summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/vmx/vmx.c
blob: ab432a930ae865d0000d8273643de236d0738fb8 (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
/*
 * 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 <linux/frame.h>
#include <linux/highmem.h>
#include <linux/hrtimer.h>
#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/mod_devicetable.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/smt.h>
#include <linux/slab.h>
#include <linux/tboot.h>
#include <linux/trace_events.h>

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

#include "capabilities.h"
#include "cpuid.h"
#include "evmcs.h"
#include "irq.h"
#include "kvm_cache_regs.h"
#include "lapic.h"
#include "mmu.h"
#include "nested.h"
#include "ops.h"
#include "pmu.h"
#include "trace.h"
#include "vmcs.h"
#include "vmcs12.h"
#include "vmx.h"
#include "x86.h"

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);

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

static bool __read_mostly enable_vnmi = 1;
module_param_named(vnmi, enable_vnmi, bool, S_IRUGO);

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

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

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

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);

/*
 * 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 = 1;
module_param(nested, bool, S_IRUGO);

static u64 __read_mostly host_xss;

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

#define MSR_BITMAP_MODE_X2APIC		1
#define MSR_BITMAP_MODE_X2APIC_APICV	2

#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_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
#define KVM_VM_CR0_ALWAYS_ON				\
	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
	 X86_CR0_WP | 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_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
#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 MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \
	RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \
	RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \
	RTIT_STATUS_BYTECNT))

#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \
	(~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f)

/*
 * 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.
 */
static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP;
module_param(ple_gap, uint, 0444);

static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, uint, 0444);

/* Default doubles per-vcpu window every exit. */
static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW;
module_param(ple_window_grow, uint, 0444);

/* Default resets per-vcpu window every exit to ple_window. */
static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK;
module_param(ple_window_shrink, uint, 0444);

/* Default is to compute the maximum so we can never overflow. */
static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
module_param(ple_window_max, uint, 0444);

/* Default is SYSTEM mode, 1 for host-guest mode */
int __read_mostly pt_mode = PT_MODE_SYSTEM;
module_param(pt_mode, int, S_IRUGO);

static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
static DEFINE_MUTEX(vmx_l1d_flush_mutex);

/* Storage for pre module init parameter parsing */
static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;

static const struct {
	const char *option;
	bool for_parse;
} vmentry_l1d_param[] = {
	[VMENTER_L1D_FLUSH_AUTO]	 = {"auto", true},
	[VMENTER_L1D_FLUSH_NEVER]	 = {"never", true},
	[VMENTER_L1D_FLUSH_COND]	 = {"cond", true},
	[VMENTER_L1D_FLUSH_ALWAYS]	 = {"always", true},
	[VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false},
	[VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false},
};

#define L1D_CACHE_ORDER 4
static void *vmx_l1d_flush_pages;

static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
{
	struct page *page;
	unsigned int i;

	if (!enable_ept) {
		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
		return 0;
	}

	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
		u64 msr;

		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
			return 0;
		}
	}

	/* If set to auto use the default l1tf mitigation method */
	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
		switch (l1tf_mitigation) {
		case L1TF_MITIGATION_OFF:
			l1tf = VMENTER_L1D_FLUSH_NEVER;
			break;
		case L1TF_MITIGATION_FLUSH_NOWARN:
		case L1TF_MITIGATION_FLUSH:
		case L1TF_MITIGATION_FLUSH_NOSMT:
			l1tf = VMENTER_L1D_FLUSH_COND;
			break;
		case L1TF_MITIGATION_FULL:
		case L1TF_MITIGATION_FULL_FORCE:
			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
			break;
		}
	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
	}

	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
		/*
		 * This allocation for vmx_l1d_flush_pages is not tied to a VM
		 * lifetime and so should not be charged to a memcg.
		 */
		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
		if (!page)
			return -ENOMEM;
		vmx_l1d_flush_pages = page_address(page);

		/*
		 * Initialize each page with a different pattern in
		 * order to protect against KSM in the nested
		 * virtualization case.
		 */
		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
			       PAGE_SIZE);
		}
	}

	l1tf_vmx_mitigation = l1tf;

	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
		static_branch_enable(&vmx_l1d_should_flush);
	else
		static_branch_disable(&vmx_l1d_should_flush);

	if (l1tf == VMENTER_L1D_FLUSH_COND)
		static_branch_enable(&vmx_l1d_flush_cond);
	else
		static_branch_disable(&vmx_l1d_flush_cond);
	return 0;
}

static int vmentry_l1d_flush_parse(const char *s)
{
	unsigned int i;

	if (s) {
		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
			if (vmentry_l1d_param[i].for_parse &&
			    sysfs_streq(s, vmentry_l1d_param[i].option))
				return i;
		}
	}
	return -EINVAL;
}

static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
{
	int l1tf, ret;

	l1tf = vmentry_l1d_flush_parse(s);
	if (l1tf < 0)
		return l1tf;

	if (!boot_cpu_has(X86_BUG_L1TF))
		return 0;

	/*
	 * Has vmx_init() run already? If not then this is the pre init
	 * parameter parsing. In that case just store the value and let
	 * vmx_init() do the proper setup after enable_ept has been
	 * established.
	 */
	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
		vmentry_l1d_flush_param = l1tf;
		return 0;
	}

	mutex_lock(&vmx_l1d_flush_mutex);
	ret = vmx_setup_l1d_flush(l1tf);
	mutex_unlock(&vmx_l1d_flush_mutex);
	return ret;
}

static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
{
	if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
		return sprintf(s, "???\n");

	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
}

static const struct kernel_param_ops vmentry_l1d_flush_ops = {
	.set = vmentry_l1d_flush_set,
	.get = vmentry_l1d_flush_get,
};
module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);

static bool guest_state_valid(struct kvm_vcpu *vcpu);
static u32 vmx_segment_access_rights(struct kvm_segment *var);
static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
							  u32 msr, int type);

void vmx_vmexit(void);

static DEFINE_PER_CPU(struct vmcs *, vmxarea);
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);

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

struct vmcs_config vmcs_config;
struct vmx_capability 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),
};

u64 host_efer;

/*
 * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm
 * will emulate SYSCALL in legacy mode if the vendor string in guest
 * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To
 * support this emulation, IA32_STAR must always be included in
 * vmx_msr_index[], even in i386 builds.
 */
const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};

#if IS_ENABLED(CONFIG_HYPERV)
static bool __read_mostly enlightened_vmcs = true;
module_param(enlightened_vmcs, bool, 0444);

/* check_ept_pointer() should be under protection of ept_pointer_lock. */
static void check_ept_pointer_match(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	u64 tmp_eptp = INVALID_PAGE;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (!VALID_PAGE(tmp_eptp)) {
			tmp_eptp = to_vmx(vcpu)->ept_pointer;
		} else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) {
			to_kvm_vmx(kvm)->ept_pointers_match
				= EPT_POINTERS_MISMATCH;
			return;
		}
	}

	to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
}

static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
		void *data)
{
	struct kvm_tlb_range *range = data;

	return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn,
			range->pages);
}

static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm,
		struct kvm_vcpu *vcpu, struct kvm_tlb_range *range)
{
	u64 ept_pointer = to_vmx(vcpu)->ept_pointer;

	/*
	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address
	 * of the base of EPT PML4 table, strip off EPT configuration
	 * information.
	 */
	if (range)
		return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK,
				kvm_fill_hv_flush_list_func, (void *)range);
	else
		return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK);
}

static int hv_remote_flush_tlb_with_range(struct kvm *kvm,
		struct kvm_tlb_range *range)
{
	struct kvm_vcpu *vcpu;
	int ret = 0, i;

	spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);

	if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK)
		check_ept_pointer_match(kvm);

	if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
		kvm_for_each_vcpu(i, vcpu, kvm) {
			/* If ept_pointer is invalid pointer, bypass flush request. */
			if (VALID_PAGE(to_vmx(vcpu)->ept_pointer))
				ret |= __hv_remote_flush_tlb_with_range(
					kvm, vcpu, range);
		}
	} else {
		ret = __hv_remote_flush_tlb_with_range(kvm,
				kvm_get_vcpu(kvm, 0), range);
	}

	spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
	return ret;
}
static int hv_remote_flush_tlb(struct kvm *kvm)
{
	return hv_remote_flush_tlb_with_range(kvm, NULL);
}

#endif /* IS_ENABLED(CONFIG_HYPERV) */

/*
 * 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,
 /* Xeon E3-1220 V2 */
0x000306A8,
};

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_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
{
	return flexpriority_enabled && lapic_in_kernel(vcpu);
}

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

static inline 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;
}

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;
}

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;
}

#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);
}

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 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;
}

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);
	/*
	 * Guest access to VMware backdoor ports could legitimately
	 * trigger #GP because of TSS I/O permission bitmap.
	 * We intercept those #GP and allow access to them anyway
	 * as VMware does.
	 */
	if (enable_vmware_backdoor)
		eb |= (1u << GP_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);
}

/*
 * Check if MSR is intercepted for currently loaded MSR bitmap.
 */
static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
{
	unsigned long *msr_bitmap;
	int f = sizeof(unsigned long);

	if (!cpu_has_vmx_msr_bitmap())
		return true;

	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;

	if (msr <= 0x1fff) {
		return !!test_bit(msr, msr_bitmap + 0x800 / f);
	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
		msr &= 0x1fff;
		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
	}

	return true;
}

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 int find_msr(struct vmx_msrs *m, unsigned int msr)
{
	unsigned int i;

	for (i = 0; i < m->nr; ++i) {
		if (m->val[i].index == msr)
			return i;
	}
	return -ENOENT;
}

static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
	int 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;
	}
	i = find_msr(&m->guest, msr);
	if (i < 0)
		goto skip_guest;
	--m->guest.nr;
	m->guest.val[i] = m->guest.val[m->guest.nr];
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);

skip_guest:
	i = find_msr(&m->host, msr);
	if (i < 0)
		return;

	--m->host.nr;
	m->host.val[i] = m->host.val[m->host.nr];
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.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);
	if (host_val_vmcs != HOST_IA32_EFER)
		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, bool entry_only)
{
	int i, j = 0;
	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);
	}

	i = find_msr(&m->guest, msr);
	if (!entry_only)
		j = find_msr(&m->host, msr);

	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
		printk_once(KERN_WARNING "Not enough msr switch entries. "
				"Can't add msr %x\n", msr);
		return;
	}
	if (i < 0) {
		i = m->guest.nr++;
		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
	}
	m->guest.val[i].index = msr;
	m->guest.val[i].value = guest_val;

	if (entry_only)
		return;

	if (j < 0) {
		j = m->host.nr++;
		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
	}
	m->host.val[j].index = msr;
	m->host.val[j].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

	/*
	 * 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, false);
		else
			clear_atomic_switch_msr(vmx, MSR_EFER);
		return false;
	} else {
		clear_atomic_switch_msr(vmx, MSR_EFER);

		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 inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
{
	u32 i;

	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
	for (i = 0; i < addr_range; i++) {
		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
		wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
	}
}

static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
{
	u32 i;

	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
	for (i = 0; i < addr_range; i++) {
		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
		rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
	}
}

static void pt_guest_enter(struct vcpu_vmx *vmx)
{
	if (pt_mode == PT_MODE_SYSTEM)
		return;

	/*
	 * GUEST_IA32_RTIT_CTL is already set in the VMCS.
	 * Save host state before VM entry.
	 */
	rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
		wrmsrl(MSR_IA32_RTIT_CTL, 0);
		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
	}
}

static void pt_guest_exit(struct vcpu_vmx *vmx)
{
	if (pt_mode == PT_MODE_SYSTEM)
		return;

	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
	}

	/* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */
	wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
}

void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct vmcs_host_state *host_state;
#ifdef CONFIG_X86_64
	int cpu = raw_smp_processor_id();
#endif
	unsigned long fs_base, gs_base;
	u16 fs_sel, gs_sel;
	int i;

	vmx->req_immediate_exit = false;

	/*
	 * Note that guest MSRs to be saved/restored can also be changed
	 * when guest state is loaded. This happens when guest transitions
	 * to/from long-mode by setting MSR_EFER.LMA.
	 */
	if (!vmx->loaded_cpu_state || vmx->guest_msrs_dirty) {
		vmx->guest_msrs_dirty = false;
		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);

	}

	if (vmx->loaded_cpu_state)
		return;

	vmx->loaded_cpu_state = vmx->loaded_vmcs;
	host_state = &vmx->loaded_cpu_state->host_state;

	/*
	 * Set host fs and gs selectors.  Unfortunately, 22.2.3 does not
	 * allow segment selectors with cpl > 0 or ti == 1.
	 */
	host_state->ldt_sel = kvm_read_ldt();

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

	gs_base = cpu_kernelmode_gs_base(cpu);
	if (likely(is_64bit_mm(current->mm))) {
		save_fsgs_for_kvm();
		fs_sel = current->thread.fsindex;
		gs_sel = current->thread.gsindex;
		fs_base = current->thread.fsbase;
		vmx->msr_host_kernel_gs_base = current->thread.gsbase;
	} else {
		savesegment(fs, fs_sel);
		savesegment(gs, gs_sel);
		fs_base = read_msr(MSR_FS_BASE);
		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
	}

	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#else
	savesegment(fs, fs_sel);
	savesegment(gs, gs_sel);
	fs_base = segment_base(fs_sel);
	gs_base = segment_base(gs_sel);
#endif

	if (unlikely(fs_sel != host_state->fs_sel)) {
		if (!(fs_sel & 7))
			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
		else
			vmcs_write16(HOST_FS_SELECTOR, 0);
		host_state->fs_sel = fs_sel;
	}
	if (unlikely(gs_sel != host_state->gs_sel)) {
		if (!(gs_sel & 7))
			vmcs_write16(HOST_GS_SELECTOR, gs_sel);
		else
			vmcs_write16(HOST_GS_SELECTOR, 0);
		host_state->gs_sel = gs_sel;
	}
	if (unlikely(fs_base != host_state->fs_base)) {
		vmcs_writel(HOST_FS_BASE, fs_base);
		host_state->fs_base = fs_base;
	}
	if (unlikely(gs_base != host_state->gs_base)) {
		vmcs_writel(HOST_GS_BASE, gs_base);
		host_state->gs_base = gs_base;
	}
}

static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
{
	struct vmcs_host_state *host_state;

	if (!vmx->loaded_cpu_state)
		return;

	WARN_ON_ONCE(vmx->loaded_cpu_state != vmx->loaded_vmcs);
	host_state = &vmx->loaded_cpu_state->host_state;

	++vmx->vcpu.stat.host_state_reload;
	vmx->loaded_cpu_state = NULL;

#ifdef CONFIG_X86_64
	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
		kvm_load_ldt(host_state->ldt_sel);
#ifdef CONFIG_X86_64
		load_gs_index(host_state->gs_sel);
#else
		loadsegment(gs, host_state->gs_sel);
#endif
	}
	if (host_state->fs_sel & 7)
		loadsegment(fs, host_state->fs_sel);
#ifdef CONFIG_X86_64
	if (unlikely(host_state->ds_sel | host_state->es_sel)) {
		loadsegment(ds, host_state->ds_sel);
		loadsegment(es, host_state->es_sel);
	}
#endif
	invalidate_tss_limit();
#ifdef CONFIG_X86_64
	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
#endif
	load_fixmap_gdt(raw_smp_processor_id());
}

#ifdef CONFIG_X86_64
static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
{
	preempt_disable();
	if (vmx->loaded_cpu_state)
		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
	preempt_enable();
	return vmx->msr_guest_kernel_gs_base;
}

static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
{
	preempt_disable();
	if (vmx->loaded_cpu_state)
		wrmsrl(MSR_KERNEL_GS_BASE, data);
	preempt_enable();
	vmx->msr_guest_kernel_gs_base = data;
}
#endif

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;

	/* 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);

	/*
	 * Clear SN before reading the bitmap.  The VT-d firmware
	 * writes the bitmap and reads SN atomically (5.2.3 in the
	 * spec), so it doesn't really have a memory barrier that
	 * pairs with this, but we cannot do that and we need one.
	 */
	smp_mb__after_atomic();

	if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS))
		pi_set_on(pi_desc);
}

/*
 * Switches to specified vcpu, until a matching vcpu_put(), but assumes
 * vcpu mutex is already taken.
 */
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);
		indirect_branch_prediction_barrier();
	}

	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)&get_cpu_entry_area(cpu)->tss.x86_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();
	vmx->host_debugctlmsr = get_debugctlmsr();
}

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);
}

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

	vmx_prepare_switch_to_host(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);

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;
}

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);
}

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;
}

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 int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long value;

	/*
	 * Any MSR write that attempts to change bits marked reserved will
	 * case a #GP fault.
	 */
	if (data & vmx->pt_desc.ctl_bitmask)
		return 1;

	/*
	 * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will
	 * result in a #GP unless the same write also clears TraceEn.
	 */
	if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) &&
		((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN))
		return 1;

	/*
	 * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit
	 * and FabricEn would cause #GP, if
	 * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0
	 */
	if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) &&
		!(data & RTIT_CTL_FABRIC_EN) &&
		!intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_single_range_output))
		return 1;

	/*
	 * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that
	 * utilize encodings marked reserved will casue a #GP fault.
	 */
	value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods);
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) &&
			!test_bit((data & RTIT_CTL_MTC_RANGE) >>
			RTIT_CTL_MTC_RANGE_OFFSET, &value))
		return 1;
	value = intel_pt_validate_cap(vmx->pt_desc.caps,
						PT_CAP_cycle_thresholds);
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) &&
			!test_bit((data & RTIT_CTL_CYC_THRESH) >>
			RTIT_CTL_CYC_THRESH_OFFSET, &value))
		return 1;
	value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods);
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) &&
			!test_bit((data & RTIT_CTL_PSB_FREQ) >>
			RTIT_CTL_PSB_FREQ_OFFSET, &value))
		return 1;

	/*
	 * If ADDRx_CFG is reserved or the encodings is >2 will
	 * cause a #GP fault.
	 */
	value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET;
	if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2))
		return 1;
	value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET;
	if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2))
		return 1;
	value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET;
	if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2))
		return 1;
	value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET;
	if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2))
		return 1;

	return 0;
}


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 vmx_clear_hlt(struct kvm_vcpu *vcpu)
{
	/*
	 * Ensure that we clear the HLT state in the VMCS.  We don't need to
	 * explicitly skip the instruction because if the HLT state is set,
	 * then the instruction is already executing and RIP has already been
	 * advanced.
	 */
	if (kvm_hlt_in_guest(vcpu->kvm) &&
			vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
		vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
}

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;

	kvm_deliver_exception_payload(vcpu);

	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;
	}

	WARN_ON_ONCE(vmx->emulation_required);

	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);

	vmx_clear_hlt(vcpu);
}

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

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

/*
 * 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;
}

/*
 * 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
	/*
	 * The SYSCALL MSRs are only needed on long mode guests, and only
	 * when EFER.SCE is set.
	 */
	if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) {
		index = __find_msr_index(vmx, MSR_STAR);
		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_SYSCALL_MASK);
		if (index >= 0)
			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++);
	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++);

	vmx->save_nmsrs = save_nmsrs;
	vmx->guest_msrs_dirty = true;

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

static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

	if (is_guest_mode(vcpu) &&
	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;

	return vcpu->arch.tsc_offset;
}

static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	u64 g_tsc_offset = 0;

	/*
	 * 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.
	 */
	if (is_guest_mode(vcpu) &&
	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
		g_tsc_offset = vmcs12->tsc_offset;

	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
				   vcpu->arch.tsc_offset - g_tsc_offset,
				   offset);
	vmcs_write64(TSC_OFFSET, offset + g_tsc_offset);
	return offset + g_tsc_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.
 */
bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
{
	return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
}

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);
}

static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
{
	switch (msr->index) {
	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
		if (!nested)
			return 1;
		return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
	default:
		return 1;
	}

	return 0;
}

/*
 * 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 vcpu_vmx *vmx = to_vmx(vcpu);
	struct shared_msr_entry *msr;
	u32 index;

	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:
		msr_info->data = vmx_read_guest_kernel_gs_base(vmx);
		break;
#endif
	case MSR_EFER:
		return kvm_get_msr_common(vcpu, msr_info);
	case MSR_IA32_SPEC_CTRL:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
			return 1;

		msr_info->data = to_vmx(vcpu)->spec_ctrl;
		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 &&
		    !(vmx->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 = vmx->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(&vmx->nested.msrs, 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_IA32_RTIT_CTL:
		if (pt_mode != PT_MODE_HOST_GUEST)
			return 1;
		msr_info->data = vmx->pt_desc.guest.ctl;
		break;
	case MSR_IA32_RTIT_STATUS:
		if (pt_mode != PT_MODE_HOST_GUEST)
			return 1;
		msr_info->data = vmx->pt_desc.guest.status;
		break;
	case MSR_IA32_RTIT_CR3_MATCH:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			!intel_pt_validate_cap(vmx->pt_desc.caps,
						PT_CAP_cr3_filtering))
			return 1;
		msr_info->data = vmx->pt_desc.guest.cr3_match;
		break;
	case MSR_IA32_RTIT_OUTPUT_BASE:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(!intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_topa_output) &&
			 !intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_single_range_output)))
			return 1;
		msr_info->data = vmx->pt_desc.guest.output_base;
		break;
	case MSR_IA32_RTIT_OUTPUT_MASK:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(!intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_topa_output) &&
			 !intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_single_range_output)))
			return 1;
		msr_info->data = vmx->pt_desc.guest.output_mask;
		break;
	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_num_address_ranges)))
			return 1;
		if (index % 2)
			msr_info->data = vmx->pt_desc.guest.addr_b[index / 2];
		else
			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
		break;
	case MSR_TSC_AUX:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
			return 1;
		/* Else, falls through */
	default:
		msr = find_msr_entry(vmx, msr_info->index);
		if (msr) {
			msr_info->data = msr->data;
			break;
		}
		return kvm_get_msr_common(vcpu, msr_info);
	}

	return 0;
}

/*
 * 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;
	u32 index;

	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_write_guest_kernel_gs_base(vmx, 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_SPEC_CTRL:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
			return 1;

		/* The STIBP bit doesn't fault even if it's not advertised */
		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
			return 1;

		vmx->spec_ctrl = data;

		if (!data)
			break;

		/*
		 * For non-nested:
		 * When it's written (to non-zero) for the first time, pass
		 * it through.
		 *
		 * For nested:
		 * The handling of the MSR bitmap for L2 guests is done in
		 * nested_vmx_merge_msr_bitmap. We should not touch the
		 * vmcs02.msr_bitmap here since it gets completely overwritten
		 * in the merging. We update the vmcs01 here for L1 as well
		 * since it will end up touching the MSR anyway now.
		 */
		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
					      MSR_IA32_SPEC_CTRL,
					      MSR_TYPE_RW);
		break;
	case MSR_IA32_PRED_CMD:
		if (!msr_info->host_initiated &&
		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
			return 1;

		if (data & ~PRED_CMD_IBPB)
			return 1;

		if (!data)
			break;

		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);

		/*
		 * For non-nested:
		 * When it's written (to non-zero) for the first time, pass
		 * it through.
		 *
		 * For nested:
		 * The handling of the MSR bitmap for L2 guests is done in
		 * nested_vmx_merge_msr_bitmap. We should not touch the
		 * vmcs02.msr_bitmap here since it gets completely overwritten
		 * in the merging.
		 */
		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
					      MSR_TYPE_W);
		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, false);
		else
			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
		break;
	case MSR_IA32_RTIT_CTL:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			vmx_rtit_ctl_check(vcpu, data) ||
			vmx->nested.vmxon)
			return 1;
		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
		vmx->pt_desc.guest.ctl = data;
		pt_update_intercept_for_msr(vmx);
		break;
	case MSR_IA32_RTIT_STATUS:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
			(data & MSR_IA32_RTIT_STATUS_MASK))
			return 1;
		vmx->pt_desc.guest.status = data;
		break;
	case MSR_IA32_RTIT_CR3_MATCH:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
			!intel_pt_validate_cap(vmx->pt_desc.caps,
						PT_CAP_cr3_filtering))
			return 1;
		vmx->pt_desc.guest.cr3_match = data;
		break;
	case MSR_IA32_RTIT_OUTPUT_BASE:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
			(!intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_topa_output) &&
			 !intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_single_range_output)) ||
			(data & MSR_IA32_RTIT_OUTPUT_BASE_MASK))
			return 1;
		vmx->pt_desc.guest.output_base = data;
		break;
	case MSR_IA32_RTIT_OUTPUT_MASK:
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
			(!intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_topa_output) &&
			 !intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_single_range_output)))
			return 1;
		vmx->pt_desc.guest.output_mask = data;
		break;
	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
		if ((pt_mode != PT_MODE_HOST_GUEST) ||
			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
					PT_CAP_num_address_ranges)))
			return 1;
		if (index % 2)
			vmx->pt_desc.guest.addr_b[index / 2] = data;
		else
			vmx->pt_desc.guest.addr_a[index / 2] = data;
		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;
		/* Else, 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 ("vmxon %0" : : "m"(addr));
}

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;

	/*
	 * This can happen if we hot-added a CPU but failed to allocate
	 * VP assist page for it.
	 */
	if (static_branch_unlikely(&enable_evmcs) &&
	    !hv_get_vp_assist_page(cpu))
		return -EFAULT;

	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);
	if (enable_ept)
		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("vmxoff"));

	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 int setup_vmcs_config(struct vmcs_config *vmcs_conf,
				    struct vmx_capability *vmx_cap)
{
	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;

	memset(vmcs_conf, 0, sizeof(*vmcs_conf));
	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_UNCOND_IO_EXITING |
	      CPU_BASED_MOV_DR_EXITING |
	      CPU_BASED_USE_TSC_OFFSETING |
	      CPU_BASED_MWAIT_EXITING |
	      CPU_BASED_MONITOR_EXITING |
	      CPU_BASED_INVLPG_EXITING |
	      CPU_BASED_RDPMC_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_DESC |
			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_EXITING |
			SECONDARY_EXEC_RDRAND_EXITING |
			SECONDARY_EXEC_ENABLE_PML |
			SECONDARY_EXEC_TSC_SCALING |
			SECONDARY_EXEC_PT_USE_GPA |
			SECONDARY_EXEC_PT_CONCEAL_VMX |
			SECONDARY_EXEC_ENABLE_VMFUNC |
			SECONDARY_EXEC_ENCLS_EXITING;
		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);

	rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP,
		&vmx_cap->ept, &vmx_cap->vpid);

	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);
	} else if (vmx_cap->ept) {
		vmx_cap->ept = 0;
		pr_warn_once("EPT CAP should not exist if not support "
				"1-setting enable EPT VM-execution control\n");
	}
	if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&
		vmx_cap->vpid) {
		vmx_cap->vpid = 0;
		pr_warn_once("VPID CAP should not exist if not support "
				"1-setting enable VPID VM-execution control\n");
	}

	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_LOAD_IA32_PERF_GLOBAL_CTRL |
	      VM_EXIT_SAVE_IA32_PAT |
	      VM_EXIT_LOAD_IA32_PAT |
	      VM_EXIT_LOAD_IA32_EFER |
	      VM_EXIT_CLEAR_BNDCFGS |
	      VM_EXIT_PT_CONCEAL_PIP |
	      VM_EXIT_CLEAR_IA32_RTIT_CTL;
	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;
	opt = PIN_BASED_VIRTUAL_NMIS | 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_PERF_GLOBAL_CTRL |
	      VM_ENTRY_LOAD_IA32_PAT |
	      VM_ENTRY_LOAD_IA32_EFER |
	      VM_ENTRY_LOAD_BNDCFGS |
	      VM_ENTRY_PT_CONCEAL_PIP |
	      VM_ENTRY_LOAD_IA32_RTIT_CTL;
	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
				&_vmentry_control) < 0)
		return -EIO;

	/*
	 * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they
	 * can't be used due to an errata where VM Exit may incorrectly clear
	 * IA32_PERF_GLOBAL_CTRL[34:32].  Workaround the errata by using the
	 * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL.
	 */
	if (boot_cpu_data.x86 == 0x6) {
		switch (boot_cpu_data.x86_model) {
		case 26: /* AAK155 */
		case 30: /* AAP115 */
		case 37: /* AAT100 */
		case 44: /* BC86,AAY89,BD102 */
		case 46: /* BA97 */
			_vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
			_vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
			pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
					"does not work properly. Using workaround\n");
			break;
		default:
			break;
		}
	}


	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;

	if (static_branch_unlikely(&enable_evmcs))
		evmcs_sanitize_exec_ctrls(vmcs_conf);

	return 0;
}

struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags)
{
	int node = cpu_to_node(cpu);
	struct page *pages;
	struct vmcs *vmcs;

	pages = __alloc_pages_node(node, flags, vmcs_config.order);
	if (!pages)
		return NULL;
	vmcs = page_address(pages);
	memset(vmcs, 0, vmcs_config.size);

	/* KVM supports Enlightened VMCS v1 only */
	if (static_branch_unlikely(&enable_evmcs))
		vmcs->hdr.revision_id = KVM_EVMCS_VERSION;
	else
		vmcs->hdr.revision_id = vmcs_config.revision_id;

	if (shadow)
		vmcs->hdr.shadow_vmcs = 1;
	return vmcs;
}

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
 */
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;
	if (loaded_vmcs->msr_bitmap)
		free_page((unsigned long)loaded_vmcs->msr_bitmap);
	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
}

int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
{
	loaded_vmcs->vmcs = alloc_vmcs(false);
	if (!loaded_vmcs->vmcs)
		return -ENOMEM;

	loaded_vmcs->shadow_vmcs = NULL;
	loaded_vmcs_init(loaded_vmcs);

	if (cpu_has_vmx_msr_bitmap()) {
		loaded_vmcs->msr_bitmap = (unsigned long *)
				__get_free_page(GFP_KERNEL_ACCOUNT);
		if (!loaded_vmcs->msr_bitmap)
			goto out_vmcs;
		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);

		if (IS_ENABLED(CONFIG_HYPERV) &&
		    static_branch_unlikely(&enable_evmcs) &&
		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
			struct hv_enlightened_vmcs *evmcs =
				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;

			evmcs->hv_enlightenments_control.msr_bitmap = 1;
		}
	}

	memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));

	return 0;

out_vmcs:
	free_loaded_vmcs(loaded_vmcs);
	return -ENOMEM;
}

static void free_kvm_area(void)
{
	int cpu;

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

static __init int alloc_kvm_area(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct vmcs *vmcs;

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

		/*
		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
		 * revision_id reported by MSR_IA32_VMX_BASIC.
		 *
		 * However, even though not explicitly documented by
		 * TLFS, VMXArea passed as VMXON argument should
		 * still be marked with revision_id reported by
		 * physical CPU.
		 */
		if (static_branch_unlikely(&enable_evmcs))
			vmcs->hdr.revision_id = vmcs_config.revision_id;

		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);
	struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm);

	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 (!kvm_vmx->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, kvm_vmx->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);
}

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;

	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 void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
{
	int vpid = to_vmx(vcpu)->vpid;

	if (!vpid_sync_vcpu_addr(vpid, addr))
		vpid_sync_context(vpid);

	/*
	 * If VPIDs are not supported or enabled, then the above is a no-op.
	 * But we don't really need a TLB flush in that case anyway, because
	 * each VM entry/exit includes an implicit flush when VPID is 0.
	 */
}

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_unrestricted_guest || (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]);
	}
}

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 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;
}

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_VM_CR0_ALWAYS_OFF);
	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 && !enable_unrestricted_guest)
		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;
}

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;
}

void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long guest_cr3;
	u64 eptp;

	guest_cr3 = cr3;
	if (enable_ept) {
		eptp = construct_eptp(vcpu, cr3);
		vmcs_write64(EPT_POINTER, eptp);

		if (kvm_x86_ops->tlb_remote_flush) {
			spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
			to_vmx(vcpu)->ept_pointer = eptp;
			to_kvm_vmx(kvm)->ept_pointers_match
				= EPT_POINTERS_CHECK;
			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
		}

		if (enable_unrestricted_guest || is_paging(vcpu) ||
		    is_guest_mode(vcpu))
			guest_cr3 = kvm_read_cr3(vcpu);
		else
			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
		ept_load_pdptrs(vcpu);
	}

	vmcs_writel(GUEST_CR3, guest_cr3);
}

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;

	hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
	if (enable_unrestricted_guest)
		hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
	else if (to_vmx(vcpu)->rmode.vm86_active)
		hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON;
	else
		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;

	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
		if (cr4 & X86_CR4_UMIP) {
			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
				SECONDARY_EXEC_DESC);
			hw_cr4 &= ~X86_CR4_UMIP;
		} else if (!is_guest_mode(vcpu) ||
			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
					SECONDARY_EXEC_DESC);
	}

	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.  We operate under the default treatment of SMM,
		 * so VMX cannot be enabled under SMM.
		 */
		if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
			return 1;
	}

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

	vcpu->arch.cr4 = cr4;

	if (!enable_unrestricted_guest) {
		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;
			}
		}

		/*
		 * 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.
		 */
		if (!is_paging(vcpu))
			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;
}

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);
}

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;
}

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

	idx = srcu_read_lock(&kvm->srcu);
	fn = to_kvm_vmx(kvm)->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)
{
	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
	int i, idx, r = 0;
	kvm_pfn_t identity_map_pfn;
	u32 tmp;

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

	if (likely(kvm_vmx->ept_identity_pagetable_done))
		goto out2;

	if (!kvm_vmx->ept_identity_map_addr)
		kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
	identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT;

	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
				    kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
	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_vmx->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;
}

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;
}

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);
}

static __always_inline 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;

	if (static_branch_unlikely(&enable_evmcs))
		evmcs_touch_msr_bitmap();

	/*
	 * 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);

	}
}

static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
							 u32 msr, int type)
{
	int f = sizeof(unsigned long);

	if (!cpu_has_vmx_msr_bitmap())
		return;

	if (static_branch_unlikely(&enable_evmcs))
		evmcs_touch_msr_bitmap();

	/*
	 * 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 */
			__set_bit(msr, msr_bitmap + 0x000 / f);

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

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

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

	}
}

static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
			     			      u32 msr, int type, bool value)
{
	if (value)
		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
	else
		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
}

static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
{
	u8 mode = 0;

	if (cpu_has_secondary_exec_ctrls() &&
	    (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
	     SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
		mode |= MSR_BITMAP_MODE_X2APIC;
		if (enable_apicv && kvm_vcpu_apicv_active(vcpu))
			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
	}

	return mode;
}

static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
					 u8 mode)
{
	int msr;

	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
		unsigned word = msr / BITS_PER_LONG;
		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
	}

	if (mode & MSR_BITMAP_MODE_X2APIC) {
		/*
		 * TPR reads and writes can be virtualized even if virtual interrupt
		 * delivery is not in use.
		 */
		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
		}
	}
}

void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
	u8 mode = vmx_msr_bitmap_mode(vcpu);
	u8 changed = mode ^ vmx->msr_bitmap_mode;

	if (!changed)
		return;

	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);

	vmx->msr_bitmap_mode = mode;
}

void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
{
	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
	bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
	u32 i;

	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
							MSR_TYPE_RW, flag);
	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
							MSR_TYPE_RW, flag);
	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
							MSR_TYPE_RW, flag);
	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
							MSR_TYPE_RW, flag);
	for (i = 0; i < vmx->pt_desc.addr_range; i++) {
		vmx_set_intercept_for_msr(msr_bitmap,
			MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
		vmx_set_intercept_for_msr(msr_bitmap,
			MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
	}
}

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

static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	void *vapic_page;
	u32 vppr;
	int rvi;

	if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
		!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
		WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
		return false;

	rvi = vmx_get_rvi();

	vapic_page = kmap(vmx->nested.virtual_apic_page);
	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
	kunmap(vmx->nested.virtual_apic_page);

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

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) {
		/*
		 * 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);
		/* the PIR and ON have been set by L1. */
		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
			kvm_vcpu_kick(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.
 */
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->host_state.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->host_state.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_prepare_switch_to_host(), 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, (unsigned long)vmx_vmexit); /* 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));
	}

	if (cpu_has_load_ia32_efer())
		vmcs_write64(HOST_IA32_EFER, host_efer);
}

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;

	if (!enable_vnmi)
		pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS;

	/* 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_update_msr_bitmap(vcpu);
}

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;
	if (kvm_mwait_in_guest(vmx->vcpu.kvm))
		exec_control &= ~(CPU_BASED_MWAIT_EXITING |
				CPU_BASED_MONITOR_EXITING);
	if (kvm_hlt_in_guest(vmx->vcpu.kvm))
		exec_control &= ~CPU_BASED_HLT_EXITING;
	return exec_control;
}


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 (pt_mode == PT_MODE_SYSTEM)
		exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX);
	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;
	}
	if (!enable_unrestricted_guest)
		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
	if (kvm_pause_in_guest(vmx->vcpu.kvm))
		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_DESC is enabled/disabled on writes to CR4.UMIP,
	 * in vmx_set_cr4.  */
	exec_control &= ~SECONDARY_EXEC_DESC;

	/* 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.msrs.secondary_ctls_high |=
					SECONDARY_EXEC_XSAVES;
			else
				vmx->nested.msrs.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.msrs.secondary_ctls_high |=
					SECONDARY_EXEC_RDTSCP;
			else
				vmx->nested.msrs.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.msrs.secondary_ctls_high |=
					SECONDARY_EXEC_ENABLE_INVPCID;
			else
				vmx->nested.msrs.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_EXITING;

		if (nested) {
			if (rdrand_enabled)
				vmx->nested.msrs.secondary_ctls_high |=
					SECONDARY_EXEC_RDRAND_EXITING;
			else
				vmx->nested.msrs.secondary_ctls_high &=
					~SECONDARY_EXEC_RDRAND_EXITING;
		}
	}

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

		if (nested) {
			if (rdseed_enabled)
				vmx->nested.msrs.secondary_ctls_high |=
					SECONDARY_EXEC_RDSEED_EXITING;
			else
				vmx->nested.msrs.secondary_ctls_high &=
					~SECONDARY_EXEC_RDSEED_EXITING;
		}
	}

	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 void vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
	int i;

	if (nested)
		nested_vmx_vcpu_setup();

	if (cpu_has_vmx_msr_bitmap())
		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));

	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 (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
		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);
	vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
	vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */

	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.val));
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));

	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, vmx_vmexit_ctrl());

	/* 22.2.1, 20.8.1 */
	vm_entry_controls_init(vmx, vmx_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) {
		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
	}

	if (cpu_has_vmx_encls_vmexit())
		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);

	if (pt_mode == PT_MODE_HOST_GUEST) {
		memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc));
		/* Bit[6~0] are forced to 1, writes are ignored. */
		vmx->pt_desc.guest.output_mask = 0x7F;
		vmcs_write64(GUEST_IA32_RTIT_CTL, 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->spec_ctrl = 0;

	vcpu->arch.microcode_version = 0x100000000ULL;
	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);
	}

	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
	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);
	if (kvm_mpx_supported())
		vmcs_write64(GUEST_BNDCFGS, 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 (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);
	if (init_event)
		vmx_clear_hlt(vcpu);
}

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 (!enable_vnmi ||
	    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);

	vmx_clear_hlt(vcpu);
}

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

	if (!enable_vnmi) {
		/*
		 * Tracking the NMI-blocked state in software is built upon
		 * finding the next open IRQ window. This, in turn, depends on
		 * well-behaving guests: They have to keep IRQs disabled at
		 * least as long as the NMI handler runs. Otherwise we may
		 * cause NMI nesting, maybe breaking the guest. But as this is
		 * highly unlikely, we can live with the residual risk.
		 */
		vmx->loaded_vmcs->soft_vnmi_blocked = 1;
		vmx->loaded_vmcs->vnmi_blocked_time = 0;
	}

	++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);

	vmx_clear_hlt(vcpu);
}

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

	if (!enable_vnmi)
		return vmx->loaded_vmcs->soft_vnmi_blocked;
	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;
}

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

	if (!enable_vnmi) {
		if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) {
			vmx->loaded_vmcs->soft_vnmi_blocked = masked;
			vmx->loaded_vmcs->vnmi_blocked_time = 0;
		}
	} else {
		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;

	if (!enable_vnmi &&
	    to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked)
		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;

	if (enable_unrestricted_guest)
		return 0;

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

static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
{
	to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr;
	return 0;
}

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 (kvm_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))
		return handle_ud(vcpu);

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

	if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
		WARN_ON_ONCE(!enable_vmware_backdoor);
		er = kvm_emulate_instruction(vcpu,
			EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
		if (er == EMULATE_USER_EXIT)
			return 0;
		else if (er != EMULATE_DONE)
			kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
		return 1;
	}

	/*
	 * 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);
	}

	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 (is_icebp(intr_info))
				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;
	unsigned port;

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

	++vcpu->stat.io_exits;

	if (string)
		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;

	port = exit_qualification >> 16;
	size = (exit_qualification & 7) + 1;
	in = (exit_qualification & 8) != 0;

	return kvm_fast_pio(vcpu, size, port, in);
}

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_desc(struct kvm_vcpu *vcpu)
{
	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
}

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:
			WARN_ON_ONCE(enable_unrestricted_guest);
			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:
			WARN_ON_ONCE(enable_unrestricted_guest);
			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 kvm_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 kvm_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) &&
			enable_vnmi &&
			(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)
{
	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);
		/*
		 * Doing kvm_skip_emulated_instruction() depends on undefined
		 * behavior: Intel's manual doesn't mandate
		 * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
		 * occurs and while on real hardware it was observed to be set,
		 * other hypervisors (namely Hyper-V) don't set it, we end up
		 * advancing IP with some random value. Disable fast mmio when
		 * running nested and keep it for real hardware in hope that
		 * VM_EXIT_INSTRUCTION_LEN will always be set correctly.
		 */
		if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
			return kvm_skip_emulated_instruction(vcpu);
		else
			return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) ==
								EMULATE_DONE;
	}

	return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
}

static int handle_nmi_window(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(!enable_vnmi);
	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;

	/*
	 * We should never reach the point where we are emulating L2
	 * due to invalid guest state as that means we incorrectly
	 * allowed a nested VMEntry with an invalid vmcs12.
	 */
	WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending);

	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 = kvm_emulate_instruction(vcpu, 0);

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

		if (err != EMULATE_DONE)
			goto emulation_error;

		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
		    vcpu->arch.exception.pending)
			goto emulation_error;

		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;

emulation_error:
	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
	vcpu->run->internal.ndata = 0;
	return 0;
}

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, ple_window,
					    ple_window_grow,
					    ple_window_max);

	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,
					      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);
}

/*
 * 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));
}

static 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();
}

/*
 * 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 (!kvm_pause_in_guest(vcpu->kvm))
		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);
}

static int handle_invpcid(struct kvm_vcpu *vcpu)
{
	u32 vmx_instruction_info;
	unsigned long type;
	bool pcid_enabled;
	gva_t gva;
	struct x86_exception e;
	unsigned i;
	unsigned long roots_to_free = 0;
	struct {
		u64 pcid;
		u64 gla;
	} operand;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);

	if (type > 3) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	/* According to the Intel instruction reference, the memory operand
	 * is read even if it isn't needed (e.g., for type==all)
	 */
	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
				vmx_instruction_info, false, &gva))
		return 1;

	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
		kvm_inject_page_fault(vcpu, &e);
		return 1;
	}

	if (operand.pcid >> 12 != 0) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);

	switch (type) {
	case INVPCID_TYPE_INDIV_ADDR:
		if ((!pcid_enabled && (operand.pcid != 0)) ||
		    is_noncanonical_address(operand.gla, vcpu)) {
			kvm_inject_gp(vcpu, 0);
			return 1;
		}
		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
		return kvm_skip_emulated_instruction(vcpu);

	case INVPCID_TYPE_SINGLE_CTXT:
		if (!pcid_enabled && (operand.pcid != 0)) {
			kvm_inject_gp(vcpu, 0);
			return 1;
		}

		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
			kvm_mmu_sync_roots(vcpu);
			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
		}

		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
			if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
			    == operand.pcid)
				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);

		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
		/*
		 * If neither the current cr3 nor any of the prev_roots use the
		 * given PCID, then nothing needs to be done here because a
		 * resync will happen anyway before switching to any other CR3.
		 */

		return kvm_skip_emulated_instruction(vcpu);

	case INVPCID_TYPE_ALL_NON_GLOBAL:
		/*
		 * Currently, KVM doesn't mark global entries in the shadow
		 * page tables, so a non-global flush just degenerates to a
		 * global flush. If needed, we could optimize this later by
		 * keeping track of global entries in shadow page tables.
		 */

		/* fall-through */
	case INVPCID_TYPE_ALL_INCL_GLOBAL:
		kvm_mmu_unload(vcpu);
		return kvm_skip_emulated_instruction(vcpu);

	default:
		BUG(); /* We have already checked above that type <= 3 */
	}
}

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) &&
			enable_vnmi &&
			(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)
{
	if (!to_vmx(vcpu)->req_immediate_exit)
		kvm_lapic_expired_hv_timer(vcpu);
	return 1;
}

/*
 * When nested=0, all VMX instruction VM Exits filter here.  The handlers
 * are overwritten by nested_vmx_setup() when nested=1.
 */
static int handle_vmx_instruction(struct kvm_vcpu *vcpu)
{
	kvm_queue_exception(vcpu, UD_VECTOR);
	return 1;
}

static int handle_encls(struct kvm_vcpu *vcpu)
{
	/*
	 * SGX virtualization is not yet supported.  There is no software
	 * enable bit for SGX, so we have to trap ENCLS and inject a #UD
	 * to prevent the guest from executing ENCLS.
	 */
	kvm_queue_exception(vcpu, UD_VECTOR);
	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 (*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_vmx_instruction,
	[EXIT_REASON_VMLAUNCH]		      = handle_vmx_instruction,
	[EXIT_REASON_VMPTRLD]		      = handle_vmx_instruction,
	[EXIT_REASON_VMPTRST]		      = handle_vmx_instruction,
	[EXIT_REASON_VMREAD]		      = handle_vmx_instruction,
	[EXIT_REASON_VMRESUME]		      = handle_vmx_instruction,
	[EXIT_REASON_VMWRITE]		      = handle_vmx_instruction,
	[EXIT_REASON_VMOFF]		      = handle_vmx_instruction,
	[EXIT_REASON_VMON]		      = handle_vmx_instruction,
	[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_GDTR_IDTR]		      = handle_desc,
	[EXIT_REASON_LDTR_TR]		      = handle_desc,
	[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_vmx_instruction,
	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
	[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_INVPCID]                 = handle_invpcid,
	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
	[EXIT_REASON_ENCLS]		      = handle_encls,
};

static const int kvm_vmx_max_exit_handlers =
	ARRAY_SIZE(kvm_vmx_exit_handlers);

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 (cpu_has_load_perf_global_ctrl() &&
	    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 (cpu_has_load_perf_global_ctrl() &&
	    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 (unlikely(!enable_vnmi &&
		     vmx->loaded_vmcs->soft_vnmi_blocked)) {
		if (vmx_interrupt_allowed(vcpu)) {
			vmx->loaded_vmcs->soft_vnmi_blocked = 0;
		} else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL &&
			   vcpu->arch.nmi_pending) {
			/*
			 * This CPU don't support us in finding the end of an
			 * NMI-blocked window if the guest runs with IRQs
			 * disabled. So we pull the trigger after 1 s of
			 * futile waiting, but inform the user about this.
			 */
			printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
			       "state on VCPU %d after 1 s timeout\n",
			       __func__, vcpu->vcpu_id);
			vmx->loaded_vmcs->soft_vnmi_blocked = 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;
	}
}

/*
 * Software based L1D cache flush which is used when microcode providing
 * the cache control MSR is not loaded.
 *
 * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
 * flush it is required to read in 64 KiB because the replacement algorithm
 * is not exactly LRU. This could be sized at runtime via topology
 * information but as all relevant affected CPUs have 32KiB L1D cache size
 * there is no point in doing so.
 */
static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
{
	int size = PAGE_SIZE << L1D_CACHE_ORDER;

	/*
	 * This code is only executed when the the flush mode is 'cond' or
	 * 'always'
	 */
	if (static_branch_likely(&vmx_l1d_flush_cond)) {
		bool flush_l1d;

		/*
		 * Clear the per-vcpu flush bit, it gets set again
		 * either from vcpu_run() or from one of the unsafe
		 * VMEXIT handlers.
		 */
		flush_l1d = vcpu->arch.l1tf_flush_l1d;
		vcpu->arch.l1tf_flush_l1d = false;

		/*
		 * Clear the per-cpu flush bit, it gets set again from
		 * the interrupt handlers.
		 */
		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
		kvm_clear_cpu_l1tf_flush_l1d();

		if (!flush_l1d)
			return;
	}

	vcpu->stat.l1d_flush++;

	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
		return;
	}

	asm volatile(
		/* First ensure the pages are in the TLB */
		"xorl	%%eax, %%eax\n"
		".Lpopulate_tlb:\n\t"
		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
		"addl	$4096, %%eax\n\t"
		"cmpl	%%eax, %[size]\n\t"
		"jne	.Lpopulate_tlb\n\t"
		"xorl	%%eax, %%eax\n\t"
		"cpuid\n\t"
		/* Now fill the cache */
		"xorl	%%eax, %%eax\n"
		".Lfill_cache:\n"
		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
		"addl	$64, %%eax\n\t"
		"cmpl	%%eax, %[size]\n\t"
		"jne	.Lfill_cache\n\t"
		"lfence\n"
		:: [flush_pages] "r" (vmx_l1d_flush_pages),
		    [size] "r" (size)
		: "eax", "ebx", "ecx", "edx");
}

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);
}

void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
{
	u32 sec_exec_control;

	if (!lapic_in_kernel(vcpu))
		return;

	if (!flexpriority_enabled &&
	    !cpu_has_vmx_virtualize_x2apic_mode())
		return;

	/* Postpone execution until vmcs01 is the current VMCS. */
	if (is_guest_mode(vcpu)) {
		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
		return;
	}

	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);

	switch (kvm_get_apic_mode(vcpu)) {
	case LAPIC_MODE_INVALID:
		WARN_ONCE(true, "Invalid local APIC state");
	case LAPIC_MODE_DISABLED:
		break;
	case LAPIC_MODE_XAPIC:
		if (flexpriority_enabled) {
			sec_exec_control |=
				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
			vmx_flush_tlb(vcpu, true);
		}
		break;
	case LAPIC_MODE_X2APIC:
		if (cpu_has_vmx_virtualize_x2apic_mode())
			sec_exec_control |=
				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
		break;
	}
	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);

	vmx_update_msr_bitmap(vcpu);
}

static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
{
	if (!is_guest_mode(vcpu)) {
		vmcs_write64(APIC_ACCESS_ADDR, hpa);
		vmx_flush_tlb(vcpu, true);
	}
}

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)
{
	/*
	 * When running L2, updating RVI is only relevant when
	 * vmcs12 virtual-interrupt-delivery enabled.
	 * However, it can be enabled only when L1 also
	 * intercepts external-interrupts and in that case
	 * we should not update vmcs02 RVI but instead intercept
	 * interrupt. Therefore, do nothing when running L2.
	 */
	if (!is_guest_mode(vcpu))
		vmx_set_rvi(max_irr);
}

static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int max_irr;
	bool max_irr_updated;

	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_updated =
			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);

		/*
		 * If we are running L2 and L1 has a new pending interrupt
		 * which can be injected, we should re-evaluate
		 * what should be done with this new L1 interrupt.
		 * If L1 intercepts external-interrupts, we should
		 * exit from L2 to L1. Otherwise, interrupt should be
		 * delivered directly to L2.
		 */
		if (is_guest_mode(vcpu) && max_irr_updated) {
			if (nested_exit_on_intr(vcpu))
				kvm_vcpu_exiting_guest_mode(vcpu);
			else
				kvm_make_request(KVM_REQ_EVENT, vcpu);
		}
	} 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_interrupt(&vmx->vcpu);
		asm("int $2");
		kvm_after_interrupt(&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_NOSPEC
			:
#ifdef CONFIG_X86_64
			[sp]"=&r"(tmp),
#endif
			ASM_CALL_CONSTRAINT
			:
			THUNK_TARGET(entry),
			[ss]"i"(__KERNEL_DS),
			[cs]"i"(__KERNEL_CS)
			);
	}
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);

static bool vmx_has_emulated_msr(int index)
{
	switch (index) {
	case MSR_IA32_SMBASE:
		/*
		 * We cannot do SMM unless we can run the guest in big
		 * real mode.
		 */
		return enable_unrestricted_guest || emulate_invalid_guest_state;
	case MSR_AMD64_VIRT_SPEC_CTRL:
		/* This is AMD only.  */
		return false;
	default:
		return true;
	}
}

static bool vmx_pt_supported(void)
{
	return pt_mode == PT_MODE_HOST_GUEST;
}

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 (enable_vnmi) {
		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);
	} else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked))
		vmx->loaded_vmcs->vnmi_blocked_time +=
			ktime_to_ns(ktime_sub(ktime_get(),
					      vmx->loaded_vmcs->entry_time));
}

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, false);
}

static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
{
	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
	if (!vmx->loaded_vmcs->hv_timer_armed)
		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
			      PIN_BASED_VMX_PREEMPTION_TIMER);
	vmx->loaded_vmcs->hv_timer_armed = true;
}

static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 tscl;
	u32 delta_tsc;

	if (vmx->req_immediate_exit) {
		vmx_arm_hv_timer(vmx, 0);
		return;
	}

	if (vmx->hv_deadline_tsc != -1) {
		tscl = rdtsc();
		if (vmx->hv_deadline_tsc > tscl)
			/* set_hv_timer ensures the delta fits in 32-bits */
			delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
				cpu_preemption_timer_multi);
		else
			delta_tsc = 0;

		vmx_arm_hv_timer(vmx, delta_tsc);
		return;
	}

	if (vmx->loaded_vmcs->hv_timer_armed)
		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
				PIN_BASED_VMX_PREEMPTION_TIMER);
	vmx->loaded_vmcs->hv_timer_armed = false;
}

void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
{
	if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) {
		vmx->loaded_vmcs->host_state.rsp = host_rsp;
		vmcs_writel(HOST_RSP, host_rsp);
	}
}

bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);

static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	unsigned long cr3, cr4;

	/* Record the guest's net vcpu time for enforced NMI injections. */
	if (unlikely(!enable_vnmi &&
		     vmx->loaded_vmcs->soft_vnmi_blocked))
		vmx->loaded_vmcs->entry_time = ktime_get();

	/* 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.need_vmcs12_sync)
		nested_sync_from_vmcs12(vcpu);

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

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

	/* 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);

	pt_guest_enter(vmx);

	atomic_switch_perf_msrs(vmx);

	vmx_update_hv_timer(vcpu);

	/*
	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
	 * is no need to worry about the conditional branch over the wrmsr
	 * being speculatively taken.
	 */
	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);

	if (static_branch_unlikely(&vmx_l1d_should_flush))
		vmx_l1d_flush(vcpu);

	if (vcpu->arch.cr2 != read_cr2())
		write_cr2(vcpu->arch.cr2);

	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
				   vmx->loaded_vmcs->launched);

	vcpu->arch.cr2 = read_cr2();

	/*
	 * We do not use IBRS in the kernel. If this vCPU has used the
	 * SPEC_CTRL MSR it may have left it on; save the value and
	 * turn it off. This is much more efficient than blindly adding
	 * it to the atomic save/restore list. Especially as the former
	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
	 *
	 * For non-nested case:
	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
	 * save it.
	 *
	 * For nested case:
	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
	 * save it.
	 */
	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);

	/* Eliminate branch target predictions from guest mode */
	vmexit_fill_RSB();

	/* All fields are clean at this point */
	if (static_branch_unlikely(&enable_evmcs))
		current_evmcs->hv_clean_fields |=
			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;

	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
	if (vmx->host_debugctlmsr)
		update_debugctlmsr(vmx->host_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_prepare_switch_to_host() 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;

	pt_guest_exit(vmx);

	/*
	 * 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);
	}

	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);
}

static struct kvm *vmx_vm_alloc(void)
{
	struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx),
					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
					    PAGE_KERNEL);
	return &kvm_vmx->kvm;
}

static void vmx_vm_free(struct kvm *kvm)
{
	vfree(to_kvm_vmx(kvm));
}

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);
	nested_vmx_free_vcpu(vcpu);
	free_loaded_vmcs(vmx->loaded_vmcs);
	kfree(vmx->guest_msrs);
	kvm_vcpu_uninit(vcpu);
	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
	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;
	unsigned long *msr_bitmap;
	int cpu;

	vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
	if (!vmx)
		return ERR_PTR(-ENOMEM);

	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
			GFP_KERNEL_ACCOUNT);
	if (!vmx->vcpu.arch.guest_fpu) {
		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
		err = -ENOMEM;
		goto free_partial_vcpu;
	}

	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_ACCOUNT | __GFP_ZERO);
		if (!vmx->pml_pg)
			goto uninit_vcpu;
	}

	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
		     > PAGE_SIZE);

	if (!vmx->guest_msrs)
		goto free_pml;

	err = alloc_loaded_vmcs(&vmx->vmcs01);
	if (err < 0)
		goto free_msrs;

	msr_bitmap = vmx->vmcs01.msr_bitmap;
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
	vmx->msr_bitmap_mode = 0;

	vmx->loaded_vmcs = &vmx->vmcs01;
	cpu = get_cpu();
	vmx_vcpu_load(&vmx->vcpu, cpu);
	vmx->vcpu.cpu = cpu;
	vmx_vcpu_setup(vmx);
	vmx_vcpu_put(&vmx->vcpu);
	put_cpu();
	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
		err = alloc_apic_access_page(kvm);
		if (err)
			goto free_vmcs;
	}

	if (enable_ept && !enable_unrestricted_guest) {
		err = init_rmode_identity_map(kvm);
		if (err)
			goto free_vmcs;
	}

	if (nested)
		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
					   vmx_capability.ept,
					   kvm_vcpu_apicv_active(&vmx->vcpu));
	else
		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));

	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;

	vmx->ept_pointer = INVALID_PAGE;

	return &vmx->vcpu;

free_vmcs:
	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(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
free_partial_vcpu:
	kmem_cache_free(kvm_vcpu_cache, vmx);
	return ERR_PTR(err);
}

#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"

static int vmx_vm_init(struct kvm *kvm)
{
	spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock);

	if (!ple_gap)
		kvm->arch.pause_in_guest = true;

	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
		switch (l1tf_mitigation) {
		case L1TF_MITIGATION_OFF:
		case L1TF_MITIGATION_FLUSH_NOWARN:
			/* 'I explicitly don't care' is set */
			break;
		case L1TF_MITIGATION_FLUSH:
		case L1TF_MITIGATION_FLUSH_NOSMT:
		case L1TF_MITIGATION_FULL:
			/*
			 * Warn upon starting the first VM in a potentially
			 * insecure environment.
			 */
			if (sched_smt_active())
				pr_warn_once(L1TF_MSG_SMT);
			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
				pr_warn_once(L1TF_MSG_L1D);
			break;
		case L1TF_MITIGATION_FULL_FORCE:
			/* Flush is enforced */
			break;
		}
	}
	return 0;
}

static void __init vmx_check_processor_compat(void *rtn)
{
	struct vmcs_config vmcs_conf;
	struct vmx_capability vmx_cap;

	*(int *)rtn = 0;
	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
		*(int *)rtn = -EIO;
	if (nested)
		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
					   enable_apicv);
	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 |
		SECONDARY_EXEC_DESC;

	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.msrs.cr0_fixed1 = 0xffffffff;
	vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE;

#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do {		\
	if (entry && (entry->_reg & (_cpuid_mask)))			\
		vmx->nested.msrs.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));
	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));

#undef cr4_fixed1_update
}

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

	if (kvm_mpx_supported()) {
		bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);

		if (mpx_enabled) {
			vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
			vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
		} else {
			vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
			vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
		}
	}
}

static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	struct kvm_cpuid_entry2 *best = NULL;
	int i;

	for (i = 0; i < PT_CPUID_LEAVES; i++) {
		best = kvm_find_cpuid_entry(vcpu, 0x14, i);
		if (!best)
			return;
		vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax;
		vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx;
		vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx;
		vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx;
	}

	/* Get the number of configurable Address Ranges for filtering */
	vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps,
						PT_CAP_num_address_ranges);

	/* Initialize and clear the no dependency bits */
	vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS |
			RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC);

	/*
	 * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise
	 * will inject an #GP
	 */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering))
		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN;

	/*
	 * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and
	 * PSBFreq can be set
	 */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc))
		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC |
				RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ);

	/*
	 * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and
	 * MTCFreq can be set
	 */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc))
		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN |
				RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE);

	/* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite))
		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW |
							RTIT_CTL_PTW_EN);

	/* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace))
		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN;

	/* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output))
		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA;

	/* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */
	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys))
		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN;

	/* unmask address range configure area */
	for (i = 0; i < vmx->pt_desc.addr_range; i++)
		vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
}

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);
		nested_vmx_entry_exit_ctls_update(vcpu);
	}

	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
		update_intel_pt_cfg(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 vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
{
	to_vmx(vcpu)->req_immediate_exit = true;
}

static int vmx_check_intercept(struct kvm_vcpu *vcpu,
			       struct x86_instruction_info *info,
			       enum x86_intercept_stage stage)
{
	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;

	/*
	 * RDPID causes #UD if disabled through secondary execution controls.
	 * Because it is marked as EmulateOnUD, we need to intercept it here.
	 */
	if (info->intercept == x86_intercept_rdtscp &&
	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
		ctxt->exception.vector = UD_VECTOR;
		ctxt->exception.error_code_valid = false;
		return X86EMUL_PROPAGATE_FAULT;
	}

	/* TODO: check more intercepts... */
	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;
	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;

	if (kvm_mwait_in_guest(vcpu->kvm))
		return -EOPNOTSUPP;

	vmx = to_vmx(vcpu);
	tscl = rdtsc();
	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
	lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);

	if (delta_tsc > lapic_timer_advance_cycles)
		delta_tsc -= lapic_timer_advance_cycles;
	else
		delta_tsc = 0;

	/* 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;
	return delta_tsc == 0;
}

static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
	to_vmx(vcpu)->hv_deadline_tsc = -1;
}
#endif

static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
	if (!kvm_pause_in_guest(vcpu->kvm))
		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(host_irq, vcpu->vcpu_id, 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 int vmx_smi_allowed(struct kvm_vcpu *vcpu)
{
	/* we need a nested vmexit to enter SMM, postpone if run is pending */
	if (to_vmx(vcpu)->nested.nested_run_pending)
		return 0;
	return 1;
}

static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	vmx->nested.smm.guest_mode = is_guest_mode(vcpu);
	if (vmx->nested.smm.guest_mode)
		nested_vmx_vmexit(vcpu, -1, 0, 0);

	vmx->nested.smm.vmxon = vmx->nested.vmxon;
	vmx->nested.vmxon = false;
	vmx_clear_hlt(vcpu);
	return 0;
}

static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	int ret;

	if (vmx->nested.smm.vmxon) {
		vmx->nested.vmxon = true;
		vmx->nested.smm.vmxon = false;
	}

	if (vmx->nested.smm.guest_mode) {
		vcpu->arch.hflags &= ~HF_SMM_MASK;
		ret = nested_vmx_enter_non_root_mode(vcpu, false);
		vcpu->arch.hflags |= HF_SMM_MASK;
		if (ret)
			return ret;

		vmx->nested.smm.guest_mode = false;
	}
	return 0;
}

static int enable_smi_window(struct kvm_vcpu *vcpu)
{
	return 0;
}

static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
{
	return 0;
}

static __init int hardware_setup(void)
{
	unsigned long host_bndcfgs;
	int r, i;

	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]);

	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
		return -EIO;

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

	if (boot_cpu_has(X86_FEATURE_MPX)) {
		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
	}

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

	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_ept() ||
	    !cpu_has_vmx_ept_4levels() ||
	    !cpu_has_vmx_ept_mt_wb() ||
	    !cpu_has_vmx_invept_global())
		enable_ept = 0;

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

	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)
		enable_unrestricted_guest = 0;

	if (!cpu_has_vmx_flexpriority())
		flexpriority_enabled = 0;

	if (!cpu_has_virtual_nmis())
		enable_vnmi = 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 IS_ENABLED(CONFIG_HYPERV)
	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH
	    && enable_ept) {
		kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb;
		kvm_x86_ops->tlb_remote_flush_with_range =
				hv_remote_flush_tlb_with_range;
	}
#endif

	if (!cpu_has_vmx_ple()) {
		ple_gap = 0;
		ple_window = 0;
		ple_window_grow = 0;
		ple_window_max = 0;
		ple_window_shrink = 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;
	}

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

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

	/*
	 * 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())
		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;

	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;

	if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST)
		return -EINVAