summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/vmx.c
blob: 95a01609d7eea13633a6d53383a6e2859463c3e5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "irq.h"
#include "mmu.h"
#include "cpuid.h"
#include "lapic.h"

#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/mod_devicetable.h>
#include <linux/trace_events.h>
#include <linux/slab.h>
#include <linux/tboot.h>
#include <linux/hrtimer.h>
#include <linux/frame.h>
#include "kvm_cache_regs.h"
#include "x86.h"

#include <asm/cpu.h>
#include <asm/io.h>
#include <asm/desc.h>
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
#include <asm/fpu/internal.h>
#include <asm/perf_event.h>
#include <asm/debugreg.h>
#include <asm/kexec.h>
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>

#include "trace.h"
#include "pmu.h"

#define __ex(x) __kvm_handle_fault_on_reboot(x)
#define __ex_clear(x, reg) \
	____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

static const struct x86_cpu_id vmx_cpu_id[] = {
	X86_FEATURE_MATCH(X86_FEATURE_VMX),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);

static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);

static bool __read_mostly flexpriority_enabled = 1;
module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);

static bool __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);

static bool __read_mostly enable_unrestricted_guest = 1;
module_param_named(unrestricted_guest,
			enable_unrestricted_guest, bool, S_IRUGO);

static bool __read_mostly enable_ept_ad_bits = 1;
module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO);

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

static bool __read_mostly fasteoi = 1;
module_param(fasteoi, bool, S_IRUGO);

static bool __read_mostly enable_apicv = 1;
module_param(enable_apicv, bool, S_IRUGO);

static bool __read_mostly enable_shadow_vmcs = 1;
module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
/*
 * If nested=1, nested virtualization is supported, i.e., guests may use
 * VMX and be a hypervisor for its own guests. If nested=0, guests may not
 * use VMX instructions.
 */
static bool __read_mostly nested = 0;
module_param(nested, bool, S_IRUGO);

static u64 __read_mostly host_xss;

static bool __read_mostly enable_pml = 1;
module_param_named(pml, enable_pml, bool, S_IRUGO);

#define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL

/* Guest_tsc -> host_tsc conversion requires 64-bit division.  */
static int __read_mostly cpu_preemption_timer_multi;
static bool __read_mostly enable_preemption_timer = 1;
#ifdef CONFIG_X86_64
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
#endif

#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
#define KVM_VM_CR0_ALWAYS_ON						\
	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_CR4_GUEST_OWNED_BITS				      \
	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)

#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)

#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))

#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5

/*
 * 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)

/*
 * These 2 parameters are used to config the controls for Pause-Loop Exiting:
 * ple_gap:    upper bound on the amount of time between two successive
 *             executions of PAUSE in a loop. Also indicate if ple enabled.
 *             According to test, this time is usually smaller than 128 cycles.
 * ple_window: upper bound on the amount of time a guest is allowed to execute
 *             in a PAUSE loop. Tests indicate that most spinlocks are held for
 *             less than 2^12 cycles
 * Time is measured based on a counter that runs at the same rate as the TSC,
 * refer SDM volume 3b section 21.6.13 & 22.1.3.
 */
#define KVM_VMX_DEFAULT_PLE_GAP           128
#define KVM_VMX_DEFAULT_PLE_WINDOW        4096
#define KVM_VMX_DEFAULT_PLE_WINDOW_GROW   2
#define KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK 0
#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX    \
		INT_MAX / KVM_VMX_DEFAULT_PLE_WINDOW_GROW

static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
module_param(ple_gap, int, S_IRUGO);

static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);

/* Default doubles per-vcpu window every exit. */
static int ple_window_grow = KVM_VMX_DEFAULT_PLE_WINDOW_GROW;
module_param(ple_window_grow, int, S_IRUGO);

/* Default resets per-vcpu window every exit to ple_window. */
static int ple_window_shrink = KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK;
module_param(ple_window_shrink, int, S_IRUGO);

/* Default is to compute the maximum so we can never overflow. */
static int ple_window_actual_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
static int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
module_param(ple_window_max, int, S_IRUGO);

extern const ulong vmx_return;

#define NR_AUTOLOAD_MSRS 8
#define VMCS02_POOL_SIZE 1

struct vmcs {
	u32 revision_id;
	u32 abort;
	char data[0];
};

/*
 * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also
 * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs
 * loaded on this CPU (so we can clear them if the CPU goes down).
 */
struct loaded_vmcs {
	struct vmcs *vmcs;
	struct vmcs *shadow_vmcs;
	int cpu;
	bool launched;
	bool nmi_known_unmasked;
	unsigned long vmcs_host_cr3;	/* May not match real cr3 */
	unsigned long vmcs_host_cr4;	/* May not match real cr4 */
	struct list_head loaded_vmcss_on_cpu_link;
};

struct shared_msr_entry {
	unsigned index;
	u64 data;
	u64 mask;
};

/*
 * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a
 * single nested guest (L2), hence the name vmcs12. Any VMX implementation has
 * a VMCS structure, and vmcs12 is our emulated VMX's VMCS. This structure is
 * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
 * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
 * More than one of these structures may exist, if L1 runs multiple L2 guests.
 * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
 * underlying hardware which will be used to run L2.
 * This structure is packed to ensure that its layout is identical across
 * machines (necessary for live migration).
 * If there are changes in this struct, VMCS12_REVISION must be changed.
 */
typedef u64 natural_width;
struct __packed vmcs12 {
	/* According to the Intel spec, a VMCS region must start with the
	 * following two fields. Then follow implementation-specific data.
	 */
	u32 revision_id;
	u32 abort;

	u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
	u32 padding[7]; /* room for future expansion */

	u64 io_bitmap_a;
	u64 io_bitmap_b;
	u64 msr_bitmap;
	u64 vm_exit_msr_store_addr;
	u64 vm_exit_msr_load_addr;
	u64 vm_entry_msr_load_addr;
	u64 tsc_offset;
	u64 virtual_apic_page_addr;
	u64 apic_access_addr;
	u64 posted_intr_desc_addr;
	u64 vm_function_control;
	u64 ept_pointer;
	u64 eoi_exit_bitmap0;
	u64 eoi_exit_bitmap1;
	u64 eoi_exit_bitmap2;
	u64 eoi_exit_bitmap3;
	u64 eptp_list_address;
	u64 xss_exit_bitmap;
	u64 guest_physical_address;
	u64 vmcs_link_pointer;
	u64 pml_address;
	u64 guest_ia32_debugctl;
	u64 guest_ia32_pat;
	u64 guest_ia32_efer;
	u64 guest_ia32_perf_global_ctrl;
	u64 guest_pdptr0;
	u64 guest_pdptr1;
	u64 guest_pdptr2;
	u64 guest_pdptr3;
	u64 guest_bndcfgs;
	u64 host_ia32_pat;
	u64 host_ia32_efer;
	u64 host_ia32_perf_global_ctrl;
	u64 padding64[8]; /* room for future expansion */
	/*
	 * To allow migration of L1 (complete with its L2 guests) between
	 * machines of different natural widths (32 or 64 bit), we cannot have
	 * unsigned long fields with no explict size. We use u64 (aliased
	 * natural_width) instead. Luckily, x86 is little-endian.
	 */
	natural_width cr0_guest_host_mask;
	natural_width cr4_guest_host_mask;
	natural_width cr0_read_shadow;
	natural_width cr4_read_shadow;
	natural_width cr3_target_value0;
	natural_width cr3_target_value1;
	natural_width cr3_target_value2;
	natural_width cr3_target_value3;
	natural_width exit_qualification;
	natural_width guest_linear_address;
	natural_width guest_cr0;
	natural_width guest_cr3;
	natural_width guest_cr4;
	natural_width guest_es_base;
	natural_width guest_cs_base;
	natural_width guest_ss_base;
	natural_width guest_ds_base;
	natural_width guest_fs_base;
	natural_width guest_gs_base;
	natural_width guest_ldtr_base;
	natural_width guest_tr_base;
	natural_width guest_gdtr_base;
	natural_width guest_idtr_base;
	natural_width guest_dr7;
	natural_width guest_rsp;
	natural_width guest_rip;
	natural_width guest_rflags;
	natural_width guest_pending_dbg_exceptions;
	natural_width guest_sysenter_esp;
	natural_width guest_sysenter_eip;
	natural_width host_cr0;
	natural_width host_cr3;
	natural_width host_cr4;
	natural_width host_fs_base;
	natural_width host_gs_base;
	natural_width host_tr_base;
	natural_width host_gdtr_base;
	natural_width host_idtr_base;
	natural_width host_ia32_sysenter_esp;
	natural_width host_ia32_sysenter_eip;
	natural_width host_rsp;
	natural_width host_rip;
	natural_width paddingl[8]; /* room for future expansion */
	u32 pin_based_vm_exec_control;
	u32 cpu_based_vm_exec_control;
	u32 exception_bitmap;
	u32 page_fault_error_code_mask;
	u32 page_fault_error_code_match;
	u32 cr3_target_count;
	u32 vm_exit_controls;
	u32 vm_exit_msr_store_count;
	u32 vm_exit_msr_load_count;
	u32 vm_entry_controls;
	u32 vm_entry_msr_load_count;
	u32 vm_entry_intr_info_field;
	u32 vm_entry_exception_error_code;
	u32 vm_entry_instruction_len;
	u32 tpr_threshold;
	u32 secondary_vm_exec_control;
	u32 vm_instruction_error;
	u32 vm_exit_reason;
	u32 vm_exit_intr_info;
	u32 vm_exit_intr_error_code;
	u32 idt_vectoring_info_field;
	u32 idt_vectoring_error_code;
	u32 vm_exit_instruction_len;
	u32 vmx_instruction_info;
	u32 guest_es_limit;
	u32 guest_cs_limit;
	u32 guest_ss_limit;
	u32 guest_ds_limit;
	u32 guest_fs_limit;
	u32 guest_gs_limit;
	u32 guest_ldtr_limit;
	u32 guest_tr_limit;
	u32 guest_gdtr_limit;
	u32 guest_idtr_limit;
	u32 guest_es_ar_bytes;
	u32 guest_cs_ar_bytes;
	u32 guest_ss_ar_bytes;
	u32 guest_ds_ar_bytes;
	u32 guest_fs_ar_bytes;
	u32 guest_gs_ar_bytes;
	u32 guest_ldtr_ar_bytes;
	u32 guest_tr_ar_bytes;
	u32 guest_interruptibility_info;
	u32 guest_activity_state;
	u32 guest_sysenter_cs;
	u32 host_ia32_sysenter_cs;
	u32 vmx_preemption_timer_value;
	u32 padding32[7]; /* room for future expansion */
	u16 virtual_processor_id;
	u16 posted_intr_nv;
	u16 guest_es_selector;
	u16 guest_cs_selector;
	u16 guest_ss_selector;
	u16 guest_ds_selector;
	u16 guest_fs_selector;
	u16 guest_gs_selector;
	u16 guest_ldtr_selector;
	u16 guest_tr_selector;
	u16 guest_intr_status;
	u16 guest_pml_index;
	u16 host_es_selector;
	u16 host_cs_selector;
	u16 host_ss_selector;
	u16 host_ds_selector;
	u16 host_fs_selector;
	u16 host_gs_selector;
	u16 host_tr_selector;
};

/*
 * VMCS12_REVISION is an arbitrary id that should be changed if the content or
 * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
 * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
 */
#define VMCS12_REVISION 0x11e57ed0

/*
 * VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region
 * and any VMCS region. Although only sizeof(struct vmcs12) are used by the
 * current implementation, 4K are reserved to avoid future complications.
 */
#define VMCS12_SIZE 0x1000

/* Used to remember the last vmcs02 used for some recently used vmcs12s */
struct vmcs02_list {
	struct list_head list;
	gpa_t vmptr;
	struct loaded_vmcs vmcs02;
};

/*
 * The nested_vmx structure is part of vcpu_vmx, and holds information we need
 * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
 */
struct nested_vmx {
	/* Has the level1 guest done vmxon? */
	bool vmxon;
	gpa_t vmxon_ptr;
	bool pml_full;

	/* The guest-physical address of the current VMCS L1 keeps for L2 */
	gpa_t current_vmptr;
	/*
	 * Cache of the guest's VMCS, existing outside of guest memory.
	 * Loaded from guest memory during VMPTRLD. Flushed to guest
	 * memory during VMCLEAR and VMPTRLD.
	 */
	struct vmcs12 *cached_vmcs12;
	/*
	 * Indicates if the shadow vmcs must be updated with the
	 * data hold by vmcs12
	 */
	bool sync_shadow_vmcs;

	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
	struct list_head vmcs02_pool;
	int vmcs02_num;
	bool change_vmcs01_virtual_x2apic_mode;
	/* L2 must run next, and mustn't decide to exit to L1. */
	bool nested_run_pending;
	/*
	 * Guest pages referred to in vmcs02 with host-physical pointers, so
	 * we must keep them pinned while L2 runs.
	 */
	struct page *apic_access_page;
	struct page *virtual_apic_page;
	struct page *pi_desc_page;
	struct pi_desc *pi_desc;
	bool pi_pending;
	u16 posted_intr_nv;

	unsigned long *msr_bitmap;

	struct hrtimer preemption_timer;
	bool preemption_timer_expired;

	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
	u64 vmcs01_debugctl;

	u16 vpid02;
	u16 last_vpid;

	/*
	 * We only store the "true" versions of the VMX capability MSRs. We
	 * generate the "non-true" versions by setting the must-be-1 bits
	 * according to the SDM.
	 */
	u32 nested_vmx_procbased_ctls_low;
	u32 nested_vmx_procbased_ctls_high;
	u32 nested_vmx_secondary_ctls_low;
	u32 nested_vmx_secondary_ctls_high;
	u32 nested_vmx_pinbased_ctls_low;
	u32 nested_vmx_pinbased_ctls_high;
	u32 nested_vmx_exit_ctls_low;
	u32 nested_vmx_exit_ctls_high;
	u32 nested_vmx_entry_ctls_low;
	u32 nested_vmx_entry_ctls_high;
	u32 nested_vmx_misc_low;
	u32 nested_vmx_misc_high;
	u32 nested_vmx_ept_caps;
	u32 nested_vmx_vpid_caps;
	u64 nested_vmx_basic;
	u64 nested_vmx_cr0_fixed0;
	u64 nested_vmx_cr0_fixed1;
	u64 nested_vmx_cr4_fixed0;
	u64 nested_vmx_cr4_fixed1;
	u64 nested_vmx_vmcs_enum;
	u64 nested_vmx_vmfunc_controls;
};

#define POSTED_INTR_ON  0
#define POSTED_INTR_SN  1

/* Posted-Interrupt Descriptor */
struct pi_desc {
	u32 pir[8];     /* Posted interrupt requested */
	union {
		struct {
				/* bit 256 - Outstanding Notification */
			u16	on	: 1,
				/* bit 257 - Suppress Notification */
				sn	: 1,
				/* bit 271:258 - Reserved */
				rsvd_1	: 14;
				/* bit 279:272 - Notification Vector */
			u8	nv;
				/* bit 287:280 - Reserved */
			u8	rsvd_2;
				/* bit 319:288 - Notification Destination */
			u32	ndst;
		};
		u64 control;
	};
	u32 rsvd[6];
} __aligned(64);

static bool pi_test_and_set_on(struct pi_desc *pi_desc)
{
	return test_and_set_bit(POSTED_INTR_ON,
			(unsigned long *)&pi_desc->control);
}

static bool pi_test_and_clear_on(struct pi_desc *pi_desc)
{
	return test_and_clear_bit(POSTED_INTR_ON,
			(unsigned long *)&pi_desc->control);
}

static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
{
	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
}

static inline void pi_clear_sn(struct pi_desc *pi_desc)
{
	return clear_bit(POSTED_INTR_SN,
			(unsigned long *)&pi_desc->control);
}

static inline void pi_set_sn(struct pi_desc *pi_desc)
{
	return set_bit(POSTED_INTR_SN,
			(unsigned long *)&pi_desc->control);
}

static inline void pi_clear_on(struct pi_desc *pi_desc)
{
	clear_bit(POSTED_INTR_ON,
  		  (unsigned long *)&pi_desc->control);
}

static inline int pi_test_on(struct pi_desc *pi_desc)
{
	return test_bit(POSTED_INTR_ON,
			(unsigned long *)&pi_desc->control);
}

static inline int pi_test_sn(struct pi_desc *pi_desc)
{
	return test_bit(POSTED_INTR_SN,
			(unsigned long *)&pi_desc->control);
}

struct vcpu_vmx {
	struct kvm_vcpu       vcpu;
	unsigned long         host_rsp;
	u8                    fail;
	u32                   exit_intr_info;
	u32                   idt_vectoring_info;
	ulong                 rflags;
	struct shared_msr_entry *guest_msrs;
	int                   nmsrs;
	int                   save_nmsrs;
	unsigned long	      host_idt_base;
#ifdef CONFIG_X86_64
	u64 		      msr_host_kernel_gs_base;
	u64 		      msr_guest_kernel_gs_base;
#endif
	u32 vm_entry_controls_shadow;
	u32 vm_exit_controls_shadow;
	u32 secondary_exec_control;

	/*
	 * loaded_vmcs points to the VMCS currently used in this vcpu. For a
	 * non-nested (L1) guest, it always points to vmcs01. For a nested
	 * guest (L2), it points to a different VMCS.
	 */
	struct loaded_vmcs    vmcs01;
	struct loaded_vmcs   *loaded_vmcs;
	bool                  __launched; /* temporary, used in vmx_vcpu_run */
	struct msr_autoload {
		unsigned nr;
		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
	} msr_autoload;
	struct {
		int           loaded;
		u16           fs_sel, gs_sel, ldt_sel;
#ifdef CONFIG_X86_64
		u16           ds_sel, es_sel;
#endif
		int           gs_ldt_reload_needed;
		int           fs_reload_needed;
		u64           msr_host_bndcfgs;
	} host_state;
	struct {
		int vm86_active;
		ulong save_rflags;
		struct kvm_segment segs[8];
	} rmode;
	struct {
		u32 bitmask; /* 4 bits per segment (1 bit per field) */
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
		} seg[8];
	} segment_cache;
	int vpid;
	bool emulation_required;

	u32 exit_reason;

	/* Posted interrupt descriptor */
	struct pi_desc pi_desc;

	/* Support for a guest hypervisor (nested VMX) */
	struct nested_vmx nested;

	/* Dynamic PLE window. */
	int ple_window;
	bool ple_window_dirty;

	/* Support for PML */
#define PML_ENTITY_NUM		512
	struct page *pml_pg;

	/* apic deadline value in host tsc */
	u64 hv_deadline_tsc;

	u64 current_tsc_ratio;

	u32 host_pkru;

	/*
	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
	 * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
	 * in msr_ia32_feature_control_valid_bits.
	 */
	u64 msr_ia32_feature_control;
	u64 msr_ia32_feature_control_valid_bits;
};

enum segment_cache_field {
	SEG_FIELD_SEL = 0,
	SEG_FIELD_BASE = 1,
	SEG_FIELD_LIMIT = 2,
	SEG_FIELD_AR = 3,

	SEG_FIELD_NR = 4
};

static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
{
	return container_of(vcpu, struct vcpu_vmx, vcpu);
}

static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
	return &(to_vmx(vcpu)->pi_desc);
}

#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
#define FIELD(number, name)	[number] = VMCS12_OFFSET(name)
#define FIELD64(number, name)	[number] = VMCS12_OFFSET(name), \
				[number##_HIGH] = VMCS12_OFFSET(name)+4


static unsigned long shadow_read_only_fields[] = {
	/*
	 * We do NOT shadow fields that are modified when L0
	 * traps and emulates any vmx instruction (e.g. VMPTRLD,
	 * VMXON...) executed by L1.
	 * For example, VM_INSTRUCTION_ERROR is read
	 * by L1 if a vmx instruction fails (part of the error path).
	 * Note the code assumes this logic. If for some reason
	 * we start shadowing these fields then we need to
	 * force a shadow sync when L0 emulates vmx instructions
	 * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified
	 * by nested_vmx_failValid)
	 */
	VM_EXIT_REASON,
	VM_EXIT_INTR_INFO,
	VM_EXIT_INSTRUCTION_LEN,
	IDT_VECTORING_INFO_FIELD,
	IDT_VECTORING_ERROR_CODE,
	VM_EXIT_INTR_ERROR_CODE,
	EXIT_QUALIFICATION,
	GUEST_LINEAR_ADDRESS,
	GUEST_PHYSICAL_ADDRESS
};
static int max_shadow_read_only_fields =
	ARRAY_SIZE(shadow_read_only_fields);

static unsigned long shadow_read_write_fields[] = {
	TPR_THRESHOLD,
	GUEST_RIP,
	GUEST_RSP,
	GUEST_CR0,
	GUEST_CR3,
	GUEST_CR4,
	GUEST_INTERRUPTIBILITY_INFO,
	GUEST_RFLAGS,
	GUEST_CS_SELECTOR,
	GUEST_CS_AR_BYTES,
	GUEST_CS_LIMIT,
	GUEST_CS_BASE,
	GUEST_ES_BASE,
	GUEST_BNDCFGS,
	CR0_GUEST_HOST_MASK,
	CR0_READ_SHADOW,
	CR4_READ_SHADOW,
	TSC_OFFSET,
	EXCEPTION_BITMAP,
	CPU_BASED_VM_EXEC_CONTROL,
	VM_ENTRY_EXCEPTION_ERROR_CODE,
	VM_ENTRY_INTR_INFO_FIELD,
	VM_ENTRY_INSTRUCTION_LEN,
	VM_ENTRY_EXCEPTION_ERROR_CODE,
	HOST_FS_BASE,
	HOST_GS_BASE,
	HOST_FS_SELECTOR,
	HOST_GS_SELECTOR
};
static int max_shadow_read_write_fields =
	ARRAY_SIZE(shadow_read_write_fields);

static const unsigned short vmcs_field_to_offset_table[] = {
	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
	FIELD(POSTED_INTR_NV, posted_intr_nv),
	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
	FIELD(GUEST_SS_SELECTOR, guest_ss_selector),
	FIELD(GUEST_DS_SELECTOR, guest_ds_selector),
	FIELD(GUEST_FS_SELECTOR, guest_fs_selector),
	FIELD(GUEST_GS_SELECTOR, guest_gs_selector),
	FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
	FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
	FIELD(GUEST_INTR_STATUS, guest_intr_status),
	FIELD(GUEST_PML_INDEX, guest_pml_index),
	FIELD(HOST_ES_SELECTOR, host_es_selector),
	FIELD(HOST_CS_SELECTOR, host_cs_selector),
	FIELD(HOST_SS_SELECTOR, host_ss_selector),
	FIELD(HOST_DS_SELECTOR, host_ds_selector),
	FIELD(HOST_FS_SELECTOR, host_fs_selector),
	FIELD(HOST_GS_SELECTOR, host_gs_selector),
	FIELD(HOST_TR_SELECTOR, host_tr_selector),
	FIELD64(IO_BITMAP_A, io_bitmap_a),
	FIELD64(IO_BITMAP_B, io_bitmap_b),
	FIELD64(MSR_BITMAP, msr_bitmap),
	FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
	FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
	FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
	FIELD64(TSC_OFFSET, tsc_offset),
	FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
	FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
	FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr),
	FIELD64(VM_FUNCTION_CONTROL, vm_function_control),
	FIELD64(EPT_POINTER, ept_pointer),
	FIELD64(EOI_EXIT_BITMAP0, eoi_exit_bitmap0),
	FIELD64(EOI_EXIT_BITMAP1, eoi_exit_bitmap1),
	FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
	FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
	FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
	FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
	FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
	FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
	FIELD64(PML_ADDRESS, pml_address),
	FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
	FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
	FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
	FIELD64(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl),
	FIELD64(GUEST_PDPTR0, guest_pdptr0),
	FIELD64(GUEST_PDPTR1, guest_pdptr1),
	FIELD64(GUEST_PDPTR2, guest_pdptr2),
	FIELD64(GUEST_PDPTR3, guest_pdptr3),
	FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
	FIELD64(HOST_IA32_PAT, host_ia32_pat),
	FIELD64(HOST_IA32_EFER, host_ia32_efer),
	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
	FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
	FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
	FIELD(EXCEPTION_BITMAP, exception_bitmap),
	FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask),
	FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match),
	FIELD(CR3_TARGET_COUNT, cr3_target_count),
	FIELD(VM_EXIT_CONTROLS, vm_exit_controls),
	FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count),
	FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count),
	FIELD(VM_ENTRY_CONTROLS, vm_entry_controls),
	FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count),
	FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field),
	FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code),
	FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len),
	FIELD(TPR_THRESHOLD, tpr_threshold),
	FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control),
	FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error),
	FIELD(VM_EXIT_REASON, vm_exit_reason),
	FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info),
	FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code),
	FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field),
	FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code),
	FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len),
	FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info),
	FIELD(GUEST_ES_LIMIT, guest_es_limit),
	FIELD(GUEST_CS_LIMIT, guest_cs_limit),
	FIELD(GUEST_SS_LIMIT, guest_ss_limit),
	FIELD(GUEST_DS_LIMIT, guest_ds_limit),
	FIELD(GUEST_FS_LIMIT, guest_fs_limit),
	FIELD(GUEST_GS_LIMIT, guest_gs_limit),
	FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit),
	FIELD(GUEST_TR_LIMIT, guest_tr_limit),
	FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit),
	FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit),
	FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes),
	FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes),
	FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes),
	FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes),
	FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes),
	FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes),
	FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes),
	FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes),
	FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info),
	FIELD(GUEST_ACTIVITY_STATE, guest_activity_state),
	FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs),
	FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs),
	FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value),
	FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask),
	FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask),
	FIELD(CR0_READ_SHADOW, cr0_read_shadow),
	FIELD(CR4_READ_SHADOW, cr4_read_shadow),
	FIELD(CR3_TARGET_VALUE0, cr3_target_value0),
	FIELD(CR3_TARGET_VALUE1, cr3_target_value1),
	FIELD(CR3_TARGET_VALUE2, cr3_target_value2),
	FIELD(CR3_TARGET_VALUE3, cr3_target_value3),
	FIELD(EXIT_QUALIFICATION, exit_qualification),
	FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address),
	FIELD(GUEST_CR0, guest_cr0),
	FIELD(GUEST_CR3, guest_cr3),
	FIELD(GUEST_CR4, guest_cr4),
	FIELD(GUEST_ES_BASE, guest_es_base),
	FIELD(GUEST_CS_BASE, guest_cs_base),
	FIELD(GUEST_SS_BASE, guest_ss_base),
	FIELD(GUEST_DS_BASE, guest_ds_base),
	FIELD(GUEST_FS_BASE, guest_fs_base),
	FIELD(GUEST_GS_BASE, guest_gs_base),
	FIELD(GUEST_LDTR_BASE, guest_ldtr_base),
	FIELD(GUEST_TR_BASE, guest_tr_base),
	FIELD(GUEST_GDTR_BASE, guest_gdtr_base),
	FIELD(GUEST_IDTR_BASE, guest_idtr_base),
	FIELD(GUEST_DR7, guest_dr7),
	FIELD(GUEST_RSP, guest_rsp),
	FIELD(GUEST_RIP, guest_rip),
	FIELD(GUEST_RFLAGS, guest_rflags),
	FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions),
	FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp),
	FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip),
	FIELD(HOST_CR0, host_cr0),
	FIELD(HOST_CR3, host_cr3),
	FIELD(HOST_CR4, host_cr4),
	FIELD(HOST_FS_BASE, host_fs_base),
	FIELD(HOST_GS_BASE, host_gs_base),
	FIELD(HOST_TR_BASE, host_tr_base),
	FIELD(HOST_GDTR_BASE, host_gdtr_base),
	FIELD(HOST_IDTR_BASE, host_idtr_base),
	FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp),
	FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip),
	FIELD(HOST_RSP, host_rsp),
	FIELD(HOST_RIP, host_rip),
};

static inline short vmcs_field_to_offset(unsigned long field)
{
	BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);

	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
	    vmcs_field_to_offset_table[field] == 0)
		return -ENOENT;

	return vmcs_field_to_offset_table[field];
}

static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
{
	return to_vmx(vcpu)->nested.cached_vmcs12;
}

static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu);
static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
static bool vmx_xsaves_supported(void);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
static void vmx_set_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
static void vmx_get_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
static bool guest_state_valid(struct kvm_vcpu *vcpu);
static u32 vmx_segment_access_rights(struct kvm_segment *var);
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
static int alloc_identity_pagetable(struct kvm *kvm);
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
					    u16 error_code);

static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
/*
 * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed
 * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
 */
static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);

/*
 * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
 * can find which vCPU should be waken up.
 */
static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);

enum {
	VMX_IO_BITMAP_A,
	VMX_IO_BITMAP_B,
	VMX_MSR_BITMAP_LEGACY,
	VMX_MSR_BITMAP_LONGMODE,
	VMX_MSR_BITMAP_LEGACY_X2APIC_APICV,
	VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV,
	VMX_MSR_BITMAP_LEGACY_X2APIC,
	VMX_MSR_BITMAP_LONGMODE_X2APIC,
	VMX_VMREAD_BITMAP,
	VMX_VMWRITE_BITMAP,
	VMX_BITMAP_NR
};

static unsigned long *vmx_bitmap[VMX_BITMAP_NR];

#define vmx_io_bitmap_a                      (vmx_bitmap[VMX_IO_BITMAP_A])
#define vmx_io_bitmap_b                      (vmx_bitmap[VMX_IO_BITMAP_B])
#define vmx_msr_bitmap_legacy                (vmx_bitmap[VMX_MSR_BITMAP_LEGACY])
#define vmx_msr_bitmap_longmode              (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE])
#define vmx_msr_bitmap_legacy_x2apic_apicv   (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV])
#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV])
#define vmx_msr_bitmap_legacy_x2apic         (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC])
#define vmx_msr_bitmap_longmode_x2apic       (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC])
#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])

static bool cpu_has_load_ia32_efer;
static bool cpu_has_load_perf_global_ctrl;

static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);

static struct vmcs_config {
	int size;
	int order;
	u32 basic_cap;
	u32 revision_id;
	u32 pin_based_exec_ctrl;
	u32 cpu_based_exec_ctrl;
	u32 cpu_based_2nd_exec_ctrl;
	u32 vmexit_ctrl;
	u32 vmentry_ctrl;
} vmcs_config;

static struct vmx_capability {
	u32 ept;
	u32 vpid;
} vmx_capability;

#define VMX_SEGMENT_FIELD(seg)					\
	[VCPU_SREG_##seg] = {                                   \
		.selector = GUEST_##seg##_SELECTOR,		\
		.base = GUEST_##seg##_BASE,		   	\
		.limit = GUEST_##seg##_LIMIT,		   	\
		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
	}

static const struct kvm_vmx_segment_field {
	unsigned selector;
	unsigned base;
	unsigned limit;
	unsigned ar_bytes;
} kvm_vmx_segment_fields[] = {
	VMX_SEGMENT_FIELD(CS),
	VMX_SEGMENT_FIELD(DS),
	VMX_SEGMENT_FIELD(ES),
	VMX_SEGMENT_FIELD(FS),
	VMX_SEGMENT_FIELD(GS),
	VMX_SEGMENT_FIELD(SS),
	VMX_SEGMENT_FIELD(TR),
	VMX_SEGMENT_FIELD(LDTR),
};

static u64 host_efer;

static void ept_save_pdptrs(struct kvm_vcpu *vcpu);

/*
 * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it
 * away by decrementing the array size.
 */
static const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};

static inline bool is_exception_n(u32 intr_info, u8 vector)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
}

static inline bool is_debug(u32 intr_info)
{
	return is_exception_n(intr_info, DB_VECTOR);
}

static inline bool is_breakpoint(u32 intr_info)
{
	return is_exception_n(intr_info, BP_VECTOR);
}

static inline bool is_page_fault(u32 intr_info)
{
	return is_exception_n(intr_info, PF_VECTOR);
}

static inline bool is_no_device(u32 intr_info)
{
	return is_exception_n(intr_info, NM_VECTOR);
}

static inline bool is_invalid_opcode(u32 intr_info)
{
	return is_exception_n(intr_info, UD_VECTOR);
}

static inline bool is_external_interrupt(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}

static inline bool is_machine_check(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}

static inline bool cpu_has_vmx_msr_bitmap(void)
{
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}

static inline bool cpu_has_vmx_tpr_shadow(void)
{
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}

static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu)
{
	return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu);
}

static inline bool cpu_has_secondary_exec_ctrls(void)
{
	return vmcs_config.cpu_based_exec_ctrl &
		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
}

static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
}

static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
}

static inline bool cpu_has_vmx_apic_register_virt(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_APIC_REGISTER_VIRT;
}

static inline bool cpu_has_vmx_virtual_intr_delivery(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
}

/*
 * Comment's format: document - errata name - stepping - processor name.
 * Refer from
 * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
 */
static u32 vmx_preemption_cpu_tfms[] = {
/* 323344.pdf - BA86   - D0 - Xeon 7500 Series */
0x000206E6,
/* 323056.pdf - AAX65  - C2 - Xeon L3406 */
/* 322814.pdf - AAT59  - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
/* 322911.pdf - AAU65  - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
0x00020652,
/* 322911.pdf - AAU65  - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
0x00020655,
/* 322373.pdf - AAO95  - B1 - Xeon 3400 Series */
/* 322166.pdf - AAN92  - B1 - i7-800 and i5-700 Desktop */
/*
 * 320767.pdf - AAP86  - B1 -
 * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
 */
0x000106E5,
/* 321333.pdf - AAM126 - C0 - Xeon 3500 */
0x000106A0,
/* 321333.pdf - AAM126 - C1 - Xeon 3500 */
0x000106A1,
/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
0x000106A4,
 /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
 /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
 /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
0x000106A5,
};

static inline bool cpu_has_broken_vmx_preemption_timer(void)
{
	u32 eax = cpuid_eax(0x00000001), i;

