summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/vmx/nested.c
blob: 643935a0f70ab77b8de56e1c0a145211af5af2ed (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
// SPDX-License-Identifier: GPL-2.0
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/objtool.h>
#include <linux/percpu.h>

#include <asm/debugreg.h>
#include <asm/mmu_context.h>

#include "cpuid.h"
#include "hyperv.h"
#include "mmu.h"
#include "nested.h"
#include "pmu.h"
#include "sgx.h"
#include "trace.h"
#include "vmx.h"
#include "x86.h"
#include "smm.h"

static bool __read_mostly enable_shadow_vmcs = 1;
module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);

static bool __read_mostly nested_early_check = 0;
module_param(nested_early_check, bool, S_IRUGO);

#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK

/*
 * Hyper-V requires all of these, so mark them as supported even though
 * they are just treated the same as all-context.
 */
#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)

#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5

enum {
	VMX_VMREAD_BITMAP,
	VMX_VMWRITE_BITMAP,
	VMX_BITMAP_NR
};
static unsigned long *vmx_bitmap[VMX_BITMAP_NR];

#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])

struct shadow_vmcs_field {
	u16	encoding;
	u16	offset;
};
static struct shadow_vmcs_field shadow_read_only_fields[] = {
#define SHADOW_FIELD_RO(x, y) { x, offsetof(struct vmcs12, y) },
#include "vmcs_shadow_fields.h"
};
static int max_shadow_read_only_fields =
	ARRAY_SIZE(shadow_read_only_fields);

static struct shadow_vmcs_field shadow_read_write_fields[] = {
#define SHADOW_FIELD_RW(x, y) { x, offsetof(struct vmcs12, y) },
#include "vmcs_shadow_fields.h"
};
static int max_shadow_read_write_fields =
	ARRAY_SIZE(shadow_read_write_fields);

static void init_vmcs_shadow_fields(void)
{
	int i, j;

	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);

	for (i = j = 0; i < max_shadow_read_only_fields; i++) {
		struct shadow_vmcs_field entry = shadow_read_only_fields[i];
		u16 field = entry.encoding;

		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
		    (i + 1 == max_shadow_read_only_fields ||
		     shadow_read_only_fields[i + 1].encoding != field + 1))
			pr_err("Missing field from shadow_read_only_field %x\n",
			       field + 1);

		clear_bit(field, vmx_vmread_bitmap);
		if (field & 1)
#ifdef CONFIG_X86_64
			continue;
#else
			entry.offset += sizeof(u32);
#endif
		shadow_read_only_fields[j++] = entry;
	}
	max_shadow_read_only_fields = j;

	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
		struct shadow_vmcs_field entry = shadow_read_write_fields[i];
		u16 field = entry.encoding;

		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
		    (i + 1 == max_shadow_read_write_fields ||
		     shadow_read_write_fields[i + 1].encoding != field + 1))
			pr_err("Missing field from shadow_read_write_field %x\n",
			       field + 1);

		WARN_ONCE(field >= GUEST_ES_AR_BYTES &&
			  field <= GUEST_TR_AR_BYTES,
			  "Update vmcs12_write_any() to drop reserved bits from AR_BYTES");

		/*
		 * PML and the preemption timer can be emulated, but the
		 * processor cannot vmwrite to fields that don't exist
		 * on bare metal.
		 */
		switch (field) {
		case GUEST_PML_INDEX:
			if (!cpu_has_vmx_pml())
				continue;
			break;
		case VMX_PREEMPTION_TIMER_VALUE:
			if (!cpu_has_vmx_preemption_timer())
				continue;
			break;
		case GUEST_INTR_STATUS:
			if (!cpu_has_vmx_apicv())
				continue;
			break;
		default:
			break;
		}

		clear_bit(field, vmx_vmwrite_bitmap);
		clear_bit(field, vmx_vmread_bitmap);
		if (field & 1)
#ifdef CONFIG_X86_64
			continue;
#else
			entry.offset += sizeof(u32);
#endif
		shadow_read_write_fields[j++] = entry;
	}
	max_shadow_read_write_fields = j;
}

/*
 * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
 * set the success or error code of an emulated VMX instruction (as specified
 * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
 * instruction.
 */
static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
{
	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
	return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
{
	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
			    X86_EFLAGS_SF | X86_EFLAGS_OF))
			| X86_EFLAGS_CF);
	return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
				u32 vm_instruction_error)
{
	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
			    X86_EFLAGS_SF | X86_EFLAGS_OF))
			| X86_EFLAGS_ZF);
	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
	/*
	 * We don't need to force sync to shadow VMCS because
	 * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all
	 * fields and thus must be synced.
	 */
	if (nested_vmx_is_evmptr12_set(to_vmx(vcpu)))
		to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true;

	return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * failValid writes the error number to the current VMCS, which
	 * can't be done if there isn't a current VMCS.
	 */
	if (vmx->nested.current_vmptr == INVALID_GPA &&
	    !nested_vmx_is_evmptr12_valid(vmx))
		return nested_vmx_failInvalid(vcpu);

	return nested_vmx_failValid(vcpu, vm_instruction_error);
}

static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
{
	/* TODO: not to reset guest simply here. */
	kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
	pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator);
}

static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
{
	return fixed_bits_valid(control, low, high);
}

static inline u64 vmx_control_msr(u32 low, u32 high)
{
	return low | ((u64)high << 32);
}

static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
{
	secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
	vmx->nested.need_vmcs12_to_shadow_sync = false;
}

static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_KVM_HYPERV
	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (nested_vmx_is_evmptr12_valid(vmx)) {
		kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
		vmx->nested.hv_evmcs = NULL;
	}

	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;

	if (hv_vcpu) {
		hv_vcpu->nested.pa_page_gpa = INVALID_GPA;
		hv_vcpu->nested.vm_id = 0;
		hv_vcpu->nested.vp_id = 0;
	}
#endif
}

static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
{
#ifdef CONFIG_KVM_HYPERV
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	/*
	 * When Enlightened VMEntry is enabled on the calling CPU we treat
	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
	 * way to distinguish it from VMCS12) and we must not corrupt it by
	 * writing to the non-existent 'launch_state' field. The area doesn't
	 * have to be the currently active EVMCS on the calling CPU and there's
	 * nothing KVM has to do to transition it from 'active' to 'non-active'
	 * state. It is possible that the area will stay mapped as
	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
	 */
	if (!guest_cpuid_has_evmcs(vcpu) ||
	    !evmptr_is_valid(nested_get_evmptr(vcpu)))
		return false;

	if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr)
		nested_release_evmcs(vcpu);

	return true;
#else
	return false;
#endif
}

static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
				     struct loaded_vmcs *prev)
{
	struct vmcs_host_state *dest, *src;

	if (unlikely(!vmx->guest_state_loaded))
		return;

	src = &prev->host_state;
	dest = &vmx->loaded_vmcs->host_state;

	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
	dest->ldt_sel = src->ldt_sel;
#ifdef CONFIG_X86_64
	dest->ds_sel = src->ds_sel;
	dest->es_sel = src->es_sel;
#endif
}

static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct loaded_vmcs *prev;
	int cpu;

	if (WARN_ON_ONCE(vmx->loaded_vmcs == vmcs))
		return;

	cpu = get_cpu();
	prev = vmx->loaded_vmcs;
	vmx->loaded_vmcs = vmcs;
	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
	vmx_sync_vmcs_host_state(vmx, prev);
	put_cpu();

	vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET;

	/*
	 * All lazily updated registers will be reloaded from VMCS12 on both
	 * vmentry and vmexit.
	 */
	vcpu->arch.regs_dirty = 0;
}

/*
 * Free whatever needs to be freed from vmx->nested when L1 goes down, or
 * just stops using VMX.
 */
static void free_nested(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01))
		vmx_switch_vmcs(vcpu, &vmx->vmcs01);

	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
		return;

	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);

	vmx->nested.vmxon = false;
	vmx->nested.smm.vmxon = false;
	vmx->nested.vmxon_ptr = INVALID_GPA;
	free_vpid(vmx->nested.vpid02);
	vmx->nested.posted_intr_nv = -1;
	vmx->nested.current_vmptr = INVALID_GPA;
	if (enable_shadow_vmcs) {
		vmx_disable_shadow_vmcs(vmx);
		vmcs_clear(vmx->vmcs01.shadow_vmcs);
		free_vmcs(vmx->vmcs01.shadow_vmcs);
		vmx->vmcs01.shadow_vmcs = NULL;
	}
	kfree(vmx->nested.cached_vmcs12);
	vmx->nested.cached_vmcs12 = NULL;
	kfree(vmx->nested.cached_shadow_vmcs12);
	vmx->nested.cached_shadow_vmcs12 = NULL;
	/*
	 * Unpin physical memory we referred to in the vmcs02.  The APIC access
	 * page's backing page (yeah, confusing) shouldn't actually be accessed,
	 * and if it is written, the contents are irrelevant.
	 */
	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
	vmx->nested.pi_desc = NULL;

	kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);

	nested_release_evmcs(vcpu);

	free_loaded_vmcs(&vmx->nested.vmcs02);
}

/*
 * Ensure that the current vmcs of the logical processor is the
 * vmcs01 of the vcpu before calling free_nested().
 */
void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
	vcpu_load(vcpu);
	vmx_leave_nested(vcpu);
	vcpu_put(vcpu);
}

#define EPTP_PA_MASK   GENMASK_ULL(51, 12)

static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
{
	return VALID_PAGE(root_hpa) &&
	       ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
}

static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp,
				       gpa_t addr)
{
	unsigned long roots = 0;
	uint i;
	struct kvm_mmu_root_info *cached_root;

	WARN_ON_ONCE(!mmu_is_nested(vcpu));

	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
		cached_root = &vcpu->arch.mmu->prev_roots[i];

		if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd,
					    eptp))
			roots |= KVM_MMU_ROOT_PREVIOUS(i);
	}
	if (roots)
		kvm_mmu_invalidate_addr(vcpu, vcpu->arch.mmu, addr, roots);
}

static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
		struct x86_exception *fault)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long exit_qualification;
	u32 vm_exit_reason;

	if (vmx->nested.pml_full) {
		vm_exit_reason = EXIT_REASON_PML_FULL;
		vmx->nested.pml_full = false;

		/*
		 * It should be impossible to trigger a nested PML Full VM-Exit
		 * for anything other than an EPT Violation from L2.  KVM *can*
		 * trigger nEPT page fault injection in response to an EPT
		 * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT
		 * tables also changed, but KVM should not treat EPT Misconfig
		 * VM-Exits as writes.
		 */
		WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);

		/*
		 * PML Full and EPT Violation VM-Exits both use bit 12 to report
		 * "NMI unblocking due to IRET", i.e. the bit can be propagated
		 * as-is from the original EXIT_QUALIFICATION.
		 */
		exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI;
	} else {
		if (fault->error_code & PFERR_RSVD_MASK) {
			vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
			exit_qualification = 0;
		} else {
			exit_qualification = fault->exit_qualification;
			exit_qualification |= vmx_get_exit_qual(vcpu) &
					      (EPT_VIOLATION_GVA_IS_VALID |
					       EPT_VIOLATION_GVA_TRANSLATED);
			vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
		}

		/*
		 * Although the caller (kvm_inject_emulated_page_fault) would
		 * have already synced the faulting address in the shadow EPT
		 * tables for the current EPTP12, we also need to sync it for
		 * any other cached EPTP02s based on the same EP4TA, since the
		 * TLB associates mappings to the EP4TA rather than the full EPTP.
		 */
		nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer,
					   fault->address);
	}

	nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification);
	vmcs12->guest_physical_address = fault->address;
}

static void nested_ept_new_eptp(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT;
	int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps);

	kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level,
				nested_ept_ad_enabled(vcpu),
				nested_ept_get_eptp(vcpu));
}

static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
	WARN_ON(mmu_is_nested(vcpu));

	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
	nested_ept_new_eptp(vcpu);
	vcpu->arch.mmu->get_guest_pgd     = nested_ept_get_eptp;
	vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
	vcpu->arch.mmu->get_pdptr         = kvm_pdptr_read;

	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
}

static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
	vcpu->arch.mmu = &vcpu->arch.root_mmu;
	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}

static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
					    u16 error_code)
{
	bool inequality, bit;

	bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0;
	inequality =
		(error_code & vmcs12->page_fault_error_code_mask) !=
		 vmcs12->page_fault_error_code_match;
	return inequality ^ bit;
}

static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector,
					   u32 error_code)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	/*
	 * Drop bits 31:16 of the error code when performing the #PF mask+match
	 * check.  All VMCS fields involved are 32 bits, but Intel CPUs never
	 * set bits 31:16 and VMX disallows setting bits 31:16 in the injected
	 * error code.  Including the to-be-dropped bits in the check might
	 * result in an "impossible" or missed exit from L1's perspective.
	 */
	if (vector == PF_VECTOR)
		return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code);

	return (vmcs12->exception_bitmap & (1u << vector));
}

static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
					       struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
		return 0;

	if (CC(!page_address_valid(vcpu, vmcs12->io_bitmap_a)) ||
	    CC(!page_address_valid(vcpu, vmcs12->io_bitmap_b)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
						struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
		return 0;

	if (CC(!page_address_valid(vcpu, vmcs12->msr_bitmap)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
						struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
		return 0;

	if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr)))
		return -EINVAL;

	return 0;
}

/*
 * For x2APIC MSRs, ignore the vmcs01 bitmap.  L1 can enable x2APIC without L1
 * itself utilizing x2APIC.  All MSRs were previously set to be intercepted,
 * only the "disable intercept" case needs to be handled.
 */
static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1,
							unsigned long *msr_bitmap_l0,
							u32 msr, int type)
{
	if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr))
		vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr);

	if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr))
		vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr);
}

static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
{
	int msr;

	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
		unsigned word = msr / BITS_PER_LONG;

		msr_bitmap[word] = ~0;
		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
	}
}

#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw)					\
static inline									\
void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx,			\
					 unsigned long *msr_bitmap_l1,		\
					 unsigned long *msr_bitmap_l0, u32 msr)	\
{										\
	if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) ||		\
	    vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr))			\
		vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
	else									\
		vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
}
BUILD_NVMX_MSR_INTERCEPT_HELPER(read)
BUILD_NVMX_MSR_INTERCEPT_HELPER(write)

static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx,
						    unsigned long *msr_bitmap_l1,
						    unsigned long *msr_bitmap_l0,
						    u32 msr, int types)
{
	if (types & MSR_TYPE_R)
		nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1,
						  msr_bitmap_l0, msr);
	if (types & MSR_TYPE_W)
		nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1,
						   msr_bitmap_l0, msr);
}

/*
 * Merge L0's and L1's MSR bitmap, return false to indicate that
 * we do not use the hardware.
 */
static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
						 struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int msr;
	unsigned long *msr_bitmap_l1;
	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;

	/* Nothing to do if the MSR bitmap is not in use.  */
	if (!cpu_has_vmx_msr_bitmap() ||
	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
		return false;

	/*
	 * MSR bitmap update can be skipped when:
	 * - MSR bitmap for L1 hasn't changed.
	 * - Nested hypervisor (L1) is attempting to launch the same L2 as
	 *   before.
	 * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature
	 *   and tells KVM (L0) there were no changes in MSR bitmap for L2.
	 */
	if (!vmx->nested.force_msr_bitmap_recalc) {
		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);

		if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap &&
		    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
			return true;
	}

	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
		return false;

	msr_bitmap_l1 = (unsigned long *)map->hva;

	/*
	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
	 * the x2APIC MSR range and selectively toggle those relevant to L2.
	 */
	enable_x2apic_msr_intercepts(msr_bitmap_l0);

	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
		if (nested_cpu_has_apic_reg_virt(vmcs12)) {
			/*
			 * L0 need not intercept reads for MSRs between 0x800
			 * and 0x8ff, it just lets the processor take the value
			 * from the virtual-APIC page; take those 256 bits
			 * directly from the L1 bitmap.
			 */
			for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
				unsigned word = msr / BITS_PER_LONG;

				msr_bitmap_l0[word] = msr_bitmap_l1[word];
			}
		}

		nested_vmx_disable_intercept_for_x2apic_msr(
			msr_bitmap_l1, msr_bitmap_l0,
			X2APIC_MSR(APIC_TASKPRI),
			MSR_TYPE_R | MSR_TYPE_W);

		if (nested_cpu_has_vid(vmcs12)) {
			nested_vmx_disable_intercept_for_x2apic_msr(
				msr_bitmap_l1, msr_bitmap_l0,
				X2APIC_MSR(APIC_EOI),
				MSR_TYPE_W);
			nested_vmx_disable_intercept_for_x2apic_msr(
				msr_bitmap_l1, msr_bitmap_l0,
				X2APIC_MSR(APIC_SELF_IPI),
				MSR_TYPE_W);
		}
	}

	/*
	 * Always check vmcs01's bitmap to honor userspace MSR filters and any
	 * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through.
	 */
#ifdef CONFIG_X86_64
	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_FS_BASE, MSR_TYPE_RW);

	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_GS_BASE, MSR_TYPE_RW);

	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
#endif
	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_IA32_SPEC_CTRL, MSR_TYPE_RW);

	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_IA32_PRED_CMD, MSR_TYPE_W);

	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
					 MSR_IA32_FLUSH_CMD, MSR_TYPE_W);

	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);

	vmx->nested.force_msr_bitmap_recalc = false;

	return true;
}

static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;

	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
	    vmcs12->vmcs_link_pointer == INVALID_GPA)
		return;

	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
		return;

	kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
			      VMCS12_SIZE);
}

static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
					      struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;

	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
	    vmcs12->vmcs_link_pointer == INVALID_GPA)
		return;

	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
		return;

	kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
			       VMCS12_SIZE);
}

/*
 * In nested virtualization, check if L1 has set
 * VM_EXIT_ACK_INTR_ON_EXIT
 */
static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
{
	return get_vmcs12(vcpu)->vm_exit_controls &
		VM_EXIT_ACK_INTR_ON_EXIT;
}

static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
					  struct vmcs12 *vmcs12)
{
	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
	    CC(!page_address_valid(vcpu, vmcs12->apic_access_addr)))
		return -EINVAL;
	else
		return 0;
}

static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
					   struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
	    !nested_cpu_has_apic_reg_virt(vmcs12) &&
	    !nested_cpu_has_vid(vmcs12) &&
	    !nested_cpu_has_posted_intr(vmcs12))
		return 0;

	/*
	 * If virtualize x2apic mode is enabled,
	 * virtualize apic access must be disabled.
	 */
	if (CC(nested_cpu_has_virt_x2apic_mode(vmcs12) &&
	       nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)))
		return -EINVAL;

	/*
	 * If virtual interrupt delivery is enabled,
	 * we must exit on external interrupts.
	 */
	if (CC(nested_cpu_has_vid(vmcs12) && !nested_exit_on_intr(vcpu)))
		return -EINVAL;

	/*
	 * bits 15:8 should be zero in posted_intr_nv,
	 * the descriptor address has been already checked
	 * in nested_get_vmcs12_pages.
	 *
	 * bits 5:0 of posted_intr_desc_addr should be zero.
	 */
	if (nested_cpu_has_posted_intr(vmcs12) &&
	   (CC(!nested_cpu_has_vid(vmcs12)) ||
	    CC(!nested_exit_intr_ack_set(vcpu)) ||
	    CC((vmcs12->posted_intr_nv & 0xff00)) ||
	    CC(!kvm_vcpu_is_legal_aligned_gpa(vcpu, vmcs12->posted_intr_desc_addr, 64))))
		return -EINVAL;

	/* tpr shadow is needed by all apicv features. */
	if (CC(!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
				       u32 count, u64 addr)
{
	if (count == 0)
		return 0;

	if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) ||
	    !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu,
						     struct vmcs12 *vmcs12)
{
	if (CC(nested_vmx_check_msr_switch(vcpu,
					   vmcs12->vm_exit_msr_load_count,
					   vmcs12->vm_exit_msr_load_addr)) ||
	    CC(nested_vmx_check_msr_switch(vcpu,
					   vmcs12->vm_exit_msr_store_count,
					   vmcs12->vm_exit_msr_store_addr)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu,
                                                      struct vmcs12 *vmcs12)
{
	if (CC(nested_vmx_check_msr_switch(vcpu,
					   vmcs12->vm_entry_msr_load_count,
					   vmcs12->vm_entry_msr_load_addr)))
                return -EINVAL;

	return 0;
}

static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
					 struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has_pml(vmcs12))
		return 0;

	if (CC(!nested_cpu_has_ept(vmcs12)) ||
	    CC(!page_address_valid(vcpu, vmcs12->pml_address)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu,
							struct vmcs12 *vmcs12)
{
	if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) &&
	       !nested_cpu_has_ept(vmcs12)))
		return -EINVAL;
	return 0;
}

static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu,
							 struct vmcs12 *vmcs12)
{
	if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) &&
	       !nested_cpu_has_ept(vmcs12)))
		return -EINVAL;
	return 0;
}

static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu,
						 struct vmcs12 *vmcs12)
{
	if (!nested_cpu_has_shadow_vmcs(vmcs12))
		return 0;

	if (CC(!page_address_valid(vcpu, vmcs12->vmread_bitmap)) ||
	    CC(!page_address_valid(vcpu, vmcs12->vmwrite_bitmap)))
		return -EINVAL;

	return 0;
}

static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
				       struct vmx_msr_entry *e)
{
	/* x2APIC MSR accesses are not allowed */
	if (CC(vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8))
		return -EINVAL;
	if (CC(e->index == MSR_IA32_UCODE_WRITE) || /* SDM Table 35-2 */
	    CC(e->index == MSR_IA32_UCODE_REV))
		return -EINVAL;
	if (CC(e->reserved != 0))
		return -EINVAL;
	return 0;
}

static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu,
				     struct vmx_msr_entry *e)
{
	if (CC(e->index == MSR_FS_BASE) ||
	    CC(e->index == MSR_GS_BASE) ||
	    CC(e->index == MSR_IA32_SMM_MONITOR_CTL) || /* SMM is not supported */
	    nested_vmx_msr_check_common(vcpu, e))
		return -EINVAL;
	return 0;
}

static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
				      struct vmx_msr_entry *e)
{
	if (CC(e->index == MSR_IA32_SMBASE) || /* SMM is not supported */
	    nested_vmx_msr_check_common(vcpu, e))
		return -EINVAL;
	return 0;
}

static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
				       vmx->nested.msrs.misc_high);

	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
}

/*
 * Load guest's/host's msr at nested entry/exit.
 * return 0 for success, entry index for failure.
 *
 * One of the failure modes for MSR load/store is when a list exceeds the
 * virtual hardware's capacity. To maintain compatibility with hardware inasmuch
 * as possible, process all valid entries before failing rather than precheck
 * for a capacity violation.
 */
static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
	u32 i;
	struct vmx_msr_entry e;
	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);

	for (i = 0; i < count; i++) {
		if (unlikely(i >= max_msr_list_size))
			goto fail;

		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
					&e, sizeof(e))) {
			pr_debug_ratelimited(
				"%s cannot read MSR entry (%u, 0x%08llx)\n",
				__func__, i, gpa + i * sizeof(e));
			goto fail;
		}
		if (nested_vmx_load_msr_check(vcpu, &e)) {
			pr_debug_ratelimited(
				"%s check failed (%u, 0x%x, 0x%x)\n",
				__func__, i, e.index, e.reserved);
			goto fail;
		}
		if (kvm_set_msr(vcpu, e.index, e.value)) {
			pr_debug_ratelimited(
				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
				__func__, i, e.index, e.value);
			goto fail;
		}
	}
	return 0;
fail:
	/* Note, max_msr_list_size is at most 4096, i.e. this can't wrap. */
	return i + 1;
}

static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
					    u32 msr_index,
					    u64 *data)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * If the L0 hypervisor stored a more accurate value for the TSC that
	 * does not include the time taken for emulation of the L2->L1
	 * VM-exit in L0, use the more accurate value.
	 */
	if (msr_index == MSR_IA32_TSC) {
		int i = vmx_find_loadstore_msr_slot(&vmx->msr_autostore.guest,
						    MSR_IA32_TSC);

		if (i >= 0) {
			u64 val = vmx->msr_autostore.guest.val[i].value;

			*data = kvm_read_l1_tsc(vcpu, val);
			return true;
		}
	}

	if (kvm_get_msr(vcpu, msr_index, data)) {
		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
			msr_index);
		return false;
	}
	return true;
}

static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i,
				     struct vmx_msr_entry *e)
{
	if (kvm_vcpu_read_guest(vcpu,
				gpa + i * sizeof(*e),
				e, 2 * sizeof(u32))) {
		pr_debug_ratelimited(
			"%s cannot read MSR entry (%u, 0x%08llx)\n",
			__func__, i, gpa + i * sizeof(*e));
		return false;
	}
	if (nested_vmx_store_msr_check(vcpu, e)) {
		pr_debug_ratelimited(
			"%s check failed (%u, 0x%x, 0x%x)\n",
			__func__, i, e->index, e->reserved);
		return false;
	}
	return true;
}

static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
	u64 data;
	u32 i;
	struct vmx_msr_entry e;
	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);

	for (i = 0; i < count; i++) {
		if (unlikely(i >= max_msr_list_size))
			return -EINVAL;

		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
			return -EINVAL;

		if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data))
			return -EINVAL;

		if (kvm_vcpu_write_guest(vcpu,
					 gpa + i * sizeof(e) +
					     offsetof(struct vmx_msr_entry, value),
					 &data, sizeof(data))) {
			pr_debug_ratelimited(
				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
				__func__, i, e.index, data);
			return -EINVAL;
		}
	}
	return 0;
}

static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	u32 count = vmcs12->vm_exit_msr_store_count;
	u64 gpa = vmcs12->vm_exit_msr_store_addr;
	struct vmx_msr_entry e;
	u32 i;

	for (i = 0; i < count; i++) {
		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
			return false;

		if (e.index == msr_index)
			return true;
	}
	return false;
}

static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
					   u32 msr_index)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
	bool in_vmcs12_store_list;
	int msr_autostore_slot;
	bool in_autostore_list;
	int last;

	msr_autostore_slot = vmx_find_loadstore_msr_slot(autostore, msr_index);
	in_autostore_list = msr_autostore_slot >= 0;
	in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);

	if (in_vmcs12_store_list && !in_autostore_list) {
		if (autostore->nr == MAX_NR_LOADSTORE_MSRS) {
			/*
			 * Emulated VMEntry does not fail here.  Instead a less
			 * accurate value will be returned by
			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
			 * instead of reading the value from the vmcs02 VMExit
			 * MSR-store area.
			 */
			pr_warn_ratelimited(
				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
				msr_index);
			return;
		}
		last = autostore->nr++;
		autostore->val[last].index = msr_index;
	} else if (!in_vmcs12_store_list && in_autostore_list) {
		last = --autostore->nr;
		autostore->val[msr_autostore_slot] = autostore->val[last];
	}
}

/*
 * Load guest's/host's cr3 at nested entry/exit.  @nested_ept is true if we are
 * emulating VM-Entry into a guest with EPT enabled.  On failure, the expected
 * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to
 * @entry_failure_code.
 */
static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
			       bool nested_ept, bool reload_pdptrs,
			       enum vm_entry_failure_code *entry_failure_code)
{
	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) {
		*entry_failure_code = ENTRY_FAIL_DEFAULT;
		return -EINVAL;
	}

	/*
	 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
	 * must not be dereferenced.
	 */
	if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) &&
	    CC(!load_pdptrs(vcpu, cr3))) {
		*entry_failure_code = ENTRY_FAIL_PDPTE;
		return -EINVAL;
	}

	vcpu->arch.cr3 = cr3;
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);

	/* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */
	kvm_init_mmu(vcpu);

	if (!nested_ept)
		kvm_mmu_new_pgd(vcpu, cr3);

	return 0;
}

/*
 * Returns if KVM is able to config CPU to tag TLB entries
 * populated by L2 differently than TLB entries populated
 * by L1.
 *
 * If L0 uses EPT, L1 and L2 run with different EPTP because
 * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries
 * are tagged with different EPTP.
 *
 * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
 * with different VPID (L1 entries are tagged with vmx->vpid
 * while L2 entries are tagged with vmx->nested.vpid02).
 */
static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	return enable_ept ||
	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
}

static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
					    struct vmcs12 *vmcs12,
					    bool is_vmenter)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/* Handle pending Hyper-V TLB flush requests */
	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);

	/*
	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
	 * full TLB flush from the guest's perspective.  This is required even
	 * if VPID is disabled in the host as KVM may need to synchronize the
	 * MMU in response to the guest TLB flush.
	 *
	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
	 * EPT is a special snowflake, as guest-physical mappings aren't
	 * flushed on VPID invalidations, including VM-Enter or VM-Exit with
	 * VPID disabled.  As a result, KVM _never_ needs to sync nEPT
	 * entries on VM-Enter because L1 can't rely on VM-Enter to flush
	 * those mappings.
	 */
	if (!nested_cpu_has_vpid(vmcs12)) {
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
		return;
	}

	/* L2 should never have a VPID if VPID is disabled. */
	WARN_ON(!enable_vpid);

	/*
	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
	 * that the new vpid12 has never been used and thus represents a new
	 * guest ASID that cannot have entries in the TLB.
	 */
	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
		return;
	}

	/*
	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
	 * KVM was unable to allocate a VPID for L2, flush the current context
	 * as the effective ASID is common to both L1 and L2.
	 */
	if (!nested_has_guest_tlb_tag(vcpu))
		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}

static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
{
	superset &= mask;
	subset &= mask;

	return (superset | subset) == superset;
}

static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
{
	const u64 feature_and_reserved =
		/* feature (except bit 48; see below) */
		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
		/* reserved */
		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
	u64 vmx_basic = vmcs_config.nested.basic;

	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
		return -EINVAL;

	/*
	 * KVM does not emulate a version of VMX that constrains physical
	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
	 */
	if (data & BIT_ULL(48))
		return -EINVAL;

	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
	    vmx_basic_vmcs_revision_id(data))
		return -EINVAL;

	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
		return -EINVAL;

	vmx->nested.msrs.basic = data;
	return 0;
}

static void vmx_get_control_msr(struct nested_vmx_msrs *msrs, u32 msr_index,
				u32 **low, u32 **high)
{
	switch (msr_index) {
	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
		*low = &msrs->pinbased_ctls_low;
		*high = &msrs->pinbased_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
		*low = &msrs->procbased_ctls_low;
		*high = &msrs->procbased_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
		*low = &msrs->exit_ctls_low;
		*high = &msrs->exit_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
		*low = &msrs->entry_ctls_low;
		*high = &msrs->entry_ctls_high;
		break;
	case MSR_IA32_VMX_PROCBASED_CTLS2:
		*low = &msrs->secondary_ctls_low;
		*high = &msrs->secondary_ctls_high;
		break;
	default:
		BUG();
	}
}

static int
vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
{
	u32 *lowp, *highp;
	u64 supported;

	vmx_get_control_msr(&vmcs_config.nested, msr_index, &lowp, &highp);

	supported = vmx_control_msr(*lowp, *highp);

	/* Check must-be-1 bits are still 1. */
	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
		return -EINVAL;

	/* Check must-be-0 bits are still 0. */
	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
		return -EINVAL;

	vmx_get_control_msr(&vmx->nested.msrs, msr_index, &lowp, &highp);
	*lowp = data;
	*highp = data >> 32;
	return 0;
}

static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
{
	const u64 feature_and_reserved_bits =
		/* feature */
		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
		/* reserved */
		GENMASK_ULL(13, 9) | BIT_ULL(31);
	u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low,
				       vmcs_config.nested.misc_high);

	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
		return -EINVAL;

	if ((vmx->nested.msrs.pinbased_ctls_high &
	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
	    vmx_misc_preemption_timer_rate(data) !=
	    vmx_misc_preemption_timer_rate(vmx_misc))
		return -EINVAL;

	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
		return -EINVAL;

	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
		return -EINVAL;

	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
		return -EINVAL;

	vmx->nested.msrs.misc_low = data;
	vmx->nested.msrs.misc_high = data >> 32;

	return 0;
}

static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
{
	u64 vmx_ept_vpid_cap = vmx_control_msr(vmcs_config.nested.ept_caps,
					       vmcs_config.nested.vpid_caps);

	/* Every bit is either reserved or a feature bit. */
	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
		return -EINVAL;

	vmx->nested.msrs.ept_caps = data;
	vmx->nested.msrs.vpid_caps = data >> 32;
	return 0;
}

static u64 *vmx_get_fixed0_msr(struct nested_vmx_msrs *msrs, u32 msr_index)
{
	switch (msr_index) {
	case MSR_IA32_VMX_CR0_FIXED0:
		return &msrs->cr0_fixed0;
	case MSR_IA32_VMX_CR4_FIXED0:
		return &msrs->cr4_fixed0;
	default:
		BUG();
	}
}

static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
{
	const u64 *msr = vmx_get_fixed0_msr(&vmcs_config.nested, msr_index);

	/*
	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
	 * must be 1 in the restored value.
	 */
	if (!is_bitwise_subset(data, *msr, -1ULL))
		return -EINVAL;

	*vmx_get_fixed0_msr(&vmx->nested.msrs, msr_index) = data;
	return 0;
}

/*
 * Called when userspace is restoring VMX MSRs.
 *
 * Returns 0 on success, non-0 otherwise.
 */
int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * Don't allow changes to the VMX capability MSRs while the vCPU
	 * is in VMX operation.
	 */
	if (vmx->nested.vmxon)
		return -EBUSY;

	switch (msr_index) {
	case MSR_IA32_VMX_BASIC:
		return vmx_restore_vmx_basic(vmx, data);
	case MSR_IA32_VMX_PINBASED_CTLS:
	case MSR_IA32_VMX_PROCBASED_CTLS:
	case MSR_IA32_VMX_EXIT_CTLS:
	case MSR_IA32_VMX_ENTRY_CTLS:
		/*
		 * The "non-true" VMX capability MSRs are generated from the
		 * "true" MSRs, so we do not support restoring them directly.
		 *
		 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
		 * should restore the "true" MSRs with the must-be-1 bits
		 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
		 * DEFAULT SETTINGS".
		 */
		return -EINVAL;
	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
	case MSR_IA32_VMX_PROCBASED_CTLS2:
		return vmx_restore_control_msr(vmx, msr_index, data);
	case MSR_IA32_VMX_MISC:
		return vmx_restore_vmx_misc(vmx, data);
	case MSR_IA32_VMX_CR0_FIXED0:
	case MSR_IA32_VMX_CR4_FIXED0:
		return vmx_restore_fixed0_msr(vmx, msr_index, data);
	case MSR_IA32_VMX_CR0_FIXED1:
	case MSR_IA32_VMX_CR4_FIXED1:
		/*
		 * These MSRs are generated based on the vCPU's CPUID, so we
		 * do not support restoring them directly.
		 */
		return -EINVAL;
	case MSR_IA32_VMX_EPT_VPID_CAP:
		return vmx_restore_vmx_ept_vpid_cap(vmx, data);
	case MSR_IA32_VMX_VMCS_ENUM:
		vmx->nested.msrs.vmcs_enum = data;
		return 0;
	case MSR_IA32_VMX_VMFUNC:
		if (data & ~vmcs_config.nested.vmfunc_controls)
			return -EINVAL;
		vmx->nested.msrs.vmfunc_controls = data;
		return 0;
	default:
		/*
		 * The rest of the VMX capability MSRs do not support restore.
		 */
		return -EINVAL;
	}
}

/* Returns 0 on success, non-0 otherwise. */
int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
{
	switch (msr_index) {
	case MSR_IA32_VMX_BASIC:
		*pdata = msrs->basic;
		break;
	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
	case MSR_IA32_VMX_PINBASED_CTLS:
		*pdata = vmx_control_msr(
			msrs->pinbased_ctls_low,
			msrs->pinbased_ctls_high);
		if (msr_index == MSR_IA32_VMX_PINBASED_CTLS)
			*pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
		break;
	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
	case MSR_IA32_VMX_PROCBASED_CTLS:
		*pdata = vmx_control_msr(
			msrs->procbased_ctls_low,
			msrs->procbased_ctls_high);
		if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS)
			*pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
		break;
	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
	case MSR_IA32_VMX_EXIT_CTLS:
		*pdata = vmx_control_msr(
			msrs->exit_ctls_low,
			msrs->exit_ctls_high);
		if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
			*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
		break;
	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
	case MSR_IA32_VMX_ENTRY_CTLS:
		*pdata = vmx_control_msr(
			msrs->entry_ctls_low,
			msrs->entry_ctls_high);
		if (msr_index == MSR_IA32_VMX_ENTRY_CTLS)
			*pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
		break;
	case MSR_IA32_VMX_MISC:
		*pdata = vmx_control_msr(
			msrs->misc_low,
			msrs->misc_high);
		break;
	case MSR_IA32_VMX_CR0_FIXED0:
		*pdata = msrs->cr0_fixed0;
		break;
	case MSR_IA32_VMX_CR0_FIXED1:
		*pdata = msrs->cr0_fixed1;
		break;
	case MSR_IA32_VMX_CR4_FIXED0:
		*pdata = msrs->cr4_fixed0;
		break;
	case MSR_IA32_VMX_CR4_FIXED1:
		*pdata = msrs->cr4_fixed1;
		break;
	case MSR_IA32_VMX_VMCS_ENUM:
		*pdata = msrs->vmcs_enum;
		break;
	case MSR_IA32_VMX_PROCBASED_CTLS2:
		*pdata = vmx_control_msr(
			msrs->secondary_ctls_low,
			msrs->secondary_ctls_high);
		break;
	case MSR_IA32_VMX_EPT_VPID_CAP:
		*pdata = msrs->ept_caps |
			((u64)msrs->vpid_caps << 32);
		break;
	case MSR_IA32_VMX_VMFUNC:
		*pdata = msrs->vmfunc_controls;
		break;
	default:
		return 1;
	}

	return 0;
}

/*
 * Copy the writable VMCS shadow fields back to the VMCS12, in case they have
 * been modified by the L1 guest.  Note, "writable" in this context means
 * "writable by the guest", i.e. tagged SHADOW_FIELD_RW; the set of
 * fields tagged SHADOW_FIELD_RO may or may not align with the "read-only"
 * VM-exit information fields (which are actually writable if the vCPU is
 * configured to support "VMWRITE to any supported field in the VMCS").
 */
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
{
	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
	struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
	struct shadow_vmcs_field field;
	unsigned long val;
	int i;

	if (WARN_ON(!shadow_vmcs))
		return;

	preempt_disable();

	vmcs_load(shadow_vmcs);

	for (i = 0; i < max_shadow_read_write_fields; i++) {
		field = shadow_read_write_fields[i];
		val = __vmcs_readl(field.encoding);
		vmcs12_write_any(vmcs12, field.encoding, field.offset, val);
	}

	vmcs_clear(shadow_vmcs);
	vmcs_load(vmx->loaded_vmcs->vmcs);

	preempt_enable();
}

static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
{
	const struct shadow_vmcs_field *fields[] = {
		shadow_read_write_fields,
		shadow_read_only_fields
	};
	const int max_fields[] = {
		max_shadow_read_write_fields,
		max_shadow_read_only_fields
	};
	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
	struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
	struct shadow_vmcs_field field;
	unsigned long val;
	int i, q;

	if (WARN_ON(!shadow_vmcs))
		return;

	vmcs_load(shadow_vmcs);

	for (q = 0; q < ARRAY_SIZE(fields); q++) {
		for (i = 0; i < max_fields[q]; i++) {
			field = fields[q][i];
			val = vmcs12_read_any(vmcs12, field.encoding,
					      field.offset);
			__vmcs_writel(field.encoding, val);
		}
	}

	vmcs_clear(shadow_vmcs);
	vmcs_load(vmx->loaded_vmcs->vmcs);
}

static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields)
{
#ifdef CONFIG_KVM_HYPERV
	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu);

	/* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
	vmcs12->tpr_threshold = evmcs->tpr_threshold;
	vmcs12->guest_rip = evmcs->guest_rip;

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) {
		hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page;
		hv_vcpu->nested.vm_id = evmcs->hv_vm_id;
		hv_vcpu->nested.vp_id = evmcs->hv_vp_id;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
		vmcs12->guest_rsp = evmcs->guest_rsp;
		vmcs12->guest_rflags = evmcs->guest_rflags;
		vmcs12->guest_interruptibility_info =
			evmcs->guest_interruptibility_info;
		/*
		 * Not present in struct vmcs12:
		 * vmcs12->guest_ssp = evmcs->guest_ssp;
		 */
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
		vmcs12->cpu_based_vm_exec_control =
			evmcs->cpu_based_vm_exec_control;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) {
		vmcs12->exception_bitmap = evmcs->exception_bitmap;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
		vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
		vmcs12->vm_entry_intr_info_field =
			evmcs->vm_entry_intr_info_field;
		vmcs12->vm_entry_exception_error_code =
			evmcs->vm_entry_exception_error_code;
		vmcs12->vm_entry_instruction_len =
			evmcs->vm_entry_instruction_len;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
		vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
		vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
		vmcs12->host_cr0 = evmcs->host_cr0;
		vmcs12->host_cr3 = evmcs->host_cr3;
		vmcs12->host_cr4 = evmcs->host_cr4;
		vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp;
		vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip;
		vmcs12->host_rip = evmcs->host_rip;
		vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs;
		vmcs12->host_es_selector = evmcs->host_es_selector;
		vmcs12->host_cs_selector = evmcs->host_cs_selector;
		vmcs12->host_ss_selector = evmcs->host_ss_selector;
		vmcs12->host_ds_selector = evmcs->host_ds_selector;
		vmcs12->host_fs_selector = evmcs->host_fs_selector;
		vmcs12->host_gs_selector = evmcs->host_gs_selector;
		vmcs12->host_tr_selector = evmcs->host_tr_selector;
		vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl;
		/*
		 * Not present in struct vmcs12:
		 * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet;
		 * vmcs12->host_ssp = evmcs->host_ssp;
		 * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr;
		 */
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) {
		vmcs12->pin_based_vm_exec_control =
			evmcs->pin_based_vm_exec_control;
		vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
		vmcs12->secondary_vm_exec_control =
			evmcs->secondary_vm_exec_control;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
		vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
		vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
		vmcs12->msr_bitmap = evmcs->msr_bitmap;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
		vmcs12->guest_es_base = evmcs->guest_es_base;
		vmcs12->guest_cs_base = evmcs->guest_cs_base;
		vmcs12->guest_ss_base = evmcs->guest_ss_base;
		vmcs12->guest_ds_base = evmcs->guest_ds_base;
		vmcs12->guest_fs_base = evmcs->guest_fs_base;
		vmcs12->guest_gs_base = evmcs->guest_gs_base;
		vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base;
		vmcs12->guest_tr_base = evmcs->guest_tr_base;
		vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base;
		vmcs12->guest_idtr_base = evmcs->guest_idtr_base;
		vmcs12->guest_es_limit = evmcs->guest_es_limit;
		vmcs12->guest_cs_limit = evmcs->guest_cs_limit;
		vmcs12->guest_ss_limit = evmcs->guest_ss_limit;
		vmcs12->guest_ds_limit = evmcs->guest_ds_limit;
		vmcs12->guest_fs_limit = evmcs->guest_fs_limit;
		vmcs12->guest_gs_limit = evmcs->guest_gs_limit;
		vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit;
		vmcs12->guest_tr_limit = evmcs->guest_tr_limit;
		vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit;
		vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit;
		vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes;
		vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes;
		vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes;
		vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes;
		vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes;
		vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes;
		vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes;
		vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes;
		vmcs12->guest_es_selector = evmcs->guest_es_selector;
		vmcs12->guest_cs_selector = evmcs->guest_cs_selector;
		vmcs12->guest_ss_selector = evmcs->guest_ss_selector;
		vmcs12->guest_ds_selector = evmcs->guest_ds_selector;
		vmcs12->guest_fs_selector = evmcs->guest_fs_selector;
		vmcs12->guest_gs_selector = evmcs->guest_gs_selector;
		vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector;
		vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
		vmcs12->tsc_offset = evmcs->tsc_offset;
		vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
		vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
		vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap;
		vmcs12->tsc_multiplier = evmcs->tsc_multiplier;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
		vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
		vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
		vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow;
		vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow;
		vmcs12->guest_cr0 = evmcs->guest_cr0;
		vmcs12->guest_cr3 = evmcs->guest_cr3;
		vmcs12->guest_cr4 = evmcs->guest_cr4;
		vmcs12->guest_dr7 = evmcs->guest_dr7;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
		vmcs12->host_fs_base = evmcs->host_fs_base;
		vmcs12->host_gs_base = evmcs->host_gs_base;
		vmcs12->host_tr_base = evmcs->host_tr_base;
		vmcs12->host_gdtr_base = evmcs->host_gdtr_base;
		vmcs12->host_idtr_base = evmcs->host_idtr_base;
		vmcs12->host_rsp = evmcs->host_rsp;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
		vmcs12->ept_pointer = evmcs->ept_pointer;
		vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
	}

	if (unlikely(!(hv_clean_fields &
		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
		vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
		vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
		vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat;
		vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer;
		vmcs12->guest_pdptr0 = evmcs->guest_pdptr0;
		vmcs12->guest_pdptr1 = evmcs->guest_pdptr1;
		vmcs12->guest_pdptr2 = evmcs->guest_pdptr2;
		vmcs12->guest_pdptr3 = evmcs->guest_pdptr3;
		vmcs12->guest_pending_dbg_exceptions =
			evmcs->guest_pending_dbg_exceptions;
		vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp;
		vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip;
		vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
		vmcs12->guest_activity_state = evmcs->guest_activity_state;
		vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
		vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl;
		/*
		 * Not present in struct vmcs12:
		 * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet;
		 * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl;
		 * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr;
		 */
	}

	/*
	 * Not used?
	 * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
	 * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
	 * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
	 * vmcs12->page_fault_error_code_mask =
	 *		evmcs->page_fault_error_code_mask;
	 * vmcs12->page_fault_error_code_match =
	 *		evmcs->page_fault_error_code_match;
	 * vmcs12->cr3_target_count = evmcs->cr3_target_count;
	 * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count;
	 * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count;
	 * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count;
	 */

	/*
	 * Read only fields:
	 * vmcs12->guest_physical_address = evmcs->guest_physical_address;
	 * vmcs12->vm_instruction_error = evmcs->vm_instruction_error;
	 * vmcs12->vm_exit_reason = evmcs->vm_exit_reason;
	 * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info;
	 * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code;
	 * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field;
	 * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code;
	 * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len;
	 * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info;
	 * vmcs12->exit_qualification = evmcs->exit_qualification;
	 * vmcs12->guest_linear_address = evmcs->guest_linear_address;
	 *
	 * Not present in struct vmcs12:
	 * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx;
	 * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi;
	 * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi;
	 * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip;
	 */

	return;
#else /* CONFIG_KVM_HYPERV */
	KVM_BUG_ON(1, vmx->vcpu.kvm);
#endif /* CONFIG_KVM_HYPERV */
}

static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
{
#ifdef CONFIG_KVM_HYPERV
	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);

	/*
	 * Should not be changed by KVM:
	 *
	 * evmcs->host_es_selector = vmcs12->host_es_selector;
	 * evmcs->host_cs_selector = vmcs12->host_cs_selector;
	 * evmcs->host_ss_selector = vmcs12->host_ss_selector;
	 * evmcs->host_ds_selector = vmcs12->host_ds_selector;
	 * evmcs->host_fs_selector = vmcs12->host_fs_selector;
	 * evmcs->host_gs_selector = vmcs12->host_gs_selector;
	 * evmcs->host_tr_selector = vmcs12->host_tr_selector;
	 * evmcs->host_ia32_pat = vmcs12->host_ia32_pat;
	 * evmcs->host_ia32_efer = vmcs12->host_ia32_efer;
	 * evmcs->host_cr0 = vmcs12->host_cr0;
	 * evmcs->host_cr3 = vmcs12->host_cr3;
	 * evmcs->host_cr4 = vmcs12->host_cr4;
	 * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp;
	 * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip;
	 * evmcs->host_rip = vmcs12->host_rip;
	 * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs;
	 * evmcs->host_fs_base = vmcs12->host_fs_base;
	 * evmcs->host_gs_base = vmcs12->host_gs_base;
	 * evmcs->host_tr_base = vmcs12->host_tr_base;
	 * evmcs->host_gdtr_base = vmcs12->host_gdtr_base;
	 * evmcs->host_idtr_base = vmcs12->host_idtr_base;
	 * evmcs->host_rsp = vmcs12->host_rsp;
	 * sync_vmcs02_to_vmcs12() doesn't read these:
	 * evmcs->io_bitmap_a = vmcs12->io_bitmap_a;
	 * evmcs->io_bitmap_b = vmcs12->io_bitmap_b;
	 * evmcs->msr_bitmap = vmcs12->msr_bitmap;
	 * evmcs->ept_pointer = vmcs12->ept_pointer;
	 * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap;
	 * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
	 * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
	 * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
	 * evmcs->tpr_threshold = vmcs12->tpr_threshold;
	 * evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
	 * evmcs->exception_bitmap = vmcs12->exception_bitmap;
	 * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer;
	 * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control;
	 * evmcs->vm_exit_controls = vmcs12->vm_exit_controls;
	 * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control;
	 * evmcs->page_fault_error_code_mask =
	 *		vmcs12->page_fault_error_code_mask;
	 * evmcs->page_fault_error_code_match =
	 *		vmcs12->page_fault_error_code_match;
	 * evmcs->cr3_target_count = vmcs12->cr3_target_count;
	 * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr;
	 * evmcs->tsc_offset = vmcs12->tsc_offset;
	 * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl;
	 * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask;
	 * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask;
	 * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow;
	 * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow;
	 * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
	 * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
	 * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
	 * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl;
	 * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl;
	 * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap;
	 * evmcs->tsc_multiplier = vmcs12->tsc_multiplier;
	 *
	 * Not present in struct vmcs12:
	 * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
	 * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
	 * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
	 * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
	 * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet;
	 * evmcs->host_ssp = vmcs12->host_ssp;
	 * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr;
	 * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet;
	 * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl;
	 * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr;
	 * evmcs->guest_ssp = vmcs12->guest_ssp;
	 */

	evmcs->guest_es_selector = vmcs12->guest_es_selector;
	evmcs->guest_cs_selector = vmcs12->guest_cs_selector;
	evmcs->guest_ss_selector = vmcs12->guest_ss_selector;
	evmcs->guest_ds_selector = vmcs12->guest_ds_selector;
	evmcs->guest_fs_selector = vmcs12->guest_fs_selector;
	evmcs->guest_gs_selector = vmcs12->guest_gs_selector;
	evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector;
	evmcs->guest_tr_selector = vmcs12->guest_tr_selector;

	evmcs->guest_es_limit = vmcs12->guest_es_limit;
	evmcs->guest_cs_limit = vmcs12->guest_cs_limit;
	evmcs->guest_ss_limit = vmcs12->guest_ss_limit;
	evmcs->guest_ds_limit = vmcs12->guest_ds_limit;
	evmcs->guest_fs_limit = vmcs12->guest_fs_limit;
	evmcs->guest_gs_limit = vmcs12->guest_gs_limit;
	evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit;
	evmcs->guest_tr_limit = vmcs12->guest_tr_limit;
	evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit;
	evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit;

	evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes;
	evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes;
	evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes;
	evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes;
	evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes;
	evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes;
	evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes;
	evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes;

	evmcs->guest_es_base = vmcs12->guest_es_base;
	evmcs->guest_cs_base = vmcs12->guest_cs_base;
	evmcs->guest_ss_base = vmcs12->guest_ss_base;
	evmcs->guest_ds_base = vmcs12->guest_ds_base;
	evmcs->guest_fs_base = vmcs12->guest_fs_base;
	evmcs->guest_gs_base = vmcs12->guest_gs_base;
	evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base;
	evmcs->guest_tr_base = vmcs12->guest_tr_base;
	evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base;
	evmcs->guest_idtr_base = vmcs12->guest_idtr_base;

	evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat;
	evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer;

	evmcs->guest_pdptr0 = vmcs12->guest_pdptr0;
	evmcs->guest_pdptr1 = vmcs12->guest_pdptr1;
	evmcs->guest_pdptr2 = vmcs12->guest_pdptr2;
	evmcs->guest_pdptr3 = vmcs12->guest_pdptr3;

	evmcs->guest_pending_dbg_exceptions =
		vmcs12->guest_pending_dbg_exceptions;
	evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp;
	evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip;

	evmcs->guest_activity_state = vmcs12->guest_activity_state;
	evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs;

	evmcs->guest_cr0 = vmcs12->guest_cr0;
	evmcs->guest_cr3 = vmcs12->guest_cr3;
	evmcs->guest_cr4 = vmcs12->guest_cr4;
	evmcs->guest_dr7 = vmcs12->guest_dr7;

	evmcs->guest_physical_address = vmcs12->guest_physical_address;

	evmcs->vm_instruction_error = vmcs12->vm_instruction_error;
	evmcs->vm_exit_reason = vmcs12->vm_exit_reason;
	evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info;
	evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code;
	evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field;
	evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code;
	evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len;
	evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info;

	evmcs->exit_qualification = vmcs12->exit_qualification;

	evmcs->guest_linear_address = vmcs12->guest_linear_address;
	evmcs->guest_rsp = vmcs12->guest_rsp;
	evmcs->guest_rflags = vmcs12->guest_rflags;

	evmcs->guest_interruptibility_info =
		vmcs12->guest_interruptibility_info;
	evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control;
	evmcs->vm_entry_controls = vmcs12->vm_entry_controls;
	evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field;
	evmcs->vm_entry_exception_error_code =
		vmcs12->vm_entry_exception_error_code;
	evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len;

	evmcs->guest_rip = vmcs12->guest_rip;

	evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;

	return;
#else /* CONFIG_KVM_HYPERV */
	KVM_BUG_ON(1, vmx->vcpu.kvm);
#endif /* CONFIG_KVM_HYPERV */
}

/*
 * This is an equivalent of the nested hypervisor executing the vmptrld
 * instruction.
 */
static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
	struct kvm_vcpu *vcpu, bool from_launch)
{
#ifdef CONFIG_KVM_HYPERV
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	bool evmcs_gpa_changed = false;
	u64 evmcs_gpa;

	if (likely(!guest_cpuid_has_evmcs(vcpu)))
		return EVMPTRLD_DISABLED;

	evmcs_gpa = nested_get_evmptr(vcpu);
	if (!evmptr_is_valid(evmcs_gpa)) {
		nested_release_evmcs(vcpu);
		return EVMPTRLD_DISABLED;
	}

	if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
		vmx->nested.current_vmptr = INVALID_GPA;

		nested_release_evmcs(vcpu);

		if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa),
				 &vmx->nested.hv_evmcs_map))
			return EVMPTRLD_ERROR;

		vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva;

		/*
		 * Currently, KVM only supports eVMCS version 1
		 * (== KVM_EVMCS_VERSION) and thus we expect guest to set this
		 * value to first u32 field of eVMCS which should specify eVMCS
		 * VersionNumber.
		 *
		 * Guest should be aware of supported eVMCS versions by host by
		 * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is
		 * expected to set this CPUID leaf according to the value
		 * returned in vmcs_version from nested_enable_evmcs().
		 *
		 * However, it turns out that Microsoft Hyper-V fails to comply
		 * to their own invented interface: When Hyper-V use eVMCS, it
		 * just sets first u32 field of eVMCS to revision_id specified
		 * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number
		 * which is one of the supported versions specified in
		 * CPUID.0x4000000A.EAX[0:15].
		 *
		 * To overcome Hyper-V bug, we accept here either a supported
		 * eVMCS version or VMCS12 revision_id as valid values for first
		 * u32 field of eVMCS.
		 */
		if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) &&
		    (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) {
			nested_release_evmcs(vcpu);
			return EVMPTRLD_VMFAIL;
		}

		vmx->nested.hv_evmcs_vmptr = evmcs_gpa;

		evmcs_gpa_changed = true;
		/*
		 * Unlike normal vmcs12, enlightened vmcs12 is not fully
		 * reloaded from guest's memory (read only fields, fields not
		 * present in struct hv_enlightened_vmcs, ...). Make sure there
		 * are no leftovers.
		 */
		if (from_launch) {
			struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
			memset(vmcs12, 0, sizeof(*vmcs12));
			vmcs12->hdr.revision_id = VMCS12_REVISION;
		}

	}

	/*
	 * Clean fields data can't be used on VMLAUNCH and when we switch
	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
	 */
	if (from_launch || evmcs_gpa_changed) {
		vmx->nested.hv_evmcs->hv_clean_fields &=
			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;

		vmx->nested.force_msr_bitmap_recalc = true;
	}

	return EVMPTRLD_SUCCEEDED;
#else
	return EVMPTRLD_DISABLED;
#endif
}

void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (nested_vmx_is_evmptr12_valid(vmx))
		copy_vmcs12_to_enlightened(vmx);
	else
		copy_vmcs12_to_shadow(vmx);

	vmx->nested.need_vmcs12_to_shadow_sync = false;
}

static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
{
	struct vcpu_vmx *vmx =
		container_of(timer, struct vcpu_vmx, nested.preemption_timer);

	vmx->nested.preemption_timer_expired = true;
	kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu);
	kvm_vcpu_kick(&vmx->vcpu);

	return HRTIMER_NORESTART;
}

static u64 vmx_calc_preemption_timer_value(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	u64 l1_scaled_tsc = kvm_read_l1_tsc(vcpu, rdtsc()) >>
			    VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;

	if (!vmx->nested.has_preemption_timer_deadline) {
		vmx->nested.preemption_timer_deadline =
			vmcs12->vmx_preemption_timer_value + l1_scaled_tsc;
		vmx->nested.has_preemption_timer_deadline = true;
	}
	return vmx->nested.preemption_timer_deadline - l1_scaled_tsc;
}

static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu,
					u64 preemption_timeout)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * A timer value of zero is architecturally guaranteed to cause
	 * a VMExit prior to executing any instructions in the guest.
	 */
	if (preemption_timeout == 0) {
		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
		return;
	}

	if (vcpu->arch.virtual_tsc_khz == 0)
		return;

	preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
	preemption_timeout *= 1000000;
	do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
	hrtimer_start(&vmx->nested.preemption_timer,
		      ktime_add_ns(ktime_get(), preemption_timeout),
		      HRTIMER_MODE_ABS_PINNED);
}

static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
	if (vmx->nested.nested_run_pending &&
	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
		return vmcs12->guest_ia32_efer;
	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
		return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME);
	else
		return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME);
}

static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
{
	struct kvm *kvm = vmx->vcpu.kvm;

	/*
	 * If vmcs02 hasn't been initialized, set the constant vmcs02 state
	 * according to L0's settings (vmcs12 is irrelevant here).  Host
	 * fields that come from L0 and are not constant, e.g. HOST_CR3,
	 * will be set as needed prior to VMLAUNCH/VMRESUME.
	 */
	if (vmx->nested.vmcs02_initialized)
		return;
	vmx->nested.vmcs02_initialized = true;

	/*
	 * We don't care what the EPTP value is we just need to guarantee
	 * it's valid so we don't get a false positive when doing early
	 * consistency checks.
	 */
	if (enable_ept && nested_early_check)
		vmcs_write64(EPT_POINTER,
			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));

	if (vmx->ve_info)
		vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));

	/* All VMFUNCs are currently emulated through L0 vmexits.  */
	if (cpu_has_vmx_vmfunc())
		vmcs_write64(VM_FUNCTION_CONTROL, 0);

	if (cpu_has_vmx_posted_intr())
		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);

	if (cpu_has_vmx_msr_bitmap())
		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));

	/*
	 * PML is emulated for L2, but never enabled in hardware as the MMU
	 * handles A/D emulation.  Disabling PML for L2 also avoids having to
	 * deal with filtering out L2 GPAs from the buffer.
	 */
	if (enable_pml) {
		vmcs_write64(PML_ADDRESS, 0);
		vmcs_write16(GUEST_PML_INDEX, -1);
	}

	if (cpu_has_vmx_encls_vmexit())
		vmcs_write64(ENCLS_EXITING_BITMAP, INVALID_GPA);

	if (kvm_notify_vmexit_enabled(kvm))
		vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window);

	/*
	 * Set the MSR load/store lists to match L0's settings.  Only the
	 * addresses are constant (for vmcs02), the counts can change based
	 * on L2's behavior, e.g. switching to/from long mode.
	 */
	vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));

	vmx_set_constant_host_state(vmx);
}

static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
				      struct vmcs12 *vmcs12)
{
	prepare_vmcs02_constant_state(vmx);

	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);

	if (enable_vpid) {
		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
		else
			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
	}
}

static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01,
				 struct vmcs12 *vmcs12)
{
	u32 exec_control;
	u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);

	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx))
		prepare_vmcs02_early_rare(vmx, vmcs12);

	/*
	 * PIN CONTROLS
	 */
	exec_control = __pin_controls_get(vmcs01);
	exec_control |= (vmcs12->pin_based_vm_exec_control &
			 ~PIN_BASED_VMX_PREEMPTION_TIMER);

	/* Posted interrupts setting is only taken from vmcs12.  */
	vmx->nested.pi_pending = false;
	if (nested_cpu_has_posted_intr(vmcs12))
		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
	else
		exec_control &= ~PIN_BASED_POSTED_INTR;
	pin_controls_set(vmx, exec_control);

	/*
	 * EXEC CONTROLS
	 */
	exec_control = __exec_controls_get(vmcs01); /* L0's desires */
	exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING;
	exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING;
	exec_control &= ~CPU_BASED_TPR_SHADOW;
	exec_control |= vmcs12->cpu_based_vm_exec_control;

	vmx->nested.l1_tpr_threshold = -1;
	if (exec_control & CPU_BASED_TPR_SHADOW)
		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
#ifdef CONFIG_X86_64
	else
		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
				CPU_BASED_CR8_STORE_EXITING;
#endif

	/*
	 * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
	 * for I/O port accesses.
	 */
	exec_control |= CPU_BASED_UNCOND_IO_EXITING;
	exec_control &= ~CPU_BASED_USE_IO_BITMAPS;

	/*
	 * This bit will be computed in nested_get_vmcs12_pages, because
	 * we do not have access to L1's MSR bitmap yet.  For now, keep
	 * the same bit as before, hoping to avoid multiple VMWRITEs that
	 * only set/clear this bit.
	 */
	exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
	exec_control |= exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS;

	exec_controls_set(vmx, exec_control);

	/*
	 * SECONDARY EXEC CONTROLS
	 */
	if (cpu_has_secondary_exec_ctrls()) {
		exec_control = __secondary_exec_controls_get(vmcs01);

		/* Take the following fields only from vmcs12 */
		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
				  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
				  SECONDARY_EXEC_ENABLE_INVPCID |
				  SECONDARY_EXEC_ENABLE_RDTSCP |
				  SECONDARY_EXEC_ENABLE_XSAVES |
				  SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
				  SECONDARY_EXEC_ENABLE_VMFUNC |
				  SECONDARY_EXEC_DESC);

		if (nested_cpu_has(vmcs12,
				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
			exec_control |= vmcs12->secondary_vm_exec_control;

		/* PML is emulated and never enabled in hardware for L2. */
		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;

		/* VMCS shadowing for L2 is emulated for now */
		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;

		/*
		 * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4()
		 * will not have to rewrite the controls just for this bit.
		 */
		if (vmx_umip_emulated() && (vmcs12->guest_cr4 & X86_CR4_UMIP))
			exec_control |= SECONDARY_EXEC_DESC;

		if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
			vmcs_write16(GUEST_INTR_STATUS,
				vmcs12->guest_intr_status);

		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
		    exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;

		if (exec_control & SECONDARY_EXEC_ENCLS_EXITING)
			vmx_write_encls_bitmap(&vmx->vcpu, vmcs12);

		secondary_exec_controls_set(vmx, exec_control);
	}

	/*
	 * ENTRY CONTROLS
	 *
	 * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE
	 * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
	 * on the related bits (if supported by the CPU) in the hope that
	 * we can avoid VMWrites during vmx_set_efer().
	 *
	 * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is
	 * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to
	 * do the same for L2.
	 */
	exec_control = __vm_entry_controls_get(vmcs01);
	exec_control |= (vmcs12->vm_entry_controls &
			 ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL);
	exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER);
	if (cpu_has_load_ia32_efer()) {
		if (guest_efer & EFER_LMA)
			exec_control |= VM_ENTRY_IA32E_MODE;
		if (guest_efer != host_efer)
			exec_control |= VM_ENTRY_LOAD_IA32_EFER;
	}
	vm_entry_controls_set(vmx, exec_control);

	/*
	 * EXIT CONTROLS
	 *
	 * L2->L1 exit controls are emulated - the hardware exit is to L0 so
	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
	 * bits may be modified by vmx_set_efer() in prepare_vmcs02().
	 */
	exec_control = __vm_exit_controls_get(vmcs01);
	if (cpu_has_load_ia32_efer() && guest_efer != host_efer)
		exec_control |= VM_EXIT_LOAD_IA32_EFER;
	else
		exec_control &= ~VM_EXIT_LOAD_IA32_EFER;
	vm_exit_controls_set(vmx, exec_control);

	/*
	 * Interrupt/Exception Fields
	 */
	if (vmx->nested.nested_run_pending) {
		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
			     vmcs12->vm_entry_intr_info_field);
		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
			     vmcs12->vm_entry_exception_error_code);
		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
			     vmcs12->vm_entry_instruction_len);
		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
			     vmcs12->guest_interruptibility_info);
		vmx->loaded_vmcs->nmi_known_unmasked =
			!(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
	} else {
		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
	}
}

static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
	struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx);

	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
		vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
		vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
		vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
		vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
		vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
		vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
		vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
		vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
		vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
		vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
		vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
		vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
		vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
		vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
		vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
		vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
		vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
		vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
		vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
		vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
		vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
		vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
		vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
		vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
		vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
		vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
		vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
		vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
		vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
		vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);

		vmx->segment_cache.bitmask = 0;
	}

	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
		vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
			    vmcs12->guest_pending_dbg_exceptions);
		vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
		vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);

		/*
		 * L1 may access the L2's PDPTR, so save them to construct
		 * vmcs12
		 */
		if (enable_ept) {
			vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
			vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
			vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
			vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
		}

		if (kvm_mpx_supported() && vmx->nested.nested_run_pending &&
		    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
	}

	if (nested_cpu_has_xsaves(vmcs12))
		vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);

	/*
	 * Whether page-faults are trapped is determined by a combination of
	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.  If L0
	 * doesn't care about page faults then we should set all of these to
	 * L1's desires. However, if L0 does care about (some) page faults, it
	 * is not easy (if at all possible?) to merge L0 and L1's desires, we
	 * simply ask to exit on each and every L2 page fault. This is done by
	 * setting MASK=MATCH=0 and (see below) EB.PF=1.
	 * Note that below we don't need special code to set EB.PF beyond the
	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
	 */
	if (vmx_need_pf_intercept(&vmx->vcpu)) {
		/*
		 * TODO: if both L0 and L1 need the same MASK and MATCH,
		 * go ahead and use it?
		 */
		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
	} else {
		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, vmcs12->page_fault_error_code_mask);
		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, vmcs12->page_fault_error_code_match);
	}

	if (cpu_has_vmx_apicv()) {
		vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
		vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
		vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
	}

	/*
	 * Make sure the msr_autostore list is up to date before we set the
	 * count in the vmcs02.
	 */
	prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC);

	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr);
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);

	set_cr4_guest_host_mask(vmx);
}

/*
 * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
 * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
 * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
 * guest in a way that will both be appropriate to L1's requests, and our
 * needs. In addition to modifying the active vmcs (which is vmcs02), this
 * function also has additional necessary side-effects, like setting various
 * vcpu->arch fields.
 * Returns 0 on success, 1 on failure. Invalid state exit qualification code
 * is assigned to entry_failure_code on failure.
 */
static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
			  bool from_vmentry,
			  enum vm_entry_failure_code *entry_failure_code)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
	bool load_guest_pdptrs_vmcs12 = false;

	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) {
		prepare_vmcs02_rare(vmx, vmcs12);
		vmx->nested.dirty_vmcs12 = false;

		load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) ||
			!(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
	}

	if (vmx->nested.nested_run_pending &&
	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
	} else {
		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
	}
	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
		vmcs_write64(GUEST_BNDCFGS, vmx->nested.pre_vmenter_bndcfgs);
	vmx_set_rflags(vcpu, vmcs12->guest_rflags);

	/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
	 * bitwise-or of what L1 wants to trap for L2, and what we want to
	 * trap. Note that CR0.TS also needs updating - we do this later.
	 */
	vmx_update_exception_bitmap(vcpu);
	vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);

	if (vmx->nested.nested_run_pending &&
	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
		vcpu->arch.pat = vmcs12->guest_ia32_pat;
	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
	}

	vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset(
			vcpu->arch.l1_tsc_offset,
			vmx_get_l2_tsc_offset(vcpu),
			vmx_get_l2_tsc_multiplier(vcpu));

	vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(
			vcpu->arch.l1_tsc_scaling_ratio,
			vmx_get_l2_tsc_multiplier(vcpu));

	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
	if (kvm_caps.has_tsc_control)
		vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);

	nested_vmx_transition_tlb_flush(vcpu, vmcs12, true);

	if (nested_cpu_has_ept(vmcs12))
		nested_ept_init_mmu_context(vcpu);

	/*
	 * Override the CR0/CR4 read shadows after setting the effective guest
	 * CR0/CR4.  The common helpers also set the shadows, but they don't
	 * account for vmcs12's cr0/4_guest_host_mask.
	 */
	vmx_set_cr0(vcpu, vmcs12->guest_cr0);
	vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));

	vmx_set_cr4(vcpu, vmcs12->guest_cr4);
	vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));

	vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12);
	/* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
	vmx_set_efer(vcpu, vcpu->arch.efer);

	/*
	 * Guest state is invalid and unrestricted guest is disabled,
	 * which means L1 attempted VMEntry to L2 with invalid state.
	 * Fail the VMEntry.
	 *
	 * However when force loading the guest state (SMM exit or
	 * loading nested state after migration, it is possible to
	 * have invalid guest state now, which will be later fixed by
	 * restoring L2 register state
	 */
	if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) {
		*entry_failure_code = ENTRY_FAIL_DEFAULT;
		return -EINVAL;
	}

	/* Shadow page tables on either EPT or shadow page tables. */
	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
				from_vmentry, entry_failure_code))
		return -EINVAL;

	/*
	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
	 * on nested VM-Exit, which can occur without actually running L2 and
	 * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with
	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
	 * transition to HLT instead of running L2.
	 */
	if (enable_ept)
		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);

	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
	    is_pae_paging(vcpu)) {
		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
	}

	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
	    kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) &&
	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
				     vmcs12->guest_ia32_perf_global_ctrl))) {
		*entry_failure_code = ENTRY_FAIL_DEFAULT;
		return -EINVAL;
	}

	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
	kvm_rip_write(vcpu, vmcs12->guest_rip);

	/*
	 * It was observed that genuine Hyper-V running in L1 doesn't reset
	 * 'hv_clean_fields' by itself, it only sets the corresponding dirty
	 * bits when it changes a field in eVMCS. Mark all fields as clean
	 * here.
	 */
	if (nested_vmx_is_evmptr12_valid(vmx))
		evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;

	return 0;
}

static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
{
	if (CC(!nested_cpu_has_nmi_exiting(vmcs12) &&
	       nested_cpu_has_virtual_nmis(vmcs12)))
		return -EINVAL;

	if (CC(!nested_cpu_has_virtual_nmis(vmcs12) &&
	       nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING)))
		return -EINVAL;

	return 0;
}

static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/* Check for memory type validity */
	switch (new_eptp & VMX_EPTP_MT_MASK) {
	case VMX_EPTP_MT_UC:
		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)))
			return false;
		break;
	case VMX_EPTP_MT_WB:
		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT)))
			return false;
		break;
	default:
		return false;
	}

	/* Page-walk levels validity. */
	switch (new_eptp & VMX_EPTP_PWL_MASK) {
	case VMX_EPTP_PWL_5:
		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT)))
			return false;
		break;
	case VMX_EPTP_PWL_4:
		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT)))
			return false;
		break;
	default:
		return false;
	}

	/* Reserved bits should not be set */
	if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f)))
		return false;

	/* AD, if set, should be supported */
	if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) {
		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)))
			return false;
	}

	return true;
}

/*
 * Checks related to VM-Execution Control Fields
 */
static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu,
                                              struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (CC(!vmx_control_verify(vmcs12->pin_based_vm_exec_control,
				   vmx->nested.msrs.pinbased_ctls_low,
				   vmx->nested.msrs.pinbased_ctls_high)) ||
	    CC(!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
				   vmx->nested.msrs.procbased_ctls_low,
				   vmx->nested.msrs.procbased_ctls_high)))
		return -EINVAL;

	if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
	    CC(!vmx_control_verify(vmcs12->secondary_vm_exec_control,
				   vmx->nested.msrs.secondary_ctls_low,
				   vmx->nested.msrs.secondary_ctls_high)))
		return -EINVAL;

	if (CC(vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu)) ||
	    nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) ||
	    nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) ||
	    nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) ||
	    nested_vmx_check_apic_access_controls(vcpu, vmcs12) ||
	    nested_vmx_check_apicv_controls(vcpu, vmcs12) ||
	    nested_vmx_check_nmi_controls(vmcs12) ||
	    nested_vmx_check_pml_controls(vcpu, vmcs12) ||
	    nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) ||
	    nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) ||
	    nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) ||
	    CC(nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id))
		return -EINVAL;

	if (!nested_cpu_has_preemption_timer(vmcs12) &&
	    nested_cpu_has_save_preemption_timer(vmcs12))
		return -EINVAL;

	if (nested_cpu_has_ept(vmcs12) &&
	    CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer)))
		return -EINVAL;

	if (nested_cpu_has_vmfunc(vmcs12)) {
		if (CC(vmcs12->vm_function_control &
		       ~vmx->nested.msrs.vmfunc_controls))
			return -EINVAL;

		if (nested_cpu_has_eptp_switching(vmcs12)) {
			if (CC(!nested_cpu_has_ept(vmcs12)) ||
			    CC(!page_address_valid(vcpu, vmcs12->eptp_list_address)))
				return -EINVAL;
		}
	}

	return 0;
}

/*
 * Checks related to VM-Exit Control Fields
 */
static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu,
                                         struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (CC(!vmx_control_verify(vmcs12->vm_exit_controls,
				    vmx->nested.msrs.exit_ctls_low,
				    vmx->nested.msrs.exit_ctls_high)) ||
	    CC(nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12)))
		return -EINVAL;

	return 0;
}

/*
 * Checks related to VM-Entry Control Fields
 */
static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
					  struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (CC(!vmx_control_verify(vmcs12->vm_entry_controls,
				    vmx->nested.msrs.entry_ctls_low,
				    vmx->nested.msrs.entry_ctls_high)))
		return -EINVAL;

	/*
	 * From the Intel SDM, volume 3:
	 * Fields relevant to VM-entry event injection must be set properly.
	 * These fields are the VM-entry interruption-information field, the
	 * VM-entry exception error code, and the VM-entry instruction length.
	 */
	if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
		u32 intr_info = vmcs12->vm_entry_intr_info_field;
		u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
		u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
		bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
		bool should_have_error_code;
		bool urg = nested_cpu_has2(vmcs12,
					   SECONDARY_EXEC_UNRESTRICTED_GUEST);
		bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;

		/* VM-entry interruption-info field: interruption type */
		if (CC(intr_type == INTR_TYPE_RESERVED) ||
		    CC(intr_type == INTR_TYPE_OTHER_EVENT &&
		       !nested_cpu_supports_monitor_trap_flag(vcpu)))
			return -EINVAL;

		/* VM-entry interruption-info field: vector */
		if (CC(intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
		    CC(intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
		    CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
			return -EINVAL;

		/* VM-entry interruption-info field: deliver error code */
		should_have_error_code =
			intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
			x86_exception_has_error_code(vector);
		if (CC(has_error_code != should_have_error_code))
			return -EINVAL;

		/* VM-entry exception error code */
		if (CC(has_error_code &&
		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 16)))
			return -EINVAL;

		/* VM-entry interruption-info field: reserved bits */
		if (CC(intr_info & INTR_INFO_RESVD_BITS_MASK))
			return -EINVAL;

		/* VM-entry instruction length */
		switch (intr_type) {
		case INTR_TYPE_SOFT_EXCEPTION:
		case INTR_TYPE_SOFT_INTR:
		case INTR_TYPE_PRIV_SW_EXCEPTION:
			if (CC(vmcs12->vm_entry_instruction_len > 15) ||
			    CC(vmcs12->vm_entry_instruction_len == 0 &&
			    CC(!nested_cpu_has_zero_length_injection(vcpu))))
				return -EINVAL;
		}
	}

	if (nested_vmx_check_entry_msr_switch_controls(vcpu, vmcs12))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
				     struct vmcs12 *vmcs12)
{
	if (nested_check_vm_execution_controls(vcpu, vmcs12) ||
	    nested_check_vm_exit_controls(vcpu, vmcs12) ||
	    nested_check_vm_entry_controls(vcpu, vmcs12))
		return -EINVAL;

#ifdef CONFIG_KVM_HYPERV
	if (guest_cpuid_has_evmcs(vcpu))
		return nested_evmcs_check_controls(vmcs12);
#endif

	return 0;
}

static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
#ifdef CONFIG_X86_64
	if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
		!!(vcpu->arch.efer & EFER_LMA)))
		return -EINVAL;
#endif
	return 0;
}

static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);

	if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
	    CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
	    CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
		return -EINVAL;

	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
		return -EINVAL;

	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
	    CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
		return -EINVAL;

	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
					   vmcs12->host_ia32_perf_global_ctrl)))
		return -EINVAL;

	if (ia32e) {
		if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
			return -EINVAL;
	} else {
		if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
		    CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
		    CC((vmcs12->host_rip) >> 32))
			return -EINVAL;
	}

	if (CC(vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
	    CC(vmcs12->host_cs_selector == 0) ||
	    CC(vmcs12->host_tr_selector == 0) ||
	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
		return -EINVAL;

	if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
	    CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
		return -EINVAL;

	/*
	 * If the load IA32_EFER VM-exit control is 1, bits reserved in the
	 * IA32_EFER MSR must be 0 in the field for that register. In addition,
	 * the values of the LMA and LME bits in the field must each be that of
	 * the host address-space size VM-exit control.
	 */
	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
		if (CC(!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer)) ||
		    CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA)) ||
		    CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)))
			return -EINVAL;
	}

	return 0;
}

static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
					  struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
	struct vmcs_hdr hdr;

	if (vmcs12->vmcs_link_pointer == INVALID_GPA)
		return 0;

	if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
		return -EINVAL;

	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
	    CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
					 vmcs12->vmcs_link_pointer, VMCS12_SIZE)))
                return -EINVAL;

	if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
					    offsetof(struct vmcs12, hdr),
					    sizeof(hdr))))
		return -EINVAL;

	if (CC(hdr.revision_id != VMCS12_REVISION) ||
	    CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
		return -EINVAL;

	return 0;
}

/*
 * Checks related to Guest Non-register State
 */
static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
{
	if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT &&
	       vmcs12->guest_activity_state != GUEST_ACTIVITY_WAIT_SIPI))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
					struct vmcs12 *vmcs12,
					enum vm_entry_failure_code *entry_failure_code)
{
	bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);

	*entry_failure_code = ENTRY_FAIL_DEFAULT;

	if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) ||
	    CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)))
		return -EINVAL;

	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
	    CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
		return -EINVAL;

	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))
		return -EINVAL;

	if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
		*entry_failure_code = ENTRY_FAIL_VMCS_LINK_PTR;
		return -EINVAL;
	}

	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
					   vmcs12->guest_ia32_perf_global_ctrl)))
		return -EINVAL;

	if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
		return -EINVAL;

	if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
	    CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
		return -EINVAL;

	/*
	 * If the load IA32_EFER VM-entry control is 1, the following checks
	 * are performed on the field for the IA32_EFER MSR:
	 * - Bits reserved in the IA32_EFER MSR must be 0.
	 * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of
	 *   the IA-32e mode guest VM-exit control. It must also be identical
	 *   to bit 8 (LME) if bit 31 in the CR0 field (corresponding to
	 *   CR0.PG) is 1.
	 */
	if (to_vmx(vcpu)->nested.nested_run_pending &&
	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
		if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
		    CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
		    CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&
		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))))
			return -EINVAL;
	}

	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
	    (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
	     CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
		return -EINVAL;

	if (nested_check_guest_non_reg_state(vmcs12))
		return -EINVAL;

	return 0;
}

static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long cr3, cr4;
	bool vm_fail;

	if (!nested_early_check)
		return 0;

	if (vmx->msr_autoload.host.nr)
		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
	if (vmx->msr_autoload.guest.nr)
		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);

	preempt_disable();

	vmx_prepare_switch_to_guest(vcpu);

	/*
	 * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
	 * which is reserved to '1' by hardware.  GUEST_RFLAGS is guaranteed to
	 * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e.
	 * there is no need to preserve other bits or save/restore the field.
	 */
	vmcs_writel(GUEST_RFLAGS, 0);

	cr3 = __get_current_cr3_fast();
	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
		vmcs_writel(HOST_CR3, cr3);
		vmx->loaded_vmcs->host_state.cr3 = cr3;
	}

	cr4 = cr4_read_shadow();
	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
		vmcs_writel(HOST_CR4, cr4);
		vmx->loaded_vmcs->host_state.cr4 = cr4;
	}

	vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
				 __vmx_vcpu_run_flags(vmx));

	if (vmx->msr_autoload.host.nr)
		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
	if (vmx->msr_autoload.guest.nr)
		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);

	if (vm_fail) {
		u32 error = vmcs_read32(VM_INSTRUCTION_ERROR);

		preempt_enable();

		trace_kvm_nested_vmenter_failed(
			"early hardware check VM-instruction error: ", error);
		WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD);
		return 1;
	}

	/*
	 * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
	 */
	if (hw_breakpoint_active())
		set_debugreg(__this_cpu_read(cpu_dr7), 7);
	local_irq_enable();
	preempt_enable();

	/*
	 * A non-failing VMEntry means we somehow entered guest mode with
	 * an illegal RIP, and that's just the tip of the iceberg.  There
	 * is no telling what memory has been modified or what state has
	 * been exposed to unknown code.  Hitting this all but guarantees
	 * a (very critical) hardware issue.
	 */
	WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
		VMX_EXIT_REASONS_FAILED_VMENTRY));

	return 0;
}

#ifdef CONFIG_KVM_HYPERV
static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * hv_evmcs may end up being not mapped after migration (when
	 * L2 was running), map it here to make sure vmcs12 changes are
	 * properly reflected.
	 */
	if (guest_cpuid_has_evmcs(vcpu) &&
	    vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) {
		enum nested_evmptrld_status evmptrld_status =
			nested_vmx_handle_enlightened_vmptrld(vcpu, false);

		if (evmptrld_status == EVMPTRLD_VMFAIL ||
		    evmptrld_status == EVMPTRLD_ERROR)
			return false;

		/*
		 * Post migration VMCS12 always provides the most actual
		 * information, copy it to eVMCS upon entry.
		 */
		vmx->nested.need_vmcs12_to_shadow_sync = true;
	}

	return true;
}
#endif

static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct kvm_host_map *map;

	if (!vcpu->arch.pdptrs_from_userspace &&
	    !nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) {
		/*
		 * Reload the guest's PDPTRs since after a migration
		 * the guest CR3 might be restored prior to setting the nested
		 * state which can lead to a load of wrong PDPTRs.
		 */
		if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
			return false;
	}


	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
		map = &vmx->nested.apic_access_page_map;

		if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->apic_access_addr), map)) {
			vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(map->pfn));
		} else {
			pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n",
					     __func__);
			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
			vcpu->run->internal.suberror =
				KVM_INTERNAL_ERROR_EMULATION;
			vcpu->run->internal.ndata = 0;
			return false;
		}
	}

	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
		map = &vmx->nested.virtual_apic_map;

		if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->virtual_apic_page_addr), map)) {
			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, pfn_to_hpa(map->pfn));
		} else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
		           nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
			   !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
			/*
			 * The processor will never use the TPR shadow, simply
			 * clear the bit from the execution control.  Such a
			 * configuration is useless, but it happens in tests.
			 * For any other configuration, failing the vm entry is
			 * _not_ what the processor does but it's basically the
			 * only possibility we have.
			 */
			exec_controls_clearbit(vmx, CPU_BASED_TPR_SHADOW);
		} else {
			/*
			 * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to
			 * force VM-Entry to fail.
			 */
			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, INVALID_GPA);
		}
	}

	if (nested_cpu_has_posted_intr(vmcs12)) {
		map = &vmx->nested.pi_desc_map;

		if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->posted_intr_desc_addr), map)) {
			vmx->nested.pi_desc =
				(struct pi_desc *)(((void *)map->hva) +
				offset_in_page(vmcs12->posted_intr_desc_addr));
			vmcs_write64(POSTED_INTR_DESC_ADDR,
				     pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr));
		} else {
			/*
			 * Defer the KVM_INTERNAL_EXIT until KVM tries to
			 * access the contents of the VMCS12 posted interrupt
			 * descriptor. (Note that KVM may do this when it
			 * should not, per the architectural specification.)
			 */
			vmx->nested.pi_desc = NULL;
			pin_controls_clearbit(vmx, PIN_BASED_POSTED_INTR);
		}
	}
	if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
	else
		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);

	return true;
}

static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_KVM_HYPERV
	/*
	 * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy
	 * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory
	 * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post
	 * migration.
	 */
	if (!nested_get_evmcs_page(vcpu)) {
		pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
				     __func__);
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror =
			KVM_INTERNAL_ERROR_EMULATION;
		vcpu->run->internal.ndata = 0;

		return false;
	}
#endif

	if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
		return false;

	return true;
}

static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
{
	struct vmcs12 *vmcs12;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	gpa_t dst;

	if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
		return 0;

	if (WARN_ON_ONCE(vmx->nested.pml_full))
		return 1;

	/*
	 * Check if PML is enabled for the nested guest. Whether eptp bit 6 is
	 * set is already checked as part of A/D emulation.
	 */
	vmcs12 = get_vmcs12(vcpu);
	if (!nested_cpu_has_pml(vmcs12))
		return 0;

	if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
		vmx->nested.pml_full = true;
		return 1;
	}

	gpa &= ~0xFFFull;
	dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;

	if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
				 offset_in_page(dst), sizeof(gpa)))
		return 0;

	vmcs12->guest_pml_index--;

	return 0;
}

/*
 * Intel's VMX Instruction Reference specifies a common set of prerequisites
 * for running VMX instructions (except VMXON, whose prerequisites are
 * slightly different). It also specifies what exception to inject otherwise.
 * Note that many of these exceptions have priority over VM exits, so they
 * don't have to be checked again here.
 */
static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
{
	if (!to_vmx(vcpu)->nested.vmxon) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 0;
	}

	if (vmx_get_cpl(vcpu)) {
		kvm_inject_gp(vcpu, 0);
		return 0;
	}

	return 1;
}

static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
{
	u8 rvi = vmx_get_rvi();
	u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);

	return ((rvi & 0xf0) > (vppr & 0xf0));
}

static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
				   struct vmcs12 *vmcs12);

/*
 * If from_vmentry is false, this is being called from state restore (either RSM
 * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
 *
 * Returns:
 *	NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode
 *	NVMX_VMENTRY_VMFAIL:  Consistency check VMFail
 *	NVMX_VMENTRY_VMEXIT:  Consistency check VMExit
 *	NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error
 */
enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
							bool from_vmentry)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	enum vm_entry_failure_code entry_failure_code;
	bool evaluate_pending_interrupts;
	union vmx_exit_reason exit_reason = {
		.basic = EXIT_REASON_INVALID_STATE,
		.failed_vmentry = 1,
	};
	u32 failed_index;

	trace_kvm_nested_vmenter(kvm_rip_read(vcpu),
				 vmx->nested.current_vmptr,
				 vmcs12->guest_rip,
				 vmcs12->guest_intr_status,
				 vmcs12->vm_entry_intr_info_field,
				 vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT,
				 vmcs12->ept_pointer,
				 vmcs12->guest_cr3,
				 KVM_ISA_VMX);

	kvm_service_local_tlb_flush_requests(vcpu);

	evaluate_pending_interrupts = exec_controls_get(vmx) &
		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
	if (!evaluate_pending_interrupts)
		evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu);

	if (!vmx->nested.nested_run_pending ||
	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
		vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
	if (kvm_mpx_supported() &&
	    (!vmx->nested.nested_run_pending ||
	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
		vmx->nested.pre_vmenter_bndcfgs = vmcs_read64(GUEST_BNDCFGS);

	/*
	 * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and*
	 * nested early checks are disabled.  In the event of a "late" VM-Fail,
	 * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its
	 * software model to the pre-VMEntry host state.  When EPT is disabled,
	 * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes
	 * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3.  Stuffing
	 * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to
	 * the correct value.  Smashing vmcs01.GUEST_CR3 is safe because nested
	 * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is
	 * guaranteed to be overwritten with a shadow CR3 prior to re-entering
	 * L1.  Don't stuff vmcs01.GUEST_CR3 when using nested early checks as
	 * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks
	 * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail
	 * path would need to manually save/restore vmcs01.GUEST_CR3.
	 */
	if (!enable_ept && !nested_early_check)
		vmcs_writel(GUEST_CR3, vcpu->arch.cr3);

	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);

	prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12);

	if (from_vmentry) {
		if (unlikely(!nested_get_vmcs12_pages(vcpu))) {
			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
		}

		if (nested_vmx_check_vmentry_hw(vcpu)) {
			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
			return NVMX_VMENTRY_VMFAIL;
		}

		if (nested_vmx_check_guest_state(vcpu, vmcs12,
						 &entry_failure_code)) {
			exit_reason.basic = EXIT_REASON_INVALID_STATE;
			vmcs12->exit_qualification = entry_failure_code;
			goto vmentry_fail_vmexit;
		}
	}

	enter_guest_mode(vcpu);

	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &entry_failure_code)) {
		exit_reason.basic = EXIT_REASON_INVALID_STATE;
		vmcs12->exit_qualification = entry_failure_code;
		goto vmentry_fail_vmexit_guest_mode;
	}

	if (from_vmentry) {
		failed_index = nested_vmx_load_msr(vcpu,
						   vmcs12->vm_entry_msr_load_addr,
						   vmcs12->vm_entry_msr_load_count);
		if (failed_index) {
			exit_reason.basic = EXIT_REASON_MSR_LOAD_FAIL;
			vmcs12->exit_qualification = failed_index;
			goto vmentry_fail_vmexit_guest_mode;
		}
	} else {
		/*
		 * The MMU is not initialized to point at the right entities yet and
		 * "get pages" would need to read data from the guest (i.e. we will
		 * need to perform gpa to hpa translation). Request a call
		 * to nested_get_vmcs12_pages before the next VM-entry.  The MSRs
		 * have already been set at vmentry time and should not be reset.
		 */
		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
	}

	/*
	 * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI
	 * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can
	 * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit
	 * unconditionally.
	 */
	if (unlikely(evaluate_pending_interrupts))
		kvm_make_request(KVM_REQ_EVENT, vcpu);

	/*
	 * Do not start the preemption timer hrtimer until after we know
	 * we are successful, so that only nested_vmx_vmexit needs to cancel
	 * the timer.
	 */
	vmx->nested.preemption_timer_expired = false;
	if (nested_cpu_has_preemption_timer(vmcs12)) {
		u64 timer_value = vmx_calc_preemption_timer_value(vcpu);
		vmx_start_preemption_timer(vcpu, timer_value);
	}

	/*
	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
	 * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
	 * returned as far as L1 is concerned. It will only return (and set
	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
	 */
	return NVMX_VMENTRY_SUCCESS;

	/*
	 * A failed consistency check that leads to a VMExit during L1's
	 * VMEnter to L2 is a variation of a normal VMexit, as explained in
	 * 26.7 "VM-entry failures during or after loading guest state".
	 */
vmentry_fail_vmexit_guest_mode:
	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
	leave_guest_mode(vcpu);

vmentry_fail_vmexit:
	vmx_switch_vmcs(vcpu, &vmx->vmcs01);

	if (!from_vmentry)
		return NVMX_VMENTRY_VMEXIT;

	load_vmcs12_host_state(vcpu, vmcs12);
	vmcs12->vm_exit_reason = exit_reason.full;
	if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))
		vmx->nested.need_vmcs12_to_shadow_sync = true;
	return NVMX_VMENTRY_VMEXIT;
}

/*
 * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1
 * for running an L2 nested guest.
 */
static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
{
	struct vmcs12 *vmcs12;
	enum nvmx_vmentry_status status;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
	enum nested_evmptrld_status evmptrld_status;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch);
	if (evmptrld_status == EVMPTRLD_ERROR) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);

	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
		return nested_vmx_failInvalid(vcpu);

	if (CC(!nested_vmx_is_evmptr12_valid(vmx) &&
	       vmx->nested.current_vmptr == INVALID_GPA))
		return nested_vmx_failInvalid(vcpu);

	vmcs12 = get_vmcs12(vcpu);

	/*
	 * Can't VMLAUNCH or VMRESUME a shadow VMCS. Despite the fact
	 * that there *is* a valid VMCS pointer, RFLAGS.CF is set
	 * rather than RFLAGS.ZF, and no error number is stored to the
	 * VM-instruction error field.
	 */
	if (CC(vmcs12->hdr.shadow_vmcs))
		return nested_vmx_failInvalid(vcpu);

	if (nested_vmx_is_evmptr12_valid(vmx)) {
		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);

		copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields);
		/* Enlightened VMCS doesn't have launch state */
		vmcs12->launch_state = !launch;
	} else if (enable_shadow_vmcs) {
		copy_shadow_to_vmcs12(vmx);
	}

	/*
	 * The nested entry process starts with enforcing various prerequisites
	 * on vmcs12 as required by the Intel SDM, and act appropriately when
	 * they fail: As the SDM explains, some conditions should cause the
	 * instruction to fail, while others will cause the instruction to seem
	 * to succeed, but return an EXIT_REASON_INVALID_STATE.
	 * To speed up the normal (success) code path, we should avoid checking
	 * for misconfigurations which will anyway be caught by the processor
	 * when using the merged vmcs02.
	 */
	if (CC(interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS))
		return nested_vmx_fail(vcpu, VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);

	if (CC(vmcs12->launch_state == launch))
		return nested_vmx_fail(vcpu,
			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);

	if (nested_vmx_check_controls(vcpu, vmcs12))
		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);

	if (nested_vmx_check_address_space_size(vcpu, vmcs12))
		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);

	if (nested_vmx_check_host_state(vcpu, vmcs12))
		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);

	/*
	 * We're finally done with prerequisite checking, and can start with
	 * the nested entry.
	 */
	vmx->nested.nested_run_pending = 1;
	vmx->nested.has_preemption_timer_deadline = false;
	status = nested_vmx_enter_non_root_mode(vcpu, true);
	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
		goto vmentry_failed;

	/* Emulate processing of posted interrupts on VM-Enter. */
	if (nested_cpu_has_posted_intr(vmcs12) &&
	    kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) {
		vmx->nested.pi_pending = true;
		kvm_make_request(KVM_REQ_EVENT, vcpu);
		kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv);
	}

	/* Hide L1D cache contents from the nested guest.  */
	vmx->vcpu.arch.l1tf_flush_l1d = true;

	/*
	 * Must happen outside of nested_vmx_enter_non_root_mode() as it will
	 * also be used as part of restoring nVMX state for
	 * snapshot restore (migration).
	 *
	 * In this flow, it is assumed that vmcs12 cache was
	 * transferred as part of captured nVMX state and should
	 * therefore not be read from guest memory (which may not
	 * exist on destination host yet).
	 */
	nested_cache_shadow_vmcs12(vcpu, vmcs12);

	switch (vmcs12->guest_activity_state) {
	case GUEST_ACTIVITY_HLT:
		/*
		 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
		 * awakened by event injection or by an NMI-window VM-exit or
		 * by an interrupt-window VM-exit, halt the vcpu.
		 */
		if (!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
		    !nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING) &&
		    !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) &&
		      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
			vmx->nested.nested_run_pending = 0;
			return kvm_emulate_halt_noskip(vcpu);
		}
		break;
	case GUEST_ACTIVITY_WAIT_SIPI:
		vmx->nested.nested_run_pending = 0;
		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
		break;
	default:
		break;
	}

	return 1;

vmentry_failed:
	vmx->nested.nested_run_pending = 0;
	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
		return 0;
	if (status == NVMX_VMENTRY_VMEXIT)
		return 1;
	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
	return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
}

/*
 * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
 * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK).
 * This function returns the new value we should put in vmcs12.guest_cr0.
 * It's not enough to just return the vmcs02 GUEST_CR0. Rather,
 *  1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
 *     available in vmcs02 GUEST_CR0. (Note: It's enough to check that L0
 *     didn't trap the bit, because if L1 did, so would L0).
 *  2. Bits that L1 asked to trap (and therefore L0 also did) could not have
 *     been modified by L2, and L1 knows it. So just leave the old value of
 *     the bit from vmcs12.guest_cr0. Note that the bit from vmcs02 GUEST_CR0
 *     isn't relevant, because if L0 traps this bit it can set it to anything.
 *  3. Bits that L1 didn't trap, but L0 did. L1 believes the guest could have
 *     changed these bits, and therefore they need to be updated, but L0
 *     didn't necessarily allow them to be changed in GUEST_CR0 - and rather
 *     put them in vmcs02 CR0_READ_SHADOW. So take these bits from there.
 */
static inline unsigned long
vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
	return
	/*1*/	(vmcs_readl(GUEST_CR0) & vcpu->arch.cr0_guest_owned_bits) |
	/*2*/	(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask) |
	/*3*/	(vmcs_readl(CR0_READ_SHADOW) & ~(vmcs12->cr0_guest_host_mask |
			vcpu->arch.cr0_guest_owned_bits));
}

static inline unsigned long
vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
	return
	/*1*/	(vmcs_readl(GUEST_CR4) & vcpu->arch.cr4_guest_owned_bits) |
	/*2*/	(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask) |
	/*3*/	(vmcs_readl(CR4_READ_SHADOW) & ~(vmcs12->cr4_guest_host_mask |
			vcpu->arch.cr4_guest_owned_bits));
}

static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
				      struct vmcs12 *vmcs12,
				      u32 vm_exit_reason, u32 exit_intr_info)
{
	u32 idt_vectoring;
	unsigned int nr;

	/*
	 * Per the SDM, VM-Exits due to double and triple faults are never
	 * considered to occur during event delivery, even if the double/triple
	 * fault is the result of an escalating vectoring issue.
	 *
	 * Note, the SDM qualifies the double fault behavior with "The original
	 * event results in a double-fault exception".  It's unclear why the
	 * qualification exists since exits due to double fault can occur only
	 * while vectoring a different exception (injected events are never
	 * subject to interception), i.e. there's _always_ an original event.
	 *
	 * The SDM also uses NMI as a confusing example for the "original event
	 * causes the VM exit directly" clause.  NMI isn't special in any way,
	 * the same rule applies to all events that cause an exit directly.
	 * NMI is an odd choice for the example because NMIs can only occur on
	 * instruction boundaries, i.e. they _can't_ occur during vectoring.
	 */
	if ((u16)vm_exit_reason == EXIT_REASON_TRIPLE_FAULT ||
	    ((u16)vm_exit_reason == EXIT_REASON_EXCEPTION_NMI &&
	     is_double_fault(exit_intr_info))) {
		vmcs12->idt_vectoring_info_field = 0;
	} else if (vcpu->arch.exception.injected) {
		nr = vcpu->arch.exception.vector;
		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;

		if (kvm_exception_is_soft(nr)) {
			vmcs12->vm_exit_instruction_len =
				vcpu->arch.event_exit_inst_len;
			idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION;
		} else
			idt_vectoring |= INTR_TYPE_HARD_EXCEPTION;

		if (vcpu->arch.exception.has_error_code) {
			idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK;
			vmcs12->idt_vectoring_error_code =
				vcpu->arch.exception.error_code;
		}

		vmcs12->idt_vectoring_info_field = idt_vectoring;
	} else if (vcpu->arch.nmi_injected) {
		vmcs12->idt_vectoring_info_field =
			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
	} else if (vcpu->arch.interrupt.injected) {
		nr = vcpu->arch.interrupt.nr;
		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;

		if (vcpu->arch.interrupt.soft) {
			idt_vectoring |= INTR_TYPE_SOFT_INTR;
			vmcs12->vm_entry_instruction_len =
				vcpu->arch.event_exit_inst_len;
		} else
			idt_vectoring |= INTR_TYPE_EXT_INTR;

		vmcs12->idt_vectoring_info_field = idt_vectoring;
	} else {
		vmcs12->idt_vectoring_info_field = 0;
	}
}


void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	gfn_t gfn;

	/*
	 * Don't need to mark the APIC access page dirty; it is never
	 * written to by the CPU during APIC virtualization.
	 */

	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
		kvm_vcpu_mark_page_dirty(vcpu, gfn);
	}

	if (nested_cpu_has_posted_intr(vmcs12)) {
		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
		kvm_vcpu_mark_page_dirty(vcpu, gfn);
	}
}

static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int max_irr;
	void *vapic_page;
	u16 status;

	if (!vmx->nested.pi_pending)
		return 0;

	if (!vmx->nested.pi_desc)
		goto mmio_needed;

	vmx->nested.pi_pending = false;

	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
		return 0;

	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
	if (max_irr != 256) {
		vapic_page = vmx->nested.virtual_apic_map.hva;
		if (!vapic_page)
			goto mmio_needed;

		__kvm_apic_update_irr(vmx->nested.pi_desc->pir,
			vapic_page, &max_irr);
		status = vmcs_read16(GUEST_INTR_STATUS);
		if ((u8)max_irr > ((u8)status & 0xff)) {
			status &= ~0xff;
			status |= (u8)max_irr;
			vmcs_write16(GUEST_INTR_STATUS, status);
		}
	}

	nested_mark_vmcs12_pages_dirty(vcpu);
	return 0;

mmio_needed:
	kvm_handle_memory_failure(vcpu, X86EMUL_IO_NEEDED, NULL);
	return -ENXIO;
}

static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu)
{
	struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit;
	u32 intr_info = ex->vector | INTR_INFO_VALID_MASK;
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	unsigned long exit_qual;

	if (ex->has_payload) {
		exit_qual = ex->payload;
	} else if (ex->vector == PF_VECTOR) {
		exit_qual = vcpu->arch.cr2;
	} else if (ex->vector == DB_VECTOR) {
		exit_qual = vcpu->arch.dr6;
		exit_qual &= ~DR6_BT;
		exit_qual ^= DR6_ACTIVE_LOW;
	} else {
		exit_qual = 0;
	}

	/*
	 * Unlike AMD's Paged Real Mode, which reports an error code on #PF
	 * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the
	 * "has error code" flags on VM-Exit if the CPU is in Real Mode.
	 */
	if (ex->has_error_code && is_protmode(vcpu)) {
		/*
		 * Intel CPUs do not generate error codes with bits 31:16 set,
		 * and more importantly VMX disallows setting bits 31:16 in the
		 * injected error code for VM-Entry.  Drop the bits to mimic
		 * hardware and avoid inducing failure on nested VM-Entry if L1
		 * chooses to inject the exception back to L2.  AMD CPUs _do_
		 * generate "full" 32-bit error codes, so KVM allows userspace
		 * to inject exception error codes with bits 31:16 set.
		 */
		vmcs12->vm_exit_intr_error_code = (u16)ex->error_code;
		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
	}

	if (kvm_exception_is_soft(ex->vector))
		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
	else
		intr_info |= INTR_TYPE_HARD_EXCEPTION;

	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
	    vmx_get_nmi_mask(vcpu))
		intr_info |= INTR_INFO_UNBLOCK_NMI;

	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
}

/*
 * Returns true if a debug trap is (likely) pending delivery.  Infer the class
 * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6).
 * Using the payload is flawed because code breakpoints (fault-like) and data
 * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e.
 * this will return false positives if a to-be-injected code breakpoint #DB is
 * pending (from KVM's perspective, but not "pending" across an instruction
 * boundary).  ICEBP, a.k.a. INT1, is also not reflected here even though it
 * too is trap-like.
 *
 * KVM "works" despite these flaws as ICEBP isn't currently supported by the
 * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the
 * #DB has already happened), and MTF isn't marked pending on code breakpoints
 * from the emulator (because such #DBs are fault-like and thus don't trigger
 * actions that fire on instruction retire).
 */
static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex)
{
	if (!ex->pending || ex->vector != DB_VECTOR)
		return 0;

	/* General Detect #DBs are always fault-like. */
	return ex->payload & ~DR6_BD;
}

/*
 * Returns true if there's a pending #DB exception that is lower priority than
 * a pending Monitor Trap Flag VM-Exit.  TSS T-flag #DBs are not emulated by
 * KVM, but could theoretically be injected by userspace.  Note, this code is
 * imperfect, see above.
 */
static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex)
{
	return vmx_get_pending_dbg_trap(ex) & ~DR6_BT;
}

/*
 * Certain VM-exits set the 'pending debug exceptions' field to indicate a
 * recognized #DB (data or single-step) that has yet to be delivered. Since KVM
 * represents these debug traps with a payload that is said to be compatible
 * with the 'pending debug exceptions' field, write the payload to the VMCS
 * field if a VM-exit is delivered before the debug trap.
 */
static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
{
	unsigned long pending_dbg;

	pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception);
	if (pending_dbg)
		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg);
}

static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
{
	return nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
	       to_vmx(vcpu)->nested.preemption_timer_expired;
}

static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
{
	return nested_vmx_preemption_timer_pending(vcpu) ||
	       to_vmx(vcpu)->nested.mtf_pending;
}

/*
 * Per the Intel SDM's table "Priority Among Concurrent Events", with minor
 * edits to fill in missing examples, e.g. #DB due to split-lock accesses,
 * and less minor edits to splice in the priority of VMX Non-Root specific
 * events, e.g. MTF and NMI/INTR-window exiting.
 *
 * 1 Hardware Reset and Machine Checks
 *	- RESET
 *	- Machine Check
 *
 * 2 Trap on Task Switch
 *	- T flag in TSS is set (on task switch)
 *
 * 3 External Hardware Interventions
 *	- FLUSH
 *	- STOPCLK
 *	- SMI
 *	- INIT
 *
 * 3.5 Monitor Trap Flag (MTF) VM-exit[1]
 *
 * 4 Traps on Previous Instruction
 *	- Breakpoints
 *	- Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O
 *	  breakpoint, or #DB due to a split-lock access)
 *
 * 4.3	VMX-preemption timer expired VM-exit
 *
 * 4.6	NMI-window exiting VM-exit[2]
 *
 * 5 Nonmaskable Interrupts (NMI)
 *
 * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery
 *
 * 6 Maskable Hardware Interrupts
 *
 * 7 Code Breakpoint Fault
 *
 * 8 Faults from Fetching Next Instruction
 *	- Code-Segment Limit Violation
 *	- Code Page Fault
 *	- Control protection exception (missing ENDBRANCH at target of indirect
 *					call or jump)
 *
 * 9 Faults from Decoding Next Instruction
 *	- Instruction length > 15 bytes
 *	- Invalid Opcode
 *	- Coprocessor Not Available
 *
 *10 Faults on Executing Instruction
 *	- Overflow
 *	- Bound error
 *	- Invalid TSS
 *	- Segment Not Present
 *	- Stack fault
 *	- General Protection
 *	- Data Page Fault
 *	- Alignment Check
 *	- x86 FPU Floating-point exception
 *	- SIMD floating-point exception
 *	- Virtualization exception
 *	- Control protection exception
 *
 * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs),
 *     INIT signals, and higher priority events take priority over MTF VM exits.
 *     MTF VM exits take priority over debug-trap exceptions and lower priority
 *     events.
 *
 * [2] Debug-trap exceptions and higher priority events take priority over VM exits
 *     caused by the VMX-preemption timer.  VM exits caused by the VMX-preemption
 *     timer take priority over VM exits caused by the "NMI-window exiting"
 *     VM-execution control and lower priority events.
 *
 * [3] Debug-trap exceptions and higher priority events take priority over VM exits
 *     caused by "NMI-window exiting".  VM exits caused by this control take
 *     priority over non-maskable interrupts (NMIs) and lower priority events.
 *
 * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to
 *     the 1-setting of the "interrupt-window exiting" VM-execution control.  Thus,
 *     non-maskable interrupts (NMIs) and higher priority events take priority over
 *     delivery of a virtual interrupt; delivery of a virtual interrupt takes
 *     priority over external interrupts and lower priority events.
 */
static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	/*
	 * Only a pending nested run blocks a pending exception.  If there is a
	 * previously injected event, the pending exception occurred while said
	 * event was being delivered and thus needs to be handled.
	 */
	bool block_nested_exceptions = vmx->nested.nested_run_pending;
	/*
	 * New events (not exceptions) are only recognized at instruction
	 * boundaries.  If an event needs reinjection, then KVM is handling a
	 * VM-Exit that occurred _during_ instruction execution; new events are
	 * blocked until the instruction completes.
	 */
	bool block_nested_events = block_nested_exceptions ||
				   kvm_event_needs_reinjection(vcpu);

	if (lapic_in_kernel(vcpu) &&
		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
		if (block_nested_events)
			return -EBUSY;
		nested_vmx_update_pending_dbg(vcpu);
		clear_bit(KVM_APIC_INIT, &apic->pending_events);
		if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED)
			nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);

		/* MTF is discarded if the vCPU is in WFS. */
		vmx->nested.mtf_pending = false;
		return 0;
	}

	if (lapic_in_kernel(vcpu) &&
	    test_bit(KVM_APIC_SIPI, &apic->pending_events)) {
		if (block_nested_events)
			return -EBUSY;

		clear_bit(KVM_APIC_SIPI, &apic->pending_events);
		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
			nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0,
						apic->sipi_vector & 0xFFUL);
			return 0;
		}
		/* Fallthrough, the SIPI is completely ignored. */
	}

	/*
	 * Process exceptions that are higher priority than Monitor Trap Flag:
	 * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but
	 * could theoretically come in from userspace), and ICEBP (INT1).
	 *
	 * TODO: SMIs have higher priority than MTF and trap-like #DBs (except
	 * for TSS T flag #DBs).  KVM also doesn't save/restore pending MTF
	 * across SMI/RSM as it should; that needs to be addressed in order to
	 * prioritize SMI over MTF and trap-like #DBs.
	 */
	if (vcpu->arch.exception_vmexit.pending &&
	    !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) {
		if (block_nested_exceptions)
			return -EBUSY;

		nested_vmx_inject_exception_vmexit(vcpu);
		return 0;
	}

	if (vcpu->arch.exception.pending &&
	    !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) {
		if (block_nested_exceptions)
			return -EBUSY;
		goto no_vmexit;
	}

	if (vmx->nested.mtf_pending) {
		if (block_nested_events)
			return -EBUSY;
		nested_vmx_update_pending_dbg(vcpu);
		nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0);
		return 0;
	}

	if (vcpu->arch.exception_vmexit.pending) {
		if (block_nested_exceptions)
			return -EBUSY;

		nested_vmx_inject_exception_vmexit(vcpu);
		return 0;
	}

	if (vcpu->arch.exception.pending) {
		if (block_nested_exceptions)
			return -EBUSY;
		goto no_vmexit;
	}

	if (nested_vmx_preemption_timer_pending(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
		return 0;
	}

	if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		goto no_vmexit;
	}

	if (vcpu->arch.nmi_pending && !vmx_nmi_blocked(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_nmi(vcpu))
			goto no_vmexit;

		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
				  INTR_INFO_VALID_MASK, 0);
		/*
		 * The NMI-triggered VM exit counts as injection:
		 * clear this one and block further NMIs.
		 */
		vcpu->arch.nmi_pending = 0;
		vmx_set_nmi_mask(vcpu, true);
		return 0;
	}

	if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_intr(vcpu))
			goto no_vmexit;
		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
		return 0;
	}

no_vmexit:
	return vmx_complete_nested_posted_interrupt(vcpu);
}

static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
{
	ktime_t remaining =
		hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer);
	u64 value;

	if (ktime_to_ns(remaining) <= 0)
		return 0;

	value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz;
	do_div(value, 1000000);
	return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
}

static bool is_vmcs12_ext_field(unsigned long field)
{
	switch (field) {
	case GUEST_ES_SELECTOR:
	case GUEST_CS_SELECTOR:
	case GUEST_SS_SELECTOR:
	case GUEST_DS_SELECTOR:
	case GUEST_FS_SELECTOR:
	case GUEST_GS_SELECTOR:
	case GUEST_LDTR_SELECTOR:
	case GUEST_TR_SELECTOR:
	case GUEST_ES_LIMIT:
	case GUEST_CS_LIMIT:
	case GUEST_SS_LIMIT:
	case GUEST_DS_LIMIT:
	case GUEST_FS_LIMIT:
	case GUEST_GS_LIMIT:
	case GUEST_LDTR_LIMIT:
	case GUEST_TR_LIMIT:
	case GUEST_GDTR_LIMIT:
	case GUEST_IDTR_LIMIT:
	case GUEST_ES_AR_BYTES:
	case GUEST_DS_AR_BYTES:
	case GUEST_FS_AR_BYTES:
	case GUEST_GS_AR_BYTES:
	case GUEST_LDTR_AR_BYTES:
	case GUEST_TR_AR_BYTES:
	case GUEST_ES_BASE:
	case GUEST_CS_BASE:
	case GUEST_SS_BASE:
	case GUEST_DS_BASE:
	case GUEST_FS_BASE:
	case GUEST_GS_BASE:
	case GUEST_LDTR_BASE:
	case GUEST_TR_BASE:
	case GUEST_GDTR_BASE:
	case GUEST_IDTR_BASE:
	case GUEST_PENDING_DBG_EXCEPTIONS:
	case GUEST_BNDCFGS:
		return true;
	default:
		break;
	}

	return false;
}

static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR);
	vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR);
	vmcs12->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR);
	vmcs12->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR);
	vmcs12->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR);
	vmcs12->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR);
	vmcs12->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR);
	vmcs12->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR);
	vmcs12->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT);
	vmcs12->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT);
	vmcs12->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT);
	vmcs12->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT);
	vmcs12->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT);
	vmcs12->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT);
	vmcs12->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT);
	vmcs12->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT);
	vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT);
	vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT);
	vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES);
	vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES);
	vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES);
	vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES);
	vmcs12->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES);
	vmcs12->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES);
	vmcs12->guest_es_base = vmcs_readl(GUEST_ES_BASE);
	vmcs12->guest_cs_base = vmcs_readl(GUEST_CS_BASE);
	vmcs12->guest_ss_base = vmcs_readl(GUEST_SS_BASE);
	vmcs12->guest_ds_base = vmcs_readl(GUEST_DS_BASE);
	vmcs12->guest_fs_base = vmcs_readl(GUEST_FS_BASE);
	vmcs12->guest_gs_base = vmcs_readl(GUEST_GS_BASE);
	vmcs12->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE);
	vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE);
	vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE);
	vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE);
	vmcs12->guest_pending_dbg_exceptions =
		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);

	vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false;
}

static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int cpu;

	if (!vmx->nested.need_sync_vmcs02_to_vmcs12_rare)
		return;


	WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01);

	cpu = get_cpu();
	vmx->loaded_vmcs = &vmx->nested.vmcs02;
	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);

	sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);

	vmx->loaded_vmcs = &vmx->vmcs01;
	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
	put_cpu();
}

/*
 * Update the guest state fields of vmcs12 to reflect changes that
 * occurred while L2 was running. (The "IA-32e mode guest" bit of the
 * VM-entry controls is also updated, since this is really a guest
 * state bit.)
 */
static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (nested_vmx_is_evmptr12_valid(vmx))
		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);

	vmx->nested.need_sync_vmcs02_to_vmcs12_rare =
		!nested_vmx_is_evmptr12_valid(vmx);

	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);

	vmcs12->guest_rsp = kvm_rsp_read(vcpu);
	vmcs12->guest_rip = kvm_rip_read(vcpu);
	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);

	vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
	vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);

	vmcs12->guest_interruptibility_info =
		vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);

	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
		vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT;
	else if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
		vmcs12->guest_activity_state = GUEST_ACTIVITY_WAIT_SIPI;
	else
		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;

	if (nested_cpu_has_preemption_timer(vmcs12) &&
	    vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER &&
	    !vmx->nested.nested_run_pending)
		vmcs12->vmx_preemption_timer_value =
			vmx_get_preemption_timer_value(vcpu);

	/*
	 * In some cases (usually, nested EPT), L2 is allowed to change its
	 * own CR3 without exiting. If it has changed it, we must keep it.
	 * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
	 * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
	 *
	 * Additionally, restore L2's PDPTR to vmcs12.
	 */
	if (enable_ept) {
		vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3);
		if (nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) {
			vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
			vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
			vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
			vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
		}
	}

	vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);

	if (nested_cpu_has_vid(vmcs12))
		vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);

	vmcs12->vm_entry_controls =
		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);

	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
		vmcs12->guest_dr7 = vcpu->arch.dr7;

	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
		vmcs12->guest_ia32_efer = vcpu->arch.efer;
}

/*
 * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
 * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
 * and this function updates it to reflect the changes to the guest state while
 * L2 was running (and perhaps made some exits which were handled directly by L0
 * without going back to L1), and to reflect the exit reason.
 * Note that we do not have to copy here all VMCS fields, just those that
 * could have changed by the L2 guest or the exit - i.e., the guest-state and
 * exit-information fields only. Other fields are modified by L1 with VMWRITE,
 * which already writes to vmcs12 directly.
 */
static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
			   u32 vm_exit_reason, u32 exit_intr_info,
			   unsigned long exit_qualification)
{
	/* update exit information fields: */
	vmcs12->vm_exit_reason = vm_exit_reason;
	if (to_vmx(vcpu)->exit_reason.enclave_mode)
		vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE;
	vmcs12->exit_qualification = exit_qualification;

	/*
	 * On VM-Exit due to a failed VM-Entry, the VMCS isn't marked launched
	 * and only EXIT_REASON and EXIT_QUALIFICATION are updated, all other
	 * exit info fields are unmodified.
	 */
	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) {
		vmcs12->launch_state = 1;

		/* vm_entry_intr_info_field is cleared on exit. Emulate this
		 * instead of reading the real value. */
		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;

		/*
		 * Transfer the event that L0 or L1 may wanted to inject into
		 * L2 to IDT_VECTORING_INFO_FIELD.
		 */
		vmcs12_save_pending_event(vcpu, vmcs12,
					  vm_exit_reason, exit_intr_info);

		vmcs12->vm_exit_intr_info = exit_intr_info;
		vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
		vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);

		/*
		 * According to spec, there's no need to store the guest's
		 * MSRs if the exit is due to a VM-entry failure that occurs
		 * during or after loading the guest state. Since this exit
		 * does not fall in that category, we need to save the MSRs.
		 */
		if (nested_vmx_store_msr(vcpu,
					 vmcs12->vm_exit_msr_store_addr,
					 vmcs12->vm_exit_msr_store_count))
			nested_vmx_abort(vcpu,
					 VMX_ABORT_SAVE_GUEST_MSR_FAIL);
	}
}

/*
 * A part of what we need to when the nested L2 guest exits and we want to
 * run its L1 parent, is to reset L1's guest state to the host state specified
 * in vmcs12.
 * This function is to be called not only on normal nested exit, but also on
 * a nested entry failure, as explained in Intel's spec, 3B.23.7 ("VM-Entry
 * Failures During or After Loading Guest State").
 * This function should be called when the active VMCS is L1's (vmcs01).
 */
static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
				   struct vmcs12 *vmcs12)
{
	enum vm_entry_failure_code ignored;
	struct kvm_segment seg;

	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
		vcpu->arch.efer = vmcs12->host_ia32_efer;
	else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
	else
		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
	vmx_set_efer(vcpu, vcpu->arch.efer);

	kvm_rsp_write(vcpu, vmcs12->host_rsp);
	kvm_rip_write(vcpu, vmcs12->host_rip);
	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
	vmx_set_interrupt_shadow(vcpu, 0);

	/*
	 * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
	 * actually changed, because vmx_set_cr0 refers to efer set above.
	 *
	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
	 * (KVM doesn't change it);
	 */
	vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
	vmx_set_cr0(vcpu, vmcs12->host_cr0);

	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
	vmx_set_cr4(vcpu, vmcs12->host_cr4);

	nested_ept_uninit_mmu_context(vcpu);

	/*
	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
	 * couldn't have changed.
	 */
	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, true, &ignored))
		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);

	nested_vmx_transition_tlb_flush(vcpu, vmcs12, false);

	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
	vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF);
	vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF);

	/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1.  */
	if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
		vmcs_write64(GUEST_BNDCFGS, 0);

	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
		vcpu->arch.pat = vmcs12->host_ia32_pat;
	}
	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
	    kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)))
		WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
					 vmcs12->host_ia32_perf_global_ctrl));

	/* Set L1 segment info according to Intel SDM
	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
	seg = (struct kvm_segment) {
		.base = 0,
		.limit = 0xFFFFFFFF,
		.selector = vmcs12->host_cs_selector,
		.type = 11,
		.present = 1,
		.s = 1,
		.g = 1
	};
	if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
		seg.l = 1;
	else
		seg.db = 1;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
	seg = (struct kvm_segment) {
		.base = 0,
		.limit = 0xFFFFFFFF,
		.type = 3,
		.present = 1,
		.s = 1,
		.db = 1,
		.g = 1
	};
	seg.selector = vmcs12->host_ds_selector;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
	seg.selector = vmcs12->host_es_selector;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
	seg.selector = vmcs12->host_ss_selector;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
	seg.selector = vmcs12->host_fs_selector;
	seg.base = vmcs12->host_fs_base;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
	seg.selector = vmcs12->host_gs_selector;
	seg.base = vmcs12->host_gs_base;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
	seg = (struct kvm_segment) {
		.base = vmcs12->host_tr_base,
		.limit = 0x67,
		.selector = vmcs12->host_tr_selector,
		.type = 11,
		.present = 1
	};
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);

	memset(&seg, 0, sizeof(seg));
	seg.unusable = 1;
	__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);

	kvm_set_dr(vcpu, 7, 0x400);
	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);

	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
				vmcs12->vm_exit_msr_load_count))
		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);

	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
}

static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
{
	struct vmx_uret_msr *efer_msr;
	unsigned int i;

	if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
		return vmcs_read64(GUEST_IA32_EFER);

	if (cpu_has_load_ia32_efer())
		return host_efer;

	for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
		if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
			return vmx->msr_autoload.guest.val[i].value;
	}

	efer_msr = vmx_find_uret_msr(vmx, MSR_EFER);
	if (efer_msr)
		return efer_msr->data;

	return host_efer;
}

static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmx_msr_entry g, h;
	gpa_t gpa;
	u32 i, j;

	vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT);

	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
		/*
		 * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set
		 * as vmcs01.GUEST_DR7 contains a userspace defined value
		 * and vcpu->arch.dr7 is not squirreled away before the
		 * nested VMENTER (not worth adding a variable in nested_vmx).
		 */
		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
			kvm_set_dr(vcpu, 7, DR7_FIXED_1);
		else
			WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
	}

	/*
	 * Note that calling vmx_set_{efer,cr0,cr4} is important as they
	 * handle a variety of side effects to KVM's software model.
	 */
	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));

	vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));

	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
	vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));

	nested_ept_uninit_mmu_context(vcpu);
	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);

	/*
	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
	 * from vmcs01 (if necessary).  The PDPTRs are not loaded on
	 * VMFail, like everything else we just need to ensure our
	 * software model is up-to-date.
	 */
	if (enable_ept && is_pae_paging(vcpu))
		ept_save_pdptrs(vcpu);

	kvm_mmu_reset_context(vcpu);

	/*
	 * This nasty bit of open coding is a compromise between blindly
	 * loading L1's MSRs using the exit load lists (incorrect emulation
	 * of VMFail), leaving the nested VM's MSRs in the software model
	 * (incorrect behavior) and snapshotting the modified MSRs (too
	 * expensive since the lists are unbound by hardware).  For each
	 * MSR that was (prematurely) loaded from the nested VMEntry load
	 * list, reload it from the exit load list if it exists and differs
	 * from the guest value.  The intent is to stuff host state as
	 * silently as possible, not to fully process the exit load list.
	 */
	for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) {
		gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g));
		if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) {
			pr_debug_ratelimited(
				"%s read MSR index failed (%u, 0x%08llx)\n",
				__func__, i, gpa);
			goto vmabort;
		}

		for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) {
			gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h));
			if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) {
				pr_debug_ratelimited(
					"%s read MSR failed (%u, 0x%08llx)\n",
					__func__, j, gpa);
				goto vmabort;
			}
			if (h.index != g.index)
				continue;
			if (h.value == g.value)
				break;

			if (nested_vmx_load_msr_check(vcpu, &h)) {
				pr_debug_ratelimited(
					"%s check failed (%u, 0x%x, 0x%x)\n",
					__func__, j, h.index, h.reserved);
				goto vmabort;
			}

			if (kvm_set_msr(vcpu, h.index, h.value)) {
				pr_debug_ratelimited(
					"%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
					__func__, j, h.index, h.value);
				goto vmabort;
			}
		}
	}

	return;

vmabort:
	nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
}

/*
 * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
 * and modify vmcs12 to make it see what it would expect to see there if
 * L2 was its real guest. Must only be called when in L2 (is_guest_mode())
 */
void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
		       u32 exit_intr_info, unsigned long exit_qualification)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	/* Pending MTF traps are discarded on VM-Exit. */
	vmx->nested.mtf_pending = false;

	/* trying to cancel vmlaunch/vmresume is a bug */
	WARN_ON_ONCE(vmx->nested.nested_run_pending);

#ifdef CONFIG_KVM_HYPERV
	if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
		/*
		 * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map
		 * Enlightened VMCS after migration and we still need to
		 * do that when something is forcing L2->L1 exit prior to
		 * the first L2 run.
		 */
		(void)nested_get_evmcs_page(vcpu);
	}
#endif

	/* Service pending TLB flush requests for L2 before switching to L1. */
	kvm_service_local_tlb_flush_requests(vcpu);

	/*
	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
	 * now and the new vmentry.  Ensure that the VMCS02 PDPTR fields are
	 * up-to-date before switching to L1.
	 */
	if (enable_ept && is_pae_paging(vcpu))
		vmx_ept_load_pdptrs(vcpu);

	leave_guest_mode(vcpu);

	if (nested_cpu_has_preemption_timer(vmcs12))
		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);

	if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) {
		vcpu->arch.tsc_offset = vcpu->arch.l1_tsc_offset;
		if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING))
			vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
	}

	if (likely(!vmx->fail)) {
		sync_vmcs02_to_vmcs12(vcpu, vmcs12);

		if (vm_exit_reason != -1)
			prepare_vmcs12(vcpu, vmcs12, vm_exit_reason,
				       exit_intr_info, exit_qualification);

		/*
		 * Must happen outside of sync_vmcs02_to_vmcs12() as it will
		 * also be used to capture vmcs12 cache as part of
		 * capturing nVMX state for snapshot (migration).
		 *
		 * Otherwise, this flush will dirty guest memory at a
		 * point it is already assumed by user-space to be
		 * immutable.
		 */
		nested_flush_cached_shadow_vmcs12(vcpu, vmcs12);
	} else {
		/*
		 * The only expected VM-instruction error is "VM entry with
		 * invalid control field(s)." Anything else indicates a
		 * problem with L0.  And we should never get here with a
		 * VMFail of any type if early consistency checks are enabled.
		 */
		WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
			     VMXERR_ENTRY_INVALID_CONTROL_FIELD);
		WARN_ON_ONCE(nested_early_check);
	}

	/*
	 * Drop events/exceptions that were queued for re-injection to L2
	 * (picked up via vmx_complete_interrupts()), as well as exceptions
	 * that were pending for L2.  Note, this must NOT be hoisted above
	 * prepare_vmcs12(), events/exceptions queued for re-injection need to
	 * be captured in vmcs12 (see vmcs12_save_pending_event()).
	 */
	vcpu->arch.nmi_injected = false;
	kvm_clear_exception_queue(vcpu);
	kvm_clear_interrupt_queue(vcpu);

	vmx_switch_vmcs(vcpu, &vmx->vmcs01);

	/*
	 * If IBRS is advertised to the vCPU, KVM must flush the indirect
	 * branch predictors when transitioning from L2 to L1, as L1 expects
	 * hardware (KVM in this case) to provide separate predictor modes.
	 * Bare metal isolates VMX root (host) from VMX non-root (guest), but
	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
	 * separate modes for L2 vs L1.
	 */
	if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
		indirect_branch_prediction_barrier();

	/* Update any VMCS fields that might have changed while L2 ran */
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
	if (kvm_caps.has_tsc_control)
		vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);

	if (vmx->nested.l1_tpr_threshold != -1)
		vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold);

	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
		vmx->nested.change_vmcs01_virtual_apic_mode = false;
		vmx_set_virtual_apic_mode(vcpu);
	}

	if (vmx->nested.update_vmcs01_cpu_dirty_logging) {
		vmx->nested.update_vmcs01_cpu_dirty_logging = false;
		vmx_update_cpu_dirty_logging(vcpu);
	}

	/* Unpin physical memory we referred to in vmcs02 */
	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
	vmx->nested.pi_desc = NULL;

	if (vmx->nested.reload_vmcs01_apic_access_page) {
		vmx->nested.reload_vmcs01_apic_access_page = false;
		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
	}

	if (vmx->nested.update_vmcs01_apicv_status) {
		vmx->nested.update_vmcs01_apicv_status = false;
		kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
	}

	if ((vm_exit_reason != -1) &&
	    (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)))
		vmx->nested.need_vmcs12_to_shadow_sync = true;

	/* in case we halted in L2 */
	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

	if (likely(!vmx->fail)) {
		if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
		    nested_exit_intr_ack_set(vcpu)) {
			int irq = kvm_cpu_get_interrupt(vcpu);
			WARN_ON(irq < 0);
			vmcs12->vm_exit_intr_info = irq |
				INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
		}

		if (vm_exit_reason != -1)
			trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
						       vmcs12->exit_qualification,
						       vmcs12->idt_vectoring_info_field,
						       vmcs12->vm_exit_intr_info,
						       vmcs12->vm_exit_intr_error_code,
						       KVM_ISA_VMX);

		load_vmcs12_host_state(vcpu, vmcs12);

		return;
	}

	/*
	 * After an early L2 VM-entry failure, we're now back
	 * in L1 which thinks it just finished a VMLAUNCH or
	 * VMRESUME instruction, so we need to set the failure
	 * flag and the VM-instruction error field of the VMCS
	 * accordingly, and skip the emulated instruction.
	 */
	(void)nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);

	/*
	 * Restore L1's host state to KVM's software model.  We're here
	 * because a consistency check was caught by hardware, which
	 * means some amount of guest state has been propagated to KVM's
	 * model and needs to be unwound to the host's state.
	 */
	nested_vmx_restore_host_state(vcpu);

	vmx->fail = 0;
}

static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
{
	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
	nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
}

/*
 * Decode the memory-address operand of a vmx instruction, as recorded on an
 * exit caused by such an instruction (run by a guest hypervisor).
 * On success, returns 0. When the operand is invalid, returns 1 and throws
 * #UD, #GP, or #SS.
 */
int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
			u32 vmx_instruction_info, bool wr, int len, gva_t *ret)
{
	gva_t off;
	bool exn;
	struct kvm_segment s;

	/*
	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
	 * Execution", on an exit, vmx_instruction_info holds most of the
	 * addressing components of the operand. Only the displacement part
	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
	 * For how an actual address is calculated from all these components,
	 * refer to Vol. 1, "Operand Addressing".
	 */
	int  scaling = vmx_instruction_info & 3;
	int  addr_size = (vmx_instruction_info >> 7) & 7;
	bool is_reg = vmx_instruction_info & (1u << 10);
	int  seg_reg = (vmx_instruction_info >> 15) & 7;
	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));

	if (is_reg) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	/* Addr = segment_base + offset */
	/* offset = base + [index * scale] + displacement */
	off = exit_qualification; /* holds the displacement */
	if (addr_size == 1)
		off = (gva_t)sign_extend64(off, 31);
	else if (addr_size == 0)
		off = (gva_t)sign_extend64(off, 15);
	if (base_is_valid)
		off += kvm_register_read(vcpu, base_reg);
	if (index_is_valid)
		off += kvm_register_read(vcpu, index_reg) << scaling;
	vmx_get_segment(vcpu, &s, seg_reg);

	/*
	 * The effective address, i.e. @off, of a memory operand is truncated
	 * based on the address size of the instruction.  Note that this is
	 * the *effective address*, i.e. the address prior to accounting for
	 * the segment's base.
	 */
	if (addr_size == 1) /* 32 bit */
		off &= 0xffffffff;
	else if (addr_size == 0) /* 16 bit */
		off &= 0xffff;

	/* Checks for #GP/#SS exceptions. */
	exn = false;
	if (is_long_mode(vcpu)) {
		/*
		 * The virtual/linear address is never truncated in 64-bit
		 * mode, e.g. a 32-bit address size can yield a 64-bit virtual
		 * address when using FS/GS with a non-zero base.
		 */
		if (seg_reg == VCPU_SREG_FS || seg_reg == VCPU_SREG_GS)
			*ret = s.base + off;
		else
			*ret = off;

		*ret = vmx_get_untagged_addr(vcpu, *ret, 0);
		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
		 * non-canonical form. This is the only check on the memory
		 * destination for long mode!
		 */
		exn = is_noncanonical_address(*ret, vcpu);
	} else {
		/*
		 * When not in long mode, the virtual/linear address is
		 * unconditionally truncated to 32 bits regardless of the
		 * address size.
		 */
		*ret = (s.base + off) & 0xffffffff;

		/* Protected mode: apply checks for segment validity in the
		 * following order:
		 * - segment type check (#GP(0) may be thrown)
		 * - usability check (#GP(0)/#SS(0))
		 * - limit check (#GP(0)/#SS(0))
		 */
		if (wr)
			/* #GP(0) if the destination operand is located in a
			 * read-only data segment or any code segment.
			 */
			exn = ((s.type & 0xa) == 0 || (s.type & 8));
		else
			/* #GP(0) if the source operand is located in an
			 * execute-only code segment
			 */
			exn = ((s.type & 0xa) == 8);
		if (exn) {
			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
			return 1;
		}
		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
		 */
		exn = (s.unusable != 0);

		/*
		 * Protected mode: #GP(0)/#SS(0) if the memory operand is
		 * outside the segment limit.  All CPUs that support VMX ignore
		 * limit checks for flat segments, i.e. segments with base==0,
		 * limit==0xffffffff and of type expand-up data or code.
		 */
		if (!(s.base == 0 && s.limit == 0xffffffff &&
		     ((s.type & 8) || !(s.type & 4))))
			exn = exn || ((u64)off + len - 1 > s.limit);
	}
	if (exn) {
		kvm_queue_exception_e(vcpu,
				      seg_reg == VCPU_SREG_SS ?
						SS_VECTOR : GP_VECTOR,
				      0);
		return 1;
	}

	return 0;
}

static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer,
				int *ret)
{
	gva_t gva;
	struct x86_exception e;
	int r;

	if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
				vmcs_read32(VMX_INSTRUCTION_INFO), false,
				sizeof(*vmpointer), &gva)) {
		*ret = 1;
		return -EINVAL;
	}

	r = kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e);
	if (r != X86EMUL_CONTINUE) {
		*ret = kvm_handle_memory_failure(vcpu, r, &e);
		return -EINVAL;
	}

	return 0;
}

/*
 * Allocate a shadow VMCS and associate it with the currently loaded
 * VMCS, unless such a shadow VMCS already exists. The newly allocated
 * VMCS is also VMCLEARed, so that it is ready for use.
 */
static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs;

	/*
	 * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it
	 * when L1 executes VMXOFF or the vCPU is forced out of nested
	 * operation.  VMXON faults if the CPU is already post-VMXON, so it
	 * should be impossible to already have an allocated shadow VMCS.  KVM
	 * doesn't support virtualization of VMCS shadowing, so vmcs01 should
	 * always be the loaded VMCS.
	 */
	if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs))
		return loaded_vmcs->shadow_vmcs;

	loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
	if (loaded_vmcs->shadow_vmcs)
		vmcs_clear(loaded_vmcs->shadow_vmcs);

	return loaded_vmcs->shadow_vmcs;
}

static int enter_vmx_operation(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int r;

	r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
	if (r < 0)
		goto out_vmcs02;

	vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
	if (!vmx->nested.cached_vmcs12)
		goto out_cached_vmcs12;

	vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA;
	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
	if (!vmx->nested.cached_shadow_vmcs12)
		goto out_cached_shadow_vmcs12;

	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
		goto out_shadow_vmcs;

	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_ABS_PINNED);
	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;

	vmx->nested.vpid02 = allocate_vpid();

	vmx->nested.vmcs02_initialized = false;
	vmx->nested.vmxon = true;

	if (vmx_pt_mode_is_host_guest()) {
		vmx->pt_desc.guest.ctl = 0;
		pt_update_intercept_for_msr(vcpu);
	}

	return 0;

out_shadow_vmcs:
	kfree(vmx->nested.cached_shadow_vmcs12);

out_cached_shadow_vmcs12:
	kfree(vmx->nested.cached_vmcs12);

out_cached_vmcs12:
	free_loaded_vmcs(&vmx->nested.vmcs02);

out_vmcs02:
	return -ENOMEM;
}

/* Emulate the VMXON instruction. */
static int handle_vmxon(struct kvm_vcpu *vcpu)
{
	int ret;
	gpa_t vmptr;
	uint32_t revision;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	const u64 VMXON_NEEDED_FEATURES = FEAT_CTL_LOCKED
		| FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;

	/*
	 * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter
	 * the guest and so cannot rely on hardware to perform the check,
	 * which has higher priority than VM-Exit (see Intel SDM's pseudocode
	 * for VMXON).
	 *
	 * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86
	 * and !COMPATIBILITY modes.  For an unrestricted guest, KVM doesn't
	 * force any of the relevant guest state.  For a restricted guest, KVM
	 * does force CR0.PE=1, but only to also force VM86 in order to emulate
	 * Real Mode, and so there's no need to check CR0.PE manually.
	 */
	if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_VMXE)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	/*
	 * The CPL is checked for "not in VMX operation" and for "in VMX root",
	 * and has higher priority than the VM-Fail due to being post-VMXON,
	 * i.e. VMXON #GPs outside of VMX non-root if CPL!=0.  In VMX non-root,
	 * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits
	 * from L2 to L1, i.e. there's no need to check for the vCPU being in
	 * VMX non-root.
	 *
	 * Forwarding the VM-Exit unconditionally, i.e. without performing the
	 * #UD checks (see above), is functionally ok because KVM doesn't allow
	 * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's
	 * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are
	 * missed by hardware due to shadowing CR0 and/or CR4.
	 */
	if (vmx_get_cpl(vcpu)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	if (vmx->nested.vmxon)
		return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);

	/*
	 * Invalid CR0/CR4 generates #GP.  These checks are performed if and
	 * only if the vCPU isn't already in VMX operation, i.e. effectively
	 * have lower priority than the VM-Fail above.
	 */
	if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) ||
	    !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
			!= VMXON_NEEDED_FEATURES) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	if (nested_vmx_get_vmptr(vcpu, &vmptr, &ret))
		return ret;

	/*
	 * SDM 3: 24.11.5
	 * The first 4 bytes of VMXON region contain the supported
	 * VMCS revision identifier
	 *
	 * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
	 * which replaces physical address width with 32
	 */
	if (!page_address_valid(vcpu, vmptr))
		return nested_vmx_failInvalid(vcpu);

	if (kvm_read_guest(vcpu->kvm, vmptr, &revision, sizeof(revision)) ||
	    revision != VMCS12_REVISION)
		return nested_vmx_failInvalid(vcpu);

	vmx->nested.vmxon_ptr = vmptr;
	ret = enter_vmx_operation(vcpu);
	if (ret)
		return ret;

	return nested_vmx_succeed(vcpu);
}

static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (vmx->nested.current_vmptr == INVALID_GPA)
		return;

	copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));

	if (enable_shadow_vmcs) {
		/* copy to memory all shadowed fields in case
		   they were modified */
		copy_shadow_to_vmcs12(vmx);
		vmx_disable_shadow_vmcs(vmx);
	}
	vmx->nested.posted_intr_nv = -1;

	/* Flush VMCS12 to guest memory */
	kvm_vcpu_write_guest_page(vcpu,
				  vmx->nested.current_vmptr >> PAGE_SHIFT,
				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);

	kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);

	vmx->nested.current_vmptr = INVALID_GPA;
}

/* Emulate the VMXOFF instruction */
static int handle_vmxoff(struct kvm_vcpu *vcpu)
{
	if (!nested_vmx_check_permission(vcpu))
		return 1;

	free_nested(vcpu);

	if (kvm_apic_has_pending_init_or_sipi(vcpu))
		kvm_make_request(KVM_REQ_EVENT, vcpu);

	return nested_vmx_succeed(vcpu);
}

/* Emulate the VMCLEAR instruction */
static int handle_vmclear(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 zero = 0;
	gpa_t vmptr;
	int r;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (nested_vmx_get_vmptr(vcpu, &vmptr, &r))
		return r;

	if (!page_address_valid(vcpu, vmptr))
		return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);

	if (vmptr == vmx->nested.vmxon_ptr)
		return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);

	if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) {
		if (vmptr == vmx->nested.current_vmptr)
			nested_release_vmcs12(vcpu);

		/*
		 * Silently ignore memory errors on VMCLEAR, Intel's pseudocode
		 * for VMCLEAR includes a "ensure that data for VMCS referenced
		 * by the operand is in memory" clause that guards writes to
		 * memory, i.e. doing nothing for I/O is architecturally valid.
		 *
		 * FIXME: Suppress failures if and only if no memslot is found,
		 * i.e. exit to userspace if __copy_to_user() fails.
		 */
		(void)kvm_vcpu_write_guest(vcpu,
					   vmptr + offsetof(struct vmcs12,
							    launch_state),
					   &zero, sizeof(zero));
	}

	return nested_vmx_succeed(vcpu);
}

/* Emulate the VMLAUNCH instruction */
static int handle_vmlaunch(struct kvm_vcpu *vcpu)
{
	return nested_vmx_run(vcpu, true);
}

/* Emulate the VMRESUME instruction */
static int handle_vmresume(struct kvm_vcpu *vcpu)
{

	return nested_vmx_run(vcpu, false);
}

static int handle_vmread(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
						    : get_vmcs12(vcpu);
	unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct x86_exception e;
	unsigned long field;
	u64 value;
	gva_t gva = 0;
	short offset;
	int len, r;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	/* Decode instruction info and find the field to read */
	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));

	if (!nested_vmx_is_evmptr12_valid(vmx)) {
		/*
		 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
		 * any VMREAD sets the ALU flags for VMfailInvalid.
		 */
		if (vmx->nested.current_vmptr == INVALID_GPA ||
		    (is_guest_mode(vcpu) &&
		     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
			return nested_vmx_failInvalid(vcpu);

		offset = get_vmcs12_field_offset(field);
		if (offset < 0)
			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);

		if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);

		/* Read the field, zero-extended to a u64 value */
		value = vmcs12_read_any(vmcs12, field, offset);
	} else {
		/*
		 * Hyper-V TLFS (as of 6.0b) explicitly states, that while an
		 * enlightened VMCS is active VMREAD/VMWRITE instructions are
		 * unsupported. Unfortunately, certain versions of Windows 11
		 * don't comply with this requirement which is not enforced in
		 * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a
		 * workaround, as misbehaving guests will panic on VM-Fail.
		 * Note, enlightened VMCS is incompatible with shadow VMCS so
		 * all VMREADs from L2 should go to L1.
		 */
		if (WARN_ON_ONCE(is_guest_mode(vcpu)))
			return nested_vmx_failInvalid(vcpu);

		offset = evmcs_field_offset(field, NULL);
		if (offset < 0)
			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);

		/* Read the field, zero-extended to a u64 value */
		value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset);
	}

	/*
	 * Now copy part of this value to register or memory, as requested.
	 * Note that the number of bits actually copied is 32 or 64 depending
	 * on the guest's mode (32 or 64 bit), not on the given field's length.
	 */
	if (instr_info & BIT(10)) {
		kvm_register_write(vcpu, (((instr_info) >> 3) & 0xf), value);
	} else {
		len = is_64_bit_mode(vcpu) ? 8 : 4;
		if (get_vmx_mem_address(vcpu, exit_qualification,
					instr_info, true, len, &gva))
			return 1;
		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
		r = kvm_write_guest_virt_system(vcpu, gva, &value, len, &e);
		if (r != X86EMUL_CONTINUE)
			return kvm_handle_memory_failure(vcpu, r, &e);
	}

	return nested_vmx_succeed(vcpu);
}

static bool is_shadow_field_rw(unsigned long field)
{
	switch (field) {
#define SHADOW_FIELD_RW(x, y) case x:
#include "vmcs_shadow_fields.h"
		return true;
	default:
		break;
	}
	return false;
}

static bool is_shadow_field_ro(unsigned long field)
{
	switch (field) {
#define SHADOW_FIELD_RO(x, y) case x:
#include "vmcs_shadow_fields.h"
		return true;
	default:
		break;
	}
	return false;
}

static int handle_vmwrite(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
						    : get_vmcs12(vcpu);
	unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct x86_exception e;
	unsigned long field;
	short offset;
	gva_t gva;
	int len, r;

	/*
	 * The value to write might be 32 or 64 bits, depending on L1's long
	 * mode, and eventually we need to write that into a field of several
	 * possible lengths. The code below first zero-extends the value to 64
	 * bit (value), and then copies only the appropriate number of
	 * bits into the vmcs12 field.
	 */
	u64 value = 0;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	/*
	 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
	 * any VMWRITE sets the ALU flags for VMfailInvalid.
	 */
	if (vmx->nested.current_vmptr == INVALID_GPA ||
	    (is_guest_mode(vcpu) &&
	     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
		return nested_vmx_failInvalid(vcpu);

	if (instr_info & BIT(10))
		value = kvm_register_read(vcpu, (((instr_info) >> 3) & 0xf));
	else {
		len = is_64_bit_mode(vcpu) ? 8 : 4;
		if (get_vmx_mem_address(vcpu, exit_qualification,
					instr_info, false, len, &gva))
			return 1;
		r = kvm_read_guest_virt(vcpu, gva, &value, len, &e);
		if (r != X86EMUL_CONTINUE)
			return kvm_handle_memory_failure(vcpu, r, &e);
	}

	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));

	offset = get_vmcs12_field_offset(field);
	if (offset < 0)
		return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);

	/*
	 * If the vCPU supports "VMWRITE to any supported field in the
	 * VMCS," then the "read-only" fields are actually read/write.
	 */
	if (vmcs_field_readonly(field) &&
	    !nested_cpu_has_vmwrite_any_field(vcpu))
		return nested_vmx_fail(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);

	/*
	 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
	 * vmcs12, else we may crush a field or consume a stale value.
	 */
	if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field))
		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);

	/*
	 * Some Intel CPUs intentionally drop the reserved bits of the AR byte
	 * fields on VMWRITE.  Emulate this behavior to ensure consistent KVM
	 * behavior regardless of the underlying hardware, e.g. if an AR_BYTE
	 * field is intercepted for VMWRITE but not VMREAD (in L1), then VMREAD
	 * from L1 will return a different value than VMREAD from L2 (L1 sees
	 * the stripped down value, L2 sees the full value as stored by KVM).
	 */
	if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES)
		value &= 0x1f0ff;

	vmcs12_write_any(vmcs12, field, offset, value);

	/*
	 * Do not track vmcs12 dirty-state if in guest-mode as we actually
	 * dirty shadow vmcs12 instead of vmcs12.  Fields that can be updated
	 * by L1 without a vmexit are always updated in the vmcs02, i.e. don't
	 * "dirty" vmcs12, all others go down the prepare_vmcs02() slow path.
	 */
	if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) {
		/*
		 * L1 can read these fields without exiting, ensure the
		 * shadow VMCS is up-to-date.
		 */
		if (enable_shadow_vmcs && is_shadow_field_ro(field)) {
			preempt_disable();
			vmcs_load(vmx->vmcs01.shadow_vmcs);

			__vmcs_writel(field, value);

			vmcs_clear(vmx->vmcs01.shadow_vmcs);
			vmcs_load(vmx->loaded_vmcs->vmcs);
			preempt_enable();
		}
		vmx->nested.dirty_vmcs12 = true;
	}

	return nested_vmx_succeed(vcpu);
}

static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
{
	vmx->nested.current_vmptr = vmptr;
	if (enable_shadow_vmcs) {
		secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
		vmcs_write64(VMCS_LINK_POINTER,
			     __pa(vmx->vmcs01.shadow_vmcs));
		vmx->nested.need_vmcs12_to_shadow_sync = true;
	}
	vmx->nested.dirty_vmcs12 = true;
	vmx->nested.force_msr_bitmap_recalc = true;
}

/* Emulate the VMPTRLD instruction */
static int handle_vmptrld(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	gpa_t vmptr;
	int r;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (nested_vmx_get_vmptr(vcpu, &vmptr, &r))
		return r;

	if (!page_address_valid(vcpu, vmptr))
		return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);

	if (vmptr == vmx->nested.vmxon_ptr)
		return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);

	/* Forbid normal VMPTRLD if Enlightened version was used */
	if (nested_vmx_is_evmptr12_valid(vmx))
		return 1;

	if (vmx->nested.current_vmptr != vmptr) {
		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
		struct vmcs_hdr hdr;

		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
			/*
			 * Reads from an unbacked page return all 1s,
			 * which means that the 32 bits located at the
			 * given physical address won't match the required
			 * VMCS12_REVISION identifier.
			 */
			return nested_vmx_fail(vcpu,
				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
		}

		if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
						 offsetof(struct vmcs12, hdr),
						 sizeof(hdr))) {
			return nested_vmx_fail(vcpu,
				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
		}

		if (hdr.revision_id != VMCS12_REVISION ||
		    (hdr.shadow_vmcs &&
		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
			return nested_vmx_fail(vcpu,
				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
		}

		nested_release_vmcs12(vcpu);

		/*
		 * Load VMCS12 from guest memory since it is not already
		 * cached.
		 */
		if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12,
					  VMCS12_SIZE)) {
			return nested_vmx_fail(vcpu,
				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
		}

		set_current_vmptr(vmx, vmptr);
	}

	return nested_vmx_succeed(vcpu);
}

/* Emulate the VMPTRST instruction */
static int handle_vmptrst(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qual = vmx_get_exit_qual(vcpu);
	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
	struct x86_exception e;
	gva_t gva;
	int r;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu))))
		return 1;

	if (get_vmx_mem_address(vcpu, exit_qual, instr_info,
				true, sizeof(gpa_t), &gva))
		return 1;
	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
	r = kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
					sizeof(gpa_t), &e);
	if (r != X86EMUL_CONTINUE)
		return kvm_handle_memory_failure(vcpu, r, &e);

	return nested_vmx_succeed(vcpu);
}

/* Emulate the INVEPT instruction */
static int handle_invept(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 vmx_instruction_info, types;
	unsigned long type, roots_to_free;
	struct kvm_mmu *mmu;
	gva_t gva;
	struct x86_exception e;
	struct {
		u64 eptp, gpa;
	} operand;
	int i, r, gpr_index;

	if (!(vmx->nested.msrs.secondary_ctls_high &
	      SECONDARY_EXEC_ENABLE_EPT) ||
	    !(vmx->nested.msrs.ept_caps & VMX_EPT_INVEPT_BIT)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
	type = kvm_register_read(vcpu, gpr_index);

	types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;

	if (type >= 32 || !(types & (1 << type)))
		return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);

	/* According to the Intel VMX instruction reference, the memory
	 * operand is read even if it isn't needed (e.g., for type==global)
	 */
	if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
			vmx_instruction_info, false, sizeof(operand), &gva))
		return 1;
	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
	if (r != X86EMUL_CONTINUE)
		return kvm_handle_memory_failure(vcpu, r, &e);

	/*
	 * Nested EPT roots are always held through guest_mmu,
	 * not root_mmu.
	 */
	mmu = &vcpu->arch.guest_mmu;

	switch (type) {
	case VMX_EPT_EXTENT_CONTEXT:
		if (!nested_vmx_check_eptp(vcpu, operand.eptp))
			return nested_vmx_fail(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);

		roots_to_free = 0;
		if (nested_ept_root_matches(mmu->root.hpa, mmu->root.pgd,
					    operand.eptp))
			roots_to_free |= KVM_MMU_ROOT_CURRENT;

		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
			if (nested_ept_root_matches(mmu->prev_roots[i].hpa,
						    mmu->prev_roots[i].pgd,
						    operand.eptp))
				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
		}
		break;
	case VMX_EPT_EXTENT_GLOBAL:
		roots_to_free = KVM_MMU_ROOTS_ALL;
		break;
	default:
		BUG();
		break;
	}

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

	return nested_vmx_succeed(vcpu);
}

static int handle_invvpid(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 vmx_instruction_info;
	unsigned long type, types;
	gva_t gva;
	struct x86_exception e;
	struct {
		u64 vpid;
		u64 gla;
	} operand;
	u16 vpid02;
	int r, gpr_index;

	if (!(vmx->nested.msrs.secondary_ctls_high &
	      SECONDARY_EXEC_ENABLE_VPID) ||
			!(vmx->nested.msrs.vpid_caps & VMX_VPID_INVVPID_BIT)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
	type = kvm_register_read(vcpu, gpr_index);

	types = (vmx->nested.msrs.vpid_caps &
			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;

	if (type >= 32 || !(types & (1 << type)))
		return nested_vmx_fail(vcpu,
			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);

	/* according to the intel vmx instruction reference, the memory
	 * operand is read even if it isn't needed (e.g., for type==global)
	 */
	if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
			vmx_instruction_info, false, sizeof(operand), &gva))
		return 1;
	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.vpid >> 16)
		return nested_vmx_fail(vcpu,
			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);

	vpid02 = nested_get_vpid02(vcpu);
	switch (type) {
	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
		/*
		 * LAM doesn't apply to addresses that are inputs to TLB
		 * invalidation.
		 */
		if (!operand.vpid ||
		    is_noncanonical_address(operand.gla, vcpu))
			return nested_vmx_fail(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
		vpid_sync_vcpu_addr(vpid02, operand.gla);
		break;
	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
		if (!operand.vpid)
			return nested_vmx_fail(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
		vpid_sync_context(vpid02);
		break;
	case VMX_VPID_EXTENT_ALL_CONTEXT:
		vpid_sync_context(vpid02);
		break;
	default:
		WARN_ON_ONCE(1);
		return kvm_skip_emulated_instruction(vcpu);
	}

	/*
	 * Sync the shadow page tables if EPT is disabled, L1 is invalidating
	 * linear mappings for L2 (tagged with L2's VPID).  Free all guest
	 * roots as VPIDs are not tracked in the MMU role.
	 *
	 * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share
	 * an MMU when EPT is disabled.
	 *
	 * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR.
	 */
	if (!enable_ept)
		kvm_mmu_free_guest_mode_roots(vcpu->kvm, &vcpu->arch.root_mmu);

	return nested_vmx_succeed(vcpu);
}

static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
				     struct vmcs12 *vmcs12)
{
	u32 index = kvm_rcx_read(vcpu);
	u64 new_eptp;

	if (WARN_ON_ONCE(!nested_cpu_has_ept(vmcs12)))
		return 1;
	if (index >= VMFUNC_EPTP_ENTRIES)
		return 1;

	if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
				     &new_eptp, index * 8, 8))
		return 1;

	/*
	 * If the (L2) guest does a vmfunc to the currently
	 * active ept pointer, we don't have to do anything else
	 */
	if (vmcs12->ept_pointer != new_eptp) {
		if (!nested_vmx_check_eptp(vcpu, new_eptp))
			return 1;

		vmcs12->ept_pointer = new_eptp;
		nested_ept_new_eptp(vcpu);

		if (!nested_cpu_has_vpid(vmcs12))
			kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
	}

	return 0;
}

static int handle_vmfunc(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12;
	u32 function = kvm_rax_read(vcpu);

	/*
	 * VMFUNC should never execute cleanly while L1 is active; KVM supports
	 * VMFUNC for nested VMs, but not for L1.
	 */
	if (WARN_ON_ONCE(!is_guest_mode(vcpu))) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	vmcs12 = get_vmcs12(vcpu);

	/*
	 * #UD on out-of-bounds function has priority over VM-Exit, and VMFUNC
	 * is enabled in vmcs02 if and only if it's enabled in vmcs12.
	 */
	if (WARN_ON_ONCE((function > 63) || !nested_cpu_has_vmfunc(vmcs12))) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	if (!(vmcs12->vm_function_control & BIT_ULL(function)))
		goto fail;

	switch (function) {
	case 0:
		if (nested_vmx_eptp_switching(vcpu, vmcs12))
			goto fail;
		break;
	default:
		goto fail;
	}
	return kvm_skip_emulated_instruction(vcpu);

fail:
	/*
	 * This is effectively a reflected VM-Exit, as opposed to a synthesized
	 * nested VM-Exit.  Pass the original exit reason, i.e. don't hardcode
	 * EXIT_REASON_VMFUNC as the exit reason.
	 */
	nested_vmx_vmexit(vcpu, vmx->exit_reason.full,
			  vmx_get_intr_info(vcpu),
			  vmx_get_exit_qual(vcpu));
	return 1;
}

/*
 * Return true if an IO instruction with the specified port and size should cause
 * a VM-exit into L1.
 */
bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
				 int size)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	gpa_t bitmap, last_bitmap;
	u8 b;

	last_bitmap = INVALID_GPA;
	b = -1;

	while (size > 0) {
		if (port < 0x8000)
			bitmap = vmcs12->io_bitmap_a;
		else if (port < 0x10000)
			bitmap = vmcs12->io_bitmap_b;
		else
			return true;
		bitmap += (port & 0x7fff) / 8;

		if (last_bitmap != bitmap)
			if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1))
				return true;
		if (b & (1 << (port & 7)))
			return true;

		port++;
		size--;
		last_bitmap = bitmap;
	}

	return false;
}

static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	unsigned long exit_qualification;
	unsigned short port;
	int size;

	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);

	exit_qualification = vmx_get_exit_qual(vcpu);

	port = exit_qualification >> 16;
	size = (exit_qualification & 7) + 1;

	return nested_vmx_check_io_bitmaps(vcpu, port, size);
}

/*
 * Return 1 if we should exit from L2 to L1 to handle an MSR access,
 * rather than handle it ourselves in L0. I.e., check whether L1 expressed
 * disinterest in the current event (read or write a specific MSR) by using an
 * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
 */
static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
					struct vmcs12 *vmcs12,
					union vmx_exit_reason exit_reason)
{
	u32 msr_index = kvm_rcx_read(vcpu);
	gpa_t bitmap;

	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
		return true;

	/*
	 * The MSR_BITMAP page is divided into four 1024-byte bitmaps,
	 * for the four combinations of read/write and low/high MSR numbers.
	 * First we need to figure out which of the four to use:
	 */
	bitmap = vmcs12->msr_bitmap;
	if (exit_reason.basic == EXIT_REASON_MSR_WRITE)
		bitmap += 2048;
	if (msr_index >= 0xc0000000) {
		msr_index -= 0xc0000000;
		bitmap += 1024;
	}

	/* Then read the msr_index'th bit from this bitmap: */
	if (msr_index < 1024*8) {
		unsigned char b;
		if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1))
			return true;
		return 1 & (b >> (msr_index & 7));
	} else
		return true; /* let L1 handle the wrong parameter */
}

/*
 * Return 1 if we should exit from L2 to L1 to handle a CR access exit,
 * rather than handle it ourselves in L0. I.e., check if L1 wanted to
 * intercept (via guest_host_mask etc.) the current event.
 */
static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
	struct vmcs12 *vmcs12)
{
	unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
	int cr = exit_qualification & 15;
	int reg;
	unsigned long val;

	switch ((exit_qualification >> 4) & 3) {
	case 0: /* mov to cr */
		reg = (exit_qualification >> 8) & 15;
		val = kvm_register_read(vcpu, reg);
		switch (cr) {
		case 0:
			if (vmcs12->cr0_guest_host_mask &
			    (val ^ vmcs12->cr0_read_shadow))
				return true;
			break;
		case 3:
			if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
				return true;
			break;
		case 4:
			if (vmcs12->cr4_guest_host_mask &
			    (vmcs12->cr4_read_shadow ^ val))
				return true;
			break;
		case 8:
			if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING))
				return true;
			break;
		}
		break;
	case 2: /* clts */
		if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) &&
		    (vmcs12->cr0_read_shadow & X86_CR0_TS))
			return true;
		break;
	case 1: /* mov from cr */
		switch (cr) {
		case 3:
			if (vmcs12->cpu_based_vm_exec_control &
			    CPU_BASED_CR3_STORE_EXITING)
				return true;
			break;
		case 8:
			if (vmcs12->cpu_based_vm_exec_control &
			    CPU_BASED_CR8_STORE_EXITING)
				return true;
			break;
		}
		break;
	case 3: /* lmsw */
		/*
		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
		 * cr0. Other attempted changes are ignored, with no exit.
		 */
		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
		if (vmcs12->cr0_guest_host_mask & 0xe &
		    (val ^ vmcs12->cr0_read_shadow))
			return true;
		if ((vmcs12->cr0_guest_host_mask & 0x1) &&
		    !(vmcs12->cr0_read_shadow & 0x1) &&
		    (val & 0x1))
			return true;
		break;
	}
	return false;
}

static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu,
					  struct vmcs12 *vmcs12)
{
	u32 encls_leaf;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) ||
	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING))
		return false;

	encls_leaf = kvm_rax_read(vcpu);
	if (encls_leaf > 62)
		encls_leaf = 63;
	return vmcs12->encls_exiting_bitmap & BIT_ULL(encls_leaf);
}

static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu,
	struct vmcs12 *vmcs12, gpa_t bitmap)
{
	u32 vmx_instruction_info;
	unsigned long field;
	u8 b;

	if (!nested_cpu_has_shadow_vmcs(vmcs12))
		return true;

	/* Decode instruction info and find the field to access */
	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));

	/* Out-of-range fields always cause a VM exit from L2 to L1 */
	if (field >> 15)
		return true;

	if (kvm_vcpu_read_guest(vcpu, bitmap + field/8, &b, 1))
		return true;

	return 1 & (b >> (field & 7));
}

static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12)
{
	u32 entry_intr_info = vmcs12->vm_entry_intr_info_field;

	if (nested_cpu_has_mtf(vmcs12))
		return true;

	/*
	 * An MTF VM-exit may be injected into the guest by setting the
	 * interruption-type to 7 (other event) and the vector field to 0. Such
	 * is the case regardless of the 'monitor trap flag' VM-execution
	 * control.
	 */
	return entry_intr_info == (INTR_INFO_VALID_MASK
				   | INTR_TYPE_OTHER_EVENT);
}

/*
 * Return true if L0 wants to handle an exit from L2 regardless of whether or not
 * L1 wants the exit.  Only call this when in is_guest_mode (L2).
 */
static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
				     union vmx_exit_reason exit_reason)
{
	u32 intr_info;

	switch ((u16)exit_reason.basic) {
	case EXIT_REASON_EXCEPTION_NMI:
		intr_info = vmx_get_intr_info(vcpu);
		if (is_nmi(intr_info))
			return true;
		else if (is_page_fault(intr_info))
			return vcpu->arch.apf.host_apf_flags ||
			       vmx_need_pf_intercept(vcpu);
		else if (is_debug(intr_info) &&
			 vcpu->guest_debug &
			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
			return true;
		else if (is_breakpoint(intr_info) &&
			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
			return true;
		else if (is_alignment_check(intr_info) &&
			 !vmx_guest_inject_ac(vcpu))
			return true;
		else if (is_ve_fault(intr_info))
			return true;
		return false;
	case EXIT_REASON_EXTERNAL_INTERRUPT:
		return true;
	case EXIT_REASON_MCE_DURING_VMENTRY:
		return true;
	case EXIT_REASON_EPT_VIOLATION:
		/*
		 * L0 always deals with the EPT violation. If nested EPT is
		 * used, and the nested mmu code discovers that the address is
		 * missing in the guest EPT table (EPT12), the EPT violation
		 * will be injected with nested_ept_inject_page_fault()
		 */
		return true;
	case EXIT_REASON_EPT_MISCONFIG:
		/*
		 * L2 never uses directly L1's EPT, but rather L0's own EPT
		 * table (shadow on EPT) or a merged EPT table that L0 built
		 * (EPT on EPT). So any problems with the structure of the
		 * table is L0's fault.
		 */
		return true;
	case EXIT_REASON_PREEMPTION_TIMER:
		return true;
	case EXIT_REASON_PML_FULL:
		/*
		 * PML is emulated for an L1 VMM and should never be enabled in
		 * vmcs02, always "handle" PML_FULL by exiting to userspace.
		 */
		return true;
	case EXIT_REASON_VMFUNC:
		/* VM functions are emulated through L2->L0 vmexits. */
		return true;
	case EXIT_REASON_BUS_LOCK:
		/*
		 * At present, bus lock VM exit is never exposed to L1.
		 * Handle L2's bus locks in L0 directly.
		 */
		return true;
#ifdef CONFIG_KVM_HYPERV
	case EXIT_REASON_VMCALL:
		/* Hyper-V L2 TLB flush hypercall is handled by L0 */
		return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
			nested_evmcs_l2_tlb_flush_enabled(vcpu) &&
			kvm_hv_is_tlb_flush_hcall(vcpu);
#endif
	default:
		break;
	}
	return false;
}

/*
 * Return 1 if L1 wants to intercept an exit from L2.  Only call this when in
 * is_guest_mode (L2).
 */
static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
				     union vmx_exit_reason exit_reason)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	u32 intr_info;

	switch ((u16)exit_reason.basic) {
	case EXIT_REASON_EXCEPTION_NMI:
		intr_info = vmx_get_intr_info(vcpu);
		if (is_nmi(intr_info))
			return true;
		else if (is_page_fault(intr_info))
			return true;
		return vmcs12->exception_bitmap &
				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
	case EXIT_REASON_EXTERNAL_INTERRUPT:
		return nested_exit_on_intr(vcpu);
	case EXIT_REASON_TRIPLE_FAULT:
		return true;
	case EXIT_REASON_INTERRUPT_WINDOW:
		return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING);
	case EXIT_REASON_NMI_WINDOW:
		return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING);
	case EXIT_REASON_TASK_SWITCH:
		return true;
	case EXIT_REASON_CPUID:
		return true;
	case EXIT_REASON_HLT:
		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
	case EXIT_REASON_INVD:
		return true;
	case EXIT_REASON_INVLPG:
		return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
	case EXIT_REASON_RDPMC:
		return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING);
	case EXIT_REASON_RDRAND:
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND_EXITING);
	case EXIT_REASON_RDSEED:
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING);
	case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP:
		return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
	case EXIT_REASON_VMREAD:
		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
			vmcs12->vmread_bitmap);
	case EXIT_REASON_VMWRITE:
		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
			vmcs12->vmwrite_bitmap);
	case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
	case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMRESUME:
	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
	case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
		/*
		 * VMX instructions trap unconditionally. This allows L1 to
		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
		 */
		return true;
	case EXIT_REASON_CR_ACCESS:
		return nested_vmx_exit_handled_cr(vcpu, vmcs12);
	case EXIT_REASON_DR_ACCESS:
		return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
	case EXIT_REASON_IO_INSTRUCTION:
		return nested_vmx_exit_handled_io(vcpu, vmcs12);
	case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR:
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC);
	case EXIT_REASON_MSR_READ:
	case EXIT_REASON_MSR_WRITE:
		return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
	case EXIT_REASON_INVALID_STATE:
		return true;
	case EXIT_REASON_MWAIT_INSTRUCTION:
		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
	case EXIT_REASON_MONITOR_TRAP_FLAG:
		return nested_vmx_exit_handled_mtf(vmcs12);
	case EXIT_REASON_MONITOR_INSTRUCTION:
		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
	case EXIT_REASON_PAUSE_INSTRUCTION:
		return nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING) ||
			nested_cpu_has2(vmcs12,
				SECONDARY_EXEC_PAUSE_LOOP_EXITING);
	case EXIT_REASON_MCE_DURING_VMENTRY:
		return true;
	case EXIT_REASON_TPR_BELOW_THRESHOLD:
		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
	case EXIT_REASON_APIC_ACCESS:
	case EXIT_REASON_APIC_WRITE:
	case EXIT_REASON_EOI_INDUCED:
		/*
		 * The controls for "virtualize APIC accesses," "APIC-
		 * register virtualization," and "virtual-interrupt
		 * delivery" only come from vmcs12.
		 */
		return true;
	case EXIT_REASON_INVPCID:
		return
			nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) &&
			nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
	case EXIT_REASON_WBINVD:
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
	case EXIT_REASON_XSETBV:
		return true;
	case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS:
		/*
		 * This should never happen, since it is not possible to
		 * set XSS to a non-zero value---neither in L1 nor in L2.
		 * If if it were, XSS would have to be checked against
		 * the XSS exit bitmap in vmcs12.
		 */
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES);
	case EXIT_REASON_UMWAIT:
	case EXIT_REASON_TPAUSE:
		return nested_cpu_has2(vmcs12,
			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE);
	case EXIT_REASON_ENCLS:
		return nested_vmx_exit_handled_encls(vcpu, vmcs12);
	case EXIT_REASON_NOTIFY:
		/* Notify VM exit is not exposed to L1 */
		return false;
	default:
		return true;
	}
}

/*
 * Conditionally reflect a VM-Exit into L1.  Returns %true if the VM-Exit was
 * reflected into L1.
 */
bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	union vmx_exit_reason exit_reason = vmx->exit_reason;
	unsigned long exit_qual;
	u32 exit_intr_info;

	WARN_ON_ONCE(vmx->nested.nested_run_pending);

	/*
	 * Late nested VM-Fail shares the same flow as nested VM-Exit since KVM
	 * has already loaded L2's state.
	 */
	if (unlikely(vmx->fail)) {
		trace_kvm_nested_vmenter_failed(
			"hardware VM-instruction error: ",
			vmcs_read32(VM_INSTRUCTION_ERROR));
		exit_intr_info = 0;
		exit_qual = 0;
		goto reflect_vmexit;
	}

	trace_kvm_nested_vmexit(vcpu, KVM_ISA_VMX);

	/* If L0 (KVM) wants the exit, it trumps L1's desires. */
	if (nested_vmx_l0_wants_exit(vcpu, exit_reason))
		return false;

	/* If L1 doesn't want the exit, handle it in L0. */
	if (!nested_vmx_l1_wants_exit(vcpu, exit_reason))
		return false;

	/*
	 * vmcs.VM_EXIT_INTR_INFO is only valid for EXCEPTION_NMI exits.  For
	 * EXTERNAL_INTERRUPT, the value for vmcs12->vm_exit_intr_info would
	 * need to be synthesized by querying the in-kernel LAPIC, but external
	 * interrupts are never reflected to L1 so it's a non-issue.
	 */
	exit_intr_info = vmx_get_intr_info(vcpu);
	if (is_exception_with_error_code(exit_intr_info)) {
		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

		vmcs12->vm_exit_intr_error_code =
			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
	}
	exit_qual = vmx_get_exit_qual(vcpu);

reflect_vmexit:
	nested_vmx_vmexit(vcpu, exit_reason.full, exit_intr_info, exit_qual);
	return true;
}

static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
				struct kvm_nested_state __user *user_kvm_nested_state,
				u32 user_data_size)
{
	struct vcpu_vmx *vmx;
	struct vmcs12 *vmcs12;
	struct kvm_nested_state kvm_state = {
		.flags = 0,
		.format = KVM_STATE_NESTED_FORMAT_VMX,
		.size = sizeof(kvm_state),
		.hdr.vmx.flags = 0,
		.hdr.vmx.vmxon_pa = INVALID_GPA,
		.hdr.vmx.vmcs12_pa = INVALID_GPA,
		.hdr.vmx.preemption_timer_deadline = 0,
	};
	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
		&user_kvm_nested_state->data.vmx[0];

	if (!vcpu)
		return kvm_state.size + sizeof(*user_vmx_nested_state);

	vmx = to_vmx(vcpu);
	vmcs12 = get_vmcs12(vcpu);

	if (guest_can_use(vcpu, X86_FEATURE_VMX) &&
	    (vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
		kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
		kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr;

		if (vmx_has_valid_vmcs12(vcpu)) {
			kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);

			/* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */
			if (nested_vmx_is_evmptr12_set(vmx))
				kvm_state.flags |= KVM_STATE_NESTED_EVMCS;

			if (is_guest_mode(vcpu) &&
			    nested_cpu_has_shadow_vmcs(vmcs12) &&
			    vmcs12->vmcs_link_pointer != INVALID_GPA)
				kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12);
		}

		if (vmx->nested.smm.vmxon)
			kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON;

		if (vmx->nested.smm.guest_mode)
			kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE;

		if (is_guest_mode(vcpu)) {
			kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;

			if (vmx->nested.nested_run_pending)
				kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;

			if (vmx->nested.mtf_pending)
				kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING;

			if (nested_cpu_has_preemption_timer(vmcs12) &&
			    vmx->nested.has_preemption_timer_deadline) {
				kvm_state.hdr.vmx.flags |=
					KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE;
				kvm_state.hdr.vmx.preemption_timer_deadline =
					vmx->nested.preemption_timer_deadline;
			}
		}
	}

	if (user_data_size < kvm_state.size)
		goto out;

	if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
		return -EFAULT;

	if (!vmx_has_valid_vmcs12(vcpu))
		goto out;

	/*
	 * When running L2, the authoritative vmcs12 state is in the
	 * vmcs02. When running L1, the authoritative vmcs12 state is
	 * in the shadow or enlightened vmcs linked to vmcs01, unless
	 * need_vmcs12_to_shadow_sync is set, in which case, the authoritative
	 * vmcs12 state is in the vmcs12 already.
	 */
	if (is_guest_mode(vcpu)) {
		sync_vmcs02_to_vmcs12(vcpu, vmcs12);
		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
	} else  {
		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
			if (nested_vmx_is_evmptr12_valid(vmx))
				/*
				 * L1 hypervisor is not obliged to keep eVMCS
				 * clean fields data always up-to-date while
				 * not in guest mode, 'hv_clean_fields' is only
				 * supposed to be actual upon vmentry so we need
				 * to ignore it here and do full copy.
				 */
				copy_enlightened_to_vmcs12(vmx, 0);
			else if (enable_shadow_vmcs)
				copy_shadow_to_vmcs12(vmx);
		}
	}

	BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
	BUILD_BUG_ON(sizeof(user_vmx_nested_state->shadow_vmcs12) < VMCS12_SIZE);

	/*
	 * Copy over the full allocated size of vmcs12 rather than just the size
	 * of the struct.
	 */
	if (copy_to_user(user_vmx_nested_state->vmcs12, vmcs12, VMCS12_SIZE))
		return -EFAULT;

	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
		if (copy_to_user(user_vmx_nested_state->shadow_vmcs12,
				 get_shadow_vmcs12(vcpu), VMCS12_SIZE))
			return -EFAULT;
	}
out:
	return kvm_state.size;
}

void vmx_leave_nested(struct kvm_vcpu *vcpu)
{
	if (is_guest_mode(vcpu)) {
		to_vmx(vcpu)->nested.nested_run_pending = 0;
		nested_vmx_vmexit(vcpu, -1, 0, 0);
	}
	free_nested(vcpu);
}

static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
				struct kvm_nested_state __user *user_kvm_nested_state,
				struct kvm_nested_state *kvm_state)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12;
	enum vm_entry_failure_code ignored;
	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
		&user_kvm_nested_state->data.vmx[0];
	int ret;

	if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX)
		return -EINVAL;

	if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) {
		if (kvm_state->hdr.vmx.smm.flags)
			return -EINVAL;

		if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA)
			return -EINVAL;

		/*
		 * KVM_STATE_NESTED_EVMCS used to signal that KVM should
		 * enable eVMCS capability on vCPU. However, since then
		 * code was changed such that flag signals vmcs12 should
		 * be copied into eVMCS in guest memory.
		 *
		 * To preserve backwards compatibility, allow user
		 * to set this flag even when there is no VMXON region.
		 */
		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
			return -EINVAL;
	} else {
		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
			return -EINVAL;

		if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
			return -EINVAL;
	}

	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
	    (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
		return -EINVAL;

	if (kvm_state->hdr.vmx.smm.flags &
	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
		return -EINVAL;

	if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE)
		return -EINVAL;

	/*
	 * SMM temporarily disables VMX, so we cannot be in guest mode,
	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
	 * must be zero.
	 */
	if (is_smm(vcpu) ?
		(kvm_state->flags &
		 (KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING))
		: kvm_state->hdr.vmx.smm.flags)
		return -EINVAL;

	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
	    !(kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
		return -EINVAL;

	if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
	    (!guest_can_use(vcpu, X86_FEATURE_VMX) ||
	     !vmx->nested.enlightened_vmcs_enabled))
			return -EINVAL;

	vmx_leave_nested(vcpu);

	if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA)
		return 0;

	vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa;
	ret = enter_vmx_operation(vcpu);
	if (ret)
		return ret;

	/* Empty 'VMXON' state is permitted if no VMCS loaded */
	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) {
		/* See vmx_has_valid_vmcs12.  */
		if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) ||
		    (kvm_state->flags & KVM_STATE_NESTED_EVMCS) ||
		    (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA))
			return -EINVAL;
		else
			return 0;
	}

	if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) {
		if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
		    !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa))
			return -EINVAL;

		set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
#ifdef CONFIG_KVM_HYPERV
	} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
		/*
		 * nested_vmx_handle_enlightened_vmptrld() cannot be called
		 * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be
		 * restored yet. EVMCS will be mapped from
		 * nested_get_vmcs12_pages().
		 */
		vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING;
		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
#endif
	} else {
		return -EINVAL;
	}

	if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
		vmx->nested.smm.vmxon = true;
		vmx->nested.vmxon = false;

		if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE)
			vmx->nested.smm.guest_mode = true;
	}

	vmcs12 = get_vmcs12(vcpu);
	if (copy_from_user(vmcs12, user_vmx_nested_state->vmcs12, sizeof(*vmcs12)))
		return -EFAULT;

	if (vmcs12->hdr.revision_id != VMCS12_REVISION)
		return -EINVAL;

	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
		return 0;

	vmx->nested.nested_run_pending =
		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);

	vmx->nested.mtf_pending =
		!!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);

	ret = -EINVAL;
	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);

		if (kvm_state->size <
		    sizeof(*kvm_state) +
		    sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12))
			goto error_guest_mode;

		if (copy_from_user(shadow_vmcs12,
				   user_vmx_nested_state->shadow_vmcs12,
				   sizeof(*shadow_vmcs12))) {
			ret = -EFAULT;
			goto error_guest_mode;
		}

		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
		    !shadow_vmcs12->hdr.shadow_vmcs)
			goto error_guest_mode;
	}

	vmx->nested.has_preemption_timer_deadline = false;
	if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) {
		vmx->nested.has_preemption_timer_deadline = true;
		vmx->nested.preemption_timer_deadline =
			kvm_state->hdr.vmx.preemption_timer_deadline;
	}

	if (nested_vmx_check_controls(vcpu, vmcs12) ||
	    nested_vmx_check_host_state(vcpu, vmcs12) ||
	    nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
		goto error_guest_mode;

	vmx->nested.dirty_vmcs12 = true;
	vmx->nested.force_msr_bitmap_recalc = true;
	ret = nested_vmx_enter_non_root_mode(vcpu, false);
	if (ret)
		goto error_guest_mode;

	if (vmx->nested.mtf_pending)
		kvm_make_request(KVM_REQ_EVENT, vcpu);

	return 0;

error_guest_mode:
	vmx->nested.nested_run_pending = 0;
	return ret;
}

void nested_vmx_set_vmcs_shadowing_bitmap(void)
{
	if (enable_shadow_vmcs) {
		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
	}
}

/*
 * Indexing into the vmcs12 uses the VMCS encoding rotated left by 6.  Undo
 * that madness to get the encoding for comparison.
 */
#define VMCS12_IDX_TO_ENC(idx) ((u16)(((u16)(idx) >> 6) | ((u16)(idx) << 10)))

static u64 nested_vmx_calc_vmcs_enum_msr(void)
{
	/*
	 * Note these are the so called "index" of the VMCS field encoding, not
	 * the index into vmcs12.
	 */
	unsigned int max_idx, idx;
	int i;

	/*
	 * For better or worse, KVM allows VMREAD/VMWRITE to all fields in
	 * vmcs12, regardless of whether or not the associated feature is
	 * exposed to L1.  Simply find the field with the highest index.
	 */
	max_idx = 0;
	for (i = 0; i < nr_vmcs12_fields; i++) {
		/* The vmcs12 table is very, very sparsely populated. */
		if (!vmcs12_field_offsets[i])
			continue;

		idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i));
		if (idx > max_idx)
			max_idx = idx;
	}

	return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT;
}

static void nested_vmx_setup_pinbased_ctls(struct vmcs_config *vmcs_conf,
					   struct nested_vmx_msrs *msrs)
{
	msrs->pinbased_ctls_low =
		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;

	msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl;
	msrs->pinbased_ctls_high &=
		PIN_BASED_EXT_INTR_MASK |
		PIN_BASED_NMI_EXITING |
		PIN_BASED_VIRTUAL_NMIS |
		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
	msrs->pinbased_ctls_high |=
		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
		PIN_BASED_VMX_PREEMPTION_TIMER;
}

static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf,
				       struct nested_vmx_msrs *msrs)
{
	msrs->exit_ctls_low =
		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;

	msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl;
	msrs->exit_ctls_high &=
#ifdef CONFIG_X86_64
		VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
		VM_EXIT_CLEAR_BNDCFGS;
	msrs->exit_ctls_high |=
		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT |
		VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;

	/* We support free control of debug control saving. */
	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
}

static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf,
					struct nested_vmx_msrs *msrs)
{
	msrs->entry_ctls_low =
		VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;

	msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl;
	msrs->entry_ctls_high &=
#ifdef CONFIG_X86_64
		VM_ENTRY_IA32E_MODE |
#endif
		VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS;
	msrs->entry_ctls_high |=
		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER |
		 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL);

	/* We support free control of debug control loading. */
	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
}

static void nested_vmx_setup_cpubased_ctls(struct vmcs_config *vmcs_conf,
					   struct nested_vmx_msrs *msrs)
{
	msrs->procbased_ctls_low =
		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;

	msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl;
	msrs->procbased_ctls_high &=
		CPU_BASED_INTR_WINDOW_EXITING |
		CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
		CPU_BASED_CR3_STORE_EXITING |
#ifdef CONFIG_X86_64
		CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
#endif
		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
		CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
		CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
		CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
	/*
	 * We can allow some features even when not supported by the
	 * hardware. For example, L1 can specify an MSR bitmap - and we
	 * can use it to avoid exits to L1 - even when L0 runs L2
	 * without MSR bitmaps.
	 */
	msrs->procbased_ctls_high |=
		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
		CPU_BASED_USE_MSR_BITMAPS;

	/* We support free control of CR3 access interception. */
	msrs->procbased_ctls_low &=
		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
}

static void nested_vmx_setup_secondary_ctls(u32 ept_caps,
					    struct vmcs_config *vmcs_conf,
					    struct nested_vmx_msrs *msrs)
{
	msrs->secondary_ctls_low = 0;

	msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl;
	msrs->secondary_ctls_high &=
		SECONDARY_EXEC_DESC |
		SECONDARY_EXEC_ENABLE_RDTSCP |
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
		SECONDARY_EXEC_WBINVD_EXITING |
		SECONDARY_EXEC_APIC_REGISTER_VIRT |
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
		SECONDARY_EXEC_RDRAND_EXITING |
		SECONDARY_EXEC_ENABLE_INVPCID |
		SECONDARY_EXEC_ENABLE_VMFUNC |
		SECONDARY_EXEC_RDSEED_EXITING |
		SECONDARY_EXEC_ENABLE_XSAVES |
		SECONDARY_EXEC_TSC_SCALING |
		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;

	/*
	 * We can emulate "VMCS shadowing," even if the hardware
	 * doesn't support it.
	 */
	msrs->secondary_ctls_high |=
		SECONDARY_EXEC_SHADOW_VMCS;

	if (enable_ept) {
		/* nested EPT: emulate EPT also to L1 */
		msrs->secondary_ctls_high |=
			SECONDARY_EXEC_ENABLE_EPT;
		msrs->ept_caps =
			VMX_EPT_PAGE_WALK_4_BIT |
			VMX_EPT_PAGE_WALK_5_BIT |
			VMX_EPTP_WB_BIT |
			VMX_EPT_INVEPT_BIT |
			VMX_EPT_EXECUTE_ONLY_BIT;

		msrs->ept_caps &= ept_caps;
		msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
			VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
			VMX_EPT_1GB_PAGE_BIT;
		if (enable_ept_ad_bits) {
			msrs->secondary_ctls_high |=
				SECONDARY_EXEC_ENABLE_PML;
			msrs->ept_caps |= VMX_EPT_AD_BIT;
		}

		/*
		 * Advertise EPTP switching irrespective of hardware support,
		 * KVM emulates it in software so long as VMFUNC is supported.
		 */
		if (cpu_has_vmx_vmfunc())
			msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING;
	}

	/*
	 * Old versions of KVM use the single-context version without
	 * checking for support, so declare that it is supported even
	 * though it is treated as global context.  The alternative is
	 * not failing the single-context invvpid, and it is worse.
	 */
	if (enable_vpid) {
		msrs->secondary_ctls_high |=
			SECONDARY_EXEC_ENABLE_VPID;
		msrs->vpid_caps = VMX_VPID_INVVPID_BIT |
			VMX_VPID_EXTENT_SUPPORTED_MASK;
	}

	if (enable_unrestricted_guest)
		msrs->secondary_ctls_high |=
			SECONDARY_EXEC_UNRESTRICTED_GUEST;

	if (flexpriority_enabled)
		msrs->secondary_ctls_high |=
			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;

	if (enable_sgx)
		msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING;
}

static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf,
				       struct nested_vmx_msrs *msrs)
{
	msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA;
	msrs->misc_low |=
		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
		VMX_MISC_ACTIVITY_HLT |
		VMX_MISC_ACTIVITY_WAIT_SIPI;
	msrs->misc_high = 0;
}

static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs)
{
	/*
	 * This MSR reports some information about VMX support. We
	 * should return information about the VMX we emulate for the
	 * guest, and the VMCS structure we give it - not about the
	 * VMX support of the underlying hardware.
	 */
	msrs->basic =
		VMCS12_REVISION |
		VMX_BASIC_TRUE_CTLS |
		((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
		(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);

	if (cpu_has_vmx_basic_inout())
		msrs->basic |= VMX_BASIC_INOUT;
}

static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs)
{
	/*
	 * These MSRs specify bits which the guest must keep fixed on
	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
	 * We picked the standard core2 setting.
	 */
#define VMXON_CR0_ALWAYSON     (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
#define VMXON_CR4_ALWAYSON     X86_CR4_VMXE
	msrs->cr0_fixed0 = VMXON_CR0_ALWAYSON;
	msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON;

	/* These MSRs specify bits which the guest must keep fixed off. */
	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);

	if (vmx_umip_emulated())
		msrs->cr4_fixed1 |= X86_CR4_UMIP;
}

/*
 * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be
 * returned for the various VMX controls MSRs when nested VMX is enabled.
 * The same values should also be used to verify that vmcs12 control fields are
 * valid during nested entry from L1 to L2.
 * Each of these control msrs has a low and high 32-bit half: A low bit is on
 * if the corresponding bit in the (32-bit) control field *must* be on, and a
 * bit in the high half is on if the corresponding bit in the control field
 * may be on. See also vmx_control_verify().
 */
void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps)
{
	struct nested_vmx_msrs *msrs = &vmcs_conf->nested;

	/*
	 * Note that as a general rule, the high half of the MSRs (bits in
	 * the control fields which may be 1) should be initialized by the
	 * intersection of the underlying hardware's MSR (i.e., features which
	 * can be supported) and the list of features we want to expose -
	 * because they are known to be properly supported in our code.
	 * Also, usually, the low half of the MSRs (bits which must be 1) can
	 * be set to 0, meaning that L1 may turn off any of these bits. The
	 * reason is that if one of these bits is necessary, it will appear
	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
	 * fields of vmcs01 and vmcs02, will turn these bits off - and
	 * nested_vmx_l1_wants_exit() will not pass related exits to L1.
	 * These rules have exceptions below.
	 */
	nested_vmx_setup_pinbased_ctls(vmcs_conf, msrs);

	nested_vmx_setup_exit_ctls(vmcs_conf, msrs);

	nested_vmx_setup_entry_ctls(vmcs_conf, msrs);

	nested_vmx_setup_cpubased_ctls(vmcs_conf, msrs);

	nested_vmx_setup_secondary_ctls(ept_caps, vmcs_conf, msrs);

	nested_vmx_setup_misc_data(vmcs_conf, msrs);

	nested_vmx_setup_basic(msrs);

	nested_vmx_setup_cr_fixed(msrs);

	msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr();
}

void nested_vmx_hardware_unsetup(void)
{
	int i;

	if (enable_shadow_vmcs) {
		for (i = 0; i < VMX_BITMAP_NR; i++)
			free_page((unsigned long)vmx_bitmap[i]);
	}
}

__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
{
	int i;

	if (!cpu_has_vmx_shadow_vmcs())
		enable_shadow_vmcs = 0;
	if (enable_shadow_vmcs) {
		for (i = 0; i < VMX_BITMAP_NR; i++) {
			/*
			 * The vmx_bitmap is not tied to a VM and so should
			 * not be charged to a memcg.
			 */
			vmx_bitmap[i] = (unsigned long *)
				__get_free_page(GFP_KERNEL);
			if (!vmx_bitmap[i]) {
				nested_vmx_hardware_unsetup();
				return -ENOMEM;
			}
		}

		init_vmcs_shadow_fields();
	}

	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear;
	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch;
	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld;
	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst;
	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread;
	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume;
	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite;
	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmxoff;
	exit_handlers[EXIT_REASON_VMON]		= handle_vmxon;
	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept;
	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid;
	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc;

	return 0;
}

struct kvm_x86_nested_ops vmx_nested_ops = {
	.leave_nested = vmx_leave_nested,
	.is_exception_vmexit = nested_vmx_is_exception_vmexit,
	.check_events = vmx_check_nested_events,
	.has_events = vmx_has_nested_events,
	.triple_fault = nested_vmx_triple_fault,
	.get_state = vmx_get_nested_state,
	.set_state = vmx_set_nested_state,
	.get_nested_state_pages = vmx_get_nested_state_pages,
	.write_log_dirty = nested_vmx_write_pml_buffer,
#ifdef CONFIG_KVM_HYPERV
	.enable_evmcs = nested_enable_evmcs,
	.get_evmcs_version = nested_get_evmcs_version,
	.hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush,
#endif
};