreq_freqs *freq = data;
	int cpu;

	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
		return 0;
	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
		return 0;

	for_each_cpu(cpu, freq->policy->cpus)
		__kvmclock_cpufreq_notifier(freq, cpu);

	return 0;
}

static struct notifier_block kvmclock_cpufreq_notifier_block = {
	.notifier_call  = kvmclock_cpufreq_notifier
};

static int kvmclock_cpu_online(unsigned int cpu)
{
	tsc_khz_changed(NULL);
	return 0;
}

static void kvm_timer_init(void)
{
	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
		max_tsc_khz = tsc_khz;

		if (IS_ENABLED(CONFIG_CPU_FREQ)) {
			struct cpufreq_policy *policy;
			int cpu;

			cpu = get_cpu();
			policy = cpufreq_cpu_get(cpu);
			if (policy) {
				if (policy->cpuinfo.max_freq)
					max_tsc_khz = policy->cpuinfo.max_freq;
				cpufreq_cpu_put(policy);
			}
			put_cpu();
		}
		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
					  CPUFREQ_TRANSITION_NOTIFIER);
	}

	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
}

#ifdef CONFIG_X86_64
static void pvclock_gtod_update_fn(struct work_struct *work)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	unsigned long i;

	mutex_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list)
		kvm_for_each_vcpu(i, vcpu, kvm)
			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
	atomic_set(&kvm_guest_has_master_clock, 0);
	mutex_unlock(&kvm_lock);
}

static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);

/*
 * Indirection to move queue_work() out of the tk_core.seq write held
 * region to prevent possible deadlocks against time accessors which
 * are invoked with work related locks held.
 */
static void pvclock_irq_work_fn(struct irq_work *w)
{
	queue_work(system_long_wq, &pvclock_gtod_work);
}

static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn);

/*
 * Notification about pvclock gtod data update.
 */
static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused,
			       void *priv)
{
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
	struct timekeeper *tk = priv;

	update_pvclock_gtod(tk);

	/*
	 * Disable master clock if host does not trust, or does not use,
	 * TSC based clocksource. Delegate queue_work() to irq_work as
	 * this is invoked with tk_core.seq write held.
	 */
	if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
	    atomic_read(&kvm_guest_has_master_clock) != 0)
		irq_work_queue(&pvclock_irq_work);
	return 0;
}

static struct notifier_block pvclock_gtod_notifier = {
	.notifier_call = pvclock_gtod_notify,
};
#endif

int kvm_arch_init(void *opaque)
{
	struct kvm_x86_init_ops *ops = opaque;
	u64 host_pat;
	int r;

	if (kvm_x86_ops.hardware_enable) {
		pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name);
		return -EEXIST;
	}

	if (!ops->cpu_has_kvm_support()) {
		pr_err_ratelimited("kvm: no hardware support for '%s'\n",
				   ops->runtime_ops->name);
		return -EOPNOTSUPP;
	}
	if (ops->disabled_by_bios()) {
		pr_err_ratelimited("kvm: support for '%s' disabled by bios\n",
				   ops->runtime_ops->name);
		return -EOPNOTSUPP;
	}

	/*
	 * KVM explicitly assumes that the guest has an FPU and
	 * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the
	 * vCPU's FPU state as a fxregs_state struct.
	 */
	if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) {
		printk(KERN_ERR "kvm: inadequate fpu\n");
		return -EOPNOTSUPP;
	}

	if (IS_ENABLED(CONFIG_PREEMPT_RT) && !boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
		pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n");
		return -EOPNOTSUPP;
	}

	/*
	 * KVM assumes that PAT entry '0' encodes WB memtype and simply zeroes
	 * the PAT bits in SPTEs.  Bail if PAT[0] is programmed to something
	 * other than WB.  Note, EPT doesn't utilize the PAT, but don't bother
	 * with an exception.  PAT[0] is set to WB on RESET and also by the
	 * kernel, i.e. failure indicates a kernel bug or broken firmware.
	 */
	if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
	    (host_pat & GENMASK(2, 0)) != 6) {
		pr_err("kvm: host PAT[0] is not WB\n");
		return -EIO;
	}

	x86_emulator_cache = kvm_alloc_emulator_cache();
	if (!x86_emulator_cache) {
		pr_err("kvm: failed to allocate cache for x86 emulator\n");
		return -ENOMEM;
	}

	user_return_msrs = alloc_percpu(struct kvm_user_return_msrs);
	if (!user_return_msrs) {
		printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n");
		r = -ENOMEM;
		goto out_free_x86_emulator_cache;
	}
	kvm_nr_uret_msrs = 0;

	r = kvm_mmu_vendor_module_init();
	if (r)
		goto out_free_percpu;

	kvm_timer_init();

	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
		kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
	}

	if (pi_inject_timer == -1)
		pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER);
#ifdef CONFIG_X86_64
	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);

	if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
		set_hv_tscchange_cb(kvm_hyperv_tsc_notifier);
#endif

	return 0;

out_free_percpu:
	free_percpu(user_return_msrs);
out_free_x86_emulator_cache:
	kmem_cache_destroy(x86_emulator_cache);
	return r;
}

void kvm_arch_exit(void)
{
#ifdef CONFIG_X86_64
	if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
		clear_hv_tscchange_cb();
#endif
	kvm_lapic_exit();

	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
					    CPUFREQ_TRANSITION_NOTIFIER);
	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
#ifdef CONFIG_X86_64
	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
	irq_work_sync(&pvclock_irq_work);
	cancel_work_sync(&pvclock_gtod_work);
#endif
	kvm_x86_ops.hardware_enable = NULL;
	kvm_mmu_vendor_module_exit();
	free_percpu(user_return_msrs);
	kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
	static_key_deferred_flush(&kvm_xen_enabled);
	WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
#endif
}

static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
{
	/*
	 * The vCPU has halted, e.g. executed HLT.  Update the run state if the
	 * local APIC is in-kernel, the run loop will detect the non-runnable
	 * state and halt the vCPU.  Exit to userspace if the local APIC is
	 * managed by userspace, in which case userspace is responsible for
	 * handling wake events.
	 */
	++vcpu->stat.halt_exits;
	if (lapic_in_kernel(vcpu)) {
		vcpu->arch.mp_state = state;
		return 1;
	} else {
		vcpu->run->exit_reason = reason;
		return 0;
	}
}

int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu)
{
	return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT);
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip);

int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
	int ret = kvm_skip_emulated_instruction(vcpu);
	/*
	 * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered
	 * KVM_EXIT_DEBUG here.
	 */
	return kvm_emulate_halt_noskip(vcpu) && ret;
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);

int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
{
	int ret = kvm_skip_emulated_instruction(vcpu);

	return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD,
					KVM_EXIT_AP_RESET_HOLD) && ret;
}
EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold);

#ifdef CONFIG_X86_64
static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
			        unsigned long clock_type)
{
	struct kvm_clock_pairing clock_pairing;
	struct timespec64 ts;
	u64 cycle;
	int ret;

	if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK)
		return -KVM_EOPNOTSUPP;

	/*
	 * When tsc is in permanent catchup mode guests won't be able to use
	 * pvclock_read_retry loop to get consistent view of pvclock
	 */
	if (vcpu->arch.tsc_always_catchup)
		return -KVM_EOPNOTSUPP;

	if (!kvm_get_walltime_and_clockread(&ts, &cycle))
		return -KVM_EOPNOTSUPP;

	clock_pairing.sec = ts.tv_sec;
	clock_pairing.nsec = ts.tv_nsec;
	clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle);
	clock_pairing.flags = 0;
	memset(&clock_pairing.pad, 0, sizeof(clock_pairing.pad));

	ret = 0;
	if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing,
			    sizeof(struct kvm_clock_pairing)))
		ret = -KVM_EFAULT;

	return ret;
}
#endif

/*
 * kvm_pv_kick_cpu_op:  Kick a vcpu.
 *
 * @apicid - apicid of vcpu to be kicked.
 */
static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
{
	/*
	 * All other fields are unused for APIC_DM_REMRD, but may be consumed by
	 * common code, e.g. for tracing. Defer initialization to the compiler.
	 */
	struct kvm_lapic_irq lapic_irq = {
		.delivery_mode = APIC_DM_REMRD,
		.dest_mode = APIC_DEST_PHYSICAL,
		.shorthand = APIC_DEST_NOSHORT,
		.dest_id = apicid,
	};

	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
}

bool kvm_apicv_activated(struct kvm *kvm)
{
	return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0);
}
EXPORT_SYMBOL_GPL(kvm_apicv_activated);

bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu)
{
	ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons);
	ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu);

	return (vm_reasons | vcpu_reasons) == 0;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated);

static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
				       enum kvm_apicv_inhibit reason, bool set)
{
	if (set)
		__set_bit(reason, inhibits);
	else
		__clear_bit(reason, inhibits);

	trace_kvm_apicv_inhibit_changed(reason, set, *inhibits);
}

static void kvm_apicv_init(struct kvm *kvm)
{
	unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons;

	init_rwsem(&kvm->arch.apicv_update_lock);

	set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true);

	if (!enable_apicv)
		set_or_clear_apicv_inhibit(inhibits,
					   APICV_INHIBIT_REASON_DISABLE, true);
}

static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
{
	struct kvm_vcpu *target = NULL;
	struct kvm_apic_map *map;

	vcpu->stat.directed_yield_attempted++;

	if (single_task_running())
		goto no_yield;

	rcu_read_lock();
	map = rcu_dereference(vcpu->kvm->arch.apic_map);

	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
		target = map->phys_map[dest_id]->vcpu;

	rcu_read_unlock();

	if (!target || !READ_ONCE(target->ready))
		goto no_yield;

	/* Ignore requests to yield to self */
	if (vcpu == target)
		goto no_yield;

	if (kvm_vcpu_yield_to(target) <= 0)
		goto no_yield;

	vcpu->stat.directed_yield_successful++;

no_yield:
	return;
}

static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
{
	u64 ret = vcpu->run->hypercall.ret;

	if (!is_64_bit_mode(vcpu))
		ret = (u32)ret;
	kvm_rax_write(vcpu, ret);
	++vcpu->stat.hypercalls;
	return kvm_skip_emulated_instruction(vcpu);
}

int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
	unsigned long nr, a0, a1, a2, a3, ret;
	int op_64_bit;

	if (kvm_xen_hypercall_enabled(vcpu->kvm))
		return kvm_xen_hypercall(vcpu);

	if (kvm_hv_hypercall_enabled(vcpu))
		return kvm_hv_hypercall(vcpu);

	nr = kvm_rax_read(vcpu);
	a0 = kvm_rbx_read(vcpu);
	a1 = kvm_rcx_read(vcpu);
	a2 = kvm_rdx_read(vcpu);
	a3 = kvm_rsi_read(vcpu);

	trace_kvm_hypercall(nr, a0, a1, a2, a3);

	op_64_bit = is_64_bit_hypercall(vcpu);
	if (!op_64_bit) {
		nr &= 0xFFFFFFFF;
		a0 &= 0xFFFFFFFF;
		a1 &= 0xFFFFFFFF;
		a2 &= 0xFFFFFFFF;
		a3 &= 0xFFFFFFFF;
	}

	if (static_call(kvm_x86_get_cpl)(vcpu) != 0) {
		ret = -KVM_EPERM;
		goto out;
	}

	ret = -KVM_ENOSYS;

	switch (nr) {
	case KVM_HC_VAPIC_POLL_IRQ:
		ret = 0;
		break;
	case KVM_HC_KICK_CPU:
		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT))
			break;

		kvm_pv_kick_cpu_op(vcpu->kvm, a1);
		kvm_sched_yield(vcpu, a1);
		ret = 0;
		break;
#ifdef CONFIG_X86_64
	case KVM_HC_CLOCK_PAIRING:
		ret = kvm_pv_clock_pairing(vcpu, a0, a1);
		break;
#endif
	case KVM_HC_SEND_IPI:
		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI))
			break;

		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
		break;
	case KVM_HC_SCHED_YIELD:
		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD))
			break;

		kvm_sched_yield(vcpu, a0);
		ret = 0;
		break;
	case KVM_HC_MAP_GPA_RANGE: {
		u64 gpa = a0, npages = a1, attrs = a2;

		ret = -KVM_ENOSYS;
		if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE)))
			break;

		if (!PAGE_ALIGNED(gpa) || !npages ||
		    gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) {
			ret = -KVM_EINVAL;
			break;
		}

		vcpu->run->exit_reason        = KVM_EXIT_HYPERCALL;
		vcpu->run->hypercall.nr       = KVM_HC_MAP_GPA_RANGE;
		vcpu->run->hypercall.args[0]  = gpa;
		vcpu->run->hypercall.args[1]  = npages;
		vcpu->run->hypercall.args[2]  = attrs;
		vcpu->run->hypercall.longmode = op_64_bit;
		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
		return 0;
	}
	default:
		ret = -KVM_ENOSYS;
		break;
	}
out:
	if (!op_64_bit)
		ret = (u32)ret;
	kvm_rax_write(vcpu, ret);

	++vcpu->stat.hypercalls;
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);

static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
{
	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
	char instruction[3];
	unsigned long rip = kvm_rip_read(vcpu);

	/*
	 * If the quirk is disabled, synthesize a #UD and let the guest pick up
	 * the pieces.
	 */
	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) {
		ctxt->exception.error_code_valid = false;
		ctxt->exception.vector = UD_VECTOR;
		ctxt->have_exception = true;
		return X86EMUL_PROPAGATE_FAULT;
	}

	static_call(kvm_x86_patch_hypercall)(vcpu, instruction);

	return emulator_write_emulated(ctxt, rip, instruction, 3,
		&ctxt->exception);
}

static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
{
	return vcpu->run->request_interrupt_window &&
		likely(!pic_in_kernel(vcpu->kvm));
}

/* Called within kvm->srcu read side.  */
static void post_kvm_run_save(struct kvm_vcpu *vcpu)
{
	struct kvm_run *kvm_run = vcpu->run;

	kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu);
	kvm_run->cr8 = kvm_get_cr8(vcpu);
	kvm_run->apic_base = kvm_get_apic_base(vcpu);

	kvm_run->ready_for_interrupt_injection =
		pic_in_kernel(vcpu->kvm) ||
		kvm_vcpu_ready_for_interrupt_injection(vcpu);

	if (is_smm(vcpu))
		kvm_run->flags |= KVM_RUN_X86_SMM;
}

static void update_cr8_intercept(struct kvm_vcpu *vcpu)
{
	int max_irr, tpr;

	if (!kvm_x86_ops.update_cr8_intercept)
		return;

	if (!lapic_in_kernel(vcpu))
		return;

	if (vcpu->arch.apic->apicv_active)
		return;

	if (!vcpu->arch.apic->vapic_addr)
		max_irr = kvm_lapic_find_highest_irr(vcpu);
	else
		max_irr = -1;

	if (max_irr != -1)
		max_irr >>= 4;

	tpr = kvm_lapic_get_cr8(vcpu);

	static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr);
}


int kvm_check_nested_events(struct kvm_vcpu *vcpu)
{
	if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
		kvm_x86_ops.nested_ops->triple_fault(vcpu);
		return 1;
	}

	return kvm_x86_ops.nested_ops->check_events(vcpu);
}

static void kvm_inject_exception(struct kvm_vcpu *vcpu)
{
	trace_kvm_inj_exception(vcpu->arch.exception.vector,
				vcpu->arch.exception.has_error_code,
				vcpu->arch.exception.error_code,
				vcpu->arch.exception.injected);

	if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
		vcpu->arch.exception.error_code = false;
	static_call(kvm_x86_inject_exception)(vcpu);
}

/*
 * Check for any event (interrupt or exception) that is ready to be injected,
 * and if there is at least one event, inject the event with the highest
 * priority.  This handles both "pending" events, i.e. events that have never
 * been injected into the guest, and "injected" events, i.e. events that were
 * injected as part of a previous VM-Enter, but weren't successfully delivered
 * and need to be re-injected.
 *
 * Note, this is not guaranteed to be invoked on a guest instruction boundary,
 * i.e. doesn't guarantee that there's an event window in the guest.  KVM must
 * be able to inject exceptions in the "middle" of an instruction, and so must
 * also be able to re-inject NMIs and IRQs in the middle of an instruction.
 * I.e. for exceptions and re-injected events, NOT invoking this on instruction
 * boundaries is necessary and correct.
 *
 * For simplicity, KVM uses a single path to inject all events (except events
 * that are injected directly from L1 to L2) and doesn't explicitly track
 * instruction boundaries for asynchronous events.  However, because VM-Exits
 * that can occur during instruction execution typically result in KVM skipping
 * the instruction or injecting an exception, e.g. instruction and exception
 * intercepts, and because pending exceptions have higher priority than pending
 * interrupts, KVM still honors instruction boundaries in most scenarios.
 *
 * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip
 * the instruction or inject an exception, then KVM can incorrecty inject a new
 * asynchrounous event if the event became pending after the CPU fetched the
 * instruction (in the guest).  E.g. if a page fault (#PF, #NPF, EPT violation)
 * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be
 * injected on the restarted instruction instead of being deferred until the
 * instruction completes.
 *
 * In practice, this virtualization hole is unlikely to be observed by the
 * guest, and even less likely to cause functional problems.  To detect the
 * hole, the guest would have to trigger an event on a side effect of an early
 * phase of instruction execution, e.g. on the instruction fetch from memory.
 * And for it to be a functional problem, the guest would need to depend on the
 * ordering between that side effect, the instruction completing, _and_ the
 * delivery of the asynchronous event.
 */
static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
				       bool *req_immediate_exit)
{
	bool can_inject;
	int r;

	/*
	 * Process nested events first, as nested VM-Exit supercedes event
	 * re-injection.  If there's an event queued for re-injection, it will
	 * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit.
	 */
	if (is_guest_mode(vcpu))
		r = kvm_check_nested_events(vcpu);
	else
		r = 0;

	/*
	 * Re-inject exceptions and events *especially* if immediate entry+exit
	 * to/from L2 is needed, as any event that has already been injected
	 * into L2 needs to complete its lifecycle before injecting a new event.
	 *
	 * Don't re-inject an NMI or interrupt if there is a pending exception.
	 * This collision arises if an exception occurred while vectoring the
	 * injected event, KVM intercepted said exception, and KVM ultimately
	 * determined the fault belongs to the guest and queues the exception
	 * for injection back into the guest.
	 *
	 * "Injected" interrupts can also collide with pending exceptions if
	 * userspace ignores the "ready for injection" flag and blindly queues
	 * an interrupt.  In that case, prioritizing the exception is correct,
	 * as the exception "occurred" before the exit to userspace.  Trap-like
	 * exceptions, e.g. most #DBs, have higher priority than interrupts.
	 * And while fault-like exceptions, e.g. #GP and #PF, are the lowest
	 * priority, they're only generated (pended) during instruction
	 * execution, and interrupts are recognized at instruction boundaries.
	 * Thus a pending fault-like exception means the fault occurred on the
	 * *previous* instruction and must be serviced prior to recognizing any
	 * new events in order to fully complete the previous instruction.
	 */
	if (vcpu->arch.exception.injected)
		kvm_inject_exception(vcpu);
	else if (kvm_is_exception_pending(vcpu))
		; /* see above */
	else if (vcpu->arch.nmi_injected)
		static_call(kvm_x86_inject_nmi)(vcpu);
	else if (vcpu->arch.interrupt.injected)
		static_call(kvm_x86_inject_irq)(vcpu, true);

	/*
	 * Exceptions that morph to VM-Exits are handled above, and pending
	 * exceptions on top of injected exceptions that do not VM-Exit should
	 * either morph to #DF or, sadly, override the injected exception.
	 */
	WARN_ON_ONCE(vcpu->arch.exception.injected &&
		     vcpu->arch.exception.pending);

	/*
	 * Bail if immediate entry+exit to/from the guest is needed to complete
	 * nested VM-Enter or event re-injection so that a different pending
	 * event can be serviced (or if KVM needs to exit to userspace).
	 *
	 * Otherwise, continue processing events even if VM-Exit occurred.  The
	 * VM-Exit will have cleared exceptions that were meant for L2, but
	 * there may now be events that can be injected into L1.
	 */
	if (r < 0)
		goto out;

	/*
	 * A pending exception VM-Exit should either result in nested VM-Exit
	 * or force an immediate re-entry and exit to/from L2, and exception
	 * VM-Exits cannot be injected (flag should _never_ be set).
	 */
	WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected ||
		     vcpu->arch.exception_vmexit.pending);

	/*
	 * New events, other than exceptions, cannot be injected if KVM needs
	 * to re-inject a previous event.  See above comments on re-injecting
	 * for why pending exceptions get priority.
	 */
	can_inject = !kvm_event_needs_reinjection(vcpu);

	if (vcpu->arch.exception.pending) {
		/*
		 * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS
		 * value pushed on the stack.  Trap-like exception and all #DBs
		 * leave RF as-is (KVM follows Intel's behavior in this regard;
		 * AMD states that code breakpoint #DBs excplitly clear RF=0).
		 *
		 * Note, most versions of Intel's SDM and AMD's APM incorrectly
		 * describe the behavior of General Detect #DBs, which are
		 * fault-like.  They do _not_ set RF, a la code breakpoints.
		 */
		if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT)
			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
					     X86_EFLAGS_RF);

		if (vcpu->arch.exception.vector == DB_VECTOR) {
			kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception);
			if (vcpu->arch.dr7 & DR7_GD) {
				vcpu->arch.dr7 &= ~DR7_GD;
				kvm_update_dr7(vcpu);
			}
		}

		kvm_inject_exception(vcpu);

		vcpu->arch.exception.pending = false;
		vcpu->arch.exception.injected = true;

		can_inject = false;
	}

	/* Don't inject interrupts if the user asked to avoid doing so */
	if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ)
		return 0;

	/*
	 * Finally, inject interrupt events.  If an event cannot be injected
	 * due to architectural conditions (e.g. IF=0) a window-open exit
	 * will re-request KVM_REQ_EVENT.  Sometimes however an event is pending
	 * and can architecturally be injected, but we cannot do it right now:
	 * an interrupt could have arrived just now and we have to inject it
	 * as a vmexit, or there could already an event in the queue, which is
	 * indicated by can_inject.  In that case we request an immediate exit
	 * in order to make progress and get back here for another iteration.
	 * The kvm_x86_ops hooks communicate this by returning -EBUSY.
	 */
#ifdef CONFIG_KVM_SMM
	if (vcpu->arch.smi_pending) {
		r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY;
		if (r < 0)
			goto out;
		if (r) {
			vcpu->arch.smi_pending = false;
			++vcpu->arch.smi_count;
			enter_smm(vcpu);
			can_inject = false;
		} else
			static_call(kvm_x86_enable_smi_window)(vcpu);
	}
#endif

	if (vcpu->arch.nmi_pending) {
		r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY;
		if (r < 0)
			goto out;
		if (r) {
			--vcpu->arch.nmi_pending;
			vcpu->arch.nmi_injected = true;
			static_call(kvm_x86_inject_nmi)(vcpu);
			can_inject = false;
			WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0);
		}
		if (vcpu->arch.nmi_pending)
			static_call(kvm_x86_enable_nmi_window)(vcpu);
	}

	if (kvm_cpu_has_injectable_intr(vcpu)) {
		r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY;
		if (r < 0)
			goto out;
		if (r) {
			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false);
			static_call(kvm_x86_inject_irq)(vcpu, false);
			WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0);
		}
		if (kvm_cpu_has_injectable_intr(vcpu))
			static_call(kvm_x86_enable_irq_window)(vcpu);
	}

	if (is_guest_mode(vcpu) &&
	    kvm_x86_ops.nested_ops->has_events &&
	    kvm_x86_ops.nested_ops->has_events(vcpu))
		*req_immediate_exit = true;

	/*
	 * KVM must never queue a new exception while injecting an event; KVM
	 * is done emulating and should only propagate the to-be-injected event
	 * to the VMCS/VMCB.  Queueing a new exception can put the vCPU into an
	 * infinite loop as KVM will bail from VM-Enter to inject the pending
	 * exception and start the cycle all over.
	 *
	 * Exempt triple faults as they have special handling and won't put the
	 * vCPU into an infinite loop.  Triple fault can be queued when running
	 * VMX without unrestricted guest, as that requires KVM to emulate Real
	 * Mode events (see kvm_inject_realmode_interrupt()).
	 */
	WARN_ON_ONCE(vcpu->arch.exception.pending ||
		     vcpu->arch.exception_vmexit.pending);
	return 0;

out:
	if (r == -EBUSY) {
		*req_immediate_exit = true;
		r = 0;
	}
	return r;
}

static void process_nmi(struct kvm_vcpu *vcpu)
{
	unsigned limit = 2;

	/*
	 * x86 is limited to one NMI running, and one NMI pending after it.
	 * If an NMI is already in progress, limit further NMIs to just one.
	 * Otherwise, allow two (and we'll inject the first one immediately).
	 */
	if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected)
		limit = 1;

	vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0);
	vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit);
	kvm_make_request(KVM_REQ_EVENT, vcpu);
}

void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
				       unsigned long *vcpu_bitmap)
{
	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap);
}

void kvm_make_scan_ioapic_request(struct kvm *kvm)
{
	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
}

void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	bool activate;

	if (!lapic_in_kernel(vcpu))
		return;

	down_read(&vcpu->kvm->arch.apicv_update_lock);
	preempt_disable();

	/* Do not activate APICV when APIC is disabled */
	activate = kvm_vcpu_apicv_activated(vcpu) &&
		   (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED);

	if (apic->apicv_active == activate)
		goto out;

	apic->apicv_active = activate;
	kvm_apic_update_apicv(vcpu);
	static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu);

	/*
	 * When APICv gets disabled, we may still have injected interrupts
	 * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was
	 * still active when the interrupt got accepted. Make sure
	 * kvm_check_and_inject_events() is called to check for that.
	 */
	if (!apic->apicv_active)
		kvm_make_request(KVM_REQ_EVENT, vcpu);

out:
	preempt_enable();
	up_read(&vcpu->kvm->arch.apicv_update_lock);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);

void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
				      enum kvm_apicv_inhibit reason, bool set)
{
	unsigned long old, new;

	lockdep_assert_held_write(&kvm->arch.apicv_update_lock);

	if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason))
		return;

	old = new = kvm->arch.apicv_inhibit_reasons;

	set_or_clear_apicv_inhibit(&new, reason, set);

	if (!!old != !!new) {
		/*
		 * Kick all vCPUs before setting apicv_inhibit_reasons to avoid
		 * false positives in the sanity check WARN in svm_vcpu_run().
		 * This task will wait for all vCPUs to ack the kick IRQ before
		 * updating apicv_inhibit_reasons, and all other vCPUs will
		 * block on acquiring apicv_update_lock so that vCPUs can't
		 * redo svm_vcpu_run() without seeing the new inhibit state.
		 *
		 * Note, holding apicv_update_lock and taking it in the read
		 * side (handling the request) also prevents other vCPUs from
		 * servicing the request with a stale apicv_inhibit_reasons.
		 */
		kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE);
		kvm->arch.apicv_inhibit_reasons = new;
		if (new) {
			unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
			int idx = srcu_read_lock(&kvm->srcu);

			kvm_zap_gfn_range(kvm, gfn, gfn+1);
			srcu_read_unlock(&kvm->srcu, idx);
		}
	} else {
		kvm->arch.apicv_inhibit_reasons = new;
	}
}

void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
				    enum kvm_apicv_inhibit reason, bool set)
{
	if (!enable_apicv)
		return;

	down_write(&kvm->arch.apicv_update_lock);
	__kvm_set_or_clear_apicv_inhibit(kvm, reason, set);
	up_write(&kvm->arch.apicv_update_lock);
}
EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit);

static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
{
	if (!kvm_apic_present(vcpu))
		return;

	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);

	if (irqchip_split(vcpu->kvm))
		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
	else {
		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
		if (ioapic_in_kernel(vcpu->kvm))
			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
	}

	if (is_guest_mode(vcpu))
		vcpu->arch.load_eoi_exitmap_pending = true;
	else
		kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu);
}

static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
{
	u64 eoi_exit_bitmap[4];

	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
		return;

	if (to_hv_vcpu(vcpu)) {
		bitmap_or((ulong *)eoi_exit_bitmap,
			  vcpu->arch.ioapic_handled_vectors,
			  to_hv_synic(vcpu)->vec_bitmap, 256);
		static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
		return;
	}

	static_call_cond(kvm_x86_load_eoi_exitmap)(
		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
}

void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
					    unsigned long start, unsigned long end)
{
	unsigned long apic_address;

	/*
	 * The physical address of apic access page is stored in the VMCS.
	 * Update it when it becomes invalid.
	 */
	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
	if (start <= apic_address && apic_address < end)
		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
}

void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
{
	static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm);
}

static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
	if (!lapic_in_kernel(vcpu))
		return;

	static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu);
}

void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
{
	smp_send_reschedule(vcpu->cpu);
}
EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit);

/*
 * Called within kvm->srcu read side.
 * Returns 1 to let vcpu_run() continue the guest execution loop without
 * exiting to the userspace.  Otherwise, the value will be returned to the
 * userspace.
 */
static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
{
	int r;
	bool req_int_win =
		dm_request_for_irq_injection(vcpu) &&
		kvm_cpu_accept_dm_intr(vcpu);
	fastpath_t exit_fastpath;

	bool req_immediate_exit = false;

	/* Forbid vmenter if vcpu dirty ring is soft-full */
	if (unlikely(vcpu->kvm->dirty_ring_size &&
		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
		trace_kvm_dirty_ring_exit(vcpu);
		r = 0;
		goto out;
	}

	if (kvm_request_pending(vcpu)) {
		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
			r = -EIO;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
				r = 0;
				goto out;
			}
		}
		if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
			kvm_mmu_free_obsolete_roots(vcpu);
		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
			__kvm_migrate_timers(vcpu);
		if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu))
			kvm_update_masterclock(vcpu->kvm);
		if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu))
			kvm_gen_kvmclock_update(vcpu);
		if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
			r = kvm_guest_time_update(vcpu);
			if (unlikely(r))
				goto out;
		}
		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
			kvm_mmu_sync_roots(vcpu);
		if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu))
			kvm_mmu_load_pgd(vcpu);

		/*
		 * Note, the order matters here, as flushing "all" TLB entries
		 * also flushes the "current" TLB entries, i.e. servicing the
		 * flush "all" will clear any request to flush "current".
		 */
		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
			kvm_vcpu_flush_tlb_all(vcpu);

		kvm_service_local_tlb_flush_requests(vcpu);

		/*
		 * Fall back to a "full" guest flush if Hyper-V's precise
		 * flushing fails.  Note, Hyper-V's flushing is per-vCPU, but
		 * the flushes are considered "remote" and not "local" because
		 * the requests can be initiated from other vCPUs.
		 */
		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) &&
		    kvm_hv_vcpu_flush_tlb(vcpu))
			kvm_vcpu_flush_tlb_guest(vcpu);

		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
			r = 0;
			goto out;
		}
		if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
			if (is_guest_mode(vcpu))
				kvm_x86_ops.nested_ops->triple_fault(vcpu);

			if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
				vcpu->mmio_needed = 0;
				r = 0;
			}
			goto out;
		}
		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
			/* Page is swapped out. Do synthetic halt */
			vcpu->arch.apf.halted = true;
			r = 1;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
			record_steal_time(vcpu);
#ifdef CONFIG_KVM_SMM
		if (kvm_check_request(KVM_REQ_SMI, vcpu))
			process_smi(vcpu);
#endif
		if (kvm_check_request(KVM_REQ_NMI, vcpu))
			process_nmi(vcpu);
		if (kvm_check_request(KVM_REQ_PMU, vcpu))
			kvm_pmu_handle_event(vcpu);
		if (kvm_check_request(KVM_REQ_PMI, vcpu))
			kvm_pmu_deliver_pmi(vcpu);
		if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) {
			BUG_ON(vcpu->arch.pending_ioapic_eoi > 255);
			if (test_bit(vcpu->arch.pending_ioapic_eoi,
				     vcpu->arch.ioapic_handled_vectors)) {
				vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI;
				vcpu->run->eoi.vector =
						vcpu->arch.pending_ioapic_eoi;
				r = 0;
				goto out;
			}
		}
		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
			vcpu_scan_ioapic(vcpu);
		if (kvm_check_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu))
			vcpu_load_eoi_exitmap(vcpu);
		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
			kvm_vcpu_reload_apic_access_page(vcpu);
		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
			vcpu->run->system_event.ndata = 0;
			r = 0;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) {
			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET;
			vcpu->run->system_event.ndata = 0;
			r = 0;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) {
			struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);

			vcpu->run->exit_reason = KVM_EXIT_HYPERV;
			vcpu->run->hyperv = hv_vcpu->exit;
			r = 0;
			goto out;
		}

		/*
		 * KVM_REQ_HV_STIMER has to be processed after
		 * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers
		 * depend on the guest clock being up-to-date
		 */
		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
			kvm_hv_process_stimers(vcpu);
		if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
			kvm_vcpu_update_apicv(vcpu);
		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
			kvm_check_async_pf_completion(vcpu);
		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
			static_call(kvm_x86_msr_filter_changed)(vcpu);

		if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
			static_call(kvm_x86_update_cpu_dirty_logging)(vcpu);
	}

	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win ||
	    kvm_xen_has_interrupt(vcpu)) {
		++vcpu->stat.req_event;
		r = kvm_apic_accept_events(vcpu);
		if (r < 0) {
			r = 0;
			goto out;
		}
		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
			r = 1;
			goto out;
		}

		r = kvm_check_and_inject_events(vcpu, &req_immediate_exit);
		if (r < 0) {
			r = 0;
			goto out;
		}
		if (req_int_win)
			static_call(kvm_x86_enable_irq_window)(vcpu);

		if (kvm_lapic_enabled(vcpu)) {
			update_cr8_intercept(vcpu);
			kvm_lapic_sync_to_vapic(vcpu);
		}
	}

	r = kvm_mmu_reload(vcpu);
	if (unlikely(r)) {
		goto cancel_injection;
	}

	preempt_disable();

	static_call(kvm_x86_prepare_switch_to_guest)(vcpu);

	/*
	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
	 * IPI are then delayed after guest entry, which ensures that they
	 * result in virtual interrupt delivery.
	 */
	local_irq_disable();

	/* Store vcpu->apicv_active before vcpu->mode.  */
	smp_store_release(&vcpu->mode, IN_GUEST_MODE);

	kvm_vcpu_srcu_read_unlock(vcpu);

	/*
	 * 1) We should set ->mode before checking ->requests.  Please see
	 * the comment in kvm_vcpu_exiting_guest_mode().
	 *
	 * 2) For APICv, we should set ->mode before checking PID.ON. This
	 * pairs with the memory barrier implicit in pi_test_and_set_on
	 * (see vmx_deliver_posted_interrupt).
	 *
	 * 3) This also orders the write to mode from any reads to the page
	 * tables done while the VCPU is running.  Please see the comment
	 * in kvm_flush_remote_tlbs.
	 */
	smp_mb__after_srcu_read_unlock();

	/*
	 * Process pending posted interrupts to handle the case where the
	 * notification IRQ arrived in the host, or was never sent (because the
	 * target vCPU wasn't running).  Do this regardless of the vCPU's APICv
	 * status, KVM doesn't update assigned devices when APICv is inhibited,
	 * i.e. they can post interrupts even if APICv is temporarily disabled.
	 */
	if (kvm_lapic_enabled(vcpu))
		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);

	if (kvm_vcpu_exit_request(vcpu)) {
		vcpu->mode = OUTSIDE_GUEST_MODE;
		smp_wmb();
		local_irq_enable();
		preempt_enable();
		kvm_vcpu_srcu_read_lock(vcpu);
		r = 1;
		goto cancel_injection;
	}

	if (req_immediate_exit) {
		kvm_make_request(KVM_REQ_EVENT, vcpu);
		static_call(kvm_x86_request_immediate_exit)(vcpu);
	}

	fpregs_assert_state_consistent();
	if (test_thread_flag(TIF_NEED_FPU_LOAD))
		switch_fpu_return();

	if (vcpu->arch.guest_fpu.xfd_err)
		wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);

	if (unlikely(vcpu->arch.switch_db_regs)) {
		set_debugreg(0, 7);
		set_debugreg(vcpu->arch.eff_db[0], 0);
		set_debugreg(vcpu->arch.eff_db[1], 1);
		set_debugreg(vcpu->arch.eff_db[2], 2);
		set_debugreg(vcpu->arch.eff_db[3], 3);
	} else if (unlikely(hw_breakpoint_active())) {
		set_debugreg(0, 7);
	}

	guest_timing_enter_irqoff();

	for (;;) {
		/*
		 * Assert that vCPU vs. VM APICv state is consistent.  An APICv
		 * update must kick and wait for all vCPUs before toggling the
		 * per-VM state, and responsing vCPUs must wait for the update
		 * to complete before servicing KVM_REQ_APICV_UPDATE.
		 */
		WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
			     (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));

		exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu);
		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
			break;

		if (kvm_lapic_enabled(vcpu))
			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);

		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
			break;
		}
	}

	/*
	 * Do this here before restoring debug registers on the host.  And
	 * since we do this before handling the vmexit, a DR access vmexit
	 * can (a) read the correct value of the debug registers, (b) set
	 * KVM_DEBUGREG_WONT_EXIT again.
	 */
	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
		static_call(kvm_x86_sync_dirty_debug_regs)(vcpu);
		kvm_update_dr0123(vcpu);
		kvm_update_dr7(vcpu);
	}

	/*
	 * If the guest has used debug registers, at least dr7
	 * will be disabled while returning to the host.
	 * If we don't have active breakpoints in the host, we don't
	 * care about the messed up debug address registers. But if
	 * we have some of them active, restore the old state.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_restore();

	vcpu->arch.last_vmentry_cpu = vcpu->cpu;
	vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

	vcpu->mode = OUTSIDE_GUEST_MODE;
	smp_wmb();

	/*
	 * Sync xfd before calling handle_exit_irqoff() which may
	 * rely on the fact that guest_fpu::xfd is up-to-date (e.g.
	 * in #NM irqoff handler).
	 */
	if (vcpu->arch.xfd_no_write_intercept)
		fpu_sync_guest_vmexit_xfd_state();

	static_call(kvm_x86_handle_exit_irqoff)(vcpu);

	if (vcpu->arch.guest_fpu.xfd_err)
		wrmsrl(MSR_IA32_XFD_ERR, 0);

	/*
	 * Consume any pending interrupts, including the possible source of
	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.
	 * An instruction is required after local_irq_enable() to fully unblock
	 * interrupts on processors that implement an interrupt shadow, the
	 * stat.exits increment will do nicely.
	 */
	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
	local_irq_enable();
	++vcpu->stat.exits;
	local_irq_disable();
	kvm_after_interrupt(vcpu);

	/*
	 * Wait until after servicing IRQs to account guest time so that any
	 * ticks that occurred while running the guest are properly accounted
	 * to the guest.  Waiting until IRQs are enabled degrades the accuracy
	 * of accounting via context tracking, but the loss of accuracy is
	 * acceptable for all known use cases.
	 */
	guest_timing_exit_irqoff();

	local_irq_enable();
	preempt_enable();

	kvm_vcpu_srcu_read_lock(vcpu);

	/*
	 * Profile KVM exit RIPs:
	 */
	if (unlikely(prof_on == KVM_PROFILING)) {
		unsigned long rip = kvm_rip_read(vcpu);
		profile_hit(KVM_PROFILING, (void *)rip);
	}

	if (unlikely(vcpu->arch.tsc_always_catchup))
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

	if (vcpu->arch.apic_attention)
		kvm_lapic_sync_from_vapic(vcpu);

	r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath);
	return r;

cancel_injection:
	if (req_immediate_exit)
		kvm_make_request(KVM_REQ_EVENT, vcpu);
	static_call(kvm_x86_cancel_injection)(vcpu);
	if (unlikely(vcpu->arch.apic_attention))
		kvm_lapic_sync_from_vapic(vcpu);
out:
	return r;
}

/* Called within kvm->srcu read side.  */
static inline int vcpu_block(struct kvm_vcpu *vcpu)
{
	bool hv_timer;

	if (!kvm_arch_vcpu_runnable(vcpu)) {
		/*
		 * Switch to the software timer before halt-polling/blocking as
		 * the guest's timer may be a break event for the vCPU, and the
		 * hypervisor timer runs only when the CPU is in guest mode.
		 * Switch before halt-polling so that KVM recognizes an expired
		 * timer before blocking.
		 */
		hv_timer = kvm_lapic_hv_timer_in_use(vcpu);
		if (hv_timer)
			kvm_lapic_switch_to_sw_timer(vcpu);

		kvm_vcpu_srcu_read_unlock(vcpu);
		if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
			kvm_vcpu_halt(vcpu);
		else
			kvm_vcpu_block(vcpu);
		kvm_vcpu_srcu_read_lock(vcpu);

		if (hv_timer)
			kvm_lapic_switch_to_hv_timer(vcpu);

		/*
		 * If the vCPU is not runnable, a signal or another host event
		 * of some kind is pending; service it without changing the
		 * vCPU's activity state.
		 */
		if (!kvm_arch_vcpu_runnable(vcpu))
			return 1;
	}

	/*
	 * Evaluate nested events before exiting the halted state.  This allows
	 * the halt state to be recorded properly in the VMCS12's activity
	 * state field (AMD does not have a similar field and a VM-Exit always
	 * causes a spurious wakeup from HLT).
	 */
	if (is_guest_mode(vcpu)) {
		if (kvm_check_nested_events(vcpu) < 0)
			return 0;
	}

	if (kvm_apic_accept_events(vcpu) < 0)
		return 0;
	switch(vcpu->arch.mp_state) {
	case KVM_MP_STATE_HALTED:
	case KVM_MP_STATE_AP_RESET_HOLD:
		vcpu->arch.pv.pv_unhalted = false;
		vcpu->arch.mp_state =
			KVM_MP_STATE_RUNNABLE;
		fallthrough;
	case KVM_MP_STATE_RUNNABLE:
		vcpu->arch.apf.halted = false;
		break;
	case KVM_MP_STATE_INIT_RECEIVED:
		break;
	default:
		WARN_ON_ONCE(1);
		break;
	}
	return 1;
}

static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
{
	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
		!vcpu->arch.apf.halted);
}

/* Called within kvm->srcu read side.  */
static int vcpu_run(struct kvm_vcpu *vcpu)
{
	int r;

	vcpu->arch.l1tf_flush_l1d = true;

	for (;;) {
		/*
		 * If another guest vCPU requests a PV TLB flush in the middle
		 * of instruction emulation, the rest of the emulation could
		 * use a stale page translation. Assume that any code after
		 * this point can start executing an instruction.
		 */
		vcpu->arch.at_instruction_boundary = false;
		if (kvm_vcpu_running(vcpu)) {
			r = vcpu_enter_guest(vcpu);
		} else {
			r = vcpu_block(vcpu);
		}

		if (r <= 0)
			break;

		kvm_clear_request(KVM_REQ_UNBLOCK, vcpu);
		if (kvm_xen_has_pending_events(vcpu))
			kvm_xen_inject_pending_events(vcpu);

		if (kvm_cpu_has_pending_timer(vcpu))
			kvm_inject_pending_timer_irqs(vcpu);

		if (dm_request_for_irq_injection(vcpu) &&
			kvm_vcpu_ready_for_interrupt_injection(vcpu)) {
			r = 0;
			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
			++vcpu->stat.request_irq_exits;
			break;
		}

		if (__xfer_to_guest_mode_work_pending()) {
			kvm_vcpu_srcu_read_unlock(vcpu);
			r = xfer_to_guest_mode_handle_work(vcpu);
			kvm_vcpu_srcu_read_lock(vcpu);
			if (r)
				return r;
		}
	}

	return r;
}

static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
}

static int complete_emulated_pio(struct kvm_vcpu *vcpu)
{
	BUG_ON(!vcpu->arch.pio.count);

	return complete_emulated_io(vcpu);
}

/*
 * Implements the following, as a state machine:
 *
 * read:
 *   for each fragment
 *     for each mmio piece in the fragment
 *       write gpa, len
 *       exit
 *       copy data
 *   execute insn
 *
 * write:
 *   for each fragment
 *     for each mmio piece in the fragment
 *       write gpa, len
 *       copy data
 *       exit
 */
static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	struct kvm_mmio_fragment *frag;
	unsigned len;

	BUG_ON(!vcpu->mmio_needed);

	/* Complete previous fragment */
	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
	len = min(8u, frag->len);
	if (!vcpu->mmio_is_write)
		memcpy(frag->data, run->mmio.data, len);

	if (frag->len <= 8) {
		/* Switch to the next fragment. */
		frag++;
		vcpu->mmio_cur_fragment++;
	} else {
		/* Go forward to the next mmio piece. */
		frag->data += len;
		frag->gpa += len;
		frag->len -= len;
	}

	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
		vcpu->mmio_needed = 0;

		/* FIXME: return into emulator if single-stepping.  */
		if (vcpu->mmio_is_write)
			return 1;
		vcpu->mmio_read_completed = 1;
		return complete_emulated_io(vcpu);
	}

	run->exit_reason = KVM_EXIT_MMIO;
	run->mmio.phys_addr = frag->gpa;
	if (vcpu->mmio_is_write)
		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
	run->mmio.len = min(8u, frag->len);
	run->mmio.is_write = vcpu->mmio_is_write;
	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
	return 0;
}

/* Swap (qemu) user FPU context for the guest FPU context. */
static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
	/* Exclude PKRU, it's restored separately immediately after VM-Exit. */
	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true);
	trace_kvm_fpu(1);
}

/* When vcpu_run ends, restore user space FPU context. */
static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false);
	++vcpu->stat.fpu_reload;
	trace_kvm_fpu(0);
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
	struct kvm_queued_exception *ex = &vcpu->arch.exception;
	struct kvm_run *kvm_run = vcpu->run;
	int r;

	vcpu_load(vcpu);
	kvm_sigset_activate(vcpu);
	kvm_run->flags = 0;
	kvm_load_guest_fpu(vcpu);

	kvm_vcpu_srcu_read_lock(vcpu);
	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
		if (kvm_run->immediate_exit) {
			r = -EINTR;
			goto out;
		}
		/*
		 * It should be impossible for the hypervisor timer to be in
		 * use before KVM has ever run the vCPU.
		 */
		WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));

		kvm_vcpu_srcu_read_unlock(vcpu);
		kvm_vcpu_block(vcpu);
		kvm_vcpu_srcu_read_lock(vcpu);

		if (kvm_apic_accept_events(vcpu) < 0) {
			r = 0;
			goto out;
		}
		r = -EAGAIN;
		if (signal_pending(current)) {
			r = -EINTR;
			kvm_run->exit_reason = KVM_EXIT_INTR;
			++vcpu->stat.signal_exits;
		}
		goto out;
	}

	if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) ||
	    (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) {
		r = -EINVAL;
		goto out;
	}

	if (kvm_run->kvm_dirty_regs) {
		r = sync_regs(vcpu);
		if (r != 0)
			goto out;
	}

	/* re-sync apic's tpr */
	if (!lapic_in_kernel(vcpu)) {
		if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) {
			r = -EINVAL;
			goto out;
		}
	}

	/*
	 * If userspace set a pending exception and L2 is active, convert it to
	 * a pending VM-Exit if L1 wants to intercept the exception.
	 */
	if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) &&
	    kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector,
							ex->error_code)) {
		kvm_queue_exception_vmexit(vcpu, ex->vector,
					   ex->has_error_code, ex->error_code,
					   ex->has_payload, ex->payload);
		ex->injected = false;
		ex->pending = false;
	}
	vcpu->arch.exception_from_userspace = false;

	if (unlikely(vcpu->arch.complete_userspace_io)) {
		int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
		vcpu->arch.complete_userspace_io = NULL;
		r = cui(vcpu);
		if (r <= 0)
			goto out;
	} else {
		WARN_ON_ONCE(vcpu->arch.pio.count);
		WARN_ON_ONCE(vcpu->mmio_needed);
	}

	if (kvm_run->immediate_exit) {
		r = -EINTR;
		goto out;
	}

	r = static_call(kvm_x86_vcpu_pre_run)(vcpu);
	if (r <= 0)
		goto out;

	r = vcpu_run(vcpu);

out:
	kvm_put_guest_fpu(vcpu);
	if (kvm_run->kvm_valid_regs)
		store_regs(vcpu);
	post_kvm_run_save(vcpu);
	kvm_vcpu_srcu_read_unlock(vcpu);

	kvm_sigset_deactivate(vcpu);
	vcpu_put(vcpu);
	return r;
}

static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	if (vcpu->arch.emulate_regs_need_sync_to_vcpu) {
		/*
		 * We are here if userspace calls get_regs() in the middle of
		 * instruction emulation. Registers state needs to be copied
		 * back from emulation context to vcpu. Userspace shouldn't do
		 * that usually, but some bad designed PV devices (vmware
		 * backdoor interface) need this to work
		 */
		emulator_writeback_register_cache(vcpu->arch.emulate_ctxt);
		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
	}
	regs->rax = kvm_rax_read(vcpu);
	regs->rbx = kvm_rbx_read(vcpu);
	regs->rcx = kvm_rcx_read(vcpu);
	regs->rdx = kvm_rdx_read(vcpu);
	regs->rsi = kvm_rsi_read(vcpu);
	regs->rdi = kvm_rdi_read(vcpu);
	regs->rsp = kvm_rsp_read(vcpu);
	regs->rbp = kvm_rbp_read(vcpu);
#ifdef CONFIG_X86_64
	regs->r8 = kvm_r8_read(vcpu);
	regs->r9 = kvm_r9_read(vcpu);
	regs->r10 = kvm_r10_read(vcpu);
	regs->r11 = kvm_r11_read(vcpu);
	regs->r12 = kvm_r12_read(vcpu);
	regs->r13 = kvm_r13_read(vcpu);
	regs->r14 = kvm_r14_read(vcpu);
	regs->r15 = kvm_r15_read(vcpu);
#endif

	regs->rip = kvm_rip_read(vcpu);
	regs->rflags = kvm_get_rflags(vcpu);
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);
	__get_regs(vcpu, regs);
	vcpu_put(vcpu);
	return 0;
}

static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu->arch.emulate_regs_need_sync_from_vcpu = true;
	vcpu->arch.emulate_regs_need_sync_to_vcpu = false;

	kvm_rax_write(vcpu, regs->rax);
	kvm_rbx_write(vcpu, regs->rbx);
	kvm_rcx_write(vcpu, regs->rcx);
	kvm_rdx_write(vcpu, regs->rdx);
	kvm_rsi_write(vcpu, regs->rsi);
	kvm_rdi_write(vcpu, regs->rdi);
	kvm_rsp_write(vcpu, regs->rsp);
	kvm_rbp_write(vcpu, regs->rbp);
#ifdef CONFIG_X86_64
	kvm_r8_write(vcpu, regs->r8);
	kvm_r9_write(vcpu, regs->r9);
	kvm_r10_write(vcpu, regs->r10);
	kvm_r11_write(vcpu, regs->r11);
	kvm_r12_write(vcpu, regs->r12);
	kvm_r13_write(vcpu, regs->r13);
	kvm_r14_write(vcpu, regs->r14);
	kvm_r15_write(vcpu, regs->r15);
#endif

	kvm_rip_write(vcpu, regs->rip);
	kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);

	vcpu->arch.exception.pending = false;
	vcpu->arch.exception_vmexit.pending = false;

	kvm_make_request(KVM_REQ_EVENT, vcpu);
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);
	__set_regs(vcpu, regs);
	vcpu_put(vcpu);
	return 0;
}

static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	struct desc_ptr dt;

	if (vcpu->arch.guest_state_protected)
		goto skip_protected_regs;

	kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
	kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
	kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
	kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
	kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
	kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS);

	kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
	kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);

	static_call(kvm_x86_get_idt)(vcpu, &dt);
	sregs->idt.limit = dt.size;
	sregs->idt.base = dt.address;
	static_call(kvm_x86_get_gdt)(vcpu, &dt);
	sregs->gdt.limit = dt.size;
	sregs->gdt.base = dt.address;

	sregs->cr2 = vcpu->arch.cr2;
	sregs->cr3 = kvm_read_cr3(vcpu);

skip_protected_regs:
	sregs->cr0 = kvm_read_cr0(vcpu);
	sregs->cr4 = kvm_read_cr4(vcpu);
	sregs->cr8 = kvm_get_cr8(vcpu);
	sregs->efer = vcpu->arch.efer;
	sregs->apic_base = kvm_get_apic_base(vcpu);
}

static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	__get_sregs_common(vcpu, sregs);

	if (vcpu->arch.guest_state_protected)
		return;

	if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft)
		set_bit(vcpu->arch.interrupt.nr,
			(unsigned long *)sregs->interrupt_bitmap);
}

static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2)
{
	int i;

	__get_sregs_common(vcpu, (struct kvm_sregs *)sregs2);

	if (vcpu->arch.guest_state_protected)
		return;

	if (is_pae_paging(vcpu)) {
		for (i = 0 ; i < 4 ; i++)
			sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i);
		sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID;
	}
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	vcpu_load(vcpu);
	__get_sregs(vcpu, sregs);
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	int r;

	vcpu_load(vcpu);
	if (kvm_mpx_supported())
		kvm_load_guest_fpu(vcpu);

	r = kvm_apic_accept_events(vcpu);
	if (r < 0)
		goto out;
	r = 0;

	if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED ||
	     vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) &&
	    vcpu->arch.pv.pv_unhalted)
		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
	else
		mp_state->mp_state = vcpu->arch.mp_state;

out:
	if (kvm_mpx_supported())
		kvm_put_guest_fpu(vcpu);
	vcpu_put(vcpu);
	return r;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	int ret = -EINVAL;

	vcpu_load(vcpu);

	switch (mp_state->mp_state) {
	case KVM_MP_STATE_UNINITIALIZED:
	case KVM_MP_STATE_HALTED:
	case KVM_MP_STATE_AP_RESET_HOLD:
	case KVM_MP_STATE_INIT_RECEIVED:
	case KVM_MP_STATE_SIPI_RECEIVED:
		if (!lapic_in_kernel(vcpu))
			goto out;
		break;

	case KVM_MP_STATE_RUNNABLE:
		break;

	default:
		goto out;
	}

	/*
	 * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow
	 * forcing the guest into INIT/SIPI if those events are supposed to be
	 * blocked.  KVM prioritizes SMI over INIT, so reject INIT/SIPI state
	 * if an SMI is pending as well.
	 */
	if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) &&
	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
		goto out;

	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
	} else
		vcpu->arch.mp_state = mp_state->mp_state;
	kvm_make_request(KVM_REQ_EVENT, vcpu);

	ret = 0;
out:
	vcpu_put(vcpu);
	return ret;
}

int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
		    int reason, bool has_error_code, u32 error_code)
{
	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
	int ret;

	init_emulate_ctxt(vcpu);

	ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason,
				   has_error_code, error_code);
	if (ret) {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
		vcpu->run->internal.ndata = 0;
		return 0;
	}

	kvm_rip_write(vcpu, ctxt->eip);
	kvm_set_rflags(vcpu, ctxt->eflags);
	return 1;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);

static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
		/*
		 * When EFER.LME and CR0.PG are set, the processor is in
		 * 64-bit mode (though maybe in a 32-bit code segment).
		 * CR4.PAE and EFER.LMA must be set.
		 */
		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
			return false;
		if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3))
			return false;
	} else {
		/*
		 * Not in 64-bit mode: EFER.LMA is clear and the code
		 * segment cannot be 64-bit.
		 */
		if (sregs->efer & EFER_LMA || sregs->cs.l)
			return false;
	}

	return kvm_is_valid_cr4(vcpu, sregs->cr4);
}

static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
		int *mmu_reset_needed, bool update_pdptrs)
{
	struct msr_data apic_base_msr;
	int idx;
	struct desc_ptr dt;

	if (!kvm_is_valid_sregs(vcpu, sregs))
		return -EINVAL;

	apic_base_msr.data = sregs->apic_base;
	apic_base_msr.host_initiated = true;
	if (kvm_set_apic_base(vcpu, &apic_base_msr))
		return -EINVAL;

	if (vcpu->arch.guest_state_protected)
		return 0;

	dt.size = sregs->idt.limit;
	dt.address = sregs->idt.base;
	static_call(kvm_x86_set_idt)(vcpu, &dt);
	dt.size = sregs->gdt.limit;
	dt.address = sregs->gdt.base;
	static_call(kvm_x86_set_gdt)(vcpu, &dt);

	vcpu->arch.cr2 = sregs->cr2;
	*mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
	vcpu->arch.cr3 = sregs->cr3;
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
	static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3);

	kvm_set_cr8(vcpu, sregs->cr8);

	*mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
	static_call(kvm_x86_set_efer)(vcpu, sregs->efer);

	*mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
	static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0);
	vcpu->arch.cr0 = sregs->cr0;

	*mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
	static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4);

	if (update_pdptrs) {
		idx = srcu_read_lock(&vcpu->kvm->srcu);
		if (is_pae_paging(vcpu)) {
			load_pdptrs(vcpu, kvm_read_cr3(vcpu));
			*mmu_reset_needed = 1;
		}
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
	}

	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
	kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
	kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
	kvm_set_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
	kvm_set_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
	kvm_set_segment(vcpu, &sregs->ss, VCPU_SREG_SS);

	kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
	kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);

	update_cr8_intercept(vcpu);

	/* Older userspace won't unhalt the vcpu on reset. */
	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
	    !is_protmode(vcpu))
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

	return 0;
}

static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	int pending_vec, max_bits;
	int mmu_reset_needed = 0;
	int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true);

	if (ret)
		return ret;

	if (mmu_reset_needed)
		kvm_mmu_reset_context(vcpu);

	max_bits = KVM_NR_INTERRUPTS;
	pending_vec = find_first_bit(
		(const unsigned long *)sregs->interrupt_bitmap, max_bits);

	if (pending_vec < max_bits) {
		kvm_queue_interrupt(vcpu, pending_vec, false);
		pr_debug("Set back pending irq %d\n", pending_vec);
		kvm_make_request(KVM_REQ_EVENT, vcpu);
	}
	return 0;
}

static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2)
{
	int mmu_reset_needed = 0;
	bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID;
	bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) &&
		!(sregs2->efer & EFER_LMA);
	int i, ret;

	if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID)
		return -EINVAL;

	if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected))
		return -EINVAL;

	ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2,
				 &mmu_reset_needed, !valid_pdptrs);
	if (ret)
		return ret;

	if (valid_pdptrs) {
		for (i = 0; i < 4 ; i++)
			kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]);

		kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
		mmu_reset_needed = 1;
		vcpu->arch.pdptrs_from_userspace = true;
	}
	if (mmu_reset_needed)
		kvm_mmu_reset_context(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	int ret;

	vcpu_load(vcpu);
	ret = __set_sregs(vcpu, sregs);
	vcpu_put(vcpu);
	return ret;
}

static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm)
{
	bool set = false;
	struct kvm_vcpu *vcpu;
	unsigned long i;

	if (!enable_apicv)
		return;

	down_write(&kvm->arch.apicv_update_lock);

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) {
			set = true;
			break;
		}
	}
	__kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set);
	up_write(&kvm->arch.apicv_update_lock);
}

int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
{
	unsigned long rflags;
	int i, r;

	if (vcpu->arch.guest_state_protected)
		return -EINVAL;

	vcpu_load(vcpu);

	if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
		r = -EBUSY;
		if (kvm_is_exception_pending(vcpu))
			goto out;
		if (dbg->control & KVM_GUESTDBG_INJECT_DB)
			kvm_queue_exception(vcpu, DB_VECTOR);
		else
			kvm_queue_exception(vcpu, BP_VECTOR);
	}

	/*
	 * Read rflags as long as potentially injected trace flags are still
	 * filtered out.
	 */
	rflags = kvm_get_rflags(vcpu);

	vcpu->guest_debug = dbg->control;
	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
		vcpu->guest_debug = 0;

	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
		for (i = 0; i < KVM_NR_DB_REGS; ++i)
			vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
		vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7];
	} else {
		for (i = 0; i < KVM_NR_DB_REGS; i++)
			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
	}
	kvm_update_dr7(vcpu);

	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
		vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu);

	/*
	 * Trigger an rflags update that will inject or remove the trace
	 * flags.
	 */
	kvm_set_rflags(vcpu, rflags);

	static_call(kvm_x86_update_exception_bitmap)(vcpu);

	kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm);

	r = 0;

out:
	vcpu_put(vcpu);
	return r;
}

/*
 * Translate a guest virtual address to a guest physical address.
 */
int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				    struct kvm_translation *tr)
{
	unsigned long vaddr = tr->linear_address;
	gpa_t gpa;
	int idx;

	vcpu_load(vcpu);

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	tr->physical_address = gpa;
	tr->valid = gpa != INVALID_GPA;
	tr->writeable = 1;
	tr->usermode = 0;

	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct fxregs_state *fxsave;

	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
		return 0;

	vcpu_load(vcpu);

	fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;
	memcpy(fpu->fpr, fxsave->st_space, 128);
	fpu->fcw = fxsave->cwd;
	fpu->fsw = fxsave->swd;
	fpu->ftwx = fxsave->twd;
	fpu->last_opcode = fxsave->fop;
	fpu->last_ip = fxsave->rip;
	fpu->last_dp = fxsave->rdp;
	memcpy(fpu->xmm, fxsave->xmm_space, sizeof(fxsave->xmm_space));

	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct fxregs_state *fxsave;

	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
		return 0;

	vcpu_load(vcpu);

	fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;

	memcpy(fxsave->st_space, fpu->fpr, 128);
	fxsave->cwd = fpu->fcw;
	fxsave->swd = fpu->fsw;
	fxsave->twd = fpu->ftwx;
	fxsave->fop = fpu->last_opcode;
	fxsave->rip = fpu->last_ip;
	fxsave->rdp = fpu->last_dp;
	memcpy(fxsave->xmm_space, fpu->xmm, sizeof(fxsave->xmm_space));

	vcpu_put(vcpu);
	return 0;
}

static void store_regs(struct kvm_vcpu *vcpu)
{
	BUILD_BUG_ON(sizeof(struct kvm_sync_regs) > SYNC_REGS_SIZE_BYTES);

	if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_REGS)
		__get_regs(vcpu, &vcpu->run->s.regs.regs);

	if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_SREGS)
		__get_sregs(vcpu, &vcpu->run->s.regs.sregs);

	if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_EVENTS)
		kvm_vcpu_ioctl_x86_get_vcpu_events(
				vcpu, &vcpu->run->s.regs.events);
}

static int sync_regs(struct kvm_vcpu *vcpu)
{
	if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) {
		__set_regs(vcpu, &vcpu->run->s.regs.regs);
		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS;
	}
	if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) {
		if (__set_sregs(vcpu, &vcpu->run->s.regs.sregs))
			return -EINVAL;
		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS;
	}
	if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) {
		if (kvm_vcpu_ioctl_x86_set_vcpu_events(
				vcpu, &vcpu->run->s.regs.events))
			return -EINVAL;
		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS;
	}

	return 0;
}

int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
	if (kvm_check_tsc_unstable() && kvm->created_vcpus)
		pr_warn_once("kvm: SMP vm created on host with unstable TSC; "
			     "guest TSC will not be reliable\n");

	if (!kvm->arch.max_vcpu_ids)
		kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS;

	if (id >= kvm->arch.max_vcpu_ids)
		return -EINVAL;

	return static_call(kvm_x86_vcpu_precreate)(kvm);
}

int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
	struct page *page;
	int r;

	vcpu->arch.last_vmentry_cpu = -1;
	vcpu->arch.regs_avail = ~0;
	vcpu->arch.regs_dirty = ~0;

	kvm_gpc_init(&vcpu->arch.pv_time);

	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
	else
		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;

	r = kvm_mmu_create(vcpu);
	if (r < 0)
		return r;

	if (irqchip_in_kernel(vcpu->kvm)) {
		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
		if (r < 0)
			goto fail_mmu_destroy;

		/*
		 * Defer evaluating inhibits until the vCPU is first run, as
		 * this vCPU will not get notified of any changes until this
		 * vCPU is visible to other vCPUs (marked online and added to
		 * the set of vCPUs).  Opportunistically mark APICv active as
		 * VMX in particularly is highly unlikely to have inhibits.
		 * Ignore the current per-VM APICv state so that vCPU creation
		 * is guaranteed to run with a deterministic value, the request
		 * will ensure the vCPU gets the correct state before VM-Entry.
		 */
		if (enable_apicv) {
			vcpu->arch.apic->apicv_active = true;
			kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
		}
	} else
		static_branch_inc(&kvm_has_noapic_vcpu);

	r = -ENOMEM;

	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
	if (!page)
		goto fail_free_lapic;
	vcpu->arch.pio_data = page_address(page);

	vcpu->arch.mce_banks = kcalloc(KVM_MAX_MCE_BANKS * 4, sizeof(u64),
				       GFP_KERNEL_ACCOUNT);
	vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64),
					    GFP_KERNEL_ACCOUNT);
	if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks)
		goto fail_free_mce_banks;
	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;

	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
				GFP_KERNEL_ACCOUNT))
		goto fail_free_mce_banks;

	if (!alloc_emulate_ctxt(vcpu))
		goto free_wbinvd_dirty_mask;

	if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) {
		pr_err("kvm: failed to allocate vcpu's fpu\n");
		goto free_emulate_ctxt;
	}

	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
	vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu);

	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;

	kvm_async_pf_hash_reset(vcpu);

	vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
	kvm_pmu_init(vcpu);

	vcpu->arch.pending_external_vector = -1;
	vcpu->arch.preempted_in_kernel = false;

#if IS_ENABLED(CONFIG_HYPERV)
	vcpu->arch.hv_root_tdp = INVALID_PAGE;
#endif

	r = static_call(kvm_x86_vcpu_create)(vcpu);
	if (r)
		goto free_guest_fpu;

	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
	vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
	kvm_xen_init_vcpu(vcpu);
	kvm_vcpu_mtrr_init(vcpu);
	vcpu_load(vcpu);
	kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz);
	kvm_vcpu_reset(vcpu, false);
	kvm_init_mmu(vcpu);
	vcpu_put(vcpu);
	return 0;

free_guest_fpu:
	fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
free_emulate_ctxt:
	kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_wbinvd_dirty_mask:
	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
fail_free_mce_banks:
	kfree(vcpu->arch.mce_banks);
	kfree(vcpu->arch.mci_ctl2_banks);
	free_page((unsigned long)vcpu->arch.pio_data);
fail_free_lapic:
	kvm_free_lapic(vcpu);
fail_mmu_destroy:
	kvm_mmu_destroy(vcpu);
	return r;
}

void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;

	if (mutex_lock_killable(&vcpu->mutex))
		return;
	vcpu_load(vcpu);
	kvm_synchronize_tsc(vcpu, 0);
	vcpu_put(vcpu);

	/* poll control enabled by default */
	vcpu->arch.msr_kvm_poll_control = 1;

	mutex_unlock(&vcpu->mutex);

	if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0)
		schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
						KVMCLOCK_SYNC_PERIOD);
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	int idx;

	kvmclock_reset(vcpu);

	static_call(kvm_x86_vcpu_free)(vcpu);

	kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
	fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);

	kvm_xen_destroy_vcpu(vcpu);
	kvm_hv_vcpu_uninit(vcpu);
	kvm_pmu_destroy(vcpu);
	kfree(vcpu->arch.mce_banks);
	kfree(vcpu->arch.mci_ctl2_banks);
	kvm_free_lapic(vcpu);
	idx = srcu_read_lock(&vcpu->kvm->srcu);
	kvm_mmu_destroy(vcpu);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	free_page((unsigned long)vcpu->arch.pio_data);
	kvfree(vcpu->arch.cpuid_entries);
	if (!lapic_in_kernel(vcpu))
		static_branch_dec(&kvm_has_noapic_vcpu);
}

void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
	struct kvm_cpuid_entry2 *cpuid_0x1;
	unsigned long old_cr0 = kvm_read_cr0(vcpu);
	unsigned long new_cr0;

	/*
	 * Several of the "set" flows, e.g. ->set_cr0(), read other registers
	 * to handle side effects.  RESET emulation hits those flows and relies
	 * on emulated/virtualized registers, including those that are loaded
	 * into hardware, to be zeroed at vCPU creation.  Use CRs as a sentinel
	 * to detect improper or missing initialization.
	 */
	WARN_ON_ONCE(!init_event &&
		     (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));

	/*
	 * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
	 * possible to INIT the vCPU while L2 is active.  Force the vCPU back
	 * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
	 * bits), i.e. virtualization is disabled.
	 */
	if (is_guest_mode(vcpu))
		kvm_leave_nested(vcpu);

	kvm_lapic_reset(vcpu, init_event);

	WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
	vcpu->arch.hflags = 0;

	vcpu->arch.smi_pending = 0;
	vcpu->arch.smi_count = 0;
	atomic_set(&vcpu->arch.nmi_queued, 0);
	vcpu->arch.nmi_pending = 0;
	vcpu->arch.nmi_injected = false;
	kvm_clear_interrupt_queue(vcpu);
	kvm_clear_exception_queue(vcpu);

	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
	kvm_update_dr0123(vcpu);
	vcpu->arch.dr6 = DR6_ACTIVE_LOW;
	vcpu->arch.dr7 = DR7_FIXED_1;
	kvm_update_dr7(vcpu);

	vcpu->arch.cr2 = 0;

	kvm_make_request(KVM_REQ_EVENT, vcpu);
	vcpu->arch.apf.msr_en_val = 0;
	vcpu->arch.apf.msr_int_val = 0;
	vcpu->arch.st.msr_val = 0;

	kvmclock_reset(vcpu);

	kvm_clear_async_pf_completion_queue(vcpu);
	kvm_async_pf_hash_reset(vcpu);
	vcpu->arch.apf.halted = false;

	if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) {
		struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;

		/*
		 * All paths that lead to INIT are required to load the guest's
		 * FPU state (because most paths are buried in KVM_RUN).
		 */
		if (init_event)
			kvm_put_guest_fpu(vcpu);

		fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS);
		fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR);

		if (init_event)
			kvm_load_guest_fpu(vcpu);
	}

	if (!init_event) {
		kvm_pmu_reset(vcpu);
		vcpu->arch.smbase = 0x30000;

		vcpu->arch.msr_misc_features_enables = 0;
		vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL |
						  MSR_IA32_MISC_ENABLE_BTS_UNAVAIL;

		__kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP);
		__kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true);
	}

	/* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */
	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
	kvm_register_mark_dirty(vcpu, VCPU_REGS_RSP);

	/*
	 * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon)
	 * if no CPUID match is found.  Note, it's impossible to get a match at
	 * RESET since KVM emulates RESET before exposing the vCPU to userspace,
	 * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry
	 * on RESET.  But, go through the motions in case that's ever remedied.
	 */
	cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1);
	kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600);

	static_call(kvm_x86_vcpu_reset)(vcpu, init_event);

	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
	kvm_rip_write(vcpu, 0xfff0);

	vcpu->arch.cr3 = 0;
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);

	/*
	 * CR0.CD/NW are set on RESET, preserved on INIT.  Note, some versions
	 * of Intel's SDM list CD/NW as being set on INIT, but they contradict
	 * (or qualify) that with a footnote stating that CD/NW are preserved.
	 */
	new_cr0 = X86_CR0_ET;
	if (init_event)
		new_cr0 |= (old_cr0 & (X86_CR0_NW | X86_CR0_CD));
	else
		new_cr0 |= X86_CR0_NW | X86_CR0_CD;

	static_call(kvm_x86_set_cr0)(vcpu, new_cr0);
	static_call(kvm_x86_set_cr4)(vcpu, 0);
	static_call(kvm_x86_set_efer)(vcpu, 0);
	static_call(kvm_x86_update_exception_bitmap)(vcpu);

	/*
	 * On the standard CR0/CR4/EFER modification paths, there are several
	 * complex conditions determining whether the MMU has to be reset and/or
	 * which PCIDs have to be flushed.  However, CR0.WP and the paging-related
	 * bits in CR4 and EFER are irrelevant if CR0.PG was '0'; and a reset+flush
	 * is needed anyway if CR0.PG was '1' (which can only happen for INIT, as
	 * CR0 will be '0' prior to RESET).  So we only need to check CR0.PG here.
	 */
	if (old_cr0 & X86_CR0_PG) {
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
		kvm_mmu_reset_context(vcpu);
	}

	/*
	 * Intel's SDM states that all TLB entries are flushed on INIT.  AMD's
	 * APM states the TLBs are untouched by INIT, but it also states that
	 * the TLBs are flushed on "External initialization of the processor."
	 * Flush the guest TLB regardless of vendor, there is no meaningful
	 * benefit in relying on the guest to flush the TLB immediately after
	 * INIT.  A spurious TLB flush is benign and likely negligible from a
	 * performance perspective.
	 */
	if (init_event)
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reset);

void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
{
	struct kvm_segment cs;

	kvm_get_segment(vcpu, &cs, VCPU_SREG_CS);
	cs.selector = vector << 8;
	cs.base = vector << 12;
	kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
	kvm_rip_write(vcpu, 0);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector);

int kvm_arch_hardware_enable(void)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	unsigned long i;
	int ret;
	u64 local_tsc;
	u64 max_tsc = 0;
	bool stable, backwards_tsc = false;

	kvm_user_return_msr_cpu_online();
	ret = static_call(kvm_x86_hardware_enable)();
	if (ret != 0)
		return ret;

	local_tsc = rdtsc();
	stable = !kvm_check_tsc_unstable();
	list_for_each_entry(kvm, &vm_list, vm_list) {
		kvm_for_each_vcpu(i, vcpu, kvm) {
			if (!stable && vcpu->cpu == smp_processor_id())
				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
			if (stable && vcpu->arch.last_host_tsc > local_tsc) {
				backwards_tsc = true;
				if (vcpu->arch.last_host_tsc > max_tsc)
					max_tsc = vcpu->arch.last_host_tsc;
			}
		}
	}

	/*
	 * Sometimes, even reliable TSCs go backwards.  This happens on
	 * platforms that reset TSC during suspend or hibernate actions, but
	 * maintain synchronization.  We must compensate.  Fortunately, we can
	 * detect that condition here, which happens early in CPU bringup,
	 * before any KVM threads can be running.  Unfortunately, we can't
	 * bring the TSCs fully up to date with real time, as we aren't yet far
	 * enough into CPU bringup that we know how much real time has actually
	 * elapsed; our helper function, ktime_get_boottime_ns() will be using boot
	 * variables that haven't been updated yet.
	 *
	 * So we simply find the maximum observed TSC above, then record the
	 * adjustment to TSC in each VCPU.  When the VCPU later gets loaded,
	 * the adjustment will be applied.  Note that we accumulate
	 * adjustments, in case multiple suspend cycles happen before some VCPU
	 * gets a chance to run again.  In the event that no KVM threads get a
	 * chance to run, we will miss the entire elapsed period, as we'll have
	 * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may
	 * loose cycle time.  This isn't too big a deal, since the loss will be
	 * uniform across all VCPUs (not to mention the scenario is extremely
	 * unlikely). It is possible that a second hibernate recovery happens
	 * much faster than a first, causing the observed TSC here to be
	 * smaller; this would require additional padding adjustment, which is
	 * why we set last_host_tsc to the local tsc observed here.
	 *
	 * N.B. - this code below runs only on platforms with reliable TSC,
	 * as that is the only way backwards_tsc is set above.  Also note
	 * that this runs for ALL vcpus, which is not a bug; all VCPUs should
	 * have the same delta_cyc adjustment applied if backwards_tsc
	 * is detected.  Note further, this adjustment is only done once,
	 * as we reset last_host_tsc on all VCPUs to stop this from being
	 * called multiple times (one for each physical CPU bringup).
	 *
	 * Platforms with unreliable TSCs don't have to deal with this, they
	 * will be compensated by the logic in vcpu_load, which sets the TSC to
	 * catchup mode.  This will catchup all VCPUs to real time, but cannot
	 * guarantee that they stay in perfect synchronization.
	 */
	if (backwards_tsc) {
		u64 delta_cyc = max_tsc - local_tsc;
		list_for_each_entry(kvm, &vm_list, vm_list) {
			kvm->arch.backwards_tsc_observed = true;
			kvm_for_each_vcpu(i, vcpu, kvm) {
				vcpu->arch.tsc_offset_adjustment += delta_cyc;
				vcpu->arch.last_host_tsc = local_tsc;
				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
			}

			/*
			 * We have to disable TSC offset matching.. if you were
			 * booting a VM while issuing an S4 host suspend....
			 * you may have some problem.  Solving this issue is
			 * left as an exercise to the reader.
			 */
			kvm->arch.last_tsc_nsec = 0;
			kvm->arch.last_tsc_write = 0;
		}

	}
	return 0;
}

void kvm_arch_hardware_disable(void)
{
	static_call(kvm_x86_hardware_disable)();
	drop_user_return_notifiers();
}

static inline void kvm_ops_update(struct kvm_x86_init_ops *ops)
{
	memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops));

#define __KVM_X86_OP(func) \
	static_call_update(kvm_x86_##func, kvm_x86_ops.func);
#define KVM_X86_OP(func) \
	WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func)
#define KVM_X86_OP_OPTIONAL __KVM_X86_OP
#define KVM_X86_OP_OPTIONAL_RET0(func) \
	static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \
					   (void *)__static_call_return0);
#include <asm/kvm-x86-ops.h>
#undef __KVM_X86_OP

	kvm_pmu_ops_update(ops->pmu_ops);
}

int kvm_arch_hardware_setup(void *opaque)
{
	struct kvm_x86_init_ops *ops = opaque;
	int r;

	rdmsrl_safe(MSR_EFER, &host_efer);

	if (boot_cpu_has(X86_FEATURE_XSAVES))
		rdmsrl(MSR_IA32_XSS, host_xss);

	kvm_init_pmu_capability();

	r = ops->hardware_setup();
	if (r != 0)
		return r;

	kvm_ops_update(ops);

	kvm_register_perf_callbacks(ops->handle_intel_pt_intr);

	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
		kvm_caps.supported_xss = 0;

#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f)
	cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_);
#undef __kvm_cpu_cap_has

	if (kvm_caps.has_tsc_control) {
		/*
		 * Make sure the user can only configure tsc_khz values that
		 * fit into a signed integer.
		 * A min value is not calculated because it will always
		 * be 1 on all machines.
		 */
		u64 max = min(0x7fffffffULL,
			      __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz));
		kvm_caps.max_guest_tsc_khz = max;
	}
	kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits;
	kvm_init_msr_list();
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
	kvm_unregister_perf_callbacks();

	static_call(kvm_x86_hardware_unsetup)();
}

int kvm_arch_check_processor_compat(void *opaque)
{
	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
	struct kvm_x86_init_ops *ops = opaque;

	WARN_ON(!irqs_disabled());

	if (__cr4_reserved_bits(cpu_has, c) !=
	    __cr4_reserved_bits(cpu_has, &boot_cpu_data))
		return -EIO;

	return ops->check_processor_compatibility();
}

bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
{
	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);

bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
{
	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
}

__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu);
EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu);

void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);

	vcpu->arch.l1tf_flush_l1d = true;
	if (pmu->version && unlikely(pmu->event_count)) {
		pmu->need_cleanup = true;
		kvm_make_request(KVM_REQ_PMU, vcpu);
	}
	static_call(kvm_x86_sched_in)(vcpu, cpu);
}

void kvm_arch_free_vm(struct kvm *kvm)
{
	kfree(to_kvm_hv(kvm)->hv_pa_pg);
	__kvm_arch_free_vm(kvm);
}


int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
	int ret;
	unsigned long flags;

	if (type)
		return -EINVAL;

	ret = kvm_page_track_init(kvm);
	if (ret)
		goto out;

	ret = kvm_mmu_init_vm(kvm);
	if (ret)
		goto out_page_track;

	ret = static_call(kvm_x86_vm_init)(kvm);
	if (ret)
		goto out_uninit_mmu;

	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
	atomic_set(&kvm->arch.noncoherent_dma_count, 0);

	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
	/* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
	set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
		&kvm->arch.irq_sources_bitmap);

	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
	mutex_init(&kvm->arch.apic_map_lock);
	seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();

	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
	pvclock_update_vm_gtod_copy(kvm);
	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);

	kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz;
	kvm->arch.guest_can_read_msr_platform_info = true;
	kvm->arch.enable_pmu = enable_pmu;

#if IS_ENABLED(CONFIG_HYPERV)
	spin_lock_init(&kvm->arch.hv_root_tdp_lock);
	kvm->arch.hv_root_tdp = INVALID_PAGE;
#endif

	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);

	kvm_apicv_init(kvm);
	kvm_hv_init_vm(kvm);
	kvm_xen_init_vm(kvm);

	return 0;

out_uninit_mmu:
	kvm_mmu_uninit_vm(kvm);
out_page_track:
	kvm_page_track_cleanup(kvm);
out:
	return ret;
}

int kvm_arch_post_init_vm(struct kvm *kvm)
{
	return kvm_mmu_post_init_vm(kvm);
}

static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
	vcpu_load(vcpu);
	kvm_mmu_unload(vcpu);
	vcpu_put(vcpu);
}

static void kvm_unload_vcpu_mmus(struct kvm *kvm)
{
	unsigned long i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_unload_vcpu_mmu(vcpu);
	}
}

void kvm_arch_sync_events(struct kvm *kvm)
{
	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
	kvm_free_pit(kvm);
}

/**
 * __x86_set_memory_region: Setup KVM internal memory slot
 *
 * @kvm: the kvm pointer to the VM.
 * @id: the slot ID to setup.
 * @gpa: the GPA to install the slot (unused when @size == 0).
 * @size: the size of the slot. Set to zero to uninstall a slot.
 *
 * This function helps to setup a KVM internal memory slot.  Specify
 * @size > 0 to install a new slot, while @size == 0 to uninstall a
 * slot.  The return code can be one of the following:
 *
 *   HVA:           on success (uninstall will return a bogus HVA)
 *   -errno:        on error
 *
 * The caller should always use IS_ERR() to check the return value
 * before use.  Note, the KVM internal memory slots are guaranteed to
 * remain valid and unchanged until the VM is destroyed, i.e., the
 * GPA->HVA translation will not change.  However, the HVA is a user
 * address, i.e. its accessibility is not guaranteed, and must be
 * accessed via __copy_{to,from}_user().
 */
void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
				      u32 size)
{
	int i, r;
	unsigned long hva, old_npages;
	struct kvm_memslots *slots = kvm_memslots(kvm);
	struct kvm_memory_slot *slot;

	/* Called with kvm->slots_lock held.  */
	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
		return ERR_PTR_USR(-EINVAL);

	slot = id_to_memslot(slots, id);
	if (size) {
		if (slot && slot->npages)
			return ERR_PTR_USR(-EEXIST);

		/*
		 * MAP_SHARED to prevent internal slot pages from being moved
		 * by fork()/COW.
		 */
		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
			      MAP_SHARED | MAP_ANONYMOUS, 0);
		if (IS_ERR((void *)hva))
			return (void __user *)hva;
	} else {
		if (!slot || !slot->npages)
			return NULL;

		old_npages = slot->npages;
		hva = slot->userspace_addr;
	}

	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
		struct kvm_userspace_memory_region m;

		m.slot = id | (i << 16);
		m.flags = 0;
		m.guest_phys_addr = gpa;
		m.userspace_addr = hva;
		m.memory_size = size;
		r = __kvm_set_memory_region(kvm, &m);
		if (r < 0)
			return ERR_PTR_USR(r);
	}

	if (!size)
		vm_munmap(hva, old_npages * PAGE_SIZE);

	return (void __user *)hva;
}
EXPORT_SYMBOL_GPL(__x86_set_memory_region);

void kvm_arch_pre_destroy_vm(struct kvm *kvm)
{
	kvm_mmu_pre_destroy_vm(kvm);
}

void kvm_arch_destroy_vm(struct kvm *kvm)
{
	if (current->mm == kvm->mm) {
		/*
		 * Free memory regions allocated on behalf of userspace,
		 * unless the memory map has changed due to process exit
		 * or fd copying.
		 */
		mutex_lock(&kvm->slots_lock);
		__x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
					0, 0);
		__x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
					0, 0);
		__x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
		mutex_unlock(&kvm->slots_lock);
	}
	kvm_unload_vcpu_mmus(kvm);
	static_call_cond(kvm_x86_vm_destroy)(kvm);
	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
	kvm_pic_destroy(kvm);
	kvm_ioapic_destroy(kvm);
	kvm_destroy_vcpus(kvm);
	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
	kvm_mmu_uninit_vm(kvm);
	kvm_page_track_cleanup(kvm);
	kvm_xen_destroy_vm(kvm);
	kvm_hv_destroy_vm(kvm);
}

static void memslot_rmap_free(struct kvm_memory_slot *slot)
{
	int i;

	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
		kvfree(slot->arch.rmap[i]);
		slot->arch.rmap[i] = NULL;
	}
}

void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
	int i;

	memslot_rmap_free(slot);

	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
		kvfree(slot->arch.lpage_info[i - 1]);
		slot->arch.lpage_info[i - 1] = NULL;
	}

	kvm_page_track_free_memslot(slot);
}

int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages)
{
	const int sz = sizeof(*slot->arch.rmap[0]);
	int i;

	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
		int level = i + 1;
		int lpages = __kvm_mmu_slot_lpages(slot, npages, level);

		if (slot->arch.rmap[i])
			continue;

		slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
		if (!slot->arch.rmap[i]) {
			memslot_rmap_free(slot);
			return -ENOMEM;
		}
	}

	return 0;
}

static int kvm_alloc_memslot_metadata(struct kvm *kvm,
				      struct kvm_memory_slot *slot)
{
	unsigned long npages = slot->npages;
	int i, r;

	/*
	 * Clear out the previous array pointers for the KVM_MR_MOVE case.  The
	 * old arrays will be freed by __kvm_set_memory_region() if installing
	 * the new memslot is successful.
	 */
	memset(&slot->arch, 0, sizeof(slot->arch));

	if (kvm_memslots_have_rmaps(kvm)) {
		r = memslot_rmap_alloc(slot, npages);
		if (r)
			return r;
	}

	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
		struct kvm_lpage_info *linfo;
		unsigned long ugfn;
		int lpages;
		int level = i + 1;

		lpages = __kvm_mmu_slot_lpages(slot, npages, level);

		linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
		if (!linfo)
			goto out_free;

		slot->arch.lpage_info[i - 1] = linfo;

		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
			linfo[0].disallow_lpage = 1;
		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
			linfo[lpages - 1].disallow_lpage = 1;
		ugfn = slot->userspace_addr >> PAGE_SHIFT;
		/*
		 * If the gfn and userspace address are not aligned wrt each
		 * other, disable large page support for this slot.
		 */
		if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) {
			unsigned long j;

			for (j = 0; j < lpages; ++j)
				linfo[j].disallow_lpage = 1;
		}
	}

	if (kvm_page_track_create_memslot(kvm, slot, npages))
		goto out_free;

	return 0;

out_free:
	memslot_rmap_free(slot);

	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
		kvfree(slot->arch.lpage_info[i - 1]);
		slot->arch.lpage_info[i - 1] = NULL;
	}
	return -ENOMEM;
}

void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;

	/*
	 * memslots->generation has been incremented.
	 * mmio generation may have reached its maximum value.
	 */
	kvm_mmu_invalidate_mmio_sptes(kvm, gen);

	/* Force re-initialization of steal_time cache */
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_vcpu_kick(vcpu);
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   const struct kvm_memory_slot *old,
				   struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) {
		if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn())
			return -EINVAL;

		return kvm_alloc_memslot_metadata(kvm, new);
	}

	if (change == KVM_MR_FLAGS_ONLY)
		memcpy(&new->arch, &old->arch, sizeof(old->arch));
	else if (WARN_ON_ONCE(change != KVM_MR_DELETE))
		return -EIO;

	return 0;
}


static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable)
{
	struct kvm_arch *ka = &kvm->arch;

	if (!kvm_x86_ops.cpu_dirty_log_size)
		return;

	if ((enable && ++ka->cpu_dirty_logging_count == 1) ||
	    (!enable && --ka->cpu_dirty_logging_count == 0))
		kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING);

	WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0);
}

static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
				     struct kvm_memory_slot *old,
				     const struct kvm_memory_slot *new,
				     enum kvm_mr_change change)
{
	u32 old_flags = old ? old->flags : 0;
	u32 new_flags = new ? new->flags : 0;
	bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES;

	/*
	 * Update CPU dirty logging if dirty logging is being toggled.  This
	 * applies to all operations.
	 */
	if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES)
		kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages);

	/*
	 * Nothing more to do for RO slots (which can't be dirtied and can't be
	 * made writable) or CREATE/MOVE/DELETE of a slot.
	 *
	 * For a memslot with dirty logging disabled:
	 * CREATE:      No dirty mappings will already exist.
	 * MOVE/DELETE: The old mappings will already have been cleaned up by
	 *		kvm_arch_flush_shadow_memslot()
	 *
	 * For a memslot with dirty logging enabled:
	 * CREATE:      No shadow pages exist, thus nothing to write-protect
	 *		and no dirty bits to clear.
	 * MOVE/DELETE: The old mappings will already have been cleaned up by
	 *		kvm_arch_flush_shadow_memslot().
	 */
	if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY))
		return;

	/*
	 * READONLY and non-flags changes were filtered out above, and the only
	 * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty
	 * logging isn't being toggled on or off.
	 */
	if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES)))
		return;

	if (!log_dirty_pages) {
		/*
		 * Dirty logging tracks sptes in 4k granularity, meaning that
		 * large sptes have to be split.  If live migration succeeds,
		 * the guest in the source machine will be destroyed and large
		 * sptes will be created in the destination.  However, if the
		 * guest continues to run in the source machine (for example if
		 * live migration fails), small sptes will remain around and
		 * cause bad performance.
		 *
		 * Scan sptes if dirty logging has been stopped, dropping those
		 * which can be collapsed into a single large-page spte.  Later
		 * page faults will create the large-page sptes.
		 */
		kvm_mmu_zap_collapsible_sptes(kvm, new);
	} else {
		/*
		 * Initially-all-set does not require write protecting any page,
		 * because they're all assumed to be dirty.
		 */
		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
			return;

		if (READ_ONCE(eager_page_split))
			kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K);

		if (kvm_x86_ops.cpu_dirty_log_size) {
			kvm_mmu_slot_leaf_clear_dirty(kvm, new);
			kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M);
		} else {
			kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K);
		}

		/*
		 * Unconditionally flush the TLBs after enabling dirty logging.
		 * A flush is almost always going to be necessary (see below),
		 * and unconditionally flushing allows the helpers to omit
		 * the subtly complex checks when removing write access.
		 *
		 * Do the flush outside of mmu_lock to reduce the amount of
		 * time mmu_lock is held.  Flushing after dropping mmu_lock is
		 * safe as KVM only needs to guarantee the slot is fully
		 * write-protected before returning to userspace, i.e. before
		 * userspace can consume the dirty status.
		 *
		 * Flushing outside of mmu_lock requires KVM to be careful when
		 * making decisions based on writable status of an SPTE, e.g. a
		 * !writable SPTE doesn't guarantee a CPU can't perform writes.
		 *
		 * Specifically, KVM also write-protects guest page tables to
		 * monitor changes when using shadow paging, and must guarantee
		 * no CPUs can write to those page before mmu_lock is dropped.
		 * Because CPUs may have stale TLB entries at this point, a
		 * !writable SPTE doesn't guarantee CPUs can't perform writes.
		 *
		 * KVM also allows making SPTES writable outside of mmu_lock,
		 * e.g. to allow dirty logging without taking mmu_lock.
		 *
		 * To handle these scenarios, KVM uses a separate software-only
		 * bit (MMU-writable) to track if a SPTE is !writable due to
		 * a guest page table being write-protected (KVM clears the
		 * MMU-writable flag when write-protecting for shadow paging).
		 *
		 * The use of MMU-writable is also the primary motivation for
		 * the unconditional flush.  Because KVM must guarantee that a
		 * CPU doesn't contain stale, writable TLB entries for a
		 * !MMU-writable SPTE, KVM must flush if it encounters any
		 * MMU-writable SPTE regardless of whether the actual hardware
		 * writable bit was set.  I.e. KVM is almost guaranteed to need
		 * to flush, while unconditionally flushing allows the "remove
		 * write access" helpers to ignore MMU-writable entirely.
		 *
		 * See is_writable_pte() for more details (the case involving
		 * access-tracked SPTEs is particularly relevant).
		 */
		kvm_arch_flush_remote_tlbs_memslot(kvm, new);
	}
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *old,
				const struct kvm_memory_slot *new,
				enum kvm_mr_change change)
{
	if (!kvm->arch.n_requested_mmu_pages &&
	    (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) {
		unsigned long nr_mmu_pages;

		nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO;
		nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
	}

	kvm_mmu_slot_apply_flags(kvm, old, new, change);

	/* Free the arrays associated with the old memslot. */
	if (change == KVM_MR_MOVE)
		kvm_arch_free_memslot(kvm, old);
}

void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
	kvm_mmu_zap_all(kvm);
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
	kvm_page_track_flush_slot(kvm, slot);
}

static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
{
	return (is_guest_mode(vcpu) &&
		static_call(kvm_x86_guest_apic_has_interrupt)(vcpu));
}

static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
	if (!list_empty_careful(&vcpu->async_pf.done))
		return true;

	if (kvm_apic_has_pending_init_or_sipi(vcpu) &&
	    kvm_apic_init_sipi_allowed(vcpu))
		return true;

	if (vcpu->arch.pv.pv_unhalted)
		return true;

	if (kvm_is_exception_pending(vcpu))
		return true;

	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
	    (vcpu->arch.nmi_pending &&
	     static_call(kvm_x86_nmi_allowed)(vcpu, false)))
		return true;

#ifdef CONFIG_KVM_SMM
	if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
	    (vcpu->arch.smi_pending &&
	     static_call(kvm_x86_smi_allowed)(vcpu, false)))
		return true;
#endif

	if (kvm_arch_interrupt_allowed(vcpu) &&
	    (kvm_cpu_has_interrupt(vcpu) ||
	    kvm_guest_apic_has_interrupt(vcpu)))
		return true;

	if (kvm_hv_has_stimer_pending(vcpu))
		return true;

	if (is_guest_mode(vcpu) &&
	    kvm_x86_ops.nested_ops->has_events &&
	    kvm_x86_ops.nested_ops->has_events(vcpu))
		return true;

	if (kvm_xen_has_pending_events(vcpu))
		return true;

	return false;
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
}

bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
	if (kvm_vcpu_apicv_active(vcpu) &&
	    static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu))
		return true;

	return false;
}

bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
{
	if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
		return true;

	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
#ifdef CONFIG_KVM_SMM
		kvm_test_request(KVM_REQ_SMI, vcpu) ||
#endif
		 kvm_test_request(KVM_REQ_EVENT, vcpu))
		return true;

	return kvm_arch_dy_has_pending_interrupt(vcpu);
}

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.guest_state_protected)
		return true;

	return vcpu->arch.preempted_in_kernel;
}

unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
{
	return kvm_rip_read(vcpu);
}

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}

int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
{
	return static_call(kvm_x86_interrupt_allowed)(vcpu, false);
}

unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu)
{
	/* Can't read the RIP when guest state is protected, just return 0 */
	if (vcpu->arch.guest_state_protected)
		return 0;

	if (is_64_bit_mode(vcpu))
		return kvm_rip_read(vcpu);
	return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) +
		     kvm_rip_read(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_get_linear_rip);

bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
{
	return kvm_get_linear_rip(vcpu) == linear_rip;
}
EXPORT_SYMBOL_GPL(kvm_is_linear_rip);

unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
{
	unsigned long rflags;

	rflags = static_call(kvm_x86_get_rflags)(vcpu);
	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
		rflags &= ~X86_EFLAGS_TF;
	return rflags;
}
EXPORT_SYMBOL_GPL(kvm_get_rflags);

static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
	    kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
		rflags |= X86_EFLAGS_TF;
	static_call(kvm_x86_set_rflags)(vcpu, rflags);
}

void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
	__kvm_set_rflags(vcpu, rflags);
	kvm_make_request(KVM_REQ_EVENT, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);

static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
{
	BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU));

	return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU));
}

static inline u32 kvm_async_pf_next_probe(u32 key)
{
	return (key + 1) & (ASYNC_PF_PER_VCPU - 1);
}

static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	u32 key = kvm_async_pf_hash_fn(gfn);

	while (vcpu->arch.apf.gfns[key] != ~0)
		key = kvm_async_pf_next_probe(key);

	vcpu->arch.apf.gfns[key] = gfn;
}

static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	int i;
	u32 key = kvm_async_pf_hash_fn(gfn);

	for (i = 0; i < ASYNC_PF_PER_VCPU &&
		     (vcpu->arch.apf.gfns[key] != gfn &&
		      vcpu->arch.apf.gfns[key] != ~0); i++)
		key = kvm_async_pf_next_probe(key);

	return key;
}

bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn;
}

static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	u32 i, j, k;

	i = j = kvm_async_pf_gfn_slot(vcpu, gfn);

	if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn))
		return;

	while (true) {
		vcpu->arch.apf.gfns[i] = ~0;
		do {
			j = kvm_async_pf_next_probe(j);
			if (vcpu->arch.apf.gfns[j] == ~0)
				return;
			k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]);
			/*
			 * k lies cyclically in ]i,j]
			 * |    i.k.j |
			 * |....j i.k.| or  |.k..j i...|
			 */
		} while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j));
		vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j];
		i = j;
	}
}

static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu)
{
	u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT;

	return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &reason,
				      sizeof(reason));
}

static inline int apf_put_user_ready(struct kvm_vcpu *vcpu, u32 token)
{
	unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token);

	return kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data,
					     &token, offset, sizeof(token));
}

static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu)
{
	unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token);
	u32 val;

	if (kvm_read_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data,
					 &val, offset, sizeof(val)))
		return false;

	return !val;
}

static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
{

	if (!kvm_pv_async_pf_enabled(vcpu))
		return false;

	if (vcpu->arch.apf.send_user_only &&
	    static_call(kvm_x86_get_cpl)(vcpu) == 0)
		return false;

	if (is_guest_mode(vcpu)) {
		/*
		 * L1 needs to opt into the special #PF vmexits that are
		 * used to deliver async page faults.
		 */
		return vcpu->arch.apf.delivery_as_pf_vmexit;
	} else {
		/*
		 * Play it safe in case the guest temporarily disables paging.
		 * The real mode IDT in particular is unlikely to have a #PF
		 * exception setup.
		 */
		return is_paging(vcpu);
	}
}

bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
	if (unlikely(!lapic_in_kernel(vcpu) ||
		     kvm_event_needs_reinjection(vcpu) ||
		     kvm_is_exception_pending(vcpu)))
		return false;

	if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu))
		return false;

	/*
	 * If interrupts are off we cannot even use an artificial
	 * halt state.
	 */
	return kvm_arch_interrupt_allowed(vcpu);
}

bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
				     struct kvm_async_pf *work)
{
	struct x86_exception fault;

	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);

	if (kvm_can_deliver_async_pf(vcpu) &&
	    !apf_put_user_notpresent(vcpu)) {
		fault.vector = PF_VECTOR;
		fault.error_code_valid = true;
		fault.error_code = 0;
		fault.nested_page_fault = false;
		fault.address = work->arch.token;
		fault.async_page_fault = true;
		kvm_inject_page_fault(vcpu, &fault);
		return true;
	} else {
		/*
		 * It is not possible to deliver a paravirtualized asynchronous
		 * page fault, but putting the guest in an artificial halt state
		 * can be beneficial nevertheless: if an interrupt arrives, we
		 * can deliver it timely and perhaps the guest will schedule
		 * another process.  When the instruction that triggered a page
		 * fault is retried, hopefully the page will be ready in the host.
		 */
		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
		return false;
	}
}

void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
				 struct kvm_async_pf *work)
{
	struct kvm_lapic_irq irq = {
		.delivery_mode = APIC_DM_FIXED,
		.vector = vcpu->arch.apf.vec
	};

	if (work->wakeup_all)
		work->arch.token = ~0; /* broadcast wakeup */
	else
		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);

	if ((work->wakeup_all || work->notpresent_injected) &&
	    kvm_pv_async_pf_enabled(vcpu) &&
	    !apf_put_user_ready(vcpu, work->arch.token)) {
		vcpu->arch.apf.pageready_pending = true;
		kvm_apic_set_irq(vcpu, &irq, NULL);
	}

	vcpu->arch.apf.halted = false;
	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}

void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu)
{
	kvm_make_request(KVM_REQ_APF_READY, vcpu);
	if (!vcpu->arch.apf.pageready_pending)
		kvm_vcpu_kick(vcpu);
}

bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
{
	if (!kvm_pv_async_pf_enabled(vcpu))
		return true;
	else
		return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu);
}

void kvm_arch_start_assignment(struct kvm *kvm)
{
	if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
		static_call_cond(kvm_x86_pi_start_assignment)(kvm);
}
EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);

void kvm_arch_end_assignment(struct kvm *kvm)
{
	atomic_dec(&kvm->arch.assigned_device_count);
}
EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);

bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm)
{
	return arch_atomic_read(&kvm->arch.assigned_device_count);
}
EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);

void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
{
	atomic_inc(&kvm->arch.noncoherent_dma_count);
}
EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma);

void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
{
	atomic_dec(&kvm->arch.noncoherent_dma_count);
}
EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma);

bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
{
	return atomic_read(&kvm->arch.noncoherent_dma_count);
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);

bool kvm_arch_has_irq_bypass(void)
{
	return true;
}

int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
				      struct irq_bypass_producer *prod)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);
	int ret;

	irqfd->producer = prod;
	kvm_arch_start_assignment(irqfd->kvm);
	ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm,
					 prod->irq, irqfd->gsi, 1);

	if (ret)
		kvm_arch_end_assignment(irqfd->kvm);

	return ret;
}

void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
				      struct irq_bypass_producer *prod)
{
	int ret;
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);

	WARN_ON(irqfd->producer != prod);
	irqfd->producer = NULL;

	/*
	 * When producer of consumer is unregistered, we change back to
	 * remapped mode, so we can re-use the current implementation
	 * when the irq is masked/disabled or the consumer side (KVM
	 * int this case doesn't want to receive the interrupts.
	*/
	ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0);
	if (ret)
		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
		       " fails: %d\n", irqfd->consumer.token, ret);

	kvm_arch_end_assignment(irqfd->kvm);
}

int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
				   uint32_t guest_irq, bool set)
{
	return static_call(kvm_x86_pi_update_irte)(kvm, host_irq, guest_irq, set);
}

bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
				  struct kvm_kernel_irq_routing_entry *new)
{
	if (new->type != KVM_IRQ_ROUTING_MSI)
		return true;

	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
}

bool kvm_vector_hashing_enabled(void)
{
	return vector_hashing;
}

bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
{
	return (vcpu->arch.msr_kvm_poll_control & 1) == 0;
}
EXPORT_SYMBOL_GPL(kvm_arch_no_poll);


int kvm_spec_ctrl_test_value(u64 value)
{
	/*
	 * test that setting IA32_SPEC_CTRL to given value
	 * is allowed by the host processor
	 */

	u64 saved_value;
	unsigned long flags;
	int ret = 0;

	local_irq_save(flags);

	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
		ret = 1;
	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
		ret = 1;
	else
		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);

	local_irq_restore(flags);

	return ret;
}
EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value);

void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
	struct x86_exception fault;
	u64 access = error_code &
		(PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK);

	if (!(error_code & PFERR_PRESENT_MASK) ||
	    mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != INVALID_GPA) {
		/*
		 * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page
		 * tables probably do not match the TLB.  Just proceed
		 * with the error code that the processor gave.
		 */
		fault.vector = PF_VECTOR;
		fault.error_code_valid = true;
		fault.error_code = error_code;
		fault.nested_page_fault = false;
		fault.address = gva;
		fault.async_page_fault = false;
	}
	vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault);
}
EXPORT_SYMBOL_GPL(kvm_fixup_and_inject_pf_error);

/*
 * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns
 * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value
 * indicates whether exit to userspace is needed.
 */
int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
			      struct x86_exception *e)
{
	if (r == X86EMUL_PROPAGATE_FAULT) {
		kvm_inject_emulated_page_fault(vcpu, e);
		return 1;
	}

	/*
	 * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED
	 * while handling a VMX instruction KVM could've handled the request
	 * correctly by exiting to userspace and performing I/O but there
	 * doesn't seem to be a real use-case behind such requests, just return
	 * KVM_EXIT_INTERNAL_ERROR for now.
	 */
	kvm_prepare_emulation_failure_exit(vcpu);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_handle_memory_failure);

int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
{
	bool pcid_enabled;
	struct x86_exception e;
	struct {
		u64 pcid;
		u64 gla;
	} operand;
	int r;

	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
	if (r != X86EMUL_CONTINUE)
		return kvm_handle_memory_failure(vcpu, r, &e);

	if (operand.pcid >> 12 != 0) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);

	switch (type) {
	case INVPCID_TYPE_INDIV_ADDR:
		if ((!pcid_enabled && (operand.pcid != 0)) ||
		    is_noncanonical_address(operand.gla, vcpu)) {
			kvm_inject_gp(vcpu, 0);
			return 1;
		}
		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
		return kvm_skip_emulated_instruction(vcpu);

	case INVPCID_TYPE_SINGLE_CTXT:
		if (!pcid_enabled && (operand.pcid != 0)) {
			kvm_inject_gp(vcpu, 0);
			return 1;
		}

		kvm_invalidate_pcid(vcpu, operand.pcid);
		return kvm_skip_emulated_instruction(vcpu);

	case INVPCID_TYPE_ALL_NON_GLOBAL:
		/*
		 * Currently, KVM doesn't mark global entries in the shadow
		 * page tables, so a non-global flush just degenerates to a
		 * global flush. If needed, we could optimize this later by
		 * keeping track of global entries in shadow page tables.
		 */

		fallthrough;
	case INVPCID_TYPE_ALL_INCL_GLOBAL:
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
		return kvm_skip_emulated_instruction(vcpu);

	default:
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
}
EXPORT_SYMBOL_GPL(kvm_handle_invpcid);

static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	struct kvm_mmio_fragment *frag;
	unsigned int len;

	BUG_ON(!vcpu->mmio_needed);

	/* Complete previous fragment */
	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
	len = min(8u, frag->len);
	if (!vcpu->mmio_is_write)
		memcpy(frag->data, run->mmio.data, len);

	if (frag->len <= 8) {
		/* Switch to the next fragment. */
		frag++;
		vcpu->mmio_cur_fragment++;
	} else {
		/* Go forward to the next mmio piece. */
		frag->data += len;
		frag->gpa += len;
		frag->len -= len;
	}

	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
		vcpu->mmio_needed = 0;

		// VMG change, at this point, we're always done
		// RIP has already been advanced
		return 1;
	}

	// More MMIO is needed
	run->mmio.phys_addr = frag->gpa;
	run->mmio.len = min(8u, frag->len);
	run->mmio.is_write = vcpu->mmio_is_write;
	if (run->mmio.is_write)
		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
	run->exit_reason = KVM_EXIT_MMIO;

	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;

	return 0;
}

int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
			  void *data)
{
	int handled;
	struct kvm_mmio_fragment *frag;

	if (!data)
		return -EINVAL;

	handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data);
	if (handled == bytes)
		return 1;

	bytes -= handled;
	gpa += handled;
	data += handled;

	/*TODO: Check if need to increment number of frags */
	frag = vcpu->mmio_fragments;
	vcpu->mmio_nr_fragments = 1;
	frag->len = bytes;
	frag->gpa = gpa;
	frag->data = data;

	vcpu->mmio_needed = 1;
	vcpu->mmio_cur_fragment = 0;

	vcpu->run->mmio.phys_addr = gpa;
	vcpu->run->mmio.len = min(8u, frag->len);
	vcpu->run->mmio.is_write = 1;
	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
	vcpu->run->exit_reason = KVM_EXIT_MMIO;

	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write);

int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
			 void *data)
{
	int handled;
	struct kvm_mmio_fragment *frag;

	if (!data)
		return -EINVAL;

	handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data);
	if (handled == bytes)
		return 1;

	bytes -= handled;
	gpa += handled;
	data += handled;

	/*TODO: Check if need to increment number of frags */
	frag = vcpu->mmio_fragments;
	vcpu->mmio_nr_fragments = 1;
	frag->len = bytes;
	frag->gpa = gpa;
	frag->data = data;

	vcpu->mmio_needed = 1;
	vcpu->mmio_cur_fragment = 0;

	vcpu->run->mmio.phys_addr = gpa;
	vcpu->run->mmio.len = min(8u, frag->len);
	vcpu->run->mmio.is_write = 0;
	vcpu->run->exit_reason = KVM_EXIT_MMIO;

	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);

static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size)
{
	vcpu->arch.sev_pio_count -= count;
	vcpu->arch.sev_pio_data += count * size;
}

static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
			   unsigned int port);

static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu)
{
	int size = vcpu->arch.pio.size;
	int port = vcpu->arch.pio.port;

	vcpu->arch.pio.count = 0;
	if (vcpu->arch.sev_pio_count)
		return kvm_sev_es_outs(vcpu, size, port);
	return 1;
}

static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
			   unsigned int port)
{
	for (;;) {
		unsigned int count =
			min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
		int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count);

		/* memcpy done already by emulator_pio_out.  */
		advance_sev_es_emulated_pio(vcpu, count, size);
		if (!ret)
			break;

		/* Emulation done by the kernel.  */
		if (!vcpu->arch.sev_pio_count)
			return 1;
	}

	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs;
	return 0;
}

static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
			  unsigned int port);

static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
{
	unsigned count = vcpu->arch.pio.count;
	int size = vcpu->arch.pio.size;
	int port = vcpu->arch.pio.port;

	complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
	advance_sev_es_emulated_pio(vcpu, count, size);
	if (vcpu->arch.sev_pio_count)
		return kvm_sev_es_ins(vcpu, size, port);
	return 1;
}

static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
			  unsigned int port)
{
	for (;;) {
		unsigned int count =
			min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
		if (!emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count))
			break;

		/* Emulation done by the kernel.  */
		advance_sev_es_emulated_pio(vcpu, count, size);
		if (!vcpu->arch.sev_pio_count)
			return 1;
	}

	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
	return 0;
}

int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
			 unsigned int port, void *data,  unsigned int count,
			 int in)
{
	vcpu->arch.sev_pio_data = data;
	vcpu->arch.sev_pio_count = count;
	return in ? kvm_sev_es_ins(vcpu, size, port)
		  : kvm_sev_es_outs(vcpu, size, port);
}
EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);

EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_kick_vcpu_slowpath);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_doorbell);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);

static int __init kvm_x86_init(void)
{
	kvm_mmu_x86_module_init();
	return 0;
}
module_init(kvm_x86_init);

static void __exit kvm_x86_exit(void)
{
	/*
	 * If module_init() is implemented, module_exit() must also be
	 * implemented to allow module unload.
	 */
}
module_exit(kvm_x86_exit);