	/* Clear the reserved bits */
	eax &= ~(0x3U << 14 | 0xfU << 28);
	for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++)
		if (eax == vmx_preemption_cpu_tfms[i])
			return true;

	return false;
}

static inline bool cpu_has_vmx_preemption_timer(void)
{
	return vmcs_config.pin_based_exec_ctrl &
		PIN_BASED_VMX_PREEMPTION_TIMER;
}

static inline bool cpu_has_vmx_posted_intr(void)
{
	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
}

static inline bool cpu_has_vmx_apicv(void)
{
	return cpu_has_vmx_apic_register_virt() &&
		cpu_has_vmx_virtual_intr_delivery() &&
		cpu_has_vmx_posted_intr();
}

static inline bool cpu_has_vmx_flexpriority(void)
{
	return cpu_has_vmx_tpr_shadow() &&
		cpu_has_vmx_virtualize_apic_accesses();
}

static inline bool cpu_has_vmx_ept_execute_only(void)
{
	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}

static inline bool cpu_has_vmx_ept_2m_page(void)
{
	return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
}

static inline bool cpu_has_vmx_ept_1g_page(void)
{
	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
}

static inline bool cpu_has_vmx_ept_4levels(void)
{
	return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
}

static inline bool cpu_has_vmx_ept_mt_wb(void)
{
	return vmx_capability.ept & VMX_EPTP_WB_BIT;
}

static inline bool cpu_has_vmx_ept_5levels(void)
{
	return vmx_capability.ept & VMX_EPT_PAGE_WALK_5_BIT;
}

static inline bool cpu_has_vmx_ept_ad_bits(void)
{
	return vmx_capability.ept & VMX_EPT_AD_BIT;
}

static inline bool cpu_has_vmx_invept_context(void)
{
	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_invept_global(void)
{
	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}

static inline bool cpu_has_vmx_invvpid_single(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_invvpid_global(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_invvpid(void)
{
	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
}

static inline bool cpu_has_vmx_ept(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_EPT;
}

static inline bool cpu_has_vmx_unrestricted_guest(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_UNRESTRICTED_GUEST;
}

static inline bool cpu_has_vmx_ple(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}

static inline bool cpu_has_vmx_basic_inout(void)
{
	return	(((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT);
}

static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
{
	return flexpriority_enabled && lapic_in_kernel(vcpu);
}

static inline bool cpu_has_vmx_vpid(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_VPID;
}

static inline bool cpu_has_vmx_rdtscp(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_RDTSCP;
}

static inline bool cpu_has_vmx_invpcid(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_INVPCID;
}

static inline bool cpu_has_vmx_wbinvd_exit(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_WBINVD_EXITING;
}

static inline bool cpu_has_vmx_shadow_vmcs(void)
{
	u64 vmx_msr;
	rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
	/* check if the cpu supports writing r/o exit information fields */
	if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
		return false;

	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_SHADOW_VMCS;
}

static inline bool cpu_has_vmx_pml(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
}

static inline bool cpu_has_vmx_tsc_scaling(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_TSC_SCALING;
}

static inline bool cpu_has_vmx_vmfunc(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_VMFUNC;
}

static inline bool report_flexpriority(void)
{
	return flexpriority_enabled;
}

static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
{
	return vmx_misc_cr3_count(to_vmx(vcpu)->nested.nested_vmx_misc_low);
}

static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
	return vmcs12->cpu_based_vm_exec_control & bit;
}

static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
{
	return (vmcs12->cpu_based_vm_exec_control &
			CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
		(vmcs12->secondary_vm_exec_control & bit);
}

static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
{
	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
}

static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
{
	return vmcs12->pin_based_vm_exec_control &
		PIN_BASED_VMX_PREEMPTION_TIMER;
}

static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
}

static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
}

static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
}

static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
}

static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID);
}

static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT);
}

static inline bool nested_cpu_has_vid(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
}

static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
{
	return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
}

static inline bool nested_cpu_has_vmfunc(struct vmcs12 *vmcs12)
{
	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VMFUNC);
}

static inline bool nested_cpu_has_eptp_switching(struct vmcs12 *vmcs12)
{
	return nested_cpu_has_vmfunc(vmcs12) &&
		(vmcs12->vm_function_control &
		 VMX_VMFUNC_EPTP_SWITCHING);
}

static inline bool is_nmi(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
}

static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
			      u32 exit_intr_info,
			      unsigned long exit_qualification);
static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
			struct vmcs12 *vmcs12,
			u32 reason, unsigned long qualification);

static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
	int i;

	for (i = 0; i < vmx->nmsrs; ++i)
		if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
			return i;
	return -1;
}

static inline void __invvpid(int ext, u16 vpid, gva_t gva)
{
    struct {
	u64 vpid : 16;
	u64 rsvd : 48;
	u64 gva;
    } operand = { vpid, 0, gva };

    asm volatile (__ex(ASM_VMX_INVVPID)
		  /* CF==1 or ZF==1 --> rc = -1 */
		  "; ja 1f ; ud2 ; 1:"
		  : : "a"(&operand), "c"(ext) : "cc", "memory");
}

static inline void __invept(int ext, u64 eptp, gpa_t gpa)
{
	struct {
		u64 eptp, gpa;
	} operand = {eptp, gpa};

	asm volatile (__ex(ASM_VMX_INVEPT)
			/* CF==1 or ZF==1 --> rc = -1 */
			"; ja 1f ; ud2 ; 1:\n"
			: : "a" (&operand), "c" (ext) : "cc", "memory");
}

static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
	int i;

	i = __find_msr_index(vmx, msr);
	if (i >= 0)
		return &vmx->guest_msrs[i];
	return NULL;
}

static void vmcs_clear(struct vmcs *vmcs)
{
	u64 phys_addr = __pa(vmcs);
	u8 error;

	asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) "; setna %0"
		      : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
		      : "cc", "memory");
	if (error)
		printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
		       vmcs, phys_addr);
}

static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
{
	vmcs_clear(loaded_vmcs->vmcs);
	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
		vmcs_clear(loaded_vmcs->shadow_vmcs);
	loaded_vmcs->cpu = -1;
	loaded_vmcs->launched = 0;
}

static void vmcs_load(struct vmcs *vmcs)
{
	u64 phys_addr = __pa(vmcs);
	u8 error;

	asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0"
			: "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
			: "cc", "memory");
	if (error)
		printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
		       vmcs, phys_addr);
}

#ifdef CONFIG_KEXEC_CORE
/*
 * This bitmap is used to indicate whether the vmclear
 * operation is enabled on all cpus. All disabled by
 * default.
 */
static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;

static inline void crash_enable_local_vmclear(int cpu)
{
	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
}

static inline void crash_disable_local_vmclear(int cpu)
{
	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
}

static inline int crash_local_vmclear_enabled(int cpu)
{
	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
}

static void crash_vmclear_local_loaded_vmcss(void)
{
	int cpu = raw_smp_processor_id();
	struct loaded_vmcs *v;

	if (!crash_local_vmclear_enabled(cpu))
		return;

	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
			    loaded_vmcss_on_cpu_link)
		vmcs_clear(v->vmcs);
}
#else
static inline void crash_enable_local_vmclear(int cpu) { }
static inline void crash_disable_local_vmclear(int cpu) { }
#endif /* CONFIG_KEXEC_CORE */

static void __loaded_vmcs_clear(void *arg)
{
	struct loaded_vmcs *loaded_vmcs = arg;
	int cpu = raw_smp_processor_id();

	if (loaded_vmcs->cpu != cpu)
		return; /* vcpu migration can race with cpu offline */
	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
		per_cpu(current_vmcs, cpu) = NULL;
	crash_disable_local_vmclear(cpu);
	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);

	/*
	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
	 * is before setting loaded_vmcs->vcpu to -1 which is done in
	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
	 * then adds the vmcs into percpu list before it is deleted.
	 */
	smp_wmb();

	loaded_vmcs_init(loaded_vmcs);
	crash_enable_local_vmclear(cpu);
}

static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
{
	int cpu = loaded_vmcs->cpu;

	if (cpu != -1)
		smp_call_function_single(cpu,
			 __loaded_vmcs_clear, loaded_vmcs, 1);
}

static inline void vpid_sync_vcpu_single(int vpid)
{
	if (vpid == 0)
		return;

	if (cpu_has_vmx_invvpid_single())
		__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0);
}

static inline void vpid_sync_vcpu_global(void)
{
	if (cpu_has_vmx_invvpid_global())
		__invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
}

static inline void vpid_sync_context(int vpid)
{
	if (cpu_has_vmx_invvpid_single())
		vpid_sync_vcpu_single(vpid);
	else
		vpid_sync_vcpu_global();
}

static inline void ept_sync_global(void)
{
	if (cpu_has_vmx_invept_global())
		__invept(VMX_EPT_EXTENT_GLOBAL, 0, 0);
}

static inline void ept_sync_context(u64 eptp)
{
	if (enable_ept) {
		if (cpu_has_vmx_invept_context())
			__invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0);
		else
			ept_sync_global();
	}
}

static __always_inline void vmcs_check16(unsigned long field)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
			 "16-bit accessor invalid for 64-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
			 "16-bit accessor invalid for 64-bit high field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
			 "16-bit accessor invalid for 32-bit high field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
			 "16-bit accessor invalid for natural width field");
}

static __always_inline void vmcs_check32(unsigned long field)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
			 "32-bit accessor invalid for 16-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
			 "32-bit accessor invalid for natural width field");
}

static __always_inline void vmcs_check64(unsigned long field)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
			 "64-bit accessor invalid for 16-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
			 "64-bit accessor invalid for 64-bit high field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
			 "64-bit accessor invalid for 32-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
			 "64-bit accessor invalid for natural width field");
}

static __always_inline void vmcs_checkl(unsigned long field)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
			 "Natural width accessor invalid for 16-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
			 "Natural width accessor invalid for 64-bit field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
			 "Natural width accessor invalid for 64-bit high field");
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
			 "Natural width accessor invalid for 32-bit field");
}

static __always_inline unsigned long __vmcs_readl(unsigned long field)
{
	unsigned long value;

	asm volatile (__ex_clear(ASM_VMX_VMREAD_RDX_RAX, "%0")
		      : "=a"(value) : "d"(field) : "cc");
	return value;
}

static __always_inline u16 vmcs_read16(unsigned long field)
{
	vmcs_check16(field);
	return __vmcs_readl(field);
}

static __always_inline u32 vmcs_read32(unsigned long field)
{
	vmcs_check32(field);
	return __vmcs_readl(field);
}

static __always_inline u64 vmcs_read64(unsigned long field)
{
	vmcs_check64(field);
#ifdef CONFIG_X86_64
	return __vmcs_readl(field);
#else
	return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32);
#endif
}

static __always_inline unsigned long vmcs_readl(unsigned long field)
{
	vmcs_checkl(field);
	return __vmcs_readl(field);
}

static noinline void vmwrite_error(unsigned long field, unsigned long value)
{
	printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
	       field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
	dump_stack();
}

static __always_inline void __vmcs_writel(unsigned long field, unsigned long value)
{
	u8 error;

	asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) "; setna %0"
		       : "=q"(error) : "a"(value), "d"(field) : "cc");
	if (unlikely(error))
		vmwrite_error(field, value);
}

static __always_inline void vmcs_write16(unsigned long field, u16 value)
{
	vmcs_check16(field);
	__vmcs_writel(field, value);
}

static __always_inline void vmcs_write32(unsigned long field, u32 value)
{
	vmcs_check32(field);
	__vmcs_writel(field, value);
}

static __always_inline void vmcs_write64(unsigned long field, u64 value)
{
	vmcs_check64(field);
	__vmcs_writel(field, value);
#ifndef CONFIG_X86_64
	asm volatile ("");
	__vmcs_writel(field+1, value >> 32);
#endif
}

static __always_inline void vmcs_writel(unsigned long field, unsigned long value)
{
	vmcs_checkl(field);
	__vmcs_writel(field, value);
}

static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
			 "vmcs_clear_bits does not support 64-bit fields");
	__vmcs_writel(field, __vmcs_readl(field) & ~mask);
}

static __always_inline void vmcs_set_bits(unsigned long field, u32 mask)
{
        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
			 "vmcs_set_bits does not support 64-bit fields");
	__vmcs_writel(field, __vmcs_readl(field) | mask);
}

static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx)
{
	vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS);
}

static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val)
{
	vmcs_write32(VM_ENTRY_CONTROLS, val);
	vmx->vm_entry_controls_shadow = val;
}

static inline void vm_entry_controls_set(struct vcpu_vmx *vmx, u32 val)
{
	if (vmx->vm_entry_controls_shadow != val)
		vm_entry_controls_init(vmx, val);
}

static inline u32 vm_entry_controls_get(struct vcpu_vmx *vmx)
{
	return vmx->vm_entry_controls_shadow;
}


static inline void vm_entry_controls_setbit(struct vcpu_vmx *vmx, u32 val)
{
	vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) | val);
}

static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val)
{
	vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val);
}

static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx)
{
	vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS);
}

static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val)
{
	vmcs_write32(VM_EXIT_CONTROLS, val);
	vmx->vm_exit_controls_shadow = val;
}

static inline void vm_exit_controls_set(struct vcpu_vmx *vmx, u32 val)
{
	if (vmx->vm_exit_controls_shadow != val)
		vm_exit_controls_init(vmx, val);
}

static inline u32 vm_exit_controls_get(struct vcpu_vmx *vmx)
{
	return vmx->vm_exit_controls_shadow;
}


static inline void vm_exit_controls_setbit(struct vcpu_vmx *vmx, u32 val)
{
	vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) | val);
}

static inline void vm_exit_controls_clearbit(struct vcpu_vmx *vmx, u32 val)
{
	vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) & ~val);
}

static void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
{
	vmx->segment_cache.bitmask = 0;
}

static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
				       unsigned field)
{
	bool ret;
	u32 mask = 1 << (seg * SEG_FIELD_NR + field);

	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
		vmx->segment_cache.bitmask = 0;
	}
	ret = vmx->segment_cache.bitmask & mask;
	vmx->segment_cache.bitmask |= mask;
	return ret;
}

static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg)
{
	u16 *p = &vmx->segment_cache.seg[seg].selector;

	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL))
		*p = vmcs_read16(kvm_vmx_segment_fields[seg].selector);
	return *p;
}

static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg)
{
	ulong *p = &vmx->segment_cache.seg[seg].base;

	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE))
		*p = vmcs_readl(kvm_vmx_segment_fields[seg].base);
	return *p;
}

static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg)
{
	u32 *p = &vmx->segment_cache.seg[seg].limit;

	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT))
		*p = vmcs_read32(kvm_vmx_segment_fields[seg].limit);
	return *p;
}

static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg)
{
	u32 *p = &vmx->segment_cache.seg[seg].ar;

	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR))
		*p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes);
	return *p;
}

static void update_exception_bitmap(struct kvm_vcpu *vcpu)
{
	u32 eb;

	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
	if ((vcpu->guest_debug &
	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
		eb |= 1u << BP_VECTOR;
	if (to_vmx(vcpu)->rmode.vm86_active)
		eb = ~0;
	if (enable_ept)
		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */

	/* When we are running a nested L2 guest and L1 specified for it a
	 * certain exception bitmap, we must trap the same exceptions and pass
	 * them to L1. When running L2, we will only handle the exceptions
	 * specified above if L1 did not want them.
	 */
	if (is_guest_mode(vcpu))
		eb |= get_vmcs12(vcpu)->exception_bitmap;

	vmcs_write32(EXCEPTION_BITMAP, eb);
}

static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
		unsigned long entry, unsigned long exit)
{
	vm_entry_controls_clearbit(vmx, entry);
	vm_exit_controls_clearbit(vmx, exit);
}

static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
	unsigned i;
	struct msr_autoload *m = &vmx->msr_autoload;

	switch (msr) {
	case MSR_EFER:
		if (cpu_has_load_ia32_efer) {
			clear_atomic_switch_msr_special(vmx,
					VM_ENTRY_LOAD_IA32_EFER,
					VM_EXIT_LOAD_IA32_EFER);
			return;
		}
		break;
	case MSR_CORE_PERF_GLOBAL_CTRL:
		if (cpu_has_load_perf_global_ctrl) {
			clear_atomic_switch_msr_special(vmx,
					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
			return;
		}
		break;
	}

	for (i = 0; i < m->nr; ++i)
		if (m->guest[i].index == msr)
			break;

	if (i == m->nr)
		return;
	--m->nr;
	m->guest[i] = m->guest[m->nr];
	m->host[i] = m->host[m->nr];
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}

static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
		unsigned long entry, unsigned long exit,
		unsigned long guest_val_vmcs, unsigned long host_val_vmcs,
		u64 guest_val, u64 host_val)
{
	vmcs_write64(guest_val_vmcs, guest_val);
	vmcs_write64(host_val_vmcs, host_val);
	vm_entry_controls_setbit(vmx, entry);
	vm_exit_controls_setbit(vmx, exit);
}

static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
				  u64 guest_val, u64 host_val)
{
	unsigned i;
	struct msr_autoload *m = &vmx->msr_autoload;

	switch (msr) {
	case MSR_EFER:
		if (cpu_has_load_ia32_efer) {
			add_atomic_switch_msr_special(vmx,
					VM_ENTRY_LOAD_IA32_EFER,
					VM_EXIT_LOAD_IA32_EFER,
					GUEST_IA32_EFER,
					HOST_IA32_EFER,
					guest_val, host_val);
			return;
		}
		break;
	case MSR_CORE_PERF_GLOBAL_CTRL:
		if (cpu_has_load_perf_global_ctrl) {
			add_atomic_switch_msr_special(vmx,
					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
					GUEST_IA32_PERF_GLOBAL_CTRL,
					HOST_IA32_PERF_GLOBAL_CTRL,
					guest_val, host_val);
			return;
		}
		break;
	case MSR_IA32_PEBS_ENABLE:
		/* PEBS needs a quiescent period after being disabled (to write
		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
		 * provide that period, so a CPU could write host's record into
		 * guest's memory.
		 */
		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
	}

	for (i = 0; i < m->nr; ++i)
		if (m->guest[i].index == msr)
			break;

	if (i == NR_AUTOLOAD_MSRS) {
		printk_once(KERN_WARNING "Not enough msr switch entries. "
				"Can't add msr %x\n", msr);
		return;
	} else if (i == m->nr) {
		++m->nr;
		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
	}

	m->guest[i].index = msr;
	m->guest[i].value = guest_val;
	m->host[i].index = msr;
	m->host[i].value = host_val;
}

static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
	u64 guest_efer = vmx->vcpu.arch.efer;
	u64 ignore_bits = 0;

	if (!enable_ept) {
		/*
		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
		 * host CPUID is more efficient than testing guest CPUID
		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
		 */
		if (boot_cpu_has(X86_FEATURE_SMEP))
			guest_efer |= EFER_NX;
		else if (!(guest_efer & EFER_NX))
			ignore_bits |= EFER_NX;
	}

	/*
	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
	 */
	ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
	ignore_bits |= EFER_LMA | EFER_LME;
	/* SCE is meaningful only in long mode on Intel */
	if (guest_efer & EFER_LMA)
		ignore_bits &= ~(u64)EFER_SCE;
#endif

	clear_atomic_switch_msr(vmx, MSR_EFER);

	/*
	 * On EPT, we can't emulate NX, so we must switch EFER atomically.
	 * On CPUs that support "load IA32_EFER", always switch EFER
	 * atomically, since it's faster than switching it manually.
	 */
	if (cpu_has_load_ia32_efer ||
	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
		if (!(guest_efer & EFER_LMA))
			guest_efer &= ~EFER_LME;
		if (guest_efer != host_efer)
			add_atomic_switch_msr(vmx, MSR_EFER,
					      guest_efer, host_efer);
		return false;
	} else {
		guest_efer &= ~ignore_bits;
		guest_efer |= host_efer & ignore_bits;

		vmx->guest_msrs[efer_offset].data = guest_efer;
		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;

		return true;
	}
}

#ifdef CONFIG_X86_32
/*
 * On 32-bit kernels, VM exits still load the FS and GS bases from the
 * VMCS rather than the segment table.  KVM uses this helper to figure
 * out the current bases to poke them into the VMCS before entry.
 */
static unsigned long segment_base(u16 selector)
{
	struct desc_struct *table;
	unsigned long v;

	if (!(selector & ~SEGMENT_RPL_MASK))
		return 0;

	table = get_current_gdt_ro();

	if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) {
		u16 ldt_selector = kvm_read_ldt();

		if (!(ldt_selector & ~SEGMENT_RPL_MASK))
			return 0;

		table = (struct desc_struct *)segment_base(ldt_selector);
	}
	v = get_desc_base(&table[selector >> 3]);
	return v;
}
#endif

static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int i;

	if (vmx->host_state.loaded)
		return;

	vmx->host_state.loaded = 1;
	/*
	 * Set host fs and gs selectors.  Unfortunately, 22.2.3 does not
	 * allow segment selectors with cpl > 0 or ti == 1.
	 */
	vmx->host_state.ldt_sel = kvm_read_ldt();
	vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
	savesegment(fs, vmx->host_state.fs_sel);
	if (!(vmx->host_state.fs_sel & 7)) {
		vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
		vmx->host_state.fs_reload_needed = 0;
	} else {
		vmcs_write16(HOST_FS_SELECTOR, 0);
		vmx->host_state.fs_reload_needed = 1;
	}
	savesegment(gs, vmx->host_state.gs_sel);
	if (!(vmx->host_state.gs_sel & 7))
		vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel);
	else {
		vmcs_write16(HOST_GS_SELECTOR, 0);
		vmx->host_state.gs_ldt_reload_needed = 1;
	}

#ifdef CONFIG_X86_64
	savesegment(ds, vmx->host_state.ds_sel);
	savesegment(es, vmx->host_state.es_sel);
#endif

#ifdef CONFIG_X86_64
	vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE));
	vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE));
#else
	vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel));
	vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel));
#endif

#ifdef CONFIG_X86_64
	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
	if (is_long_mode(&vmx->vcpu))
		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
	if (boot_cpu_has(X86_FEATURE_MPX))
		rdmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
	for (i = 0; i < vmx->save_nmsrs; ++i)
		kvm_set_shared_msr(vmx->guest_msrs[i].index,
				   vmx->guest_msrs[i].data,
				   vmx->guest_msrs[i].mask);
}

static void __vmx_load_host_state(struct vcpu_vmx *vmx)
{
	if (!vmx->host_state.loaded)
		return;

	++vmx->vcpu.stat.host_state_reload;
	vmx->host_state.loaded = 0;
#ifdef CONFIG_X86_64
	if (is_long_mode(&vmx->vcpu))
		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
	if (vmx->host_state.gs_ldt_reload_needed) {
		kvm_load_ldt(vmx->host_state.ldt_sel);
#ifdef CONFIG_X86_64
		load_gs_index(vmx->host_state.gs_sel);
#else
		loadsegment(gs, vmx->host_state.gs_sel);
#endif
	}
	if (vmx->host_state.fs_reload_needed)
		loadsegment(fs, vmx->host_state.fs_sel);
#ifdef CONFIG_X86_64
	if (unlikely(vmx->host_state.ds_sel | vmx->host_state.es_sel)) {
		loadsegment(ds, vmx->host_state.ds_sel);
		loadsegment(es, vmx->host_state.es_sel);
	}
#endif
	invalidate_tss_limit();
#ifdef CONFIG_X86_64
	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
#endif
	if (vmx->host_state.msr_host_bndcfgs)
		wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
	load_fixmap_gdt(raw_smp_processor_id());
}

static void vmx_load_host_state(struct vcpu_vmx *vmx)
{
	preempt_disable();
	__vmx_load_host_state(vmx);
	preempt_enable();
}

static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
	struct pi_desc old, new;
	unsigned int dest;

	/*
	 * In case of hot-plug or hot-unplug, we may have to undo
	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
	 * always keep PI.NDST up to date for simplicity: it makes the
	 * code easier, and CPU migration is not a fast path.
	 */
	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
		return;

	/*
	 * First handle the simple case where no cmpxchg is necessary; just
	 * allow posting non-urgent interrupts.
	 *
	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
	 * expects the VCPU to be on the blocked_vcpu_list that matches
	 * PI.NDST.
	 */
	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
	    vcpu->cpu == cpu) {
		pi_clear_sn(pi_desc);
		return;
	}

	/* The full case.  */
	do {
		old.control = new.control = pi_desc->control;

		dest = cpu_physical_id(cpu);

		if (x2apic_enabled())
			new.ndst = dest;
		else
			new.ndst = (dest << 8) & 0xFF00;

		new.sn = 0;
	} while (cmpxchg64(&pi_desc->control, old.control,
			   new.control) != old.control);
}

static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
{
	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}

/*
 * Switches to specified vcpu, until a matching vcpu_put(), but assumes
 * vcpu mutex is already taken.
 */
static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;

	if (!already_loaded) {
		loaded_vmcs_clear(vmx->loaded_vmcs);
		local_irq_disable();
		crash_disable_local_vmclear(cpu);

		/*
		 * Read loaded_vmcs->cpu should be before fetching
		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
		 * See the comments in __loaded_vmcs_clear().
		 */
		smp_rmb();

		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
			 &per_cpu(loaded_vmcss_on_cpu, cpu));
		crash_enable_local_vmclear(cpu);
		local_irq_enable();
	}

	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
		vmcs_load(vmx->loaded_vmcs->vmcs);
	}

	if (!already_loaded) {
		void *gdt = get_current_gdt_ro();
		unsigned long sysenter_esp;

		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);

		/*
		 * Linux uses per-cpu TSS and GDT, so set these when switching
		 * processors.  See 22.2.4.
		 */
		vmcs_writel(HOST_TR_BASE,
			    (unsigned long)this_cpu_ptr(&cpu_tss));
		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */

		/*
		 * VM exits change the host TR limit to 0x67 after a VM
		 * exit.  This is okay, since 0x67 covers everything except
		 * the IO bitmap and have have code to handle the IO bitmap
		 * being lost after a VM exit.
		 */
		BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67);

		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */

		vmx->loaded_vmcs->cpu = cpu;
	}

	/* Setup TSC multiplier */
	if (kvm_has_tsc_control &&
	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
		decache_tsc_multiplier(vmx);

	vmx_vcpu_pi_load(vcpu, cpu);
	vmx->host_pkru = read_pkru();
}

static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
{
	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);

	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
		!kvm_vcpu_apicv_active(vcpu))
		return;

	/* Set SN when the vCPU is preempted */
	if (vcpu->preempted)
		pi_set_sn(pi_desc);
}

static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
	vmx_vcpu_pi_put(vcpu);

	__vmx_load_host_state(to_vmx(vcpu));
}

static bool emulation_required(struct kvm_vcpu *vcpu)
{
	return emulate_invalid_guest_state && !guest_state_valid(vcpu);
}

static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);

/*
 * Return the cr0 value that a nested guest would read. This is a combination
 * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by
 * its hypervisor (cr0_read_shadow).
 */
static inline unsigned long nested_read_cr0(struct vmcs12 *fields)
{
	return (fields->guest_cr0 & ~fields->cr0_guest_host_mask) |
		(fields->cr0_read_shadow & fields->cr0_guest_host_mask);
}
static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
{
	return (fields->guest_cr4 & ~fields->cr4_guest_host_mask) |
		(fields->cr4_read_shadow & fields->cr4_guest_host_mask);
}

static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
	unsigned long rflags, save_rflags;

	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
		rflags = vmcs_readl(GUEST_RFLAGS);
		if (to_vmx(vcpu)->rmode.vm86_active) {
			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
		}
		to_vmx(vcpu)->rflags = rflags;
	}
	return to_vmx(vcpu)->rflags;
}

static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
	unsigned long old_rflags = vmx_get_rflags(vcpu);

	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
	to_vmx(vcpu)->rflags = rflags;
	if (to_vmx(vcpu)->rmode.vm86_active) {
		to_vmx(vcpu)->rmode.save_rflags = rflags;
		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
	}
	vmcs_writel(GUEST_RFLAGS, rflags);

	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
}

static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
{
	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
	int ret = 0;

	if (interruptibility & GUEST_INTR_STATE_STI)
		ret |= KVM_X86_SHADOW_INT_STI;
	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
		ret |= KVM_X86_SHADOW_INT_MOV_SS;

	return ret;
}

static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
	u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
	u32 interruptibility = interruptibility_old;

	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);

	if (mask & KVM_X86_SHADOW_INT_MOV_SS)
		interruptibility |= GUEST_INTR_STATE_MOV_SS;
	else if (mask & KVM_X86_SHADOW_INT_STI)
		interruptibility |= GUEST_INTR_STATE_STI;

	if ((interruptibility != interruptibility_old))
		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
}

static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
	unsigned long rip;

	rip = kvm_rip_read(vcpu);
	rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
	kvm_rip_write(vcpu, rip);

	/* skipping an emulated instruction also counts */
	vmx_set_interrupt_shadow(vcpu, 0);
}

static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
					       unsigned long exit_qual)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	unsigned int nr = vcpu->arch.exception.nr;
	u32 intr_info = nr | INTR_INFO_VALID_MASK;

	if (vcpu->arch.exception.has_error_code) {
		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
	}

	if (kvm_exception_is_soft(nr))
		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);
}

/*
 * KVM wants to inject page-faults which it got to the guest. This function
 * checks whether in a nested guest, we need to inject them to L1 or L2.
 */
static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	unsigned int nr = vcpu->arch.exception.nr;

	if (nr == PF_VECTOR) {
		if (vcpu->arch.exception.nested_apf) {
			*exit_qual = vcpu->arch.apf.nested_apf_token;
			return 1;
		}
		/*
		 * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
		 * The fix is to add the ancillary datum (CR2 or DR6) to structs
		 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
		 * can be written only when inject_pending_event runs.  This should be
		 * conditional on a new capability---if the capability is disabled,
		 * kvm_multiple_exception would write the ancillary information to
		 * CR2 or DR6, for backwards ABI-compatibility.
		 */
		if (nested_vmx_is_page_fault_vmexit(vmcs12,
						    vcpu->arch.exception.error_code)) {
			*exit_qual = vcpu->arch.cr2;
			return 1;
		}
	} else {
		if (vmcs12->exception_bitmap & (1u << nr)) {
			if (nr == DB_VECTOR)
				*exit_qual = vcpu->arch.dr6;
			else
				*exit_qual = 0;
			return 1;
		}
	}

	return 0;
}

static void vmx_queue_exception(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned nr = vcpu->arch.exception.nr;
	bool has_error_code = vcpu->arch.exception.has_error_code;
	u32 error_code = vcpu->arch.exception.error_code;
	u32 intr_info = nr | INTR_INFO_VALID_MASK;

	if (has_error_code) {
		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
	}

	if (vmx->rmode.vm86_active) {
		int inc_eip = 0;
		if (kvm_exception_is_soft(nr))
			inc_eip = vcpu->arch.event_exit_inst_len;
		if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE)
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}

	if (kvm_exception_is_soft(nr)) {
		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
			     vmx->vcpu.arch.event_exit_inst_len);
		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
	} else
		intr_info |= INTR_TYPE_HARD_EXCEPTION;

	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
}

static bool vmx_rdtscp_supported(void)
{
	return cpu_has_vmx_rdtscp();
}

static bool vmx_invpcid_supported(void)
{
	return cpu_has_vmx_invpcid() && enable_ept;
}

/*
 * Swap MSR entry in host/guest MSR entry array.
 */
static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
{
	struct shared_msr_entry tmp;

	tmp = vmx->guest_msrs[to];
	vmx->guest_msrs[to] = vmx->guest_msrs[from];
	vmx->guest_msrs[from] = tmp;
}

static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
{
	unsigned long *msr_bitmap;

	if (is_guest_mode(vcpu))
		msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
	else if (cpu_has_secondary_exec_ctrls() &&
		 (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
		if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) {
			if (is_long_mode(vcpu))
				msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv;
			else
				msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv;
		} else {
			if (is_long_mode(vcpu))
				msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
			else
				msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
		}
	} else {
		if (is_long_mode(vcpu))
			msr_bitmap = vmx_msr_bitmap_longmode;
		else
			msr_bitmap = vmx_msr_bitmap_legacy;
	}

	vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
}

/*
 * Set up the vmcs to automatically save and restore system
 * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
 * mode, as fiddling with msrs is very expensive.
 */
static void setup_msrs(struct vcpu_vmx *vmx)
{
	int save_nmsrs, index;

	save_nmsrs = 0;
#ifdef CONFIG_X86_64
	if (is_long_mode(&vmx->vcpu)) {
		index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
		if (index >= 0)
			move_msr_up(vmx, index, save_nmsrs++);
		index = __find_msr_index(vmx, MSR_LSTAR);
		if (index >= 0)
			move_msr_up(vmx, index, save_nmsrs++);
		index = __find_msr_index(vmx, MSR_CSTAR);
		if (index >= 0)
			move_msr_up(vmx, index, save_nmsrs++);
		index = __find_msr_index(vmx, MSR_TSC_AUX);
		if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
			move_msr_up(vmx, index, save_nmsrs++);
		/*
		 * MSR_STAR is only needed on long mode guests, and only
		 * if efer.sce is enabled.
		 */
		index = __find_msr_index(vmx, MSR_STAR);
		if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE))
			move_msr_up(vmx, index, save_nmsrs++);
	}
#endif
	index = __find_msr_index(vmx, MSR_EFER);
	if (index >= 0 && update_transition_efer(vmx, index))
		move_msr_up(vmx, index, save_nmsrs++);

	vmx->save_nmsrs = save_nmsrs;

	if (cpu_has_vmx_msr_bitmap())
		vmx_set_msr_bitmap(&vmx->vcpu);
}

/*
 * reads and returns guest's timestamp counter "register"
 * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
 * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
 */
static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
{
	u64 host_tsc, tsc_offset;

	host_tsc = rdtsc();
	tsc_offset = vmcs_read64(TSC_OFFSET);
	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
}

/*
 * writes 'offset' into guest's timestamp counter offset register
 */
static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
	if (is_guest_mode(vcpu)) {
		/*
		 * We're here if L1 chose not to trap WRMSR to TSC. According
		 * to the spec, this should set L1's TSC; The offset that L1
		 * set for L2 remains unchanged, and still needs to be added
		 * to the newly set TSC to get L2's TSC.
		 */
		struct vmcs12 *vmcs12;
		/* recalculate vmcs02.TSC_OFFSET: */
		vmcs12 = get_vmcs12(vcpu);
		vmcs_write64(TSC_OFFSET, offset +
			(nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ?
			 vmcs12->tsc_offset : 0));
	} else {
		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
					   vmcs_read64(TSC_OFFSET), offset);
		vmcs_write64(TSC_OFFSET, offset);
	}
}

/*
 * nested_vmx_allowed() checks whether a guest should be allowed to use VMX
 * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for
 * all guests if the "nested" module option is off, and can also be disabled
 * for a single guest by disabling its VMX cpuid bit.
 */
static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
{
	return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
}

/*
 * 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().
 */
static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
{
	/*
	 * 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_exit_reflected() will not pass related exits to L1.
	 * These rules have exceptions below.
	 */

	/* pin-based controls */
	rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
		vmx->nested.nested_vmx_pinbased_ctls_low,
		vmx->nested.nested_vmx_pinbased_ctls_high);
	vmx->nested.nested_vmx_pinbased_ctls_low |=
		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
	vmx->nested.nested_vmx_pinbased_ctls_high &=
		PIN_BASED_EXT_INTR_MASK |
		PIN_BASED_NMI_EXITING |
		PIN_BASED_VIRTUAL_NMIS;
	vmx->nested.nested_vmx_pinbased_ctls_high |=
		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
		PIN_BASED_VMX_PREEMPTION_TIMER;
	if (kvm_vcpu_apicv_active(&vmx->vcpu))
		vmx->nested.nested_vmx_pinbased_ctls_high |=
			PIN_BASED_POSTED_INTR;

	/* exit controls */
	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
		vmx->nested.nested_vmx_exit_ctls_low,
		vmx->nested.nested_vmx_exit_ctls_high);
	vmx->nested.nested_vmx_exit_ctls_low =
		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;

	vmx->nested.nested_vmx_exit_ctls_high &=
#ifdef CONFIG_X86_64
		VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
	vmx->nested.nested_vmx_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;

	if (kvm_mpx_supported())
		vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;

	/* We support free control of debug control saving. */
	vmx->nested.nested_vmx_exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;

	/* entry controls */
	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
		vmx->nested.nested_vmx_entry_ctls_low,
		vmx->nested.nested_vmx_entry_ctls_high);
	vmx->nested.nested_vmx_entry_ctls_low =
		VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
	vmx->nested.nested_vmx_entry_ctls_high &=
#ifdef CONFIG_X86_64
		VM_ENTRY_IA32E_MODE |
#endif
		VM_ENTRY_LOAD_IA32_PAT;
	vmx->nested.nested_vmx_entry_ctls_high |=
		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
	if (kvm_mpx_supported())
		vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;

	/* We support free control of debug control loading. */
	vmx->nested.nested_vmx_entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;

	/* cpu-based controls */
	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
		vmx->nested.nested_vmx_procbased_ctls_low,
		vmx->nested.nested_vmx_procbased_ctls_high);
	vmx->nested.nested_vmx_procbased_ctls_low =
		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
	vmx->nested.nested_vmx_procbased_ctls_high &=
		CPU_BASED_VIRTUAL_INTR_PENDING |
		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
		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.
	 */
	vmx->nested.nested_vmx_procbased_ctls_high |=
		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
		CPU_BASED_USE_MSR_BITMAPS;

	/* We support free control of CR3 access interception. */
	vmx->nested.nested_vmx_procbased_ctls_low &=
		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);

	/*
	 * secondary cpu-based controls.  Do not include those that
	 * depend on CPUID bits, they are added later by vmx_cpuid_update.
	 */
	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
		vmx->nested.nested_vmx_secondary_ctls_low,
		vmx->nested.nested_vmx_secondary_ctls_high);
	vmx->nested.nested_vmx_secondary_ctls_low = 0;
	vmx->nested.nested_vmx_secondary_ctls_high &=
		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
		SECONDARY_EXEC_DESC |
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
		SECONDARY_EXEC_APIC_REGISTER_VIRT |
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
		SECONDARY_EXEC_WBINVD_EXITING;

	if (enable_ept) {
		/* nested EPT: emulate EPT also to L1 */
		vmx->nested.nested_vmx_secondary_ctls_high |=
			SECONDARY_EXEC_ENABLE_EPT;
		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
		if (cpu_has_vmx_ept_execute_only())
			vmx->nested.nested_vmx_ept_caps |=
				VMX_EPT_EXECUTE_ONLY_BIT;
		vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept;
		vmx->nested.nested_vmx_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) {
			vmx->nested.nested_vmx_secondary_ctls_high |=
				SECONDARY_EXEC_ENABLE_PML;
			vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
		}
	} else
		vmx->nested.nested_vmx_ept_caps = 0;

	if (cpu_has_vmx_vmfunc()) {
		vmx->nested.nested_vmx_secondary_ctls_high |=
			SECONDARY_EXEC_ENABLE_VMFUNC;
		/*
		 * Advertise EPTP switching unconditionally
		 * since we emulate it
		 */
		vmx->nested.nested_vmx_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) {
		vmx->nested.nested_vmx_secondary_ctls_high |=
			SECONDARY_EXEC_ENABLE_VPID;
		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
			VMX_VPID_EXTENT_SUPPORTED_MASK;
	} else
		vmx->nested.nested_vmx_vpid_caps = 0;

	if (enable_unrestricted_guest)
		vmx->nested.nested_vmx_secondary_ctls_high |=
			SECONDARY_EXEC_UNRESTRICTED_GUEST;

	/* miscellaneous data */
	rdmsr(MSR_IA32_VMX_MISC,
		vmx->nested.nested_vmx_misc_low,
		vmx->nested.nested_vmx_misc_high);
	vmx->nested.nested_vmx_misc_low &= VMX_MISC_SAVE_EFER_LMA;
	vmx->nested.nested_vmx_misc_low |=
		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
		VMX_MISC_ACTIVITY_HLT;
	vmx->nested.nested_vmx_misc_high = 0;

	/*
	 * 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.
	 */
	vmx->nested.nested_vmx_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())
		vmx->nested.nested_vmx_basic |= VMX_BASIC_INOUT;

	/*
	 * 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
	vmx->nested.nested_vmx_cr0_fixed0 = VMXON_CR0_ALWAYSON;
	vmx->nested.nested_vmx_cr4_fixed0 = VMXON_CR4_ALWAYSON;

	/* These MSRs specify bits which the guest must keep fixed off. */
	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, vmx->nested.nested_vmx_cr0_fixed1);
	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, vmx->nested.nested_vmx_cr4_fixed1);

	/* highest index: VMX_PREEMPTION_TIMER_VALUE */
	vmx->nested.nested_vmx_vmcs_enum = 0x2e;
}

/*
 * if fixed0[i] == 1: val[i] must be 1
 * if fixed1[i] == 0: val[i] must be 0
 */
static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
{
	return ((val & fixed1) | fixed0) == val;
}

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 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 = vmx->nested.nested_vmx_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.nested_vmx_basic = data;
	return 0;
}

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

	switch (msr_index) {
	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
		lowp = &vmx->nested.nested_vmx_pinbased_ctls_low;
		highp = &vmx->nested.nested_vmx_pinbased_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
		lowp = &vmx->nested.nested_vmx_procbased_ctls_low;
		highp = &vmx->nested.nested_vmx_procbased_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
		lowp = &vmx->nested.nested_vmx_exit_ctls_low;
		highp = &vmx->nested.nested_vmx_exit_ctls_high;
		break;
	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
		lowp = &vmx->nested.nested_vmx_entry_ctls_low;
		highp = &vmx->nested.nested_vmx_entry_ctls_high;
		break;
	case MSR_IA32_VMX_PROCBASED_CTLS2:
		lowp = &vmx->nested.nested_vmx_secondary_ctls_low;
		highp = &vmx->nested.nested_vmx_secondary_ctls_high;
		break;
	default:
		BUG();
	}

	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;

	*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_misc = vmx_control_msr(vmx->nested.nested_vmx_misc_low,
				   vmx->nested.nested_vmx_misc_high);

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

	if ((vmx->nested.nested_vmx_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.nested_vmx_misc_low = data;
	vmx->nested.nested_vmx_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_ept_vpid_cap = vmx_control_msr(vmx->nested.nested_vmx_ept_caps,
					   vmx->nested.nested_vmx_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.nested_vmx_ept_caps = data;
	vmx->nested.nested_vmx_vpid_caps = data >> 32;
	return 0;
}

static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
{
	u64 *msr;

	switch (msr_index) {
	case MSR_IA32_VMX_CR0_FIXED0:
		msr = &vmx->nested.nested_vmx_cr0_fixed0;
		break;
	case MSR_IA32_VMX_CR4_FIXED0:
		msr = &vmx->nested.nested_vmx_cr4_fixed0;
		break;
	default:
		BUG();
	}

	/*
	 * 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;

	*msr = data;
	return 0;
}

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

	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.nested_vmx_vmcs_enum = data;
		return 0;
	default:
		/*
		 * The rest of the VMX capability MSRs do not support restore.
		 */
		return -EINVAL;
	}
}

/* Returns 0 on success, non-0 otherwise. */
static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	switch (msr_index) {
	case MSR_IA32_VMX_BASIC:
		*pdata = vmx->nested.nested_vmx_basic;
		break;
	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
	case MSR_IA32_VMX_PINBASED_CTLS:
		*pdata = vmx_control_msr(
			vmx->nested.nested_vmx_pinbased_ctls_low,
			vmx->nested.nested_vmx_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(
			vmx->nested.nested_vmx_procbased_ctls_low,
			vmx->nested.nested_vmx_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(
			vmx->nested.nested_vmx_exit_ctls_low,
			vmx->nested.nested_vmx_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(
			vmx->nested.nested_vmx_entry_ctls_low,
			vmx->nested.nested_vmx_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(
			vmx->nested.nested_vmx_misc_low,
			vmx->nested.nested_vmx_misc_high);
		break;
	case MSR_IA32_VMX_CR0_FIXED0:
		*pdata = vmx->nested.nested_vmx_cr0_fixed0;
		break;
	case MSR_IA32_VMX_CR0_FIXED1:
		*pdata = vmx->nested.nested_vmx_cr0_fixed1;
		break;
	case MSR_IA32_VMX_CR4_FIXED0:
		*pdata = vmx->nested.nested_vmx_cr4_fixed0;
		break;
	case MSR_IA32_VMX_CR4_FIXED1:
		*pdata = vmx->nested.nested_vmx_cr4_fixed1;
		break;
	case MSR_IA32_VMX_VMCS_ENUM:
		*pdata = vmx->nested.nested_vmx_vmcs_enum;
		break;
	case MSR_IA32_VMX_PROCBASED_CTLS2:
		*pdata = vmx_control_msr(
			vmx->nested.nested_vmx_secondary_ctls_low,
			vmx->nested.nested_vmx_secondary_ctls_high);
		break;
	case MSR_IA32_VMX_EPT_VPID_CAP:
		*pdata = vmx->nested.nested_vmx_ept_caps |
			((u64)vmx->nested.nested_vmx_vpid_caps << 32);
		break;
	case MSR_IA32_VMX_VMFUNC:
		*pdata = vmx->nested.nested_vmx_vmfunc_controls;
		break;
	default:
		return 1;
	}

	return 0;
}

static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
						 uint64_t val)
{
	uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;

	return !(val & ~valid_bits);
}

/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	struct shared_msr_entry *msr;

	switch (msr_info->index) {
#ifdef CONFIG_X86_64
	case MSR_FS_BASE:
		msr_info->data = vmcs_readl(GUEST_FS_BASE);
		break;
	case MSR_GS_BASE:
		msr_info->data = vmcs_readl(GUEST_GS_BASE);
		break;
	case MSR_KERNEL_GS_BASE:
		vmx_load_host_state(to_vmx(vcpu));
		msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
		break;
#endif
	case MSR_EFER:
		return kvm_get_msr_common(vcpu, msr_info);
	case MSR_IA32_TSC:
		msr_info->data = guest_read_tsc(vcpu);
		break;
	case MSR_IA32_SYSENTER_CS:
		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
		break;
	case MSR_IA32_SYSENTER_EIP:
		msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP);
		break;
	case MSR_IA32_SYSENTER_ESP:
		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
		break;
	case MSR_IA32_BNDCFGS:
		if (!kvm_mpx_supported() ||
		    (!msr_info->host_initiated &&
		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
			return 1;
		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
		break;
	case MSR_IA32_MCG_EXT_CTL:
		if (!msr_info->host_initiated &&
		    !(to_vmx(vcpu)->msr_ia32_feature_control &
		      FEATURE_CONTROL_LMCE))
			return 1;
		msr_info->data = vcpu->arch.mcg_ext_ctl;
		break;
	case MSR_IA32_FEATURE_CONTROL:
		msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control;
		break;
	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
		if (!nested_vmx_allowed(vcpu))
			return 1;
		return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data);
	case MSR_IA32_XSS:
		if (!vmx_xsaves_supported())
			return 1;
		msr_info->data = vcpu->arch.ia32_xss;
		break;
	case MSR_TSC_AUX:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
			return 1;
		/* Otherwise falls through */
	default:
		msr = find_msr_entry(to_vmx(vcpu), msr_info->index);
		if (msr) {
			msr_info->data = msr->data;
			break;
		}
		return kvm_get_msr_common(vcpu, msr_info);
	}

	return 0;
}

static void vmx_leave_nested(struct kvm_vcpu *vcpu);

/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct shared_msr_entry *msr;
	int ret = 0;
	u32 msr_index = msr_info->index;
	u64 data = msr_info->data;

	switch (msr_index) {
	case MSR_EFER:
		ret = kvm_set_msr_common(vcpu, msr_info);
		break;
#ifdef CONFIG_X86_64
	case MSR_FS_BASE:
		vmx_segment_cache_clear(vmx);
		vmcs_writel(GUEST_FS_BASE, data);
		break;
	case MSR_GS_BASE:
		vmx_segment_cache_clear(vmx);
		vmcs_writel(GUEST_GS_BASE, data);
		break;
	case MSR_KERNEL_GS_BASE:
		vmx_load_host_state(vmx);
		vmx->msr_guest_kernel_gs_base = data;
		break;
#endif
	case MSR_IA32_SYSENTER_CS:
		vmcs_write32(GUEST_SYSENTER_CS, data);
		break;
	case MSR_IA32_SYSENTER_EIP:
		vmcs_writel(GUEST_SYSENTER_EIP, data);
		break;
	case MSR_IA32_SYSENTER_ESP:
		vmcs_writel(GUEST_SYSENTER_ESP, data);
		break;
	case MSR_IA32_BNDCFGS:
		if (!kvm_mpx_supported() ||
		    (!msr_info->host_initiated &&
		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
			return 1;
		if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
		    (data & MSR_IA32_BNDCFGS_RSVD))
			return 1;
		vmcs_write64(GUEST_BNDCFGS, data);
		break;
	case MSR_IA32_TSC:
		kvm_write_tsc(vcpu, msr_info);
		break;
	case MSR_IA32_CR_PAT:
		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
				return 1;
			vmcs_write64(GUEST_IA32_PAT, data);
			vcpu->arch.pat = data;
			break;
		}
		ret = kvm_set_msr_common(vcpu, msr_info);
		break;
	case MSR_IA32_TSC_ADJUST:
		ret = kvm_set_msr_common(vcpu, msr_info);
		break;
	case MSR_IA32_MCG_EXT_CTL:
		if ((!msr_info->host_initiated &&
		     !(to_vmx(vcpu)->msr_ia32_feature_control &
		       FEATURE_CONTROL_LMCE)) ||
		    (data & ~MCG_EXT_CTL_LMCE_EN))
			return 1;
		vcpu->arch.mcg_ext_ctl = data;
		break;
	case MSR_IA32_FEATURE_CONTROL:
		if (!vmx_feature_control_msr_valid(vcpu, data) ||
		    (to_vmx(vcpu)->msr_ia32_feature_control &
		     FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
			return 1;
		vmx->msr_ia32_feature_control = data;
		if (msr_info->host_initiated && data == 0)
			vmx_leave_nested(vcpu);
		break;
	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
		if (!msr_info->host_initiated)
			return 1; /* they are read-only */
		if (!nested_vmx_allowed(vcpu))
			return 1;
		return vmx_set_vmx_msr(vcpu, msr_index, data);
	case MSR_IA32_XSS:
		if (!vmx_xsaves_supported())
			return 1;
		/*
		 * The only supported bit as of Skylake is bit 8, but
		 * it is not supported on KVM.
		 */
		if (data != 0)
			return 1;
		vcpu->arch.ia32_xss = data;
		if (vcpu->arch.ia32_xss != host_xss)
			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
				vcpu->arch.ia32_xss, host_xss);
		else
			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
		break;
	case MSR_TSC_AUX:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
			return 1;
		/* Check reserved bit, higher 32 bits should be zero */
		if ((data >> 32) != 0)
			return 1;
		/* Otherwise falls through */
	default:
		msr = find_msr_entry(vmx, msr_index);
		if (msr) {
			u64 old_msr_data = msr->data;
			msr->data = data;
			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
				preempt_disable();
				ret = kvm_set_shared_msr(msr->index, msr->data,
							 msr->mask);
				preempt_enable();
				if (ret)
					msr->data = old_msr_data;
			}
			break;
		}
		ret = kvm_set_msr_common(vcpu, msr_info);
	}

	return ret;
}

static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
	switch (reg) {
	case VCPU_REGS_RSP:
		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
		break;
	case VCPU_REGS_RIP:
		vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
		break;
	case VCPU_EXREG_PDPTR:
		if (enable_ept)
			ept_save_pdptrs(vcpu);
		break;
	default:
		break;
	}
}

static __init int cpu_has_kvm_support(void)
{
	return cpu_has_vmx();
}

static __init int vmx_disabled_by_bios(void)
{
	u64 msr;

	rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
	if (msr & FEATURE_CONTROL_LOCKED) {
		/* launched w/ TXT and VMX disabled */
		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
			&& tboot_enabled())
			return 1;
		/* launched w/o TXT and VMX only enabled w/ TXT */
		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
			&& (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
			&& !tboot_enabled()) {
			printk(KERN_WARNING "kvm: disable TXT in the BIOS or "
				"activate TXT before enabling KVM\n");
			return 1;
		}
		/* launched w/o TXT and VMX disabled */
		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
			&& !tboot_enabled())
			return 1;
	}

	return 0;
}

static void kvm_cpu_vmxon(u64 addr)
{
	cr4_set_bits(X86_CR4_VMXE);
	intel_pt_handle_vmx(1);

	asm volatile (ASM_VMX_VMXON_RAX
			: : "a"(&addr), "m"(addr)
			: "memory", "cc");
}

static int hardware_enable(void)
{
	int cpu = raw_smp_processor_id();
	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
	u64 old, test_bits;

	if (cr4_read_shadow() & X86_CR4_VMXE)
		return -EBUSY;

	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));

	/*
	 * Now we can enable the vmclear operation in kdump
	 * since the loaded_vmcss_on_cpu list on this cpu
	 * has been initialized.
	 *
	 * Though the cpu is not in VMX operation now, there
	 * is no problem to enable the vmclear operation
	 * for the loaded_vmcss_on_cpu list is empty!
	 */
	crash_enable_local_vmclear(cpu);

	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);

	test_bits = FEATURE_CONTROL_LOCKED;
	test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
	if (tboot_enabled())
		test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;

	if ((old & test_bits) != test_bits) {
		/* enable and lock */
		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
	}
	kvm_cpu_vmxon(phys_addr);
	ept_sync_global();

	return 0;
}

static void vmclear_local_loaded_vmcss(void)
{
	int cpu = raw_smp_processor_id();
	struct loaded_vmcs *v, *n;

	list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
				 loaded_vmcss_on_cpu_link)
		__loaded_vmcs_clear(v);
}


/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
 * tricks.
 */
static void kvm_cpu_vmxoff(void)
{
	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");

	intel_pt_handle_vmx(0);
	cr4_clear_bits(X86_CR4_VMXE);
}

static void hardware_disable(void)
{
	vmclear_local_loaded_vmcss();
	kvm_cpu_vmxoff();
}

static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
				      u32 msr, u32 *result)
{
	u32 vmx_msr_low, vmx_msr_high;
	u32 ctl = ctl_min | ctl_opt;

	rdmsr(msr, vmx_msr_low, vmx_msr_high);

	ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */
	ctl |= vmx_msr_low;  /* bit == 1 in low word  ==> must be one  */

	/* Ensure minimum (required) set of control bits are supported. */
	if (ctl_min & ~ctl)
		return -EIO;

	*result = ctl;
	return 0;
}

static __init bool allow_1_setting(u32 msr, u32 ctl)
{
	u32 vmx_msr_low, vmx_msr_high;

	rdmsr(msr, vmx_msr_low, vmx_msr_high);
	return vmx_msr_high & ctl;
}

static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
{
	u32 vmx_msr_low, vmx_msr_high;
	u32 min, opt, min2, opt2;
	u32 _pin_based_exec_control = 0;
	u32 _cpu_based_exec_control = 0;
	u32 _cpu_based_2nd_exec_control = 0;
	u32 _vmexit_control = 0;
	u32 _vmentry_control = 0;

	min = CPU_BASED_HLT_EXITING |
#ifdef CONFIG_X86_64
	      CPU_BASED_CR8_LOAD_EXITING |
	      CPU_BASED_CR8_STORE_EXITING |
#endif
	      CPU_BASED_CR3_LOAD_EXITING |
	      CPU_BASED_CR3_STORE_EXITING |
	      CPU_BASED_USE_IO_BITMAPS |
	      CPU_BASED_MOV_DR_EXITING |
	      CPU_BASED_USE_TSC_OFFSETING |
	      CPU_BASED_INVLPG_EXITING |
	      CPU_BASED_RDPMC_EXITING;

	if (!kvm_mwait_in_guest())
		min |= CPU_BASED_MWAIT_EXITING |
			CPU_BASED_MONITOR_EXITING;

	opt = CPU_BASED_TPR_SHADOW |
	      CPU_BASED_USE_MSR_BITMAPS |
	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
				&_cpu_based_exec_control) < 0)
		return -EIO;
#ifdef CONFIG_X86_64
	if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
		_cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
					   ~CPU_BASED_CR8_STORE_EXITING;
#endif
	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
		min2 = 0;
		opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
			SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
			SECONDARY_EXEC_WBINVD_EXITING |
			SECONDARY_EXEC_ENABLE_VPID |
			SECONDARY_EXEC_ENABLE_EPT |
			SECONDARY_EXEC_UNRESTRICTED_GUEST |
			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
			SECONDARY_EXEC_RDTSCP |
			SECONDARY_EXEC_ENABLE_INVPCID |
			SECONDARY_EXEC_APIC_REGISTER_VIRT |
			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
			SECONDARY_EXEC_SHADOW_VMCS |
			SECONDARY_EXEC_XSAVES |
			SECONDARY_EXEC_RDSEED |
			SECONDARY_EXEC_RDRAND |
			SECONDARY_EXEC_ENABLE_PML |
			SECONDARY_EXEC_TSC_SCALING |
			SECONDARY_EXEC_ENABLE_VMFUNC;
		if (adjust_vmx_controls(min2, opt2,
					MSR_IA32_VMX_PROCBASED_CTLS2,
					&_cpu_based_2nd_exec_control) < 0)
			return -EIO;
	}
#ifndef CONFIG_X86_64
	if (!(_cpu_based_2nd_exec_control &
				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
		_cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
#endif

	if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
		_cpu_based_2nd_exec_control &= ~(
				SECONDARY_EXEC_APIC_REGISTER_VIRT |
				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
				SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);

	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
		   enabled */
		_cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
					     CPU_BASED_CR3_STORE_EXITING |
					     CPU_BASED_INVLPG_EXITING);
		rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
		      vmx_capability.ept, vmx_capability.vpid);
	}

	min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
#ifdef CONFIG_X86_64
	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
#endif
	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
		VM_EXIT_CLEAR_BNDCFGS;
	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
				&_vmexit_control) < 0)
		return -EIO;

	min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING |
		PIN_BASED_VIRTUAL_NMIS;
	opt = PIN_BASED_POSTED_INTR | PIN_BASED_VMX_PREEMPTION_TIMER;
	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
				&_pin_based_exec_control) < 0)
		return -EIO;

	if (cpu_has_broken_vmx_preemption_timer())
		_pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
	if (!(_cpu_based_2nd_exec_control &
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
		_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;

	min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
	opt = VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS;
	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
				&_vmentry_control) < 0)
		return -EIO;

	rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);

	/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
	if ((vmx_msr_high & 0x1fff) > PAGE_SIZE)
		return -EIO;

#ifdef CONFIG_X86_64
	/* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */
	if (vmx_msr_high & (1u<<16))
		return -EIO;
#endif

	/* Require Write-Back (WB) memory type for VMCS accesses. */
	if (((vmx_msr_high >> 18) & 15) != 6)
		return -EIO;

	vmcs_conf->size = vmx_msr_high & 0x1fff;
	vmcs_conf->order = get_order(vmcs_conf->size);
	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
	vmcs_conf->revision_id = vmx_msr_low;

	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
	vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control;
	vmcs_conf->vmexit_ctrl         = _vmexit_control;
	vmcs_conf->vmentry_ctrl        = _vmentry_control;

	cpu_has_load_ia32_efer =
		allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
				VM_ENTRY_LOAD_IA32_EFER)
		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
				   VM_EXIT_LOAD_IA32_EFER);

	cpu_has_load_perf_global_ctrl =
		allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
				   VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);

	/*
	 * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
	 * but due to errata below it can't be used. Workaround is to use
	 * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
	 *
	 * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
	 *
	 * AAK155             (model 26)
	 * AAP115             (model 30)
	 * AAT100             (model 37)
	 * BC86,AAY89,BD102   (model 44)
	 * BA97               (model 46)
	 *
	 */
	if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) {
		switch (boot_cpu_data.x86_model) {
		case 26:
		case 30:
		case 37:
		case 44:
		case 46:
			cpu_has_load_perf_global_ctrl = false;
			printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
					"does not work properly. Using workaround\n");
			break;
		default:
			break;
		}
	}

	if (boot_cpu_has(X86_FEATURE_XSAVES))
		rdmsrl(MSR_IA32_XSS, host_xss);

	return 0;
}

static struct vmcs *alloc_vmcs_cpu(int cpu)
{
	int node = cpu_to_node(cpu);
	struct page *pages;
	struct vmcs *vmcs;

	pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
	if (!pages)
		return NULL;
	vmcs = page_address(pages);
	memset(vmcs, 0, vmcs_config.size);
	vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
	return vmcs;
}

static struct vmcs *alloc_vmcs(void)
{
	return alloc_vmcs_cpu(raw_smp_processor_id());
}

static void free_vmcs(struct vmcs *vmcs)
{
	free_pages((unsigned long)vmcs, vmcs_config.order);
}

/*
 * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded
 */
static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
{
	if (!loaded_vmcs->vmcs)
		return;
	loaded_vmcs_clear(loaded_vmcs);
	free_vmcs(loaded_vmcs->vmcs);
	loaded_vmcs->vmcs = NULL;
	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
}

static void free_kvm_area(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		free_vmcs(per_cpu(vmxarea, cpu));
		per_cpu(vmxarea, cpu) = NULL;
	}
}

enum vmcs_field_type {
	VMCS_FIELD_TYPE_U16 = 0,
	VMCS_FIELD_TYPE_U64 = 1,
	VMCS_FIELD_TYPE_U32 = 2,
	VMCS_FIELD_TYPE_NATURAL_WIDTH = 3
};

static inline int vmcs_field_type(unsigned long field)
{
	if (0x1 & field)	/* the *_HIGH fields are all 32 bit */
		return VMCS_FIELD_TYPE_U32;
	return (field >> 13) & 0x3 ;
}

static inline int vmcs_field_readonly(unsigned long field)
{
	return (((field >> 10) & 0x3) == 1);
}

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

	/* No checks for read only fields yet */

	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
		switch (shadow_read_write_fields[i]) {
		case GUEST_BNDCFGS:
			if (!kvm_mpx_supported())
				continue;
			break;
		default:
			break;
		}

		if (j < i)
			shadow_read_write_fields[j] =
				shadow_read_write_fields[i];
		j++;
	}
	max_shadow_read_write_fields = j;

	/* shadowed fields guest access without vmexit */
	for (i = 0; i < max_shadow_read_write_fields; i++) {
		unsigned long field = shadow_read_write_fields[i];

		clear_bit(field, vmx_vmwrite_bitmap);
		clear_bit(field, vmx_vmread_bitmap);
		if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) {
			clear_bit(field + 1, vmx_vmwrite_bitmap);
			clear_bit(field + 1, vmx_vmread_bitmap);
		}
	}
	for (i = 0; i < max_shadow_read_only_fields; i++) {
		unsigned long field = shadow_read_only_fields[i];

		clear_bit(field, vmx_vmread_bitmap);
		if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64)
			clear_bit(field + 1, vmx_vmread_bitmap);
	}
}

static __init int alloc_kvm_area(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct vmcs *vmcs;

		vmcs = alloc_vmcs_cpu(cpu);
		if (!vmcs) {
			free_kvm_area();
			return -ENOMEM;
		}

		per_cpu(vmxarea, cpu) = vmcs;
	}
	return 0;
}

static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
		struct kvm_segment *save)
{
	if (!emulate_invalid_guest_state) {
		/*
		 * CS and SS RPL should be equal during guest entry according
		 * to VMX spec, but in reality it is not always so. Since vcpu
		 * is in the middle of the transition from real mode to
		 * protected mode it is safe to assume that RPL 0 is a good
		 * default value.
		 */
		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
			save->selector &= ~SEGMENT_RPL_MASK;
		save->dpl = save->selector & SEGMENT_RPL_MASK;
		save->s = 1;
	}
	vmx_set_segment(vcpu, save, seg);
}

static void enter_pmode(struct kvm_vcpu *vcpu)
{
	unsigned long flags;
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * Update real mode segment cache. It may be not up-to-date if sement
	 * register was written while vcpu was in a guest mode.
	 */
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);

	vmx->rmode.vm86_active = 0;

	vmx_segment_cache_clear(vmx);

	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);

	flags = vmcs_readl(GUEST_RFLAGS);
	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
	flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
	vmcs_writel(GUEST_RFLAGS, flags);

	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
			(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));

	update_exception_bitmap(vcpu);

	fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
	fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
	fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
}

static void fix_rmode_seg(int seg, struct kvm_segment *save)
{
	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
	struct kvm_segment var = *save;

	var.dpl = 0x3;
	if (seg == VCPU_SREG_CS)
		var.type = 0x3;

	if (!emulate_invalid_guest_state) {
		var.selector = var.base >> 4;
		var.base = var.base & 0xffff0;
		var.limit = 0xffff;
		var.g = 0;
		var.db = 0;
		var.present = 1;
		var.s = 1;
		var.l = 0;
		var.unusable = 0;
		var.type = 0x3;
		var.avl = 0;
		if (save->base & 0xf)
			printk_once(KERN_WARNING "kvm: segment base is not "
					"paragraph aligned when entering "
					"protected mode (seg=%d)", seg);
	}

	vmcs_write16(sf->selector, var.selector);
	vmcs_writel(sf->base, var.base);
	vmcs_write32(sf->limit, var.limit);
	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
}

static void enter_rmode(struct kvm_vcpu *vcpu)
{
	unsigned long flags;
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);

	vmx->rmode.vm86_active = 1;

	/*
	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
	 * vcpu. Warn the user that an update is overdue.
	 */
	if (!vcpu->kvm->arch.tss_addr)
		printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be "
			     "called before entering vcpu\n");

	vmx_segment_cache_clear(vmx);

	vmcs_writel(GUEST_TR_BASE, vcpu->kvm->arch.tss_addr);
	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);

	flags = vmcs_readl(GUEST_RFLAGS);
	vmx->rmode.save_rflags = flags;

	flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;

	vmcs_writel(GUEST_RFLAGS, flags);
	vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
	update_exception_bitmap(vcpu);

	fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
	fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
	fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
	fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
	fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
	fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);

	kvm_mmu_reset_context(vcpu);
}

static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);

	if (!msr)
		return;

	/*
	 * Force kernel_gs_base reloading before EFER changes, as control
	 * of this msr depends on is_long_mode().
	 */
	vmx_load_host_state(to_vmx(vcpu));
	vcpu->arch.efer = efer;
	if (efer & EFER_LMA) {
		vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
		msr->data = efer;
	} else {
		vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);

		msr->data = efer & ~EFER_LME;
	}
	setup_msrs(vmx);
}

#ifdef CONFIG_X86_64

static void enter_lmode(struct kvm_vcpu *vcpu)
{
	u32 guest_tr_ar;

	vmx_segment_cache_clear(to_vmx(vcpu));

	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
	if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
		pr_debug_ratelimited("%s: tss fixup for long mode. \n",
				     __func__);
		vmcs_write32(GUEST_TR_AR_BYTES,
			     (guest_tr_ar & ~VMX_AR_TYPE_MASK)
			     | VMX_AR_TYPE_BUSY_64_TSS);
	}
	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
}

static void exit_lmode(struct kvm_vcpu *vcpu)
{
	vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
	vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
}

#endif

static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
{
	if (enable_ept) {
		if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
			return;
		ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
	} else {
		vpid_sync_context(vpid);
	}
}

static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
}

static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
{
	if (enable_ept)
		vmx_flush_tlb(vcpu);
}

static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;

	vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
}

static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
{
	if (enable_ept && is_paging(vcpu))
		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
}

static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;

	vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
	vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
}

static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	if (!test_bit(VCPU_EXREG_PDPTR,
		      (unsigned long *)&vcpu->arch.regs_dirty))
		return;

	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
	}
}

static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
	}

	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_avail);
	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_dirty);
}

static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed0;
	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed1;
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	if (to_vmx(vcpu)->nested.nested_vmx_secondary_ctls_high &
		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
		fixed0 &= ~(X86_CR0_PE | X86_CR0_PG);

	return fixed_bits_valid(val, fixed0, fixed1);
}

static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed0;
	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed1;

	return fixed_bits_valid(val, fixed0, fixed1);
}

static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr4_fixed0;
	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr4_fixed1;

	return fixed_bits_valid(val, fixed0, fixed1);
}

/* No difference in the restrictions on guest and host CR4 in VMX operation. */
#define nested_guest_cr4_valid	nested_cr4_valid
#define nested_host_cr4_valid	nested_cr4_valid

static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);

static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
					unsigned long cr0,
					struct kvm_vcpu *vcpu)
{
	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
		vmx_decache_cr3(vcpu);
	if (!(cr0 & X86_CR0_PG)) {
		/* From paging/starting to nonpaging */
		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) |
			     (CPU_BASED_CR3_LOAD_EXITING |
			      CPU_BASED_CR3_STORE_EXITING));
		vcpu->arch.cr0 = cr0;
		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
	} else if (!is_paging(vcpu)) {
		/* From nonpaging to paging */
		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
			     ~(CPU_BASED_CR3_LOAD_EXITING |
			       CPU_BASED_CR3_STORE_EXITING));
		vcpu->arch.cr0 = cr0;
		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
	}

	if (!(cr0 & X86_CR0_WP))
		*hw_cr0 &= ~X86_CR0_WP;
}

static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long hw_cr0;

	hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
	if (enable_unrestricted_guest)
		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
	else {
		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;

		if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
			enter_pmode(vcpu);

		if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
			enter_rmode(vcpu);
	}

#ifdef CONFIG_X86_64
	if (vcpu->arch.efer & EFER_LME) {
		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
			enter_lmode(vcpu);
		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
			exit_lmode(vcpu);
	}
#endif

	if (enable_ept)
		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);

	vmcs_writel(CR0_READ_SHADOW, cr0);
	vmcs_writel(GUEST_CR0, hw_cr0);
	vcpu->arch.cr0 = cr0;

	/* depends on vcpu->arch.cr0 to be set to a new value */
	vmx->emulation_required = emulation_required(vcpu);
}

static int get_ept_level(struct kvm_vcpu *vcpu)
{
	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
		return 5;
	return 4;
}

static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
{
	u64 eptp = VMX_EPTP_MT_WB;

	eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;

	if (enable_ept_ad_bits &&
	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
		eptp |= VMX_EPTP_AD_ENABLE_BIT;
	eptp |= (root_hpa & PAGE_MASK);

	return eptp;
}

static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	unsigned long guest_cr3;
	u64 eptp;

	guest_cr3 = cr3;
	if (enable_ept) {
		eptp = construct_eptp(vcpu, cr3);
		vmcs_write64(EPT_POINTER, eptp);
		if (is_paging(vcpu) || is_guest_mode(vcpu))
			guest_cr3 = kvm_read_cr3(vcpu);
		else
			guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr;
		ept_load_pdptrs(vcpu);
	}

	vmx_flush_tlb(vcpu);
	vmcs_writel(GUEST_CR3, guest_cr3);
}

static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	/*
	 * Pass through host's Machine Check Enable value to hw_cr4, which
	 * is in force while we are in guest mode.  Do not let guests control
	 * this bit, even if host CR4.MCE == 0.
	 */
	unsigned long hw_cr4 =
		(cr4_read_shadow() & X86_CR4_MCE) |
		(cr4 & ~X86_CR4_MCE) |
		(to_vmx(vcpu)->rmode.vm86_active ?
		 KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);

	if (cr4 & X86_CR4_VMXE) {
		/*
		 * To use VMXON (and later other VMX instructions), a guest
		 * must first be able to turn on cr4.VMXE (see handle_vmon()).
		 * So basically the check on whether to allow nested VMX
		 * is here.
		 */
		if (!nested_vmx_allowed(vcpu))
			return 1;
	}

	if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
		return 1;

	vcpu->arch.cr4 = cr4;
	if (enable_ept) {
		if (!is_paging(vcpu)) {
			hw_cr4 &= ~X86_CR4_PAE;
			hw_cr4 |= X86_CR4_PSE;
		} else if (!(cr4 & X86_CR4_PAE)) {
			hw_cr4 &= ~X86_CR4_PAE;
		}
	}

	if (!enable_unrestricted_guest && !is_paging(vcpu))
		/*
		 * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
		 * hardware.  To emulate this behavior, SMEP/SMAP/PKU needs
		 * to be manually disabled when guest switches to non-paging
		 * mode.
		 *
		 * If !enable_unrestricted_guest, the CPU is always running
		 * with CR0.PG=1 and CR4 needs to be modified.
		 * If enable_unrestricted_guest, the CPU automatically
		 * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
		 */
		hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);

	vmcs_writel(CR4_READ_SHADOW, cr4);
	vmcs_writel(GUEST_CR4, hw_cr4);
	return 0;
}

static void vmx_get_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 ar;

	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
		*var = vmx->rmode.segs[seg];
		if (seg == VCPU_SREG_TR
		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
			return;
		var->base = vmx_read_guest_seg_base(vmx, seg);
		var->selector = vmx_read_guest_seg_selector(vmx, seg);
		return;
	}
	var->base = vmx_read_guest_seg_base(vmx, seg);
	var->limit = vmx_read_guest_seg_limit(vmx, seg);
	var->selector = vmx_read_guest_seg_selector(vmx, seg);
	ar = vmx_read_guest_seg_ar(vmx, seg);
	var->unusable = (ar >> 16) & 1;
	var->type = ar & 15;
	var->s = (ar >> 4) & 1;
	var->dpl = (ar >> 5) & 3;
	/*
	 * Some userspaces do not preserve unusable property. Since usable
	 * segment has to be present according to VMX spec we can use present
	 * property to amend userspace bug by making unusable segment always
	 * nonpresent. vmx_segment_access_rights() already marks nonpresent
	 * segment as unusable.
	 */
	var->present = !var->unusable;
	var->avl = (ar >> 12) & 1;
	var->l = (ar >> 13) & 1;
	var->db = (ar >> 14) & 1;
	var->g = (ar >> 15) & 1;
}

static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
	struct kvm_segment s;

	if (to_vmx(vcpu)->rmode.vm86_active) {
		vmx_get_segment(vcpu, &s, seg);
		return s.base;
	}
	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
}

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

	if (unlikely(vmx->rmode.vm86_active))
		return 0;
	else {
		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
		return VMX_AR_DPL(ar);
	}
}

static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
	u32 ar;

	if (var->unusable || !var->present)
		ar = 1 << 16;
	else {
		ar = var->type & 15;
		ar |= (var->s & 1) << 4;
		ar |= (var->dpl & 3) << 5;
		ar |= (var->present & 1) << 7;
		ar |= (var->avl & 1) << 12;
		ar |= (var->l & 1) << 13;
		ar |= (var->db & 1) << 14;
		ar |= (var->g & 1) << 15;
	}

	return ar;
}

static void vmx_set_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];

	vmx_segment_cache_clear(vmx);

	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
		vmx->rmode.segs[seg] = *var;
		if (seg == VCPU_SREG_TR)
			vmcs_write16(sf->selector, var->selector);
		else if (var->s)
			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
		goto out;
	}

	vmcs_writel(sf->base, var->base);
	vmcs_write32(sf->limit, var->limit);
	vmcs_write16(sf->selector, var->selector);

	/*
	 *   Fix the "Accessed" bit in AR field of segment registers for older
	 * qemu binaries.
	 *   IA32 arch specifies that at the time of processor reset the
	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
	 * is setting it to 0 in the userland code. This causes invalid guest
	 * state vmexit when "unrestricted guest" mode is turned on.
	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
	 * tree. Newer qemu binaries with that qemu fix would not need this
	 * kvm hack.
	 */
	if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
		var->type |= 0x1; /* Accessed */

	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));

out:
	vmx->emulation_required = emulation_required(vcpu);
}

static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
	u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS);

	*db = (ar >> 14) & 1;
	*l = (ar >> 13) & 1;
}

static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
	dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
	dt->address = vmcs_readl(GUEST_IDTR_BASE);
}

static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
	vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
	vmcs_writel(GUEST_IDTR_BASE, dt->address);
}

static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
	dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
	dt->address = vmcs_readl(GUEST_GDTR_BASE);
}

static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
	vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
	vmcs_writel(GUEST_GDTR_BASE, dt->address);
}

static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
{
	struct kvm_segment var;
	u32 ar;

	vmx_get_segment(vcpu, &var, seg);
	var.dpl = 0x3;
	if (seg == VCPU_SREG_CS)
		var.type = 0x3;
	ar = vmx_segment_access_rights(&var);

	if (var.base != (var.selector << 4))
		return false;
	if (var.limit != 0xffff)
		return false;
	if (ar != 0xf3)
		return false;

	return true;
}

static bool code_segment_valid(struct kvm_vcpu *vcpu)
{
	struct kvm_segment cs;
	unsigned int cs_rpl;

	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
	cs_rpl = cs.selector & SEGMENT_RPL_MASK;

	if (cs.unusable)
		return false;
	if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
		return false;
	if (!cs.s)
		return false;
	if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
		if (cs.dpl > cs_rpl)
			return false;
	} else {
		if (cs.dpl != cs_rpl)
			return false;
	}
	if (!cs.present)
		return false;

	/* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */
	return true;
}

static bool stack_segment_valid(struct kvm_vcpu *vcpu)
{
	struct kvm_segment ss;
	unsigned int ss_rpl;

	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
	ss_rpl = ss.selector & SEGMENT_RPL_MASK;

	if (ss.unusable)
		return true;
	if (ss.type != 3 && ss.type != 7)
		return false;
	if (!ss.s)
		return false;
	if (ss.dpl != ss_rpl) /* DPL != RPL */
		return false;
	if (!ss.present)
		return false;

	return true;
}

static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
{
	struct kvm_segment var;
	unsigned int rpl;

	vmx_get_segment(vcpu, &var, seg);
	rpl = var.selector & SEGMENT_RPL_MASK;

	if (var.unusable)
		return true;
	if (!var.s)
		return false;
	if (!var.present)
		return false;
	if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
		if (var.dpl < rpl) /* DPL < RPL */
			return false;
	}

	/* TODO: Add other members to kvm_segment_field to allow checking for other access
	 * rights flags
	 */
	return true;
}

static bool tr_valid(struct kvm_vcpu *vcpu)
{
	struct kvm_segment tr;

	vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);

	if (tr.unusable)
		return false;
	if (tr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
		return false;
	if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
		return false;
	if (!tr.present)
		return false;

	return true;
}

static bool ldtr_valid(struct kvm_vcpu *vcpu)
{
	struct kvm_segment ldtr;

	vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);

	if (ldtr.unusable)
		return true;
	if (ldtr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
		return false;
	if (ldtr.type != 2)
		return false;
	if (!ldtr.present)
		return false;

	return true;
}

static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
{
	struct kvm_segment cs, ss;

	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);

	return ((cs.selector & SEGMENT_RPL_MASK) ==
		 (ss.selector & SEGMENT_RPL_MASK));
}

/*
 * Check if guest state is valid. Returns true if valid, false if
 * not.
 * We assume that registers are always usable
 */
static bool guest_state_valid(struct kvm_vcpu *vcpu)
{
	if (enable_unrestricted_guest)
		return true;

	/* real mode guest state checks */
	if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) {
		if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
			return false;
		if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
			return false;
		if (!rmode_segment_valid(vcpu, VCPU_SREG_DS))
			return false;
		if (!rmode_segment_valid(vcpu, VCPU_SREG_ES))
			return false;
		if (!rmode_segment_valid(vcpu, VCPU_SREG_FS))
			return false;
		if (!rmode_segment_valid(vcpu, VCPU_SREG_GS))
			return false;
	} else {
	/* protected mode guest state checks */
		if (!cs_ss_rpl_check(vcpu))
			return false;
		if (!code_segment_valid(vcpu))
			return false;
		if (!stack_segment_valid(vcpu))
			return false;
		if (!data_segment_valid(vcpu, VCPU_SREG_DS))
			return false;
		if (!data_segment_valid(vcpu, VCPU_SREG_ES))
			return false;
		if (!data_segment_valid(vcpu, VCPU_SREG_FS))
			return false;
		if (!data_segment_valid(vcpu, VCPU_SREG_GS))
			return false;
		if (!tr_valid(vcpu))
			return false;
		if (!ldtr_valid(vcpu))
			return false;
	}
	/* TODO:
	 * - Add checks on RIP
	 * - Add checks on RFLAGS
	 */

	return true;
}

static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
{
	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
}

static int init_rmode_tss(struct kvm *kvm)
{
	gfn_t fn;
	u16 data = 0;
	int idx, r;

	idx = srcu_read_lock(&kvm->srcu);
	fn = kvm->arch.tss_addr >> PAGE_SHIFT;
	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
	if (r < 0)
		goto out;
	data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
	r = kvm_write_guest_page(kvm, fn++, &data,
			TSS_IOPB_BASE_OFFSET, sizeof(u16));
	if (r < 0)
		goto out;
	r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
	if (r < 0)
		goto out;
	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
	if (r < 0)
		goto out;
	data = ~0;
	r = kvm_write_guest_page(kvm, fn, &data,
				 RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
				 sizeof(u8));
out:
	srcu_read_unlock(&kvm->srcu, idx);
	return r;
}

static int init_rmode_identity_map(struct kvm *kvm)
{
	int i, idx, r = 0;
	kvm_pfn_t identity_map_pfn;
	u32 tmp;

	if (!enable_ept)
		return 0;

	/* Protect kvm->arch.ept_identity_pagetable_done. */
	mutex_lock(&kvm->slots_lock);

	if (likely(kvm->arch.ept_identity_pagetable_done))
		goto out2;

	identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;

	r = alloc_identity_pagetable(kvm);
	if (r < 0)
		goto out2;

	idx = srcu_read_lock(&kvm->srcu);
	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
	if (r < 0)
		goto out;
	/* Set up identity-mapping pagetable for EPT in real mode */
	for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
		tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
		r = kvm_write_guest_page(kvm, identity_map_pfn,
				&tmp, i * sizeof(tmp), sizeof(tmp));
		if (r < 0)
			goto out;
	}
	kvm->arch.ept_identity_pagetable_done = true;

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

out2:
	mutex_unlock(&kvm->slots_lock);
	return r;
}

static void seg_setup(int seg)
{
	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
	unsigned int ar;

	vmcs_write16(sf->selector, 0);
	vmcs_writel(sf->base, 0);
	vmcs_write32(sf->limit, 0xffff);
	ar = 0x93;
	if (seg == VCPU_SREG_CS)
		ar |= 0x08; /* code segment */

	vmcs_write32(sf->ar_bytes, ar);
}

static int alloc_apic_access_page(struct kvm *kvm)
{
	struct page *page;
	int r = 0;

	mutex_lock(&kvm->slots_lock);
	if (kvm->arch.apic_access_page_done)
		goto out;
	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
	if (r)
		goto out;

	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
	if (is_error_page(page)) {
		r = -EFAULT;
		goto out;
	}

	/*
	 * Do not pin the page in memory, so that memory hot-unplug
	 * is able to migrate it.
	 */
	put_page(page);
	kvm->arch.apic_access_page_done = true;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
}

static int alloc_identity_pagetable(struct kvm *kvm)
{
	/* Called with kvm->slots_lock held. */

	int r = 0;

	BUG_ON(kvm->arch.ept_identity_pagetable_done);

	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
				    kvm->arch.ept_identity_map_addr, PAGE_SIZE);

	return r;
}

static int allocate_vpid(void)
{
	int vpid;

	if (!enable_vpid)
		return 0;
	spin_lock(&vmx_vpid_lock);
	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
	if (vpid < VMX_NR_VPIDS)
		__set_bit(vpid, vmx_vpid_bitmap);
	else
		vpid = 0;
	spin_unlock(&vmx_vpid_lock);
	return vpid;
}

static void free_vpid(int vpid)
{
	if (!enable_vpid || vpid == 0)
		return;
	spin_lock(&vmx_vpid_lock);
	__clear_bit(vpid, vmx_vpid_bitmap);
	spin_unlock(&vmx_vpid_lock);
}

#define MSR_TYPE_R	1
#define MSR_TYPE_W	2
static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
						u32 msr, int type)
{
	int f = sizeof(unsigned long);

	if (!cpu_has_vmx_msr_bitmap())
		return;

	/*
	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
	 * have the write-low and read-high bitmap offsets the wrong way round.
	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
	 */
	if (msr <= 0x1fff) {
		if (type & MSR_TYPE_R)
			/* read-low */
			__clear_bit(msr, msr_bitmap + 0x000 / f);

		if (type & MSR_TYPE_W)
			/* write-low */
			__clear_bit(msr, msr_bitmap + 0x800 / f);

	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
		msr &= 0x1fff;
		if (type & MSR_TYPE_R)
			/* read-high */
			__clear_bit(msr, msr_bitmap + 0x400 / f);

		if (type & MSR_TYPE_W)
			/* write-high */
			__clear_bit(msr, msr_bitmap + 0xc00 / f);

	}
}

/*
 * If a msr is allowed by L0, we should check whether it is allowed by L1.
 * The corresponding bit will be cleared unless both of L0 and L1 allow it.
 */
static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
					       unsigned long *msr_bitmap_nested,
					       u32 msr, int type)
{
	int f = sizeof(unsigned long);

	if (!cpu_has_vmx_msr_bitmap()) {
		WARN_ON(1);
		return;
	}

	/*
	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
	 * have the write-low and read-high bitmap offsets the wrong way round.
	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
	 */
	if (msr <= 0x1fff) {
		if (type & MSR_TYPE_R &&
		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
			/* read-low */
			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);

		if (type & MSR_TYPE_W &&
		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
			/* write-low */
			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);

	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
		msr &= 0x1fff;
		if (type & MSR_TYPE_R &&
		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
			/* read-high */
			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);

		if (type & MSR_TYPE_W &&
		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
			/* write-high */
			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);

	}
}

static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
{
	if (!longmode_only)
		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
						msr, MSR_TYPE_R | MSR_TYPE_W);
	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
						msr, MSR_TYPE_R | MSR_TYPE_W);
}

static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active)
{
	if (apicv_active) {
		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv,
				msr, type);
		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv,
				msr, type);
	} else {
		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
				msr, type);
		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
				msr, type);
	}
}

static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
{
	return enable_apicv;
}

static 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 void 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_desc || !vmx->nested.pi_pending)
		return;

	vmx->nested.pi_pending = false;
	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
		return;

	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
	if (max_irr != 256) {
		vapic_page = kmap(vmx->nested.virtual_apic_page);
		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
		kunmap(vmx->nested.virtual_apic_page);

		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);
}

static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
						     bool nested)
{
#ifdef CONFIG_SMP
	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;

	if (vcpu->mode == IN_GUEST_MODE) {
		/*
		 * The vector of interrupt to be delivered to vcpu had
		 * been set in PIR before this function.
		 *
		 * Following cases will be reached in this block, and
		 * we always send a notification event in all cases as
		 * explained below.
		 *
		 * Case 1: vcpu keeps in non-root mode. Sending a
		 * notification event posts the interrupt to vcpu.
		 *
		 * Case 2: vcpu exits to root mode and is still
		 * runnable. PIR will be synced to vIRR before the
		 * next vcpu entry. Sending a notification event in
		 * this case has no effect, as vcpu is not in root
		 * mode.
		 *
		 * Case 3: vcpu exits to root mode and is blocked.
		 * vcpu_block() has already synced PIR to vIRR and
		 * never blocks vcpu if vIRR is not cleared. Therefore,
		 * a blocked vcpu here does not wait for any requested
		 * interrupts in PIR, and sending a notification event
		 * which has no effect is safe here.
		 */

		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
		return true;
	}
#endif
	return false;
}

static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
						int vector)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (is_guest_mode(vcpu) &&
	    vector == vmx->nested.posted_intr_nv) {
		/* the PIR and ON have been set by L1. */
		kvm_vcpu_trigger_posted_interrupt(vcpu, true);
		/*
		 * If a posted intr is not recognized by hardware,
		 * we will accomplish it in the next vmentry.
		 */
		vmx->nested.pi_pending = true;
		kvm_make_request(KVM_REQ_EVENT, vcpu);
		return 0;
	}
	return -1;
}
/*
 * Send interrupt to vcpu via posted interrupt way.
 * 1. If target vcpu is running(non-root mode), send posted interrupt
 * notification to vcpu and hardware will sync PIR to vIRR atomically.
 * 2. If target vcpu isn't running(root mode), kick it to pick up the
 * interrupt from PIR in next vmentry.
 */
static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int r;

	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
	if (!r)
		return;

	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
		return;

	/* If a previous notification has sent the IPI, nothing to do.  */
	if (pi_test_and_set_on(&vmx->pi_desc))
		return;

	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
		kvm_vcpu_kick(vcpu);
}

/*
 * Set up the vmcs's constant host-state fields, i.e., host-state fields that
 * will not change in the lifetime of the guest.
 * Note that host-state that does change is set elsewhere. E.g., host-state
 * that is set differently for each CPU is set in vmx_vcpu_load(), not here.
 */
static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
{
	u32 low32, high32;
	unsigned long tmpl;
	struct desc_ptr dt;
	unsigned long cr0, cr3, cr4;

	cr0 = read_cr0();
	WARN_ON(cr0 & X86_CR0_TS);
	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */

	/*
	 * Save the most likely value for this task's CR3 in the VMCS.
	 * We can't use __get_current_cr3_fast() because we're not atomic.
	 */
	cr3 = __read_cr3();
	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
	vmx->loaded_vmcs->vmcs_host_cr3 = cr3;

	/* Save the most likely value for this task's CR4 in the VMCS. */
	cr4 = cr4_read_shadow();
	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
	vmx->loaded_vmcs->vmcs_host_cr4 = cr4;

	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
#ifdef CONFIG_X86_64
	/*
	 * Load null selectors, so we can avoid reloading them in
	 * __vmx_load_host_state(), in case userspace uses the null selectors
	 * too (the expected case).
	 */
	vmcs_write16(HOST_DS_SELECTOR, 0);
	vmcs_write16(HOST_ES_SELECTOR, 0);
#else
	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
#endif
	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */

	store_idt(&dt);
	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
	vmx->host_idt_base = dt.address;

	vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */

	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
	rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
	vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl);   /* 22.2.3 */

	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
		rdmsr(MSR_IA32_CR_PAT, low32, high32);
		vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
	}
}

static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
{
	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
	if (enable_ept)
		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
	if (is_guest_mode(&vmx->vcpu))
		vmx->vcpu.arch.cr4_guest_owned_bits &=
			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
	vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
}

static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
{
	u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl;

	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
	/* Enable the preemption timer dynamically */
	pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
	return pin_based_exec_ctrl;
}

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

	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
	if (cpu_has_secondary_exec_ctrls()) {
		if (kvm_vcpu_apicv_active(vcpu))
			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
				      SECONDARY_EXEC_APIC_REGISTER_VIRT |
				      SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
		else
			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
					SECONDARY_EXEC_APIC_REGISTER_VIRT |
					SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
	}

	if (cpu_has_vmx_msr_bitmap())
		vmx_set_msr_bitmap(vcpu);
}

static u32 vmx_exec_control(struct vcpu_vmx *vmx)
{
	u32 exec_control = vmcs_config.cpu_based_exec_ctrl;

	if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
		exec_control &= ~CPU_BASED_MOV_DR_EXITING;

	if (!cpu_need_tpr_shadow(&vmx->vcpu)) {
		exec_control &= ~CPU_BASED_TPR_SHADOW;
#ifdef CONFIG_X86_64
		exec_control |= CPU_BASED_CR8_STORE_EXITING |
				CPU_BASED_CR8_LOAD_EXITING;
#endif
	}
	if (!enable_ept)
		exec_control |= CPU_BASED_CR3_STORE_EXITING |
				CPU_BASED_CR3_LOAD_EXITING  |
				CPU_BASED_INVLPG_EXITING;
	return exec_control;
}

static bool vmx_rdrand_supported(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_RDRAND;
}

static bool vmx_rdseed_supported(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_RDSEED;
}

static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
{
	struct kvm_vcpu *vcpu = &vmx->vcpu;

	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
	if (!cpu_need_virtualize_apic_accesses(vcpu))
		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
	if (vmx->vpid == 0)
		exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
	if (!enable_ept) {
		exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
		enable_unrestricted_guest = 0;
		/* Enable INVPCID for non-ept guests may cause performance regression. */
		exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
	}
	if (!enable_unrestricted_guest)
		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
	if (!ple_gap)
		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
	if (!kvm_vcpu_apicv_active(vcpu))
		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
	/* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD
	   (handle_vmptrld).
	   We can NOT enable shadow_vmcs here because we don't have yet
	   a current VMCS12
	*/
	exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;

	if (!enable_pml)
		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;

	if (vmx_xsaves_supported()) {
		/* Exposing XSAVES only when XSAVE is exposed */
		bool xsaves_enabled =
			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);

		if (!xsaves_enabled)
			exec_control &= ~SECONDARY_EXEC_XSAVES;

		if (nested) {
			if (xsaves_enabled)
				vmx->nested.nested_vmx_secondary_ctls_high |=
					SECONDARY_EXEC_XSAVES;
			else
				vmx->nested.nested_vmx_secondary_ctls_high &=
					~SECONDARY_EXEC_XSAVES;
		}
	}

	if (vmx_rdtscp_supported()) {
		bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
		if (!rdtscp_enabled)
			exec_control &= ~SECONDARY_EXEC_RDTSCP;

		if (nested) {
			if (rdtscp_enabled)
				vmx->nested.nested_vmx_secondary_ctls_high |=
					SECONDARY_EXEC_RDTSCP;
			else
				vmx->nested.nested_vmx_secondary_ctls_high &=
					~SECONDARY_EXEC_RDTSCP;
		}
	}

	if (vmx_invpcid_supported()) {
		/* Exposing INVPCID only when PCID is exposed */
		bool invpcid_enabled =
			guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
			guest_cpuid_has(vcpu, X86_FEATURE_PCID);

		if (!invpcid_enabled) {
			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
			guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
		}

		if (nested) {
			if (invpcid_enabled)
				vmx->nested.nested_vmx_secondary_ctls_high |=
					SECONDARY_EXEC_ENABLE_INVPCID;
			else
				vmx->nested.nested_vmx_secondary_ctls_high &=
					~SECONDARY_EXEC_ENABLE_INVPCID;
		}
	}

	if (vmx_rdrand_supported()) {
		bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND);
		if (rdrand_enabled)
			exec_control &= ~SECONDARY_EXEC_RDRAND;

		if (nested) {
			if (rdrand_enabled)
				vmx->nested.nested_vmx_secondary_ctls_high |=
					SECONDARY_EXEC_RDRAND;
			else
				vmx->nested.nested_vmx_secondary_ctls_high &=
					~SECONDARY_EXEC_RDRAND;
		}
	}

	if (vmx_rdseed_supported()) {
		bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED);
		if (rdseed_enabled)
			exec_control &= ~SECONDARY_EXEC_RDSEED;

		if (nested) {
			if (rdseed_enabled)
				vmx->nested.nested_vmx_secondary_ctls_high |=
					SECONDARY_EXEC_RDSEED;
			else
				vmx->nested.nested_vmx_secondary_ctls_high &=
					~SECONDARY_EXEC_RDSEED;
		}
	}

	vmx->secondary_exec_control = exec_control;
}

static void ept_set_mmio_spte_mask(void)
{
	/*
	 * EPT Misconfigurations can be generated if the value of bits 2:0
	 * of an EPT paging-structure entry is 110b (write/execute).
	 */
	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
				   VMX_EPT_MISCONFIG_WX_VALUE);
}

#define VMX_XSS_EXIT_BITMAP 0
/*
 * Sets up the vmcs for emulated real mode.
 */
static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
#ifdef CONFIG_X86_64
	unsigned long a;
#endif
	int i;

	/* I/O */
	vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a));
	vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));

	if (enable_shadow_vmcs) {
		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
	}
	if (cpu_has_vmx_msr_bitmap())
		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));

	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */

	/* Control */
	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
	vmx->hv_deadline_tsc = -1;

	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));

	if (cpu_has_secondary_exec_ctrls()) {
		vmx_compute_secondary_exec_control(vmx);
		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
			     vmx->secondary_exec_control);
	}

	if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
		vmcs_write64(EOI_EXIT_BITMAP0, 0);
		vmcs_write64(EOI_EXIT_BITMAP1, 0);
		vmcs_write64(EOI_EXIT_BITMAP2, 0);
		vmcs_write64(EOI_EXIT_BITMAP3, 0);

		vmcs_write16(GUEST_INTR_STATUS, 0);

		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
	}

	if (ple_gap) {
		vmcs_write32(PLE_GAP, ple_gap);
		vmx->ple_window = ple_window;
		vmx->ple_window_dirty = true;
	}

	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */

	vmcs_write16(HOST_FS_SELECTOR, 0);            /* 22.2.4 */
	vmcs_write16(HOST_GS_SELECTOR, 0);            /* 22.2.4 */
	vmx_set_constant_host_state(vmx);
#ifdef CONFIG_X86_64
	rdmsrl(MSR_FS_BASE, a);
	vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */
	rdmsrl(MSR_GS_BASE, a);
	vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */
#else
	vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
	vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
#endif

	if (cpu_has_vmx_vmfunc())
		vmcs_write64(VM_FUNCTION_CONTROL, 0);

	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));

	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);

	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
		u32 index = vmx_msr_index[i];
		u32 data_low, data_high;
		int j = vmx->nmsrs;

		if (rdmsr_safe(index, &data_low, &data_high) < 0)
			continue;
		if (wrmsr_safe(index, data_low, data_high) < 0)
			continue;
		vmx->guest_msrs[j].index = i;
		vmx->guest_msrs[j].data = 0;
		vmx->guest_msrs[j].mask = -1ull;
		++vmx->nmsrs;
	}


	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);

	/* 22.2.1, 20.8.1 */
	vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl);

	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);

	set_cr4_guest_host_mask(vmx);

	if (vmx_xsaves_supported())
		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);

	if (enable_pml) {
		ASSERT(vmx->pml_pg);
		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
	}

	return 0;
}

static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct msr_data apic_base_msr;
	u64 cr0;

	vmx->rmode.vm86_active = 0;

	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
	kvm_set_cr8(vcpu, 0);

	if (!init_event) {
		apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
				     MSR_IA32_APICBASE_ENABLE;
		if (kvm_vcpu_is_reset_bsp(vcpu))
			apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
		apic_base_msr.host_initiated = true;
		kvm_set_apic_base(vcpu, &apic_base_msr);
	}

	vmx_segment_cache_clear(vmx);

	seg_setup(VCPU_SREG_CS);
	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
	vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);

	seg_setup(VCPU_SREG_DS);
	seg_setup(VCPU_SREG_ES);
	seg_setup(VCPU_SREG_FS);
	seg_setup(VCPU_SREG_GS);
	seg_setup(VCPU_SREG_SS);

	vmcs_write16(GUEST_TR_SELECTOR, 0);
	vmcs_writel(GUEST_TR_BASE, 0);
	vmcs_write32(GUEST_TR_LIMIT, 0xffff);
	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);

	vmcs_write16(GUEST_LDTR_SELECTOR, 0);
	vmcs_writel(GUEST_LDTR_BASE, 0);
	vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
	vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);

	if (!init_event) {
		vmcs_write32(GUEST_SYSENTER_CS, 0);
		vmcs_writel(GUEST_SYSENTER_ESP, 0);
		vmcs_writel(GUEST_SYSENTER_EIP, 0);
		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
	}

	vmcs_writel(GUEST_RFLAGS, 0x02);
	kvm_rip_write(vcpu, 0xfff0);

	vmcs_writel(GUEST_GDTR_BASE, 0);
	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);

	vmcs_writel(GUEST_IDTR_BASE, 0);
	vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);

	vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);

	setup_msrs(vmx);

	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */

	if (cpu_has_vmx_tpr_shadow() && !init_event) {
		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
		if (cpu_need_tpr_shadow(vcpu))
			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
				     __pa(vcpu->arch.apic->regs));
		vmcs_write32(TPR_THRESHOLD, 0);
	}

	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);

	if (kvm_vcpu_apicv_active(vcpu))
		memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));

	if (vmx->vpid != 0)
		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);

	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
	vmx->vcpu.arch.cr0 = cr0;
	vmx_set_cr0(vcpu, cr0); /* enter rmode */
	vmx_set_cr4(vcpu, 0);
	vmx_set_efer(vcpu, 0);

	update_exception_bitmap(vcpu);

	vpid_sync_context(vmx->vpid);
}

/*
 * In nested virtualization, check if L1 asked to exit on external interrupts.
 * For most existing hypervisors, this will always return true.
 */
static bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
{
	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
		PIN_BASED_EXT_INTR_MASK;
}

/*
 * 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 bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
{
	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
		PIN_BASED_NMI_EXITING;
}

static void enable_irq_window(struct kvm_vcpu *vcpu)
{
	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
		      CPU_BASED_VIRTUAL_INTR_PENDING);
}

static void enable_nmi_window(struct kvm_vcpu *vcpu)
{
	if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
		enable_irq_window(vcpu);
		return;
	}

	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
		      CPU_BASED_VIRTUAL_NMI_PENDING);
}

static void vmx_inject_irq(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	uint32_t intr;
	int irq = vcpu->arch.interrupt.nr;

	trace_kvm_inj_virq(irq);

	++vcpu->stat.irq_injections;
	if (vmx->rmode.vm86_active) {
		int inc_eip = 0;
		if (vcpu->arch.interrupt.soft)
			inc_eip = vcpu->arch.event_exit_inst_len;
		if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE)
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}
	intr = irq | INTR_INFO_VALID_MASK;
	if (vcpu->arch.interrupt.soft) {
		intr |= INTR_TYPE_SOFT_INTR;
		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
			     vmx->vcpu.arch.event_exit_inst_len);
	} else
		intr |= INTR_TYPE_EXT_INTR;
	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
}

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

	++vcpu->stat.nmi_injections;
	vmx->loaded_vmcs->nmi_known_unmasked = false;

	if (vmx->rmode.vm86_active) {
		if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}

	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
}

static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	bool masked;

	if (vmx->loaded_vmcs->nmi_known_unmasked)
		return false;
	masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
	vmx->loaded_vmcs->nmi_known_unmasked = !masked;
	return masked;
}

static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	vmx->loaded_vmcs->nmi_known_unmasked = !masked;
	if (masked)
		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
			      GUEST_INTR_STATE_NMI);
	else
		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
				GUEST_INTR_STATE_NMI);
}

static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
{
	if (to_vmx(vcpu)->nested.nested_run_pending)
		return 0;

	return	!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
		  (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI
		   | GUEST_INTR_STATE_NMI));
}

static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
{
	return (!to_vmx(vcpu)->nested.nested_run_pending &&
		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
}

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

	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
				    PAGE_SIZE * 3);
	if (ret)
		return ret;
	kvm->arch.tss_addr = addr;
	return init_rmode_tss(kvm);
}

static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
{
	switch (vec) {
	case BP_VECTOR:
		/*
		 * Update instruction length as we may reinject the exception
		 * from user space while in guest debugging mode.
		 */
		to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
			return false;
		/* fall through */
	case DB_VECTOR:
		if (vcpu->guest_debug &
			(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
			return false;
		/* fall through */
	case DE_VECTOR:
	case OF_VECTOR:
	case BR_VECTOR:
	case UD_VECTOR:
	case DF_VECTOR:
	case SS_VECTOR:
	case GP_VECTOR:
	case MF_VECTOR:
		return true;
	break;
	}
	return false;
}

static int handle_rmode_exception(struct kvm_vcpu *vcpu,
				  int vec, u32 err_code)
{
	/*
	 * Instruction with address size override prefix opcode 0x67
	 * Cause the #SS fault with 0 error code in VM86 mode.
	 */
	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
		if (emulate_instruction(vcpu, 0) == EMULATE_DONE) {
			if (vcpu->arch.halt_request) {
				vcpu->arch.halt_request = 0;
				return kvm_vcpu_halt(vcpu);
			}
			return 1;
		}
		return 0;
	}

	/*
	 * Forward all other exceptions that are valid in real mode.
	 * FIXME: Breaks guest debugging in real mode, needs to be fixed with
	 *        the required debugging infrastructure rework.
	 */
	kvm_queue_exception(vcpu, vec);
	return 1;
}

/*
 * Trigger machine check on the host. We assume all the MSRs are already set up
 * by the CPU and that we still run on the same CPU as the MCE occurred on.
 * We pass a fake environment to the machine check handler because we want
 * the guest to be always treated like user space, no matter what context
 * it used internally.
 */
static void kvm_machine_check(void)
{
#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
	struct pt_regs regs = {
		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
		.flags = X86_EFLAGS_IF,
	};

	do_machine_check(&regs, 0);
#endif
}

static int handle_machine_check(struct kvm_vcpu *vcpu)
{
	/* already handled by vcpu_run */
	return 1;
}

static int handle_exception(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct kvm_run *kvm_run = vcpu->run;
	u32 intr_info, ex_no, error_code;
	unsigned long cr2, rip, dr6;
	u32 vect_info;
	enum emulation_result er;

	vect_info = vmx->idt_vectoring_info;
	intr_info = vmx->exit_intr_info;

	if (is_machine_check(intr_info))
		return handle_machine_check(vcpu);

	if (is_nmi(intr_info))
		return 1;  /* already handled by vmx_vcpu_run() */

	if (is_invalid_opcode(intr_info)) {
		if (is_guest_mode(vcpu)) {
			kvm_queue_exception(vcpu, UD_VECTOR);
			return 1;
		}
		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
		if (er != EMULATE_DONE)
			kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	error_code = 0;
	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);

	/*
	 * The #PF with PFEC.RSVD = 1 indicates the guest is accessing
	 * MMIO, it is better to report an internal error.
	 * See the comments in vmx_handle_exit.
	 */
	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
	    !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
		vcpu->run->internal.ndata = 3;
		vcpu->run->internal.data[0] = vect_info;
		vcpu->run->internal.data[1] = intr_info;
		vcpu->run->internal.data[2] = error_code;
		return 0;
	}

	if (is_page_fault(intr_info)) {
		cr2 = vmcs_readl(EXIT_QUALIFICATION);
		/* EPT won't cause page fault directly */
		WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept);
		return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0,
				true);
	}

	ex_no = intr_info & INTR_INFO_VECTOR_MASK;

	if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no))
		return handle_rmode_exception(vcpu, ex_no, error_code);

	switch (ex_no) {
	case AC_VECTOR:
		kvm_queue_exception_e(vcpu, AC_VECTOR, error_code);
		return 1;
	case DB_VECTOR:
		dr6 = vmcs_readl(EXIT_QUALIFICATION);
		if (!(vcpu->guest_debug &
		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
			vcpu->arch.dr6 &= ~15;
			vcpu->arch.dr6 |= dr6 | DR6_RTM;
			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
				skip_emulated_instruction(vcpu);

			kvm_queue_exception(vcpu, DB_VECTOR);
			return 1;
		}
		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
		/* fall through */
	case BP_VECTOR:
		/*
		 * Update instruction length as we may reinject #BP from
		 * user space while in guest debugging mode. Reading it for
		 * #DB as well causes no harm, it is not used in that case.
		 */
		vmx->vcpu.arch.event_exit_inst_len =
			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
		kvm_run->exit_reason = KVM_EXIT_DEBUG;
		rip = kvm_rip_read(vcpu);
		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
		kvm_run->debug.arch.exception = ex_no;
		break;
	default:
		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
		kvm_run->ex.exception = ex_no;
		kvm_run->ex.error_code = error_code;
		break;
	}
	return 0;
}

static int handle_external_interrupt(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.irq_exits;
	return 1;
}

static int handle_triple_fault(struct kvm_vcpu *vcpu)
{
	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
	vcpu->mmio_needed = 0;
	return 0;
}

static int handle_io(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification;
	int size, in, string, ret;
	unsigned port;

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	string = (exit_qualification & 16) != 0;
	in = (exit_qualification & 8) != 0;

	++vcpu->stat.io_exits;

	if (string || in)
		return emulate_instruction(vcpu, 0) == EMULATE_DONE;

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

	ret = kvm_skip_emulated_instruction(vcpu);

	/*
	 * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
	 * KVM_EXIT_DEBUG here.
	 */
	return kvm_fast_pio_out(vcpu, size, port) && ret;
}

static void
vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
{
	/*
	 * Patch in the VMCALL instruction:
	 */
	hypercall[0] = 0x0f;
	hypercall[1] = 0x01;
	hypercall[2] = 0xc1;
}

/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
{
	if (is_guest_mode(vcpu)) {
		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
		unsigned long orig_val = val;

		/*
		 * We get here when L2 changed cr0 in a way that did not change
		 * any of L1's shadowed bits (see nested_vmx_exit_handled_cr),
		 * but did change L0 shadowed bits. So we first calculate the
		 * effective cr0 value that L1 would like to write into the
		 * hardware. It consists of the L2-owned bits from the new
		 * value combined with the L1-owned bits from L1's guest_cr0.
		 */
		val = (val & ~vmcs12->cr0_guest_host_mask) |
			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);

		if (!nested_guest_cr0_valid(vcpu, val))
			return 1;

		if (kvm_set_cr0(vcpu, val))
			return 1;
		vmcs_writel(CR0_READ_SHADOW, orig_val);
		return 0;
	} else {
		if (to_vmx(vcpu)->nested.vmxon &&
		    !nested_host_cr0_valid(vcpu, val))
			return 1;

		return kvm_set_cr0(vcpu, val);
	}
}

static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
{
	if (is_guest_mode(vcpu)) {
		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
		unsigned long orig_val = val;

		/* analogously to handle_set_cr0 */
		val = (val & ~vmcs12->cr4_guest_host_mask) |
			(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask);
		if (kvm_set_cr4(vcpu, val))
			return 1;
		vmcs_writel(CR4_READ_SHADOW, orig_val);
		return 0;
	} else
		return kvm_set_cr4(vcpu, val);
}

static int handle_cr(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification, val;
	int cr;
	int reg;
	int err;
	int ret;

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	cr = exit_qualification & 15;
	reg = (exit_qualification >> 8) & 15;
	switch ((exit_qualification >> 4) & 3) {
	case 0: /* mov to cr */
		val = kvm_register_readl(vcpu, reg);
		trace_kvm_cr_write(cr, val);
		switch (cr) {
		case 0:
			err = handle_set_cr0(vcpu, val);
			return kvm_complete_insn_gp(vcpu, err);
		case 3:
			err = kvm_set_cr3(vcpu, val);
			return kvm_complete_insn_gp(vcpu, err);
		case 4:
			err = handle_set_cr4(vcpu, val);
			return kvm_complete_insn_gp(vcpu, err);
		case 8: {
				u8 cr8_prev = kvm_get_cr8(vcpu);
				u8 cr8 = (u8)val;
				err = kvm_set_cr8(vcpu, cr8);
				ret = kvm_complete_insn_gp(vcpu, err);
				if (lapic_in_kernel(vcpu))
					return ret;
				if (cr8_prev <= cr8)
					return ret;
				/*
				 * TODO: we might be squashing a
				 * KVM_GUESTDBG_SINGLESTEP-triggered
				 * KVM_EXIT_DEBUG here.
				 */
				vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
				return 0;
			}
		}
		break;
	case 2: /* clts */
		WARN_ONCE(1, "Guest should always own CR0.TS");
		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
		return kvm_skip_emulated_instruction(vcpu);
	case 1: /*mov from cr*/
		switch (cr) {
		case 3:
			val = kvm_read_cr3(vcpu);
			kvm_register_write(vcpu, reg, val);
			trace_kvm_cr_read(cr, val);
			return kvm_skip_emulated_instruction(vcpu);
		case 8:
			val = kvm_get_cr8(vcpu);
			kvm_register_write(vcpu, reg, val);
			trace_kvm_cr_read(cr, val);
			return kvm_skip_emulated_instruction(vcpu);
		}
		break;
	case 3: /* lmsw */
		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
		trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
		kvm_lmsw(vcpu, val);

		return kvm_skip_emulated_instruction(vcpu);
	default:
		break;
	}
	vcpu->run->exit_reason = 0;
	vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n",
	       (int)(exit_qualification >> 4) & 3, cr);
	return 0;
}

static int handle_dr(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification;
	int dr, dr7, reg;

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;

	/* First, if DR does not exist, trigger UD */
	if (!kvm_require_dr(vcpu, dr))
		return 1;

	/* Do not handle if the CPL > 0, will trigger GP on re-entry */
	if (!kvm_require_cpl(vcpu, 0))
		return 1;
	dr7 = vmcs_readl(GUEST_DR7);
	if (dr7 & DR7_GD) {
		/*
		 * As the vm-exit takes precedence over the debug trap, we
		 * need to emulate the latter, either for the host or the
		 * guest debugging itself.
		 */
		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
			vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
			vcpu->run->debug.arch.dr7 = dr7;
			vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
			vcpu->run->debug.arch.exception = DB_VECTOR;
			vcpu->run->exit_reason = KVM_EXIT_DEBUG;
			return 0;
		} else {
			vcpu->arch.dr6 &= ~15;
			vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
			kvm_queue_exception(vcpu, DB_VECTOR);
			return 1;
		}
	}

	if (vcpu->guest_debug == 0) {
		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
				CPU_BASED_MOV_DR_EXITING);

		/*
		 * No more DR vmexits; force a reload of the debug registers
		 * and reenter on this instruction.  The next vmexit will
		 * retrieve the full state of the debug registers.
		 */
		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
		return 1;
	}

	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
	if (exit_qualification & TYPE_MOV_FROM_DR) {
		unsigned long val;

		if (kvm_get_dr(vcpu, dr, &val))
			return 1;
		kvm_register_write(vcpu, reg, val);
	} else
		if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)))
			return 1;

	return kvm_skip_emulated_instruction(vcpu);
}

static u64 vmx_get_dr6(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.dr6;
}

static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
{
}

static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
	get_debugreg(vcpu->arch.db[0], 0);
	get_debugreg(vcpu->arch.db[1], 1);
	get_debugreg(vcpu->arch.db[2], 2);
	get_debugreg(vcpu->arch.db[3], 3);
	get_debugreg(vcpu->arch.dr6, 6);
	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);

	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
}

static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
{
	vmcs_writel(GUEST_DR7, val);
}

static int handle_cpuid(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_cpuid(vcpu);
}

static int handle_rdmsr(struct kvm_vcpu *vcpu)
{
	u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
	struct msr_data msr_info;

	msr_info.index = ecx;
	msr_info.host_initiated = false;
	if (vmx_get_msr(vcpu, &msr_info)) {
		trace_kvm_msr_read_ex(ecx);
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	trace_kvm_msr_read(ecx, msr_info.data);

	/* FIXME: handling of bits 32:63 of rax, rdx */
	vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u;
	vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u;
	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_wrmsr(struct kvm_vcpu *vcpu)
{
	struct msr_data msr;
	u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
	u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
		| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);

	msr.data = data;
	msr.index = ecx;
	msr.host_initiated = false;
	if (kvm_set_msr(vcpu, &msr) != 0) {
		trace_kvm_msr_write_ex(ecx, data);
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	trace_kvm_msr_write(ecx, data);
	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
{
	kvm_apic_update_ppr(vcpu);
	return 1;
}

static int handle_interrupt_window(struct kvm_vcpu *vcpu)
{
	vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
			CPU_BASED_VIRTUAL_INTR_PENDING);

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	++vcpu->stat.irq_window_exits;
	return 1;
}

static int handle_halt(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_halt(vcpu);
}

static int handle_vmcall(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_hypercall(vcpu);
}

static int handle_invd(struct kvm_vcpu *vcpu)
{
	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
}

static int handle_invlpg(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);

	kvm_mmu_invlpg(vcpu, exit_qualification);
	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_rdpmc(struct kvm_vcpu *vcpu)
{
	int err;

	err = kvm_rdpmc(vcpu);
	return kvm_complete_insn_gp(vcpu, err);
}

static int handle_wbinvd(struct kvm_vcpu *vcpu)
{
	return kvm_emulate_wbinvd(vcpu);
}

static int handle_xsetbv(struct kvm_vcpu *vcpu)
{
	u64 new_bv = kvm_read_edx_eax(vcpu);
	u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);

	if (kvm_set_xcr(vcpu, index, new_bv) == 0)
		return kvm_skip_emulated_instruction(vcpu);
	return 1;
}

static int handle_xsaves(struct kvm_vcpu *vcpu)
{
	kvm_skip_emulated_instruction(vcpu);
	WARN(1, "this should never happen\n");
	return 1;
}

static int handle_xrstors(struct kvm_vcpu *vcpu)
{
	kvm_skip_emulated_instruction(vcpu);
	WARN(1, "this should never happen\n");
	return 1;
}

static int handle_apic_access(struct kvm_vcpu *vcpu)
{
	if (likely(fasteoi)) {
		unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
		int access_type, offset;

		access_type = exit_qualification & APIC_ACCESS_TYPE;
		offset = exit_qualification & APIC_ACCESS_OFFSET;
		/*
		 * Sane guest uses MOV to write EOI, with written value
		 * not cared. So make a short-circuit here by avoiding
		 * heavy instruction emulation.
		 */
		if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) &&
		    (offset == APIC_EOI)) {
			kvm_lapic_set_eoi(vcpu);
			return kvm_skip_emulated_instruction(vcpu);
		}
	}
	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
}

static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	int vector = exit_qualification & 0xff;

	/* EOI-induced VM exit is trap-like and thus no need to adjust IP */
	kvm_apic_set_eoi_accelerated(vcpu, vector);
	return 1;
}

static int handle_apic_write(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	u32 offset = exit_qualification & 0xfff;

	/* APIC-write VM exit is trap-like and thus no need to adjust IP */
	kvm_apic_write_nodecode(vcpu, offset);
	return 1;
}

static int handle_task_switch(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long exit_qualification;
	bool has_error_code = false;
	u32 error_code = 0;
	u16 tss_selector;
	int reason, type, idt_v, idt_index;

	idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
	idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK);
	type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);

	reason = (u32)exit_qualification >> 30;
	if (reason == TASK_SWITCH_GATE && idt_v) {
		switch (type) {
		case INTR_TYPE_NMI_INTR:
			vcpu->arch.nmi_injected = false;
			vmx_set_nmi_mask(vcpu, true);
			break;
		case INTR_TYPE_EXT_INTR:
		case INTR_TYPE_SOFT_INTR:
			kvm_clear_interrupt_queue(vcpu);
			break;
		case INTR_TYPE_HARD_EXCEPTION:
			if (vmx->idt_vectoring_info &
			    VECTORING_INFO_DELIVER_CODE_MASK) {
				has_error_code = true;
				error_code =
					vmcs_read32(IDT_VECTORING_ERROR_CODE);
			}
			/* fall through */
		case INTR_TYPE_SOFT_EXCEPTION:
			kvm_clear_exception_queue(vcpu);
			break;
		default:
			break;
		}
	}
	tss_selector = exit_qualification;

	if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
		       type != INTR_TYPE_EXT_INTR &&
		       type != INTR_TYPE_NMI_INTR))
		skip_emulated_instruction(vcpu);

	if (kvm_task_switch(vcpu, tss_selector,
			    type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason,
			    has_error_code, error_code) == EMULATE_FAIL) {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
		vcpu->run->internal.ndata = 0;
		return 0;
	}

	/*
	 * TODO: What about debug traps on tss switch?
	 *       Are we supposed to inject them and update dr6?
	 */

	return 1;
}

static int handle_ept_violation(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification;
	gpa_t gpa;
	u64 error_code;

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);

	/*
	 * EPT violation happened while executing iret from NMI,
	 * "blocked by NMI" bit has to be set before next VM entry.
	 * There are errata that may cause this bit to not be set:
	 * AAK134, BY25.
	 */
	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);

	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
	trace_kvm_page_fault(gpa, exit_qualification);

	/* Is it a read fault? */
	error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
		     ? PFERR_USER_MASK : 0;
	/* Is it a write fault? */
	error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
		      ? PFERR_WRITE_MASK : 0;
	/* Is it a fetch fault? */
	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
		      ? PFERR_FETCH_MASK : 0;
	/* ept page table entry is present? */
	error_code |= (exit_qualification &
		       (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE |
			EPT_VIOLATION_EXECUTABLE))
		      ? PFERR_PRESENT_MASK : 0;

	error_code |= (exit_qualification & 0x100) != 0 ?
	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;

	vcpu->arch.exit_qualification = exit_qualification;
	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
}

static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
{
	int ret;
	gpa_t gpa;

	/*
	 * A nested guest cannot optimize MMIO vmexits, because we have an
	 * nGPA here instead of the required GPA.
	 */
	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
	if (!is_guest_mode(vcpu) &&
	    !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
		trace_kvm_fast_mmio(gpa);
		return kvm_skip_emulated_instruction(vcpu);
	}

	ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
	if (ret >= 0)
		return ret;

	/* It is the real ept misconfig */
	WARN_ON(1);

	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
	vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;

	return 0;
}

static int handle_nmi_window(struct kvm_vcpu *vcpu)
{
	vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
			CPU_BASED_VIRTUAL_NMI_PENDING);
	++vcpu->stat.nmi_window_exits;
	kvm_make_request(KVM_REQ_EVENT, vcpu);

	return 1;
}

static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	enum emulation_result err = EMULATE_DONE;
	int ret = 1;
	u32 cpu_exec_ctrl;
	bool intr_window_requested;
	unsigned count = 130;

	cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
	intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING;

	while (vmx->emulation_required && count-- != 0) {
		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
			return handle_interrupt_window(&vmx->vcpu);

		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
			return 1;

		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);

		if (err == EMULATE_USER_EXIT) {
			++vcpu->stat.mmio_exits;
			ret = 0;
			goto out;
		}

		if (err != EMULATE_DONE) {
			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
			vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
			vcpu->run->internal.ndata = 0;
			return 0;
		}

		if (vcpu->arch.halt_request) {
			vcpu->arch.halt_request = 0;
			ret = kvm_vcpu_halt(vcpu);
			goto out;
		}

		if (signal_pending(current))
			goto out;
		if (need_resched())
			schedule();
	}

out:
	return ret;
}

static int __grow_ple_window(int val)
{
	if (ple_window_grow < 1)
		return ple_window;

	val = min(val, ple_window_actual_max);

	if (ple_window_grow < ple_window)
		val *= ple_window_grow;
	else
		val += ple_window_grow;

	return val;
}

static int __shrink_ple_window(int val, int modifier, int minimum)
{
	if (modifier < 1)
		return ple_window;

	if (modifier < ple_window)
		val /= modifier;
	else
		val -= modifier;

	return max(val, minimum);
}

static void grow_ple_window(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int old = vmx->ple_window;

	vmx->ple_window = __grow_ple_window(old);

	if (vmx->ple_window != old)
		vmx->ple_window_dirty = true;

	trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old);
}

static void shrink_ple_window(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int old = vmx->ple_window;

	vmx->ple_window = __shrink_ple_window(old,
	                                      ple_window_shrink, ple_window);

	if (vmx->ple_window != old)
		vmx->ple_window_dirty = true;

	trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old);
}

/*
 * ple_window_actual_max is computed to be one grow_ple_window() below
 * ple_window_max. (See __grow_ple_window for the reason.)
 * This prevents overflows, because ple_window_max is int.
 * ple_window_max effectively rounded down to a multiple of ple_window_grow in
 * this process.
 * ple_window_max is also prevented from setting vmx->ple_window < ple_window.
 */
static void update_ple_window_actual_max(void)
{
	ple_window_actual_max =
			__shrink_ple_window(max(ple_window_max, ple_window),
			                    ple_window_grow, INT_MIN);
}

/*
 * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
 */
static void wakeup_handler(void)
{
	struct kvm_vcpu *vcpu;
	int cpu = smp_processor_id();

	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
			blocked_vcpu_list) {
		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);

		if (pi_test_on(pi_desc) == 1)
			kvm_vcpu_kick(vcpu);
	}
	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
}

void vmx_enable_tdp(void)
{
	kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
		enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull,
		enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
		0ull, VMX_EPT_EXECUTABLE_MASK,
		cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
		VMX_EPT_RWX_MASK, 0ull);

	ept_set_mmio_spte_mask();
	kvm_enable_tdp();
}

static __init int hardware_setup(void)
{
	int r = -ENOMEM, i, msr;

	rdmsrl_safe(MSR_EFER, &host_efer);

	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
		kvm_define_shared_msr(i, vmx_msr_index[i]);

	for (i = 0; i < VMX_BITMAP_NR; i++) {
		vmx_bitmap[i] = (unsigned long *)__get_free_page(GFP_KERNEL);
		if (!vmx_bitmap[i])
			goto out;
	}

	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);

	/*
	 * Allow direct access to the PC debug port (it is often used for I/O
	 * delays, but the vmexits simply slow things down).
	 */
	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
	clear_bit(0x80, vmx_io_bitmap_a);

	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);

	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);

	if (setup_vmcs_config(&vmcs_config) < 0) {
		r = -EIO;
		goto out;
	}

	if (boot_cpu_has(X86_FEATURE_NX))
		kvm_enable_efer_bits(EFER_NX);

	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
		enable_vpid = 0;

	if (!cpu_has_vmx_shadow_vmcs())
		enable_shadow_vmcs = 0;
	if (enable_shadow_vmcs)
		init_vmcs_shadow_fields();

	if (!cpu_has_vmx_ept() ||
	    !cpu_has_vmx_ept_4levels() ||
	    !cpu_has_vmx_ept_mt_wb()) {
		enable_ept = 0;
		enable_unrestricted_guest = 0;
		enable_ept_ad_bits = 0;
	}

	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
		enable_ept_ad_bits = 0;

	if (!cpu_has_vmx_unrestricted_guest())
		enable_unrestricted_guest = 0;

	if (!cpu_has_vmx_flexpriority())
		flexpriority_enabled = 0;

	/*
	 * set_apic_access_page_addr() is used to reload apic access
	 * page upon invalidation.  No need to do anything if not
	 * using the APIC_ACCESS_ADDR VMCS field.
	 */
	if (!flexpriority_enabled)
		kvm_x86_ops->set_apic_access_page_addr = NULL;

	if (!cpu_has_vmx_tpr_shadow())
		kvm_x86_ops->update_cr8_intercept = NULL;

	if (enable_ept && !cpu_has_vmx_ept_2m_page())
		kvm_disable_largepages();

	if (!cpu_has_vmx_ple())
		ple_gap = 0;

	if (!cpu_has_vmx_apicv()) {
		enable_apicv = 0;
		kvm_x86_ops->sync_pir_to_irr = NULL;
	}

	if (cpu_has_vmx_tsc_scaling()) {
		kvm_has_tsc_control = true;
		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
		kvm_tsc_scaling_ratio_frac_bits = 48;
	}

	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);

	memcpy(vmx_msr_bitmap_legacy_x2apic_apicv,
			vmx_msr_bitmap_legacy, PAGE_SIZE);
	memcpy(vmx_msr_bitmap_longmode_x2apic_apicv,
			vmx_msr_bitmap_longmode, PAGE_SIZE);
	memcpy(vmx_msr_bitmap_legacy_x2apic,
			vmx_msr_bitmap_legacy, PAGE_SIZE);
	memcpy(vmx_msr_bitmap_longmode_x2apic,
			vmx_msr_bitmap_longmode, PAGE_SIZE);

	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */

	for (msr = 0x800; msr <= 0x8ff; msr++) {
		if (msr == 0x839 /* TMCCT */)
			continue;
		vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true);
	}

	/*
	 * TPR reads and writes can be virtualized even if virtual interrupt
	 * delivery is not in use.
	 */
	vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true);
	vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false);

	/* EOI */
	vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true);
	/* SELF-IPI */
	vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true);

	if (enable_ept)
		vmx_enable_tdp();
	else
		kvm_disable_tdp();

	update_ple_window_actual_max();

	/*
	 * Only enable PML when hardware supports PML feature, and both EPT
	 * and EPT A/D bit features are enabled -- PML depends on them to work.
	 */
	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
		enable_pml = 0;

	if (!enable_pml) {
		kvm_x86_ops->slot_enable_log_dirty = NULL;
		kvm_x86_ops->slot_disable_log_dirty = NULL;
		kvm_x86_ops->flush_log_dirty = NULL;
		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
	}

	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
		u64 vmx_msr;

		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
		cpu_preemption_timer_multi =
			 vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
	} else {
		kvm_x86_ops->set_hv_timer = NULL;
		kvm_x86_ops->cancel_hv_timer = NULL;
	}

	kvm_set_posted_intr_wakeup_handler(wakeup_handler);

	kvm_mce_cap_supported |= MCG_LMCE_P;

	return alloc_kvm_area();

out:
	for (i = 0; i < VMX_BITMAP_NR; i++)
		free_page((unsigned long)vmx_bitmap[i]);

    return r;
}

static __exit void hardware_unsetup(void)
{
	int i;

	for (i = 0; i < VMX_BITMAP_NR; i++)
		free_page((unsigned long)vmx_bitmap[i]);

	free_kvm_area();
}

/*
 * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
 * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
 */
static int handle_pause(struct kvm_vcpu *vcpu)
{
	if (ple_gap)
		grow_ple_window(vcpu);

	/*
	 * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting"
	 * VM-execution control is ignored if CPL > 0. OTOH, KVM
	 * never set PAUSE_EXITING and just set PLE if supported,
	 * so the vcpu must be CPL=0 if it gets a PAUSE exit.
	 */
	kvm_vcpu_on_spin(vcpu, true);
	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_nop(struct kvm_vcpu *vcpu)
{
	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_mwait(struct kvm_vcpu *vcpu)
{
	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
	return handle_nop(vcpu);
}

static int handle_invalid_op(struct kvm_vcpu *vcpu)
{
	kvm_queue_exception(vcpu, UD_VECTOR);
	return 1;
}

static int handle_monitor_trap(struct kvm_vcpu *vcpu)
{
	return 1;
}

static int handle_monitor(struct kvm_vcpu *vcpu)
{
	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
	return handle_nop(vcpu);
}

/*
 * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
 * We could reuse a single VMCS for all the L2 guests, but we also want the
 * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
 * allows keeping them loaded on the processor, and in the future will allow
 * optimizations where prepare_vmcs02 doesn't need to set all the fields on
 * every entry if they never change.
 * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
 * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
 *
 * The following functions allocate and free a vmcs02 in this pool.
 */

/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
{
	struct vmcs02_list *item;
	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
		if (item->vmptr == vmx->nested.current_vmptr) {
			list_move(&item->list, &vmx->nested.vmcs02_pool);
			return &item->vmcs02;
		}

	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
		/* Recycle the least recently used VMCS. */
		item = list_last_entry(&vmx->nested.vmcs02_pool,
				       struct vmcs02_list, list);
		item->vmptr = vmx->nested.current_vmptr;
		list_move(&item->list, &vmx->nested.vmcs02_pool);
		return &item->vmcs02;
	}

	/* Create a new VMCS */
	item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
	if (!item)
		return NULL;
	item->vmcs02.vmcs = alloc_vmcs();
	item->vmcs02.shadow_vmcs = NULL;
	if (!item->vmcs02.vmcs) {
		kfree(item);
		return NULL;
	}
	loaded_vmcs_init(&item->vmcs02);
	item->vmptr = vmx->nested.current_vmptr;
	list_add(&(item->list), &(vmx->nested.vmcs02_pool));
	vmx->nested.vmcs02_num++;
	return &item->vmcs02;
}

/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
{
	struct vmcs02_list *item;
	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
		if (item->vmptr == vmptr) {
			free_loaded_vmcs(&item->vmcs02);
			list_del(&item->list);
			kfree(item);
			vmx->nested.vmcs02_num--;
			return;
		}
}

/*
 * Free all VMCSs saved for this vcpu, except the one pointed by
 * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
 * must be &vmx->vmcs01.
 */
static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
{
	struct vmcs02_list *item, *n;

	WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
	list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
		/*
		 * Something will leak if the above WARN triggers.  Better than
		 * a use-after-free.
		 */
		if (vmx->loaded_vmcs == &item->vmcs02)
			continue;

		free_loaded_vmcs(&item->vmcs02);
		list_del(&item->list);
		kfree(item);
		vmx->nested.vmcs02_num--;
	}
}

/*
 * 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".
 */
static void 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));
}

static void 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);
}

static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
					u32 vm_instruction_error)
{
	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
		/*
		 * failValid writes the error number to the current VMCS, which
		 * can't be done there isn't a current VMCS.
		 */
		nested_vmx_failInvalid(vcpu);
		return;
	}
	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 a shadow sync because
	 * VM_INSTRUCTION_ERROR is not shadowed
	 */
}

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("kvm: nested vmx abort, indicator %d\n", indicator);
}

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;
}

/*
 * 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 or #GP.
 */
static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
				 unsigned long exit_qualification,
				 u32 vmx_instruction_info, bool wr, 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 (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);
	*ret = s.base + off;

	if (addr_size == 1) /* 32 bit */
		*ret &= 0xffffffff;

	/* Checks for #GP/#SS exceptions. */
	exn = false;
	if (is_long_mode(vcpu)) {
		/* 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 if (is_protmode(vcpu)) {
		/* 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.
		 */
		exn = exn || (off + sizeof(u64) > 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)
{
	gva_t gva;
	struct x86_exception e;

	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
		return 1;

	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
				sizeof(*vmpointer), &e)) {
		kvm_inject_page_fault(vcpu, &e);
		return 1;
	}

	return 0;
}

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

	if (cpu_has_vmx_msr_bitmap()) {
		vmx->nested.msr_bitmap =
				(unsigned long *)__get_free_page(GFP_KERNEL);
		if (!vmx->nested.msr_bitmap)
			goto out_msr_bitmap;
	}

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

	if (enable_shadow_vmcs) {
		shadow_vmcs = alloc_vmcs();
		if (!shadow_vmcs)
			goto out_shadow_vmcs;
		/* mark vmcs as shadow */
		shadow_vmcs->revision_id |= (1u << 31);
		/* init shadow vmcs */
		vmcs_clear(shadow_vmcs);
		vmx->vmcs01.shadow_vmcs = shadow_vmcs;
	}

	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
	vmx->nested.vmcs02_num = 0;

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

	vmx->nested.vmxon = true;
	return 0;

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

out_cached_vmcs12:
	free_page((unsigned long)vmx->nested.msr_bitmap);

out_msr_bitmap:
	return -ENOMEM;
}

/*
 * Emulate the VMXON instruction.
 * Currently, we just remember that VMX is active, and do not save or even
 * inspect the argument to VMXON (the so-called "VMXON pointer") because we
 * do not currently need to store anything in that guest-allocated memory
 * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
 * argument is different from the VMXON pointer (which the spec says they do).
 */
static int handle_vmon(struct kvm_vcpu *vcpu)
{
	int ret;
	gpa_t vmptr;
	struct page *page;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;

	/*
	 * The Intel VMX Instruction Reference lists a bunch of bits that are
	 * prerequisite to running VMXON, most notably cr4.VMXE must be set to
	 * 1 (see vmx_set_cr4() for when we allow the guest to set this).
	 * Otherwise, we should fail with #UD.  But most faulting conditions
	 * have already been checked by hardware, prior to the VM-exit for
	 * VMXON.  We do test guest cr4.VMXE because processor CR4 always has
	 * that bit set to 1 in non-root mode.
	 */
	if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	if (vmx->nested.vmxon) {
		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
		return kvm_skip_emulated_instruction(vcpu);
	}

	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))
		return 1;

	/*
	 * 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_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
		nested_vmx_failInvalid(vcpu);
		return kvm_skip_emulated_instruction(vcpu);
	}

	page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
	if (is_error_page(page)) {
		nested_vmx_failInvalid(vcpu);
		return kvm_skip_emulated_instruction(vcpu);
	}
	if (*(u32 *)kmap(page) != VMCS12_REVISION) {
		kunmap(page);
		kvm_release_page_clean(page);
		nested_vmx_failInvalid(vcpu);
		return kvm_skip_emulated_instruction(vcpu);
	}
	kunmap(page);
	kvm_release_page_clean(page);

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

	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}

/*
 * 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;
	}
	return 1;
}

static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
{
	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
	vmcs_write64(VMCS_LINK_POINTER, -1ull);
}

static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
{
	if (vmx->nested.current_vmptr == -1ull)
		return;

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

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

	vmx->nested.current_vmptr = -1ull;
}

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

	vmx->nested.vmxon = false;
	free_vpid(vmx->nested.vpid02);
	vmx->nested.posted_intr_nv = -1;
	vmx->nested.current_vmptr = -1ull;
	if (vmx->nested.msr_bitmap) {
		free_page((unsigned long)vmx->nested.msr_bitmap);
		vmx->nested.msr_bitmap = NULL;
	}
	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);
	/* Unpin physical memory we referred to in current vmcs02 */
	if (vmx->nested.apic_access_page) {
		kvm_release_page_dirty(vmx->nested.apic_access_page);
		vmx->nested.apic_access_page = NULL;
	}
	if (vmx->nested.virtual_apic_page) {
		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
		vmx->nested.virtual_apic_page = NULL;
	}
	if (vmx->nested.pi_desc_page) {
		kunmap(vmx->nested.pi_desc_page);
		kvm_release_page_dirty(vmx->nested.pi_desc_page);
		vmx->nested.pi_desc_page = NULL;
		vmx->nested.pi_desc = NULL;
	}

	nested_free_all_saved_vmcss(vmx);
}

/* Emulate the VMXOFF instruction */
static int handle_vmoff(struct kvm_vcpu *vcpu)
{
	if (!nested_vmx_check_permission(vcpu))
		return 1;
	free_nested(to_vmx(vcpu));
	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(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;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (nested_vmx_get_vmptr(vcpu, &vmptr))
		return 1;

	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
		return kvm_skip_emulated_instruction(vcpu);
	}

	if (vmptr == vmx->nested.vmxon_ptr) {
		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
		return kvm_skip_emulated_instruction(vcpu);
	}

	if (vmptr == vmx->nested.current_vmptr)
		nested_release_vmcs12(vmx);

	kvm_vcpu_write_guest(vcpu,
			vmptr + offsetof(struct vmcs12, launch_state),
			&zero, sizeof(zero));

	nested_free_vmcs02(vmx, vmptr);

	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);

/* 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);
}

/*
 * Read a vmcs12 field. Since these can have varying lengths and we return
 * one type, we chose the biggest type (u64) and zero-extend the return value
 * to that size. Note that the caller, handle_vmread, might need to use only
 * some of the bits we return here (e.g., on 32-bit guests, only 32 bits of
 * 64-bit fields are to be returned).
 */
static inline int vmcs12_read_any(struct kvm_vcpu *vcpu,
				  unsigned long field, u64 *ret)
{
	short offset = vmcs_field_to_offset(field);
	char *p;

	if (offset < 0)
		return offset;

	p = ((char *)(get_vmcs12(vcpu))) + offset;

	switch (vmcs_field_type(field)) {
	case VMCS_FIELD_TYPE_NATURAL_WIDTH:
		*ret = *((natural_width *)p);
		return 0;
	case VMCS_FIELD_TYPE_U16:
		*ret = *((u16 *)p);
		return 0;
	case VMCS_FIELD_TYPE_U32:
		*ret = *((u32 *)p);
		return 0;
	case VMCS_FIELD_TYPE_U64:
		*ret = *((u64 *)p);
		return 0;
	default:
		WARN_ON(1);
		return -ENOENT;
	}
}


static inline int vmcs12_write_any(struct kvm_vcpu *vcpu,
				   unsigned long field, u64 field_value){
	short offset = vmcs_field_to_offset(field);
	char *p = ((char *) get_vmcs12(vcpu)) + offset;
	if (offset < 0)
		return offset;

	switch (vmcs_field_type(field)) {
	case VMCS_FIELD_TYPE_U16:
		*(u16 *)p = field_value;
		return 0;
	case VMCS_FIELD_TYPE_U32:
		*(u32 *)p = field_value;
		return 0;
	case VMCS_FIELD_TYPE_U64:
		*(u64 *)p = field_value;
		return 0;
	case VMCS_FIELD_TYPE_NATURAL_WIDTH:
		*(natural_width *)p = field_value;
		return 0;
	default:
		WARN_ON(1);
		return -ENOENT;
	}

}

static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
{
	int i;
	unsigned long field;
	u64 field_value;
	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
	const unsigned long *fields = shadow_read_write_fields;
	const int num_fields = max_shadow_read_write_fields;

	preempt_disable();

	vmcs_load(shadow_vmcs);

	for (i = 0; i < num_fields; i++) {
		field = fields[i];
		switch (vmcs_field_type(field)) {
		case VMCS_FIELD_TYPE_U16:
			field_value = vmcs_read16(field);
			break;
		case VMCS_FIELD_TYPE_U32:
			field_value = vmcs_read32(field);
			break;
		case VMCS_FIELD_TYPE_U64:
			field_value = vmcs_read64(field);
			break;
		case VMCS_FIELD_TYPE_NATURAL_WIDTH:
			field_value = vmcs_readl(field);
			break;
		default:
			WARN_ON(1);
			continue;
		}
		vmcs12_write_any(&vmx->vcpu, field, field_value);
	}

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

	preempt_enable();
}

static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
{
	const unsigned long *fields[] = {
		shadow_read_write_fields,
		shadow_read_only_fields
	};
	const int max_fields[] = {
		max_shadow_read_write_fields,
		max_shadow_read_only_fields
	};
	int i, q;
	unsigned long field;
	u64 field_value = 0;
	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;

	vmcs_load(shadow_vmcs);

	for (q = 0; q < ARRAY_SIZE(fields); q++) {
		for (i = 0; i < max_fields[q]; i++) {
			field = fields[q][i];
			vmcs12_read_any(&vmx->vcpu, field, &field_value);

			switch (vmcs_field_type(field)) {
			case VMCS_FIELD_TYPE_U16:
				vmcs_write16(field, (u16)field_value);
				break;
			case VMCS_FIELD_TYPE_U32:
				vmcs_write32(field, (u32)field_value);
				break;
			case VMCS_FIELD_TYPE_U64:
				vmcs_write64(field, (u64)field_value);
				break;
			case VMCS_FIELD_TYPE_NATURAL_WIDTH:
				vmcs_writel(field, (long)field_value);
				break;
			default:
				WARN_ON(1);
				break;
			}
		}
	}

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

/*
 * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was
 * used before) all generate the same failure when it is missing.
 */
static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	if (vmx->nested.current_vmptr == -1ull) {
		nested_vmx_failInvalid(vcpu);
		return 0;
	}
	return 1;
}

static int handle_vmread(struct kvm_vcpu *vcpu)
{
	unsigned long field;
	u64 field_value;
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	gva_t gva = 0;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (!nested_vmx_check_vmcs12(vcpu))
		return kvm_skip_emulated_instruction(vcpu);

	/* Decode instruction info and find the field to read */
	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
	/* Read the field, zero-extended to a u64 field_value */
	if (vmcs12_read_any(vcpu, field, &field_value) < 0) {
		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
		return kvm_skip_emulated_instruction(vcpu);
	}
	/*
	 * 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 (vmx_instruction_info & (1u << 10)) {
		kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
			field_value);
	} else {
		if (get_vmx_mem_address(vcpu, exit_qualification,
				vmx_instruction_info, true, &gva))
			return 1;
		/* _system ok, as hardware has verified cpl=0 */
		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
			     &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
	}

	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}


static int handle_vmwrite(struct kvm_vcpu *vcpu)
{
	unsigned long field;
	gva_t gva;
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	/* 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 (field_value), and then copies only the appropriate number of
	 * bits into the vmcs12 field.
	 */
	u64 field_value = 0;
	struct x86_exception e;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (!nested_vmx_check_vmcs12(vcpu))
		return kvm_skip_emulated_instruction(vcpu);

	if (vmx_instruction_info & (1u << 10))
		field_value = kvm_register_readl(vcpu,
			(((vmx_instruction_info) >> 3) & 0xf));
	else {
		if (get_vmx_mem_address(vcpu, exit_qualification,
				vmx_instruction_info, false, &gva))
			return 1;
		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
			kvm_inject_page_fault(vcpu, &e);
			return 1;
		}
	}


	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
	if (vmcs_field_readonly(field)) {
		nested_vmx_failValid(vcpu,
			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
		return kvm_skip_emulated_instruction(vcpu);
	}

	if (vmcs12_write_any(vcpu, field, field_value) < 0) {
		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
		return kvm_skip_emulated_instruction(vcpu);
	}

	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}

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

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

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (nested_vmx_get_vmptr(vcpu, &vmptr))
		return 1;

	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
		return kvm_skip_emulated_instruction(vcpu);
	}

	if (vmptr == vmx->nested.vmxon_ptr) {
		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
		return kvm_skip_emulated_instruction(vcpu);
	}

	if (vmx->nested.current_vmptr != vmptr) {
		struct vmcs12 *new_vmcs12;
		struct page *page;
		page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
		if (is_error_page(page)) {
			nested_vmx_failInvalid(vcpu);
			return kvm_skip_emulated_instruction(vcpu);
		}
		new_vmcs12 = kmap(page);
		if (new_vmcs12->revision_id != VMCS12_REVISION) {
			kunmap(page);
			kvm_release_page_clean(page);
			nested_vmx_failValid(vcpu,
				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
			return kvm_skip_emulated_instruction(vcpu);
		}

		nested_release_vmcs12(vmx);
		/*
		 * Load VMCS12 from guest memory since it is not already
		 * cached.
		 */
		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
		kunmap(page);
		kvm_release_page_clean(page);

		set_current_vmptr(vmx, vmptr);
	}

	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(vcpu);
}

/* Emulate the VMPTRST instruction */
static int handle_vmptrst(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	gva_t vmcs_gva;
	struct x86_exception e;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (get_vmx_mem_address(vcpu, exit_qualification,
			vmx_instruction_info, true, &vmcs_gva))
		return 1;
	/* ok to use *_system, as hardware has verified cpl=0 */
	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
				 (void *)&to_vmx(vcpu)->nested.current_vmptr,
				 sizeof(u64), &e)) {
		kvm_inject_page_fault(vcpu, &e);
		return 1;
	}
	nested_vmx_succeed(vcpu);
	return kvm_skip_emulated_instruction(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;
	gva_t gva;
	struct x86_exception e;
	struct {
		u64 eptp, gpa;
	} operand;

	if (!(vmx->nested.nested_vmx_secondary_ctls_high &
	      SECONDARY_EXEC_ENABLE_EPT) ||
	    !(vmx->nested.nested_vmx_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);
	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);

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

	if (type >= 32 || !(types & (1 << type))) {
		nested_vmx_failValid(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
		return kvm_skip_emulated_instruction(vcpu);
	}

	/* 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, vmcs_readl(EXIT_QUALIFICATION),
			vmx_instruction_info, false, &gva))
		return 1;
	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
				sizeof(operand), &e)) {
		kvm_inject_page_fault(vcpu, &e);
		return 1;
	}

	switch (type) {
	case VMX_EPT_EXTENT_GLOBAL:
	/*
	 * TODO: track mappings and invalidate
	 * single context requests appropriately
	 */
	case VMX_EPT_EXTENT_CONTEXT:
		kvm_mmu_sync_roots(vcpu);
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
		nested_vmx_succeed(vcpu);
		break;
	default:
		BUG_ON(1);
		break;
	}

	return kvm_skip_emulated_instruction(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;

	if (!(vmx->nested.nested_vmx_secondary_ctls_high &
	      SECONDARY_EXEC_ENABLE_VPID) ||
			!(vmx->nested.nested_vmx_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);
	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);

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

	if (type >= 32 || !(types & (1 << type))) {
		nested_vmx_failValid(vcpu,
			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
		return kvm_skip_emulated_instruction(vcpu);
	}

	/* 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, vmcs_readl(EXIT_QUALIFICATION),
			vmx_instruction_info, false, &gva))
		return 1;
	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
				sizeof(operand), &e)) {
		kvm_inject_page_fault(vcpu, &e);
		return 1;
	}
	if (operand.vpid >> 16) {
		nested_vmx_failValid(vcpu,
			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
		return kvm_skip_emulated_instruction(vcpu);
	}

	switch (type) {
	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
		if (is_noncanonical_address(operand.gla, vcpu)) {
			nested_vmx_failValid(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
			return kvm_skip_emulated_instruction(vcpu);
		}
		/* fall through */
	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
		if (!operand.vpid) {
			nested_vmx_failValid(vcpu,
				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
			return kvm_skip_emulated_instruction(vcpu);
		}
		break;
	case VMX_VPID_EXTENT_ALL_CONTEXT:
		break;
	default:
		WARN_ON_ONCE(1);
		return kvm_skip_emulated_instruction(vcpu);
	}

	__vmx_flush_tlb(vcpu, vmx->nested.vpid02);
	nested_vmx_succeed(vcpu);

	return kvm_skip_emulated_instruction(vcpu);
}

static int handle_pml_full(struct kvm_vcpu *vcpu)
{
	unsigned long exit_qualification;

	trace_kvm_pml_full(vcpu->vcpu_id);

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);

	/*
	 * PML buffer FULL happened while executing iret from NMI,
	 * "blocked by NMI" bit has to be set before next VM entry.
	 */
	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
				GUEST_INTR_STATE_NMI);

	/*
	 * PML buffer already flushed at beginning of VMEXIT. Nothing to do
	 * here.., and there's no userspace involvement needed for PML.
	 */
	return 1;
}

static int handle_preemption_timer(struct kvm_vcpu *vcpu)
{
	kvm_lapic_expired_hv_timer(vcpu);
	return 1;
}

static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int maxphyaddr = cpuid_maxphyaddr(vcpu);

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

	/* only 4 levels page-walk length are valid */
	if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)
		return false;

	/* Reserved bits should not be set */
	if (address >> maxphyaddr || ((address >> 7) & 0x1f))
		return false;

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

	return true;
}

static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
				     struct vmcs12 *vmcs12)
{
	u32 index = vcpu->arch.regs[VCPU_REGS_RCX];
	u64 address;
	bool accessed_dirty;
	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;

	if (!nested_cpu_has_eptp_switching(vmcs12) ||
	    !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,
				     &address, index * 8, 8))
		return 1;

	accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);

	/*
	 * 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 != address) {
		if (!valid_ept_address(vcpu, address))
			return 1;

		kvm_mmu_unload(vcpu);
		mmu->ept_ad = accessed_dirty;
		mmu->base_role.ad_disabled = !accessed_dirty;
		vmcs12->ept_pointer = address;
		/*
		 * TODO: Check what's the correct approach in case
		 * mmu reload fails. Currently, we just let the next
		 * reload potentially fail
		 */
		kvm_mmu_reload(vcpu);
	}

	return 0;
}

static int handle_vmfunc(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12;
	u32 function = vcpu->arch.regs[VCPU_REGS_RAX];

	/*
	 * VMFUNC is only supported for nested guests, but we always enable the
	 * secondary control for simplicity; for non-nested mode, fake that we
	 * didn't by injecting #UD.
	 */
	if (!is_guest_mode(vcpu)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	vmcs12 = get_vmcs12(vcpu);
	if ((vmcs12->vm_function_control & (1 << function)) == 0)
		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:
	nested_vmx_vmexit(vcpu, vmx->exit_reason,
			  vmcs_read32(VM_EXIT_INTR_INFO),
			  vmcs_readl(EXIT_QUALIFICATION));
	return 1;
}

/*
 * The exit handlers return 1 if the exit was handled fully and guest execution
 * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
 * to be done to userspace and return 0.
 */
static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
	[EXIT_REASON_NMI_WINDOW]	      = handle_nmi_window,
	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
	[EXIT_REASON_CR_ACCESS]               = handle_cr,
	[EXIT_REASON_DR_ACCESS]               = handle_dr,
	[EXIT_REASON_CPUID]                   = handle_cpuid,
	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
	[EXIT_REASON_HLT]                     = handle_halt,
	[EXIT_REASON_INVD]		      = handle_invd,
	[EXIT_REASON_INVLPG]		      = handle_invlpg,
	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
	[EXIT_REASON_VMCALL]                  = handle_vmcall,
	[EXIT_REASON_VMCLEAR]	              = handle_vmclear,
	[EXIT_REASON_VMLAUNCH]                = handle_vmlaunch,
	[EXIT_REASON_VMPTRLD]                 = handle_vmptrld,
	[EXIT_REASON_VMPTRST]                 = handle_vmptrst,
	[EXIT_REASON_VMREAD]                  = handle_vmread,
	[EXIT_REASON_VMRESUME]                = handle_vmresume,
	[EXIT_REASON_VMWRITE]                 = handle_vmwrite,
	[EXIT_REASON_VMOFF]                   = handle_vmoff,
	[EXIT_REASON_VMON]                    = handle_vmon,
	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
	[EXIT_REASON_APIC_WRITE]              = handle_apic_write,
	[EXIT_REASON_EOI_INDUCED]             = handle_apic_eoi_induced,
	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
	[EXIT_REASON_MONITOR_TRAP_FLAG]       = handle_monitor_trap,
	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
	[EXIT_REASON_INVEPT]                  = handle_invept,
	[EXIT_REASON_INVVPID]                 = handle_invvpid,
	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
	[EXIT_REASON_XSAVES]                  = handle_xsaves,
	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
	[EXIT_REASON_VMFUNC]                  = handle_vmfunc,
	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
};

static const int kvm_vmx_max_exit_handlers =
	ARRAY_SIZE(kvm_vmx_exit_handlers);

static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
				       struct vmcs12 *vmcs12)
{
	unsigned long exit_qualification;
	gpa_t bitmap, last_bitmap;
	unsigned int port;
	int size;
	u8 b;

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

	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);

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

	last_bitmap = (gpa_t)-1;
	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;
}

/*
 * Return 1 if we should exit from L2 to L1 to handle an MSR access 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, u32 exit_reason)
{
	u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
	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 == 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 = vmcs_readl(EXIT_QUALIFICATION);
	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_readl(vcpu, reg);
		switch (cr) {
		case 0:
			if (vmcs12->cr0_guest_host_mask &
			    (val ^ vmcs12->cr0_read_shadow))
				return true;
			break;
		case 3:
			if ((vmcs12->cr3_target_count >= 1 &&
					vmcs12->cr3_target_value0 == val) ||
				(vmcs12->cr3_target_count >= 2 &&
					vmcs12->cr3_target_value1 == val) ||
				(vmcs12->cr3_target_count >= 3 &&
					vmcs12->cr3_target_value2 == val) ||
				(vmcs12->cr3_target_count >= 4 &&
					vmcs12->cr3_target_value3 == val))
				return false;
			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;
}

/*
 * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
 * should handle it ourselves in L0 (and then continue L2). Only call this
 * when in is_guest_mode (L2).
 */
static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
{
	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	if (vmx->nested.nested_run_pending)
		return false;

	if (unlikely(vmx->fail)) {
		pr_info_ratelimited("%s failed vm entry %x\n", __func__,
				    vmcs_read32(VM_INSTRUCTION_ERROR));
		return true;
	}

	/*
	 * The host physical addresses of some pages of guest memory
	 * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
	 * may write to these pages via their host physical address while
	 * L2 is running, bypassing any address-translation-based dirty
	 * tracking (e.g. EPT write protection).
	 *
	 * Mark them dirty on every exit from L2 to prevent them from
	 * getting out of sync with dirty tracking.
	 */
	nested_mark_vmcs12_pages_dirty(vcpu);

	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
				vmcs_readl(EXIT_QUALIFICATION),
				vmx->idt_vectoring_info,
				intr_info,
				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
				KVM_ISA_VMX);

	switch (exit_reason) {
	case EXIT_REASON_EXCEPTION_NMI:
		if (is_nmi(intr_info))
			return false;
		else if (is_page_fault(intr_info))
			return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
		else if (is_no_device(intr_info) &&
			 !(vmcs12->guest_cr0 & X86_CR0_TS))
			return false;
		else if (is_debug(intr_info) &&
			 vcpu->guest_debug &
			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
			return false;
		else if (is_breakpoint(intr_info) &&
			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
			return false;
		return vmcs12->exception_bitmap &
				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
	case EXIT_REASON_EXTERNAL_INTERRUPT:
		return false;
	case EXIT_REASON_TRIPLE_FAULT:
		return true;
	case EXIT_REASON_PENDING_INTERRUPT:
		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
	case EXIT_REASON_NMI_WINDOW:
		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
	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);
	case EXIT_REASON_RDSEED:
		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED);
	case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP:
		return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
	case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
	case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
	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_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
	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 false;
	case EXIT_REASON_TPR_BELOW_THRESHOLD:
		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
	case EXIT_REASON_APIC_ACCESS:
		return nested_cpu_has2(vmcs12,
			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
	case EXIT_REASON_APIC_WRITE:
	case EXIT_REASON_EOI_INDUCED:
		/* apic_write and eoi_induced should exit unconditionally. */
		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 false;
	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 false;
	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_XSAVES);
	case EXIT_REASON_PREEMPTION_TIMER:
		return false;
	case EXIT_REASON_PML_FULL:
		/* We emulate PML support to L1. */
		return false;
	case EXIT_REASON_VMFUNC:
		/* VM functions are emulated through L2->L0 vmexits. */
		return false;
	default:
		return true;
	}
}

static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
{
	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);

	/*
	 * At this point, the exit interruption info in exit_intr_info
	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
	 * we need to query the in-kernel LAPIC.
	 */
	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
	if ((exit_intr_info &
	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
		vmcs12->vm_exit_intr_error_code =
			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
	}

	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
			  vmcs_readl(EXIT_QUALIFICATION));
	return 1;
}

static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
{
	*info1 = vmcs_readl(EXIT_QUALIFICATION);
	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
}

static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
{
	if (vmx->pml_pg) {
		__free_page(vmx->pml_pg);
		vmx->pml_pg = NULL;
	}
}

static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 *pml_buf;
	u16 pml_idx;

	pml_idx = vmcs_read16(GUEST_PML_INDEX);

	/* Do nothing if PML buffer is empty */
	if (pml_idx == (PML_ENTITY_NUM - 1))
		return;

	/* PML index always points to next available PML buffer entity */
	if (pml_idx >= PML_ENTITY_NUM)
		pml_idx = 0;
	else
		pml_idx++;

	pml_buf = page_address(vmx->pml_pg);
	for (; pml_idx < PML_ENTITY_NUM; pml_idx++) {
		u64 gpa;

		gpa = pml_buf[pml_idx];
		WARN_ON(gpa & (PAGE_SIZE - 1));
		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
	}

	/* reset PML index */
	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
}

/*
 * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap.
 * Called before reporting dirty_bitmap to userspace.
 */
static void kvm_flush_pml_buffers(struct kvm *kvm)
{
	int i;
	struct kvm_vcpu *vcpu;
	/*
	 * We only need to kick vcpu out of guest mode here, as PML buffer
	 * is flushed at beginning of all VMEXITs, and it's obvious that only
	 * vcpus running in guest are possible to have unflushed GPAs in PML
	 * buffer.
	 */
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_vcpu_kick(vcpu);
}

static void vmx_dump_sel(char *name, uint32_t sel)
{
	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
	       name, vmcs_read16(sel),
	       vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
	       vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
	       vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
}

static void vmx_dump_dtsel(char *name, uint32_t limit)
{
	pr_err("%s                           limit=0x%08x, base=0x%016lx\n",
	       name, vmcs_read32(limit),
	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}

static void dump_vmcs(void)
{
	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
	u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
	u32 secondary_exec_control = 0;
	unsigned long cr4 = vmcs_readl(GUEST_CR4);
	u64 efer = vmcs_read64(GUEST_IA32_EFER);
	int i, n;

	if (cpu_has_secondary_exec_ctrls())
		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);

	pr_err("*** Guest State ***\n");
	pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
	       vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
	       vmcs_readl(CR0_GUEST_HOST_MASK));
	pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
	       cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
	pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
	{
		pr_err("PDPTR0 = 0x%016llx  PDPTR1 = 0x%016llx\n",
		       vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1));
		pr_err("PDPTR2 = 0x%016llx  PDPTR3 = 0x%016llx\n",
		       vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3));
	}
	pr_err("RSP = 0x%016lx  RIP = 0x%016lx\n",
	       vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
	pr_err("RFLAGS=0x%08lx         DR7 = 0x%016lx\n",
	       vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
	       vmcs_readl(GUEST_SYSENTER_ESP),
	       vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
	vmx_dump_sel("CS:  ", GUEST_CS_SELECTOR);
	vmx_dump_sel("DS:  ", GUEST_DS_SELECTOR);
	vmx_dump_sel("SS:  ", GUEST_SS_SELECTOR);
	vmx_dump_sel("ES:  ", GUEST_ES_SELECTOR);
	vmx_dump_sel("FS:  ", GUEST_FS_SELECTOR);
	vmx_dump_sel("GS:  ", GUEST_GS_SELECTOR);
	vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
		       efer, vmcs_read64(GUEST_IA32_PAT));
	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
	       vmcs_read64(GUEST_IA32_DEBUGCTL),
	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
		pr_err("PerfGlobCtl = 0x%016llx\n",
		       vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL));
	if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
		pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS));
	pr_err("Interruptibility = %08x  ActivityState = %08x\n",
	       vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
	       vmcs_read32(GUEST_ACTIVITY_STATE));
	if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
		pr_err("InterruptStatus = %04x\n",
		       vmcs_read16(GUEST_INTR_STATUS));

	pr_err("*** Host State ***\n");
	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
	       vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
	pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
	       vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
	       vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
	       vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
	       vmcs_read16(HOST_TR_SELECTOR));
	pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
	       vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
	       vmcs_readl(HOST_TR_BASE));
	pr_err("GDTBase=%016lx IDTBase=%016lx\n",
	       vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
	pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
	       vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
	       vmcs_readl(HOST_CR4));
	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
	       vmcs_readl(HOST_IA32_SYSENTER_ESP),
	       vmcs_read32(HOST_IA32_SYSENTER_CS),
	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
		pr_err("EFER = 0x%016llx  PAT = 0x%016llx\n",
		       vmcs_read64(HOST_IA32_EFER),
		       vmcs_read64(HOST_IA32_PAT));
	if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
		pr_err("PerfGlobCtl = 0x%016llx\n",
		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));

	pr_err("*** Control State ***\n");
	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
	       pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
	pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
	pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
	       vmcs_read32(EXCEPTION_BITMAP),
	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
	pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
	       vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
	       vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
	       vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
	pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
	       vmcs_read32(VM_EXIT_INTR_INFO),
	       vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
	       vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
	pr_err("        reason=%08x qualification=%016lx\n",
	       vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
	pr_err("IDTVectoring: info=%08x errcode=%08x\n",
	       vmcs_read32(IDT_VECTORING_INFO_FIELD),
	       vmcs_read32(IDT_VECTORING_ERROR_CODE));
	pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET));
	if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
		pr_err("TSC Multiplier = 0x%016llx\n",
		       vmcs_read64(TSC_MULTIPLIER));
	if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
		pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
	if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
		pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
		pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER));
	n = vmcs_read32(CR3_TARGET_COUNT);
	for (i = 0; i + 1 < n; i += 4)
		pr_err("CR3 target%u=%016lx target%u=%016lx\n",
		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
		       i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
	if (i < n)
		pr_err("CR3 target%u=%016lx\n",
		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
	if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
		pr_err("PLE Gap=%08x Window=%08x\n",
		       vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
	if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
		pr_err("Virtual processor ID = 0x%04x\n",
		       vmcs_read16(VIRTUAL_PROCESSOR_ID));
}

/*
 * The guest has exited.  See if we can fix it or if we need userspace
 * assistance.
 */
static int vmx_handle_exit(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 exit_reason = vmx->exit_reason;
	u32 vectoring_info = vmx->idt_vectoring_info;

	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);

	/*
	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more
	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
	 * querying dirty_bitmap, we only need to kick all vcpus out of guest
	 * mode as if vcpus is in root mode, the PML buffer must has been
	 * flushed already.
	 */
	if (enable_pml)
		vmx_flush_pml_buffer(vcpu);

	/* If guest state is invalid, start emulating */
	if (vmx->emulation_required)
		return handle_invalid_guest_state(vcpu);

	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
		return nested_vmx_reflect_vmexit(vcpu, exit_reason);

	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
		dump_vmcs();
		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		vcpu->run->fail_entry.hardware_entry_failure_reason
			= exit_reason;
		return 0;
	}

	if (unlikely(vmx->fail)) {
		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		vcpu->run->fail_entry.hardware_entry_failure_reason
			= vmcs_read32(VM_INSTRUCTION_ERROR);
		return 0;
	}

	/*
	 * Note:
	 * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by
	 * delivery event since it indicates guest is accessing MMIO.
	 * The vm-exit can be triggered again after return to guest that
	 * will cause infinite loop.
	 */
	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
			exit_reason != EXIT_REASON_EPT_VIOLATION &&
			exit_reason != EXIT_REASON_PML_FULL &&
			exit_reason != EXIT_REASON_TASK_SWITCH)) {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
		vcpu->run->internal.ndata = 3;
		vcpu->run->internal.data[0] = vectoring_info;
		vcpu->run->internal.data[1] = exit_reason;
		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
		if (exit_reason == EXIT_REASON_EPT_MISCONFIG) {
			vcpu->run->internal.ndata++;
			vcpu->run->internal.data[3] =
				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
		}
		return 0;
	}

	if (exit_reason < kvm_vmx_max_exit_handlers
	    && kvm_vmx_exit_handlers[exit_reason])
		return kvm_vmx_exit_handlers[exit_reason](vcpu);
	else {
		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
				exit_reason);
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}
}

static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	if (is_guest_mode(vcpu) &&
		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
		return;

	if (irr == -1 || tpr < irr) {
		vmcs_write32(TPR_THRESHOLD, 0);
		return;
	}

	vmcs_write32(TPR_THRESHOLD, irr);
}

static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
{
	u32 sec_exec_control;

	/* Postpone execution until vmcs01 is the current VMCS. */
	if (is_guest_mode(vcpu)) {
		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
		return;
	}

	if (!cpu_has_vmx_virtualize_x2apic_mode())
		return;

	if (!cpu_need_tpr_shadow(vcpu))
		return;

	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);

	if (set) {
		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
	} else {
		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
		vmx_flush_tlb_ept_only(vcpu);
	}
	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);

	vmx_set_msr_bitmap(vcpu);
}

static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	/*
	 * Currently we do not handle the nested case where L2 has an
	 * APIC access page of its own; that page is still pinned.
	 * Hence, we skip the case where the VCPU is in guest mode _and_
	 * L1 prepared an APIC access page for L2.
	 *
	 * For the case where L1 and L2 share the same APIC access page
	 * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear
	 * in the vmcs12), this function will only update either the vmcs01
	 * or the vmcs02.  If the former, the vmcs02 will be updated by
	 * prepare_vmcs02.  If the latter, the vmcs01 will be updated in
	 * the next L2->L1 exit.
	 */
	if (!is_guest_mode(vcpu) ||
	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
		vmcs_write64(APIC_ACCESS_ADDR, hpa);
		vmx_flush_tlb_ept_only(vcpu);
	}
}

static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
{
	u16 status;
	u8 old;

	if (max_isr == -1)
		max_isr = 0;

	status = vmcs_read16(GUEST_INTR_STATUS);
	old = status >> 8;
	if (max_isr != old) {
		status &= 0xff;
		status |= max_isr << 8;
		vmcs_write16(GUEST_INTR_STATUS, status);
	}
}

static void vmx_set_rvi(int vector)
{
	u16 status;
	u8 old;

	if (vector == -1)
		vector = 0;

	status = vmcs_read16(GUEST_INTR_STATUS);
	old = (u8)status & 0xff;
	if ((u8)vector != old) {
		status &= ~0xff;
		status |= (u8)vector;
		vmcs_write16(GUEST_INTR_STATUS, status);
	}
}

static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
{
	if (!is_guest_mode(vcpu)) {
		vmx_set_rvi(max_irr);
		return;
	}

	if (max_irr == -1)
		return;

	/*
	 * In guest mode.  If a vmexit is needed, vmx_check_nested_events
	 * handles it.
	 */
	if (nested_exit_on_intr(vcpu))
		return;

	/*
	 * Else, fall back to pre-APICv interrupt injection since L2
	 * is run without virtual interrupt delivery.
	 */
	if (!kvm_event_needs_reinjection(vcpu) &&
	    vmx_interrupt_allowed(vcpu)) {
		kvm_queue_interrupt(vcpu, max_irr, false);
		vmx_inject_irq(vcpu);
	}
}

static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int max_irr;

	WARN_ON(!vcpu->arch.apicv_active);
	if (pi_test_on(&vmx->pi_desc)) {
		pi_clear_on(&vmx->pi_desc);
		/*
		 * IOMMU can write to PIR.ON, so the barrier matters even on UP.
		 * But on x86 this is just a compiler barrier anyway.
		 */
		smp_mb__after_atomic();
		max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
	} else {
		max_irr = kvm_lapic_find_highest_irr(vcpu);
	}
	vmx_hwapic_irr_update(vcpu, max_irr);
	return max_irr;
}

static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
	if (!kvm_vcpu_apicv_active(vcpu))
		return;

	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
	vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]);
	vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]);
	vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
}

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

	pi_clear_on(&vmx->pi_desc);
	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
}

static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
{
	u32 exit_intr_info = 0;
	u16 basic_exit_reason = (u16)vmx->exit_reason;

	if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
	      || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI))
		return;

	if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
	vmx->exit_intr_info = exit_intr_info;

	/* if exit due to PF check for async PF */
	if (is_page_fault(exit_intr_info))
		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();

	/* Handle machine checks before interrupts are enabled */
	if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY ||
	    is_machine_check(exit_intr_info))
		kvm_machine_check();

	/* We need to handle NMIs before interrupts are enabled */
	if (is_nmi(exit_intr_info)) {
		kvm_before_handle_nmi(&vmx->vcpu);
		asm("int $2");
		kvm_after_handle_nmi(&vmx->vcpu);
	}
}

static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);

	if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
			== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
		unsigned int vector;
		unsigned long entry;
		gate_desc *desc;
		struct vcpu_vmx *vmx = to_vmx(vcpu);
#ifdef CONFIG_X86_64
		unsigned long tmp;
#endif

		vector =  exit_intr_info & INTR_INFO_VECTOR_MASK;
		desc = (gate_desc *)vmx->host_idt_base + vector;
		entry = gate_offset(desc);
		asm volatile(
#ifdef CONFIG_X86_64
			"mov %%" _ASM_SP ", %[sp]\n\t"
			"and $0xfffffffffffffff0, %%" _ASM_SP "\n\t"
			"push $%c[ss]\n\t"
			"push %[sp]\n\t"
#endif
			"pushf\n\t"
			__ASM_SIZE(push) " $%c[cs]\n\t"
			"call *%[entry]\n\t"
			:
#ifdef CONFIG_X86_64
			[sp]"=&r"(tmp),
#endif
			ASM_CALL_CONSTRAINT
			:
			[entry]"r"(entry),
			[ss]"i"(__KERNEL_DS),
			[cs]"i"(__KERNEL_CS)
			);
	}
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);

static bool vmx_has_high_real_mode_segbase(void)
{
	return enable_unrestricted_guest || emulate_invalid_guest_state;
}

static bool vmx_mpx_supported(void)
{
	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
}

static bool vmx_xsaves_supported(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_XSAVES;
}

static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
	u32 exit_intr_info;
	bool unblock_nmi;
	u8 vector;
	bool idtv_info_valid;

	idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;

	if (vmx->loaded_vmcs->nmi_known_unmasked)
		return;
	/*
	 * Can't use vmx->exit_intr_info since we're not sure what
	 * the exit reason is.
	 */
	exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
	unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
	vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
	/*
	 * SDM 3: 27.7.1.2 (September 2008)
	 * Re-set bit "block by NMI" before VM entry if vmexit caused by
	 * a guest IRET fault.
	 * SDM 3: 23.2.2 (September 2008)
	 * Bit 12 is undefined in any of the following cases:
	 *  If the VM exit sets the valid bit in the IDT-vectoring
	 *   information field.
	 *  If the VM exit is due to a double fault.
	 */
	if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
	    vector != DF_VECTOR && !idtv_info_valid)
		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
			      GUEST_INTR_STATE_NMI);
	else
		vmx->loaded_vmcs->nmi_known_unmasked =
			!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
			  & GUEST_INTR_STATE_NMI);
}

static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
				      u32 idt_vectoring_info,
				      int instr_len_field,
				      int error_code_field)
{
	u8 vector;
	int type;
	bool idtv_info_valid;

	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;

	vcpu->arch.nmi_injected = false;
	kvm_clear_exception_queue(vcpu);
	kvm_clear_interrupt_queue(vcpu);

	if (!idtv_info_valid)
		return;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
	type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;

	switch (type) {
	case INTR_TYPE_NMI_INTR:
		vcpu->arch.nmi_injected = true;
		/*
		 * SDM 3: 27.7.1.2 (September 2008)
		 * Clear bit "block by NMI" before VM entry if a NMI
		 * delivery faulted.
		 */
		vmx_set_nmi_mask(vcpu, false);
		break;
	case INTR_TYPE_SOFT_EXCEPTION:
		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
		/* fall through */
	case INTR_TYPE_HARD_EXCEPTION:
		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
			u32 err = vmcs_read32(error_code_field);
			kvm_requeue_exception_e(vcpu, vector, err);
		} else
			kvm_requeue_exception(vcpu, vector);
		break;
	case INTR_TYPE_SOFT_INTR:
		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
		/* fall through */
	case INTR_TYPE_EXT_INTR:
		kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR);
		break;
	default:
		break;
	}
}

static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
	__vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info,
				  VM_EXIT_INSTRUCTION_LEN,
				  IDT_VECTORING_ERROR_CODE);
}

static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
{
	__vmx_complete_interrupts(vcpu,
				  vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
				  VM_ENTRY_INSTRUCTION_LEN,
				  VM_ENTRY_EXCEPTION_ERROR_CODE);

	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}

static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
{
	int i, nr_msrs;
	struct perf_guest_switch_msr *msrs;

	msrs = perf_guest_get_msrs(&nr_msrs);

	if (!msrs)
		return;

	for (i = 0; i < nr_msrs; i++)
		if (msrs[i].host == msrs[i].guest)
			clear_atomic_switch_msr(vmx, msrs[i].msr);
		else
			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
					msrs[i].host);
}

static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 tscl;
	u32 delta_tsc;

	if (vmx->hv_deadline_tsc == -1)
		return;

	tscl = rdtsc();
	if (vmx->hv_deadline_tsc > tscl)
		/* sure to be 32 bit only because checked on set_hv_timer */
		delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
			cpu_preemption_timer_multi);
	else
		delta_tsc = 0;

	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
}

static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long debugctlmsr, cr3, cr4;

	/* Don't enter VMX if guest state is invalid, let the exit handler
	   start emulation until we arrive back to a valid state */
	if (vmx->emulation_required)
		return;

	if (vmx->ple_window_dirty) {
		vmx->ple_window_dirty = false;
		vmcs_write32(PLE_WINDOW, vmx->ple_window);
	}

	if (vmx->nested.sync_shadow_vmcs) {
		copy_vmcs12_to_shadow(vmx);
		vmx->nested.sync_shadow_vmcs = false;
	}

	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);

	cr3 = __get_current_cr3_fast();
	if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
		vmcs_writel(HOST_CR3, cr3);
		vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
	}

	cr4 = cr4_read_shadow();
	if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
		vmcs_writel(HOST_CR4, cr4);
		vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
	}

	/* When single-stepping over STI and MOV SS, we must clear the
	 * corresponding interruptibility bits in the guest state. Otherwise
	 * vmentry fails as it then expects bit 14 (BS) in pending debug
	 * exceptions being set, but that's not correct for the guest debugging
	 * case. */
	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
		vmx_set_interrupt_shadow(vcpu, 0);

	if (static_cpu_has(X86_FEATURE_PKU) &&
	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
	    vcpu->arch.pkru != vmx->host_pkru)
		__write_pkru(vcpu->arch.pkru);

	atomic_switch_perf_msrs(vmx);
	debugctlmsr = get_debugctlmsr();

	vmx_arm_hv_timer(vcpu);

	vmx->__launched = vmx->loaded_vmcs->launched;
	asm(
		/* Store host registers */
		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
		"push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
		"push %%" _ASM_CX " \n\t"
		"cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
		"je 1f \n\t"
		"mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
		__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
		"1: \n\t"
		/* Reload cr2 if changed */
		"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
		"mov %%cr2, %%" _ASM_DX " \n\t"
		"cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
		"je 2f \n\t"
		"mov %%" _ASM_AX", %%cr2 \n\t"
		"2: \n\t"
		/* Check if vmlaunch of vmresume is needed */
		"cmpl $0, %c[launched](%0) \n\t"
		/* Load guest registers.  Don't clobber flags. */
		"mov %c[rax](%0), %%" _ASM_AX " \n\t"
		"mov %c[rbx](%0), %%" _ASM_BX " \n\t"
		"mov %c[rdx](%0), %%" _ASM_DX " \n\t"
		"mov %c[rsi](%0), %%" _ASM_SI " \n\t"
		"mov %c[rdi](%0), %%" _ASM_DI " \n\t"
		"mov %c[rbp](%0), %%" _ASM_BP " \n\t"
#ifdef CONFIG_X86_64
		"mov %c[r8](%0),  %%r8  \n\t"
		"mov %c[r9](%0),  %%r9  \n\t"
		"mov %c[r10](%0), %%r10 \n\t"
		"mov %c[r11](%0), %%r11 \n\t"
		"mov %c[r12](%0), %%r12 \n\t"
		"mov %c[r13](%0), %%r13 \n\t"
		"mov %c[r14](%0), %%r14 \n\t"
		"mov %c[r15](%0), %%r15 \n\t"
#endif
		"mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */

		/* Enter guest mode */
		"jne 1f \n\t"
		__ex(ASM_VMX_VMLAUNCH) "\n\t"
		"jmp 2f \n\t"
		"1: " __ex(ASM_VMX_VMRESUME) "\n\t"
		"2: "
		/* Save guest registers, load host registers, keep flags */
		"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
		"pop %0 \n\t"
		"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
		"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
		__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
		"mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
		"mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
		"mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
		"mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
#ifdef CONFIG_X86_64
		"mov %%r8,  %c[r8](%0) \n\t"
		"mov %%r9,  %c[r9](%0) \n\t"
		"mov %%r10, %c[r10](%0) \n\t"
		"mov %%r11, %c[r11](%0) \n\t"
		"mov %%r12, %c[r12](%0) \n\t"
		"mov %%r13, %c[r13](%0) \n\t"
		"mov %%r14, %c[r14](%0) \n\t"
		"mov %%r15, %c[r15](%0) \n\t"
#endif
		"mov %%cr2, %%" _ASM_AX "   \n\t"
		"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"

		"pop  %%" _ASM_BP "; pop  %%" _ASM_DX " \n\t"
		"setbe %c[fail](%0) \n\t"
		".pushsection .rodata \n\t"
		".global vmx_return \n\t"
		"vmx_return: " _ASM_PTR " 2b \n\t"
		".popsection"
	      : : "c"(vmx), "d"((unsigned long)HOST_RSP),
		[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
		[fail]"i"(offsetof(struct vcpu_vmx, fail)),
		[host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)),
		[rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])),
		[rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])),
		[rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])),
		[rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])),
		[rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])),
		[rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])),
		[rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])),
#ifdef CONFIG_X86_64
		[r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])),
		[r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])),
		[r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])),
		[r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])),
		[r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])),
		[r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])),
		[r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])),
		[r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])),
#endif
		[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
		[wordsize]"i"(sizeof(ulong))
	      : "cc", "memory"
#ifdef CONFIG_X86_64
		, "rax", "rbx", "rdi", "rsi"
		, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
#else
		, "eax", "ebx", "edi", "esi"
#endif
	      );

	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
	if (debugctlmsr)
		update_debugctlmsr(debugctlmsr);

#ifndef CONFIG_X86_64
	/*
	 * The sysexit path does not restore ds/es, so we must set them to
	 * a reasonable value ourselves.
	 *
	 * We can't defer this to vmx_load_host_state() since that function
	 * may be executed in interrupt context, which saves and restore segments
	 * around it, nullifying its effect.
	 */
	loadsegment(ds, __USER_DS);
	loadsegment(es, __USER_DS);
#endif

	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
				  | (1 << VCPU_EXREG_RFLAGS)
				  | (1 << VCPU_EXREG_PDPTR)
				  | (1 << VCPU_EXREG_SEGMENTS)
				  | (1 << VCPU_EXREG_CR3));
	vcpu->arch.regs_dirty = 0;

	/*
	 * eager fpu is enabled if PKEY is supported and CR4 is switched
	 * back on host, so it is safe to read guest PKRU from current
	 * XSAVE.
	 */
	if (static_cpu_has(X86_FEATURE_PKU) &&
	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
		vcpu->arch.pkru = __read_pkru();
		if (vcpu->arch.pkru != vmx->host_pkru)
			__write_pkru(vmx->host_pkru);
	}

	/*
	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
	 * we did not inject a still-pending event to L1 now because of
	 * nested_run_pending, we need to re-enable this bit.
	 */
	if (vmx->nested.nested_run_pending)
		kvm_make_request(KVM_REQ_EVENT, vcpu);

	vmx->nested.nested_run_pending = 0;
	vmx->idt_vectoring_info = 0;

	vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON);
	if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
		return;

	vmx->loaded_vmcs->launched = 1;
	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);

	vmx_complete_atomic_exit(vmx);
	vmx_recover_nmi_blocking(vmx);
	vmx_complete_interrupts(vmx);
}
STACK_FRAME_NON_STANDARD(vmx_vcpu_run);

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

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

	cpu = get_cpu();
	vmx->loaded_vmcs = vmcs;
	vmx_vcpu_put(vcpu);
	vmx_vcpu_load(vcpu, cpu);
	vcpu->cpu = cpu;
	put_cpu();
}

/*
 * Ensure that the current vmcs of the logical processor is the
 * vmcs01 of the vcpu before calling free_nested().
 */
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
       struct vcpu_vmx *vmx = to_vmx(vcpu);
       int r;

       r = vcpu_load(vcpu);
       BUG_ON(r);
       vmx_switch_vmcs(vcpu, &vmx->vmcs01);
       free_nested(vmx);
       vcpu_put(vcpu);
}

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

	if (enable_pml)
		vmx_destroy_pml_buffer(vmx);
	free_vpid(vmx->vpid);
	leave_guest_mode(vcpu);
	vmx_free_vcpu_nested(vcpu);
	free_loaded_vmcs(vmx->loaded_vmcs);
	kfree(vmx->guest_msrs);
	kvm_vcpu_uninit(vcpu);
	kmem_cache_free(kvm_vcpu_cache, vmx);
}

static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
{
	int err;
	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
	int cpu;

	if (!vmx)
		return ERR_PTR(-ENOMEM);

	vmx->vpid = allocate_vpid();

	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
	if (err)
		goto free_vcpu;

	err = -ENOMEM;

	/*
	 * If PML is turned on, failure on enabling PML just results in failure
	 * of creating the vcpu, therefore we can simplify PML logic (by
	 * avoiding dealing with cases, such as enabling PML partially on vcpus
	 * for the guest, etc.
	 */
	if (enable_pml) {
		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
		if (!vmx->pml_pg)
			goto uninit_vcpu;
	}

	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
		     > PAGE_SIZE);

	if (!vmx->guest_msrs)
		goto free_pml;

	vmx->loaded_vmcs = &vmx->vmcs01;
	vmx->loaded_vmcs->vmcs = alloc_vmcs();
	vmx->loaded_vmcs->shadow_vmcs = NULL;
	if (!vmx->loaded_vmcs->vmcs)
		goto free_msrs;
	loaded_vmcs_init(vmx->loaded_vmcs);

	cpu = get_cpu();
	vmx_vcpu_load(&vmx->vcpu, cpu);
	vmx->vcpu.cpu = cpu;
	err = vmx_vcpu_setup(vmx);
	vmx_vcpu_put(&vmx->vcpu);
	put_cpu();
	if (err)
		goto free_vmcs;
	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
		err = alloc_apic_access_page(kvm);
		if (err)
			goto free_vmcs;
	}

	if (enable_ept) {
		if (!kvm->arch.ept_identity_map_addr)
			kvm->arch.ept_identity_map_addr =
				VMX_EPT_IDENTITY_PAGETABLE_ADDR;
		err = init_rmode_identity_map(kvm);
		if (err)
			goto free_vmcs;
	}

	if (nested) {
		nested_vmx_setup_ctls_msrs(vmx);
		vmx->nested.vpid02 = allocate_vpid();
	}

	vmx->nested.posted_intr_nv = -1;
	vmx->nested.current_vmptr = -1ull;

	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;

	/*
	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
	 * or POSTED_INTR_WAKEUP_VECTOR.
	 */
	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
	vmx->pi_desc.sn = 1;

	return &vmx->vcpu;

free_vmcs:
	free_vpid(vmx->nested.vpid02);
	free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
	kfree(vmx->guest_msrs);
free_pml:
	vmx_destroy_pml_buffer(vmx);
uninit_vcpu:
	kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
	free_vpid(vmx->vpid);
	kmem_cache_free(kvm_vcpu_cache, vmx);
	return ERR_PTR(err);
}

static void __init vmx_check_processor_compat(void *rtn)
{
	struct vmcs_config vmcs_conf;

	*(int *)rtn = 0;
	if (setup_vmcs_config(&vmcs_conf) < 0)
		*(int *)rtn = -EIO;
	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
				smp_processor_id());
		*(int *)rtn = -EIO;
	}
}

static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
	u8 cache;
	u64 ipat = 0;

	/* For VT-d and EPT combination
	 * 1. MMIO: always map as UC
	 * 2. EPT with VT-d:
	 *   a. VT-d without snooping control feature: can't guarantee the
	 *	result, try to trust guest.
	 *   b. VT-d with snooping control feature: snooping control feature of
	 *	VT-d engine can guarantee the cache correctness. Just set it
	 *	to WB to keep consistent with host. So the same as item 3.
	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
	 *    consistent with host MTRR
	 */
	if (is_mmio) {
		cache = MTRR_TYPE_UNCACHABLE;
		goto exit;
	}

	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
		ipat = VMX_EPT_IPAT_BIT;
		cache = MTRR_TYPE_WRBACK;
		goto exit;
	}

	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
		ipat = VMX_EPT_IPAT_BIT;
		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
			cache = MTRR_TYPE_WRBACK;
		else
			cache = MTRR_TYPE_UNCACHABLE;
		goto exit;
	}

	cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);

exit:
	return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
}

static int vmx_get_lpage_level(void)
{
	if (enable_ept && !cpu_has_vmx_ept_1g_page())
		return PT_DIRECTORY_LEVEL;
	else
		/* For shadow and EPT supported 1GB page */
		return PT_PDPE_LEVEL;
}

static void vmcs_set_secondary_exec_control(u32 new_ctl)
{
	/*
	 * These bits in the secondary execution controls field
	 * are dynamic, the others are mostly based on the hypervisor
	 * architecture and the guest's CPUID.  Do not touch the
	 * dynamic bits.
	 */
	u32 mask =
		SECONDARY_EXEC_SHADOW_VMCS |
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;

	u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);

	vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
		     (new_ctl & ~mask) | (cur_ctl & mask));
}

/*
 * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits
 * (indicating "allowed-1") if they are supported in the guest's CPUID.
 */
static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct kvm_cpuid_entry2 *entry;

	vmx->nested.nested_vmx_cr0_fixed1 = 0xffffffff;
	vmx->nested.nested_vmx_cr4_fixed1 = X86_CR4_PCE;

#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do {		\
	if (entry && (entry->_reg & (_cpuid_mask)))			\
		vmx->nested.nested_vmx_cr4_fixed1 |= (_cr4_mask);	\
} while (0)

	entry = kvm_find_cpuid_entry(vcpu, 0x1, 0);
	cr4_fixed1_update(X86_CR4_VME,        edx, bit(X86_FEATURE_VME));
	cr4_fixed1_update(X86_CR4_PVI,        edx, bit(X86_FEATURE_VME));
	cr4_fixed1_update(X86_CR4_TSD,        edx, bit(X86_FEATURE_TSC));
	cr4_fixed1_update(X86_CR4_DE,         edx, bit(X86_FEATURE_DE));
	cr4_fixed1_update(X86_CR4_PSE,        edx, bit(X86_FEATURE_PSE));
	cr4_fixed1_update(X86_CR4_PAE,        edx, bit(X86_FEATURE_PAE));
	cr4_fixed1_update(X86_CR4_MCE,        edx, bit(X86_FEATURE_MCE));
	cr4_fixed1_update(X86_CR4_PGE,        edx, bit(X86_FEATURE_PGE));
	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, bit(X86_FEATURE_FXSR));
	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM));
	cr4_fixed1_update(X86_CR4_VMXE,       ecx, bit(X86_FEATURE_VMX));
	cr4_fixed1_update(X86_CR4_SMXE,       ecx, bit(X86_FEATURE_SMX));
	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, bit(X86_FEATURE_PCID));
	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, bit(X86_FEATURE_XSAVE));

	entry = kvm_find_cpuid_entry(vcpu, 0x7, 0);
	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, bit(X86_FEATURE_FSGSBASE));
	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
	/* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
	cr4_fixed1_update(bit(11),            ecx, bit(2));

#undef cr4_fixed1_update
}

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

	if (cpu_has_secondary_exec_ctrls()) {
		vmx_compute_secondary_exec_control(vmx);
		vmcs_set_secondary_exec_control(vmx->secondary_exec_control);
	}

	if (nested_vmx_allowed(vcpu))
		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
	else
		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;

	if (nested_vmx_allowed(vcpu))
		nested_vmx_cr_fixed1_bits_update(vcpu);
}

static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
{
	if (func == 1 && nested)
		entry->ecx |= bit(X86_FEATURE_VMX);
}

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);
	u32 exit_reason;
	unsigned long exit_qualification = vcpu->arch.exit_qualification;

	if (vmx->nested.pml_full) {
		exit_reason = EXIT_REASON_PML_FULL;
		vmx->nested.pml_full = false;
		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
	} else if (fault->error_code & PFERR_RSVD_MASK)
		exit_reason = EXIT_REASON_EPT_MISCONFIG;
	else
		exit_reason = EXIT_REASON_EPT_VIOLATION;

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

static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
{
	return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
}

/* Callbacks for nested_ept_init_mmu_context: */

static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
{
	/* return the page table to be shadowed - in our case, EPT12 */
	return get_vmcs12(vcpu)->ept_pointer;
}

static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
	WARN_ON(mmu_is_nested(vcpu));
	if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
		return 1;

	kvm_mmu_unload(vcpu);
	kvm_init_shadow_ept_mmu(vcpu,
			to_vmx(vcpu)->nested.nested_vmx_ept_caps &
			VMX_EPT_EXECUTE_ONLY_BIT,
			nested_ept_ad_enabled(vcpu));
	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;

	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
	return 0;
}

static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
	vcpu->arch.walk_mmu = &vcpu->arch.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 void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
		struct x86_exception *fault)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	WARN_ON(!is_guest_mode(vcpu));

	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
		!to_vmx(vcpu)->nested.nested_run_pending) {
		vmcs12->vm_exit_intr_error_code = fault->error_code;
		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
				  fault->address);
	} else {
		kvm_inject_page_fault(vcpu, fault);
	}
}

static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
					       struct vmcs12 *vmcs12);

static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
					struct vmcs12 *vmcs12)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct page *page;
	u64 hpa;

	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
		/*
		 * Translate L1 physical address to host physical
		 * address for vmcs02. Keep the page pinned, so this
		 * physical address remains valid. We keep a reference
		 * to it so we can release it later.
		 */
		if (vmx->nested.apic_access_page) { /* shouldn't happen */
			kvm_release_page_dirty(vmx->nested.apic_access_page);
			vmx->nested.apic_access_page = NULL;
		}
		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
		/*
		 * If translation failed, no matter: This feature asks
		 * to exit when accessing the given address, and if it
		 * can never be accessed, this feature won't do
		 * anything anyway.
		 */
		if (!is_error_page(page)) {
			vmx->nested.apic_access_page = page;
			hpa = page_to_phys(vmx->nested.apic_access_page);
			vmcs_write64(APIC_ACCESS_ADDR, hpa);
		} else {
			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
					SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
		}
	} else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) &&
		   cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
			      SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
		kvm_vcpu_reload_apic_access_page(vcpu);
	}

	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
		if (vmx->nested.virtual_apic_page) { /* shouldn't happen */
			kvm_release_page_dirty(vmx->nested.virtual_apic_page);
			vmx->nested.virtual_apic_page = NULL;
		}
		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->virtual_apic_page_addr);

		/*
		 * If translation failed, VM entry will fail because
		 * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
		 * Failing the vm entry is _not_ what the processor
		 * does but it's basically the only possibility we
		 * have.  We could still enter the guest if CR8 load
		 * exits are enabled, CR8 store exits are enabled, and
		 * virtualize APIC access is disabled; in this case
		 * the processor would never use the TPR shadow and we
		 * could simply clear the bit from the execution
		 * control.  But such a configuration is useless, so
		 * let's keep the code simple.
		 */
		if (!is_error_page(page)) {
			vmx->nested.virtual_apic_page = page;
			hpa = page_to_phys(vmx->nested.virtual_apic_page);
			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
		}
	}

	if (nested_cpu_has_posted_intr(vmcs12)) {
		if (vmx->nested.pi_desc_page) { /* shouldn't happen */
			kunmap(vmx->nested.pi_desc_page);
			kvm_release_page_dirty(vmx->nested.pi_desc_page);
			vmx->nested.pi_desc_page = NULL;
		}
		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->posted_intr_desc_addr);
		if (is_error_page(page))
			return;
		vmx->nested.pi_desc_page = page;
		vmx->nested.pi_desc = kmap(vmx->nested.pi_desc_page);
		vmx->nested.pi_desc =
			(struct pi_desc *)((void *)vmx->nested.pi_desc +
			(unsigned long)(vmcs12->posted_intr_desc_addr &
			(PAGE_SIZE - 1)));
		vmcs_write64(POSTED_INTR_DESC_ADDR,
			page_to_phys(vmx->nested.pi_desc_page) +
			(unsigned long)(vmcs12->posted_intr_desc_addr &
			(PAGE_SIZE - 1)));
	}
	if (cpu_has_vmx_msr_bitmap() &&
	    nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) &&
	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
		;
	else
		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
				CPU_BASED_USE_MSR_BITMAPS);
}

static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
{
	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
	struct vcpu_vmx *vmx = to_vmx(vcpu);

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

	/* Make sure short timeouts reliably trigger an immediate vmexit.
	 * hrtimer_start does not guarantee this. */
	if (preemption_timeout <= 1) {
		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
		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,
		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
}

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 (!page_address_valid(vcpu, vmcs12->io_bitmap_a) ||
	    !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 (!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 (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))
		return -EINVAL;

	return 0;
}

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

	/* This shortcut is ok because we support only x2APIC MSRs so far. */
	if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
		return false;

	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
	if (is_error_page(page))
		return false;
	msr_bitmap_l1 = (unsigned long *)kmap(page);

	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);

	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
		if (nested_cpu_has_apic_reg_virt(vmcs12))
			for (msr = 0x800; msr <= 0x8ff; msr++)
				nested_vmx_disable_intercept_for_msr(
					msr_bitmap_l1, msr_bitmap_l0,
					msr, MSR_TYPE_R);

		nested_vmx_disable_intercept_for_msr(
				msr_bitmap_l1, msr_bitmap_l0,
				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
				MSR_TYPE_R | MSR_TYPE_W);

		if (nested_cpu_has_vid(vmcs12)) {
			nested_vmx_disable_intercept_for_msr(
				msr_bitmap_l1, msr_bitmap_l0,
				APIC_BASE_MSR + (APIC_EOI >> 4),
				MSR_TYPE_W);
			nested_vmx_disable_intercept_for_msr(
				msr_bitmap_l1, msr_bitmap_l0,
				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
				MSR_TYPE_W);
		}
	}
	kunmap(page);
	kvm_release_page_clean(page);

	return true;
}

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 (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 (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.
	 */
	if (nested_cpu_has_posted_intr(vmcs12) &&
	   (!nested_cpu_has_vid(vmcs12) ||
	    !nested_exit_intr_ack_set(vcpu) ||
	    vmcs12->posted_intr_nv & 0xff00))
		return -EINVAL;

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

	return 0;
}

static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
				       unsigned long count_field,
				       unsigned long addr_field)
{
	int maxphyaddr;
	u64 count, addr;

	if (vmcs12_read_any(vcpu, count_field, &count) ||
	    vmcs12_read_any(vcpu, addr_field, &addr)) {
		WARN_ON(1);
		return -EINVAL;
	}
	if (count == 0)
		return 0;
	maxphyaddr = cpuid_maxphyaddr(vcpu);
	if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
	    (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
		pr_debug_ratelimited(
			"nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)",
			addr_field, maxphyaddr, count, addr);
		return -EINVAL;
	}
	return 0;
}

static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
						struct vmcs12 *vmcs12)
{
	if (vmcs12->vm_exit_msr_load_count == 0 &&
	    vmcs12->vm_exit_msr_store_count == 0 &&
	    vmcs12->vm_entry_msr_load_count == 0)
		return 0; /* Fast path */
	if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT,
					VM_EXIT_MSR_LOAD_ADDR) ||
	    nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT,
					VM_EXIT_MSR_STORE_ADDR) ||
	    nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT,
					VM_ENTRY_MSR_LOAD_ADDR))
		return -EINVAL;
	return 0;
}

static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
					 struct vmcs12 *vmcs12)
{
	u64 address = vmcs12->pml_address;
	int maxphyaddr = cpuid_maxphyaddr(vcpu);

	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
		if (!nested_cpu_has_ept(vmcs12) ||
		    !IS_ALIGNED(address, 4096)  ||
		    address >> maxphyaddr)
			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 (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
		return -EINVAL;
	if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
	    e->index == MSR_IA32_UCODE_REV)
		return -EINVAL;
	if (e->reserved != 0)
		return -EINVAL;
	return 0;
}

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

/*
 * Load guest's/host's msr at nested entry/exit.
 * return 0 for success, entry index for failure.
 */
static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
	u32 i;
	struct vmx_msr_entry e;
	struct msr_data msr;

	msr.host_initiated = false;
	for (i = 0; i < count; i++) {
		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;
		}
		msr.index = e.index;
		msr.data = e.value;
		if (kvm_set_msr(vcpu, &msr)) {
			pr_debug_ratelimited(
				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
				__func__, i, e.index, e.value);
			goto fail;
		}
	}
	return 0;
fail:
	return i + 1;
}

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

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

static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
	unsigned long invalid_mask;

	invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
	return (val & invalid_mask) == 0;
}

/*
 * 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.
 * Returns 0 on success, 1 on failure. Invalid state exit qualification code
 * is assigned to entry_failure_code on failure.
 */
static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
			       u32 *entry_failure_code)
{
	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
		if (!nested_cr3_valid(vcpu, cr3)) {
			*entry_failure_code = ENTRY_FAIL_DEFAULT;
			return 1;
		}

		/*
		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
		 * must not be dereferenced.
		 */
		if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) &&
		    !nested_ept) {
			if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) {
				*entry_failure_code = ENTRY_FAIL_PDPTE;
				return 1;
			}
		}

		vcpu->arch.cr3 = cr3;
		__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
	}

	kvm_mmu_reset_context(vcpu);
	return 0;
}

/*
 * 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, u32 *entry_failure_code)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 exec_control, vmcs12_exec_ctrl;

	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_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
	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_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);

	if (from_vmentry &&
	    (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.vmcs01_debugctl);
	}
	if (from_vmentry) {
		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);
	}
	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
	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);

	if (nested_cpu_has_xsaves(vmcs12))
		vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
	vmcs_write64(VMCS_LINK_POINTER, -1ull);

	exec_control = vmcs12->pin_based_vm_exec_control;

	/* Preemption timer setting is only taken from vmcs01.  */
	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
	exec_control |= vmcs_config.pin_based_exec_ctrl;
	if (vmx->hv_deadline_tsc == -1)
		exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;

	/* Posted interrupts setting is only taken from vmcs12.  */
	if (nested_cpu_has_posted_intr(vmcs12)) {
		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
		vmx->nested.pi_pending = false;
		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
	} else {
		exec_control &= ~PIN_BASED_POSTED_INTR;
	}

	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);

	vmx->nested.preemption_timer_expired = false;
	if (nested_cpu_has_preemption_timer(vmcs12))
		vmx_start_preemption_timer(vcpu);

	/*
	 * Whether page-faults are trapped is determined by a combination of
	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
	 * If enable_ept, L0 doesn't care about page faults and we should
	 * set all of these to L1's desires. However, if !enable_ept, L0 does
	 * care about (at least some) page faults, and because 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.
	 */
	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
		enable_ept ? vmcs12->page_fault_error_code_match : 0);

	if (cpu_has_secondary_exec_ctrls()) {
		exec_control = vmx->secondary_exec_control;

		/* Take the following fields only from vmcs12 */
		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
				  SECONDARY_EXEC_ENABLE_INVPCID |
				  SECONDARY_EXEC_RDTSCP |
				  SECONDARY_EXEC_XSAVES |
				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
				  SECONDARY_EXEC_ENABLE_VMFUNC);
		if (nested_cpu_has(vmcs12,
				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
			vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
				~SECONDARY_EXEC_ENABLE_PML;
			exec_control |= vmcs12_exec_ctrl;
		}

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

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

		/*
		 * Write an illegal value to APIC_ACCESS_ADDR. Later,
		 * nested_get_vmcs12_pages will either fix it up or
		 * remove the VM execution control.
		 */
		if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)
			vmcs_write64(APIC_ACCESS_ADDR, -1ull);

		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
	}


	/*
	 * Set host-state according to L0's settings (vmcs12 is irrelevant here)
	 * Some constant fields are set here by vmx_set_constant_host_state().
	 * Other fields are different per CPU, and will be set later when
	 * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
	 */
	vmx_set_constant_host_state(vmx);

	/*
	 * Set the MSR load/store lists to match L0's settings.
	 */
	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));

	/*
	 * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
	 * entry, but only if the current (host) sp changed from the value
	 * we wrote last (vmx->host_rsp). This cache is no longer relevant
	 * if we switch vmcs, and rather than hold a separate cache per vmcs,
	 * here we just force the write to happen on entry.
	 */
	vmx->host_rsp = 0;

	exec_control = vmx_exec_control(vmx); /* L0's desires */
	exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
	exec_control &= ~CPU_BASED_TPR_SHADOW;
	exec_control |= vmcs12->cpu_based_vm_exec_control;

	/*
	 * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
	 * nested_get_vmcs12_pages can't fix it up, the illegal value
	 * will result in a VM entry failure.
	 */
	if (exec_control & CPU_BASED_TPR_SHADOW) {
		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
	} else {
#ifdef CONFIG_X86_64
		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
				CPU_BASED_CR8_STORE_EXITING;
#endif
	}

	/*
	 * Merging of IO bitmap not currently supported.
	 * Rather, exit every time.
	 */
	exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
	exec_control |= CPU_BASED_UNCOND_IO_EXITING;

	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);

	/* 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.
	 */
	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);

	/* 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 are further modified by vmx_set_efer() below.
	 */
	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);

	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
	 * emulated by vmx_set_efer(), below.
	 */
	vm_entry_controls_init(vmx, 
		(vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
			~VM_ENTRY_IA32E_MODE) |
		(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));

	if (from_vmentry &&
	    (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);
	}

	set_cr4_guest_host_mask(vmx);

	if (from_vmentry &&
	    vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)
		vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);

	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
		vmcs_write64(TSC_OFFSET,
			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
	else
		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
	if (kvm_has_tsc_control)
		decache_tsc_multiplier(vmx);

	if (enable_vpid) {
		/*
		 * There is no direct mapping between vpid02 and vpid12, the
		 * vpid02 is per-vCPU for L0 and reused while the value of
		 * vpid12 is changed w/ one invvpid during nested vmentry.
		 * The vpid12 is allocated by L1 for L2, so it will not
		 * influence global bitmap(for vpid01 and vpid02 allocation)
		 * even if spawn a lot of nested vCPUs.
		 */
		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
				__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
			}
		} else {
			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
			vmx_flush_tlb(vcpu);
		}

	}

	if (enable_pml) {
		/*
		 * Conceptually we want to copy the PML address and index from
		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
		 * since we always flush the log on each vmexit, this happens
		 * to be equivalent to simply resetting the fields in vmcs02.
		 */
		ASSERT(vmx->pml_pg);
		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
	}

	if (nested_cpu_has_ept(vmcs12)) {
		if (nested_ept_init_mmu_context(vcpu)) {
			*entry_failure_code = ENTRY_FAIL_DEFAULT;
			return 1;
		}
	} else if (nested_cpu_has2(vmcs12,
				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
		vmx_flush_tlb_ept_only(vcpu);
	}

	/*
	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
	 * bits which we consider mandatory enabled.
	 * The CR0_READ_SHADOW is what L2 should have expected to read given
	 * the specifications by L1; It's not enough to take
	 * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
	 * have more bits than L1 expected.
	 */
	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));

	if (from_vmentry &&
	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
		vcpu->arch.efer = vmcs12->guest_ia32_efer;
	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
	else
		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
	/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
	vmx_set_efer(vcpu, vcpu->arch.efer);

	/* Shadow page tables on either EPT or shadow page tables. */
	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
				entry_failure_code))
		return 1;

	if (!enable_ept)
		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;

	/*
	 * 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);
	}

	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
	return 0;
}

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

	if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
	    vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_apicv_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_vmx_check_pml_controls(vcpu, vmcs12))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
				vmx->nested.nested_vmx_procbased_ctls_low,
				vmx->nested.nested_vmx_procbased_ctls_high) ||
	    (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
	     !vmx_control_verify(vmcs12->secondary_vm_exec_control,
				 vmx->nested.nested_vmx_secondary_ctls_low,
				 vmx->nested.nested_vmx_secondary_ctls_high)) ||
	    !vmx_control_verify(vmcs12->pin_based_vm_exec_control,
				vmx->nested.nested_vmx_pinbased_ctls_low,
				vmx->nested.nested_vmx_pinbased_ctls_high) ||
	    !vmx_control_verify(vmcs12->vm_exit_controls,
				vmx->nested.nested_vmx_exit_ctls_low,
				vmx->nested.nested_vmx_exit_ctls_high) ||
	    !vmx_control_verify(vmcs12->vm_entry_controls,
				vmx->nested.nested_vmx_entry_ctls_low,
				vmx->nested.nested_vmx_entry_ctls_high))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (nested_cpu_has_vmfunc(vmcs12)) {
		if (vmcs12->vm_function_control &
		    ~vmx->nested.nested_vmx_vmfunc_controls)
			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

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

	if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;

	if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
	    !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
	    !nested_cr3_valid(vcpu, vmcs12->host_cr3))
		return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;

	return 0;
}

static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
				  u32 *exit_qual)
{
	bool ia32e;

	*exit_qual = ENTRY_FAIL_DEFAULT;

	if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) ||
	    !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))
		return 1;

	if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS) &&
	    vmcs12->vmcs_link_pointer != -1ull) {
		*exit_qual = ENTRY_FAIL_VMCS_LINK_PTR;
		return 1;
	}

	/*
	 * 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)) {
		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
		if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) ||
		    ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) ||
		    ((vmcs12->guest_cr0 & X86_CR0_PG) &&
		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))
			return 1;
	}

	/*
	 * 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) {
		ia32e = (vmcs12->vm_exit_controls &
			 VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
		if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
			return 1;
	}

	return 0;
}

static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	struct loaded_vmcs *vmcs02;
	u32 msr_entry_idx;
	u32 exit_qual;

	vmcs02 = nested_get_current_vmcs02(vmx);
	if (!vmcs02)
		return -ENOMEM;

	enter_guest_mode(vcpu);

	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);

	vmx_switch_vmcs(vcpu, vmcs02);
	vmx_segment_cache_clear(vmx);

	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
		leave_guest_mode(vcpu);
		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
		nested_vmx_entry_failure(vcpu, vmcs12,
					 EXIT_REASON_INVALID_STATE, exit_qual);
		return 1;
	}

	nested_get_vmcs12_pages(vcpu, vmcs12);

	msr_entry_idx = nested_vmx_load_msr(vcpu,
					    vmcs12->vm_entry_msr_load_addr,
					    vmcs12->vm_entry_msr_load_count);
	if (msr_entry_idx) {
		leave_guest_mode(vcpu);
		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
		nested_vmx_entry_failure(vcpu, vmcs12,
				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
		return 1;
	}

	/*
	 * 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 0;
}

/*
 * 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;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
	u32 exit_qual;
	int ret;

	if (!nested_vmx_check_permission(vcpu))
		return 1;

	if (!nested_vmx_check_vmcs12(vcpu))
		goto out;

	vmcs12 = get_vmcs12(vcpu);

	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 (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
		nested_vmx_failValid(vcpu,
				     VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
		goto out;
	}

	if (vmcs12->launch_state == launch) {
		nested_vmx_failValid(vcpu,
			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
		goto out;
	}

	ret = check_vmentry_prereqs(vcpu, vmcs12);
	if (ret) {
		nested_vmx_failValid(vcpu, ret);
		goto out;
	}

	/*
	 * After this point, the trap flag no longer triggers a singlestep trap
	 * on the vm entry instructions; don't call kvm_skip_emulated_instruction.
	 * This is not 100% correct; for performance reasons, we delegate most
	 * of the checks on host state to the processor.  If those fail,
	 * the singlestep trap is missed.
	 */
	skip_emulated_instruction(vcpu);

	ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual);
	if (ret) {
		nested_vmx_entry_failure(vcpu, vmcs12,
					 EXIT_REASON_INVALID_STATE, exit_qual);
		return 1;
	}

	/*
	 * We're finally done with prerequisite checking, and can start with
	 * the nested entry.
	 */

	ret = enter_vmx_non_root_mode(vcpu, true);
	if (ret)
		return ret;

	if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
		return kvm_vcpu_halt(vcpu);

	vmx->nested.nested_run_pending = 1;

	return 1;

out:
	return kvm_skip_emulated_instruction(vcpu);
}

/*
 * 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 (CRO_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 idt_vectoring;
	unsigned int nr;

	if (vcpu->arch.exception.injected) {
		nr = vcpu->arch.exception.nr;
		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.pending) {
		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;
	}
}

static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long exit_qual;

	if (kvm_event_needs_reinjection(vcpu))
		return -EBUSY;

	if (vcpu->arch.exception.pending &&
		nested_vmx_check_exception(vcpu, &exit_qual)) {
		if (vmx->nested.nested_run_pending)
			return -EBUSY;
		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
		vcpu->arch.exception.pending = false;
		return 0;
	}

	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
	    vmx->nested.preemption_timer_expired) {
		if (vmx->nested.nested_run_pending)
			return -EBUSY;
		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
		return 0;
	}

	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
		if (vmx->nested.nested_run_pending)
			return -EBUSY;
		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) || external_intr) &&
	    nested_exit_on_intr(vcpu)) {
		if (vmx->nested.nested_run_pending)
			return -EBUSY;
		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
		return 0;
	}

	vmx_complete_nested_posted_interrupt(vcpu);
	return 0;
}

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;
}

/*
 * 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_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);

	vmcs12->guest_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
	vmcs12->guest_rip = kvm_register_read(vcpu, VCPU_REGS_RIP);
	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);

	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_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
	vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_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_interruptibility_info =
		vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
	vmcs12->guest_pending_dbg_exceptions =
		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
		vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT;
	else
		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;

	if (nested_cpu_has_preemption_timer(vmcs12)) {
		if (vmcs12->vm_exit_controls &
		    VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
			vmcs12->vmx_preemption_timer_value =
				vmx_get_preemption_timer_value(vcpu);
		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
	}

	/*
	 * 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);
		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) {
		kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
		vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
	}

	/* TODO: These cannot have changed unless we have MSR bitmaps and
	 * the relevant bit asks not to trap the change */
	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
		vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
		vmcs12->guest_ia32_efer = vcpu->arch.efer;
	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
	if (kvm_mpx_supported())
		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
}

/*
 * 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 exit_reason, u32 exit_intr_info,
			   unsigned long exit_qualification)
{
	/* update guest state fields: */
	sync_vmcs12(vcpu, vmcs12);

	/* update exit information fields: */

	vmcs12->vm_exit_reason = exit_reason;
	vmcs12->exit_qualification = exit_qualification;
	vmcs12->vm_exit_intr_info = exit_intr_info;

	vmcs12->idt_vectoring_info_field = 0;
	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);

	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);
	}

	/*
	 * Drop what we picked up for L2 via vmx_complete_interrupts. It is
	 * preserved above and would only end up incorrectly in L1.
	 */
	vcpu->arch.nmi_injected = false;
	kvm_clear_exception_queue(vcpu);
	kvm_clear_interrupt_queue(vcpu);
}

/*
 * 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)
{
	struct kvm_segment seg;
	u32 entry_failure_code;

	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_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
	/*
	 * 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 = X86_CR0_TS;
	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, &entry_failure_code))
		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);

	if (!enable_ept)
		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;

	if (enable_vpid) {
		/*
		 * Trivially support vpid by letting L2s share their parent
		 * L1's vpid. TODO: move to a more elaborate solution, giving
		 * each L2 its own vpid and exposing the vpid feature to L1.
		 */
		vmx_flush_tlb(vcpu);
	}
	/* Restore posted intr vector. */
	if (nested_cpu_has_posted_intr(vmcs12))
		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);

	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);

	/* 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)
		vmcs_write64(GUEST_IA32_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);

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

	if (cpu_has_vmx_msr_bitmap())
		vmx_set_msr_bitmap(vcpu);

	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);
}

/*
 * 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())
 */
static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
			      u32 exit_intr_info,
			      unsigned long exit_qualification)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

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

	/*
	 * The only expected VM-instruction error is "VM entry with
	 * invalid control field(s)." Anything else indicates a
	 * problem with L0.
	 */
	WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
				   VMXERR_ENTRY_INVALID_CONTROL_FIELD));

	leave_guest_mode(vcpu);

	if (likely(!vmx->fail)) {
		prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
			       exit_qualification);

		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);
	}

	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
	vm_entry_controls_reset_shadow(vmx);
	vm_exit_controls_reset_shadow(vmx);
	vmx_segment_cache_clear(vmx);

	/* if no vmcs02 cache requested, remove the one we used */
	if (VMCS02_POOL_SIZE == 0)
		nested_free_vmcs02(vmx, vmx->nested.current_vmptr);

	/* Update any VMCS fields that might have changed while L2 ran */
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
	if (vmx->hv_deadline_tsc == -1)
		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
				PIN_BASED_VMX_PREEMPTION_TIMER);
	else
		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
			      PIN_BASED_VMX_PREEMPTION_TIMER);
	if (kvm_has_tsc_control)
		decache_tsc_multiplier(vmx);

	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
		vmx_set_virtual_x2apic_mode(vcpu,
				vcpu->arch.apic_base & X2APIC_ENABLE);
	} else if (!nested_cpu_has_ept(vmcs12) &&
		   nested_cpu_has2(vmcs12,
				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
		vmx_flush_tlb_ept_only(vcpu);
	}

	/* This is needed for same reason as it was needed in prepare_vmcs02 */
	vmx->host_rsp = 0;

	/* Unpin physical memory we referred to in vmcs02 */
	if (vmx->nested.apic_access_page) {
		kvm_release_page_dirty(vmx->nested.apic_access_page);
		vmx->nested.apic_access_page = NULL;
	}
	if (vmx->nested.virtual_apic_page) {
		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
		vmx->nested.virtual_apic_page = NULL;
	}
	if (vmx->nested.pi_desc_page) {
		kunmap(vmx->nested.pi_desc_page);
		kvm_release_page_dirty(vmx->nested.pi_desc_page);
		vmx->nested.pi_desc_page = NULL;
		vmx->nested.pi_desc = NULL;
	}

	/*
	 * We are now running in L2, mmu_notifier will force to reload the
	 * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
	 */
	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);

	if (enable_shadow_vmcs)
		vmx->nested.sync_shadow_vmcs = true;

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

	if (likely(!vmx->fail)) {
		/*
		 * TODO: SDM says that with acknowledge interrupt on
		 * exit, bit 31 of the VM-exit interrupt information
		 * (valid interrupt) is always set to 1 on
		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
		 * need kvm_cpu_has_interrupt().  See the commit
		 * message for details.
		 */
		if (nested_exit_intr_ack_set(vcpu) &&
		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
		    kvm_cpu_has_interrupt(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;
		}

		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.
	 */
	nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
	/*
	 * The emulated instruction was already skipped in
	 * nested_vmx_run, but the updated RIP was never
	 * written back to the vmcs01.
	 */
	skip_emulated_instruction(vcpu);
	vmx->fail = 0;
}

/*
 * Forcibly leave nested mode in order to be able to reset the VCPU later on.
 */
static 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(to_vmx(vcpu));
}

/*
 * L1's failure to enter L2 is a subset of a normal exit, as explained in
 * 23.7 "VM-entry failures during or after loading guest state" (this also
 * lists the acceptable exit-reason and exit-qualification parameters).
 * It should only be called before L2 actually succeeded to run, and when
 * vmcs01 is current (it doesn't leave_guest_mode() or switch vmcss).
 */
static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
			struct vmcs12 *vmcs12,
			u32 reason, unsigned long qualification)
{
	load_vmcs12_host_state(vcpu, vmcs12);
	vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
	vmcs12->exit_qualification = qualification;
	nested_vmx_succeed(vcpu);
	if (enable_shadow_vmcs)
		to_vmx(vcpu)->nested.sync_shadow_vmcs = true;
}

static int vmx_check_intercept(struct kvm_vcpu *vcpu,
			       struct x86_instruction_info *info,
			       enum x86_intercept_stage stage)
{
	return X86EMUL_CONTINUE;
}

#ifdef CONFIG_X86_64
/* (a << shift) / divisor, return 1 if overflow otherwise 0 */
static inline int u64_shl_div_u64(u64 a, unsigned int shift,
				  u64 divisor, u64 *result)
{
	u64 low = a << shift, high = a >> (64 - shift);

	/* To avoid the overflow on divq */
	if (high >= divisor)
		return 1;

	/* Low hold the result, high hold rem which is discarded */
	asm("divq %2\n\t" : "=a" (low), "=d" (high) :
	    "rm" (divisor), "0" (low), "1" (high));
	*result = low;

	return 0;
}

static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 tscl = rdtsc();
	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;

	/* Convert to host delta tsc if tsc scaling is enabled */
	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
			u64_shl_div_u64(delta_tsc,
				kvm_tsc_scaling_ratio_frac_bits,
				vcpu->arch.tsc_scaling_ratio,
				&delta_tsc))
		return -ERANGE;

	/*
	 * If the delta tsc can't fit in the 32 bit after the multi shift,
	 * we can't use the preemption timer.
	 * It's possible that it fits on later vmentries, but checking
	 * on every vmentry is costly so we just use an hrtimer.
	 */
	if (delta_tsc >> (cpu_preemption_timer_multi + 32))
		return -ERANGE;

	vmx->hv_deadline_tsc = tscl + delta_tsc;
	vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
			PIN_BASED_VMX_PREEMPTION_TIMER);

	return delta_tsc == 0;
}

static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	vmx->hv_deadline_tsc = -1;
	vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
			PIN_BASED_VMX_PREEMPTION_TIMER);
}
#endif

static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
	if (ple_gap)
		shrink_ple_window(vcpu);
}

static void vmx_slot_enable_log_dirty(struct kvm *kvm,
				     struct kvm_memory_slot *slot)
{
	kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
}

static void vmx_slot_disable_log_dirty(struct kvm *kvm,
				       struct kvm_memory_slot *slot)
{
	kvm_mmu_slot_set_dirty(kvm, slot);
}

static void vmx_flush_log_dirty(struct kvm *kvm)
{
	kvm_flush_pml_buffers(kvm);
}

static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12;
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	gpa_t gpa;
	struct page *page = NULL;
	u64 *pml_address;

	if (is_guest_mode(vcpu)) {
		WARN_ON_ONCE(vmx->nested.pml_full);

		/*
		 * 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 = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;

		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address);
		if (is_error_page(page))
			return 0;

		pml_address = kmap(page);
		pml_address[vmcs12->guest_pml_index--] = gpa;
		kunmap(page);
		kvm_release_page_clean(page);
	}

	return 0;
}

static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
					   struct kvm_memory_slot *memslot,
					   gfn_t offset, unsigned long mask)
{
	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
}

static void __pi_post_block(struct kvm_vcpu *vcpu)
{
	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
	struct pi_desc old, new;
	unsigned int dest;

	do {
		old.control = new.control = pi_desc->control;
		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
		     "Wakeup handler not enabled while the VCPU is blocked\n");

		dest = cpu_physical_id(vcpu->cpu);

		if (x2apic_enabled())
			new.ndst = dest;
		else
			new.ndst = (dest << 8) & 0xFF00;

		/* set 'NV' to 'notification vector' */
		new.nv = POSTED_INTR_VECTOR;
	} while (cmpxchg64(&pi_desc->control, old.control,
			   new.control) != old.control);

	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
		list_del(&vcpu->blocked_vcpu_list);
		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
		vcpu->pre_pcpu = -1;
	}
}

/*
 * This routine does the following things for vCPU which is going
 * to be blocked if VT-d PI is enabled.
 * - Store the vCPU to the wakeup list, so when interrupts happen
 *   we can find the right vCPU to wake up.
 * - Change the Posted-interrupt descriptor as below:
 *      'NDST' <-- vcpu->pre_pcpu
 *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
 * - If 'ON' is set during this process, which means at least one
 *   interrupt is posted for this vCPU, we cannot block it, in
 *   this case, return 1, otherwise, return 0.
 *
 */
static int pi_pre_block(struct kvm_vcpu *vcpu)
{
	unsigned int dest;
	struct pi_desc old, new;
	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);

	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
		!kvm_vcpu_apicv_active(vcpu))
		return 0;

	WARN_ON(irqs_disabled());
	local_irq_disable();
	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
		vcpu->pre_pcpu = vcpu->cpu;
		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
		list_add_tail(&vcpu->blocked_vcpu_list,
			      &per_cpu(blocked_vcpu_on_cpu,
				       vcpu->pre_pcpu));
		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
	}

	do {
		old.control = new.control = pi_desc->control;

		WARN((pi_desc->sn == 1),
		     "Warning: SN field of posted-interrupts "
		     "is set before blocking\n");

		/*
		 * Since vCPU can be preempted during this process,
		 * vcpu->cpu could be different with pre_pcpu, we
		 * need to set pre_pcpu as the destination of wakeup
		 * notification event, then we can find the right vCPU
		 * to wakeup in wakeup handler if interrupts happen
		 * when the vCPU is in blocked state.
		 */
		dest = cpu_physical_id(vcpu->pre_pcpu);

		if (x2apic_enabled())
			new.ndst = dest;
		else
			new.ndst = (dest << 8) & 0xFF00;

		/* set 'NV' to 'wakeup vector' */
		new.nv = POSTED_INTR_WAKEUP_VECTOR;
	} while (cmpxchg64(&pi_desc->control, old.control,
			   new.control) != old.control);

	/* We should not block the vCPU if an interrupt is posted for it.  */
	if (pi_test_on(pi_desc) == 1)
		__pi_post_block(vcpu);

	local_irq_enable();
	return (vcpu->pre_pcpu == -1);
}

static int vmx_pre_block(struct kvm_vcpu *vcpu)
{
	if (pi_pre_block(vcpu))
		return 1;

	if (kvm_lapic_hv_timer_in_use(vcpu))
		kvm_lapic_switch_to_sw_timer(vcpu);

	return 0;
}

static void pi_post_block(struct kvm_vcpu *vcpu)
{
	if (vcpu->pre_pcpu == -1)
		return;

	WARN_ON(irqs_disabled());
	local_irq_disable();
	__pi_post_block(vcpu);
	local_irq_enable();
}

static void vmx_post_block(struct kvm_vcpu *vcpu)
{
	if (kvm_x86_ops->set_hv_timer)
		kvm_lapic_switch_to_hv_timer(vcpu);

	pi_post_block(vcpu);
}

/*
 * vmx_update_pi_irte - set IRTE for Posted-Interrupts
 *
 * @kvm: kvm
 * @host_irq: host irq of the interrupt
 * @guest_irq: gsi of the interrupt
 * @set: set or unset PI
 * returns 0 on success, < 0 on failure
 */
static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
			      uint32_t guest_irq, bool set)
{
	struct kvm_kernel_irq_routing_entry *e;
	struct kvm_irq_routing_table *irq_rt;
	struct kvm_lapic_irq irq;
	struct kvm_vcpu *vcpu;
	struct vcpu_data vcpu_info;
	int idx, ret = 0;

	if (!kvm_arch_has_assigned_device(kvm) ||
		!irq_remapping_cap(IRQ_POSTING_CAP) ||
		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
		return 0;

	idx = srcu_read_lock(&kvm->irq_srcu);
	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
	if (guest_irq >= irq_rt->nr_rt_entries ||
	    hlist_empty(&irq_rt->map[guest_irq])) {
		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
			     guest_irq, irq_rt->nr_rt_entries);
		goto out;
	}

	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
		if (e->type != KVM_IRQ_ROUTING_MSI)
			continue;
		/*
		 * VT-d PI cannot support posting multicast/broadcast
		 * interrupts to a vCPU, we still use interrupt remapping
		 * for these kind of interrupts.
		 *
		 * For lowest-priority interrupts, we only support
		 * those with single CPU as the destination, e.g. user
		 * configures the interrupts via /proc/irq or uses
		 * irqbalance to make the interrupts single-CPU.
		 *
		 * We will support full lowest-priority interrupt later.
		 */

		kvm_set_msi_irq(kvm, e, &irq);
		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
			/*
			 * Make sure the IRTE is in remapped mode if
			 * we don't handle it in posted mode.
			 */
			ret = irq_set_vcpu_affinity(host_irq, NULL);
			if (ret < 0) {
				printk(KERN_INFO
				   "failed to back to remapped mode, irq: %u\n",
				   host_irq);
				goto out;
			}

			continue;
		}

		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
		vcpu_info.vector = irq.vector;

		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
				vcpu_info.vector, vcpu_info.pi_desc_addr, set);

		if (set)
			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
		else
			ret = irq_set_vcpu_affinity(host_irq, NULL);

		if (ret < 0) {
			printk(KERN_INFO "%s: failed to update PI IRTE\n",
					__func__);
			goto out;
		}
	}

	ret = 0;
out:
	srcu_read_unlock(&kvm->irq_srcu, idx);
	return ret;
}

static void vmx_setup_mce(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
			FEATURE_CONTROL_LMCE;
	else
		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
			~FEATURE_CONTROL_LMCE;
}

static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
	.cpu_has_kvm_support = cpu_has_kvm_support,
	.disabled_by_bios = vmx_disabled_by_bios,
	.hardware_setup = hardware_setup,
	.hardware_unsetup = hardware_unsetup,
	.check_processor_compatibility = vmx_check_processor_compat,
	.hardware_enable = hardware_enable,
	.hardware_disable = hardware_disable,
	.cpu_has_accelerated_tpr = report_flexpriority,
	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,

	.vcpu_create = vmx_create_vcpu,
	.vcpu_free = vmx_free_vcpu,
	.vcpu_reset = vmx_vcpu_reset,

	.prepare_guest_switch = vmx_save_host_state,
	.vcpu_load = vmx_vcpu_load,
	.vcpu_put = vmx_vcpu_put,

	.update_bp_intercept = update_exception_bitmap,
	.get_msr = vmx_get_msr,
	.set_msr = vmx_set_msr,
	.get_segment_base = vmx_get_segment_base,
	.get_segment = vmx_get_segment,
	.set_segment = vmx_set_segment,
	.get_cpl = vmx_get_cpl,
	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
	.decache_cr3 = vmx_decache_cr3,
	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
	.set_cr0 = vmx_set_cr0,
	.set_cr3 = vmx_set_cr3,
	.set_cr4 = vmx_set_cr4,
	.set_efer = vmx_set_efer,
	.get_idt = vmx_get_idt,
	.set_idt = vmx_set_idt,
	.get_gdt = vmx_get_gdt,
	.set_gdt = vmx_set_gdt,
	.get_dr6 = vmx_get_dr6,
	.set_dr6 = vmx_set_dr6,
	.set_dr7 = vmx_set_dr7,
	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
	.cache_reg = vmx_cache_reg,
	.get_rflags = vmx_get_rflags,
	.set_rflags = vmx_set_rflags,

	.tlb_flush = vmx_flush_tlb,

	.run = vmx_vcpu_run,
	.handle_exit = vmx_handle_exit,
	.skip_emulated_instruction = skip_emulated_instruction,
	.set_interrupt_shadow = vmx_set_interrupt_shadow,
	.get_interrupt_shadow = vmx_get_interrupt_shadow,
	.patch_hypercall = vmx_patch_hypercall,
	.set_irq = vmx_inject_irq,
	.set_nmi = vmx_inject_nmi,
	.queue_exception = vmx_queue_exception,
	.cancel_injection = vmx_cancel_injection,
	.interrupt_allowed = vmx_interrupt_allowed,
	.nmi_allowed = vmx_nmi_allowed,
	.get_nmi_mask = vmx_get_nmi_mask,
	.set_nmi_mask = vmx_set_nmi_mask,
	.enable_nmi_window = enable_nmi_window,
	.enable_irq_window = enable_irq_window,
	.update_cr8_intercept = update_cr8_intercept,
	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
	.get_enable_apicv = vmx_get_enable_apicv,
	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
	.load_eoi_exitmap = vmx_load_eoi_exitmap,
	.apicv_post_state_restore = vmx_apicv_post_state_restore,
	.hwapic_irr_update = vmx_hwapic_irr_update,
	.hwapic_isr_update = vmx_hwapic_isr_update,
	.sync_pir_to_irr = vmx_sync_pir_to_irr,
	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,

	.set_tss_addr = vmx_set_tss_addr,
	.get_tdp_level = get_ept_level,
	.get_mt_mask = vmx_get_mt_mask,

	.get_exit_info = vmx_get_exit_info,

	.get_lpage_level = vmx_get_lpage_level,

	.cpuid_update = vmx_cpuid_update,

	.rdtscp_supported = vmx_rdtscp_supported,
	.invpcid_supported = vmx_invpcid_supported,

	.set_supported_cpuid = vmx_set_supported_cpuid,

	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,

	.write_tsc_offset = vmx_write_tsc_offset,

	.set_tdp_cr3 = vmx_set_cr3,

	.check_intercept = vmx_check_intercept,
	.handle_external_intr = vmx_handle_external_intr,
	.mpx_supported = vmx_mpx_supported,
	.xsaves_supported = vmx_xsaves_supported,

	.check_nested_events = vmx_check_nested_events,

	.sched_in = vmx_sched_in,

	.slot_enable_log_dirty = vmx_slot_enable_log_dirty,
	.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
	.flush_log_dirty = vmx_flush_log_dirty,
	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
	.write_log_dirty = vmx_write_pml_buffer,

	.pre_block = vmx_pre_block,
	.post_block = vmx_post_block,

	.pmu_ops = &intel_pmu_ops,

	.update_pi_irte = vmx_update_pi_irte,

#ifdef CONFIG_X86_64
	.set_hv_timer = vmx_set_hv_timer,
	.cancel_hv_timer = vmx_cancel_hv_timer,
#endif

	.setup_mce = vmx_setup_mce,
};

static int __init vmx_init(void)
{
	int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
                     __alignof__(struct vcpu_vmx), THIS_MODULE);
	if (r)
		return r;

#ifdef CONFIG_KEXEC_CORE
	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
			   crash_vmclear_local_loaded_vmcss);
#endif

	return 0;
}

static void __exit vmx_exit(void)
{
#ifdef CONFIG_KEXEC_CORE
	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
	synchronize_rcu();
#endif

	kvm_exit();
}

module_init(vmx_init)
module_exit(vmx_exit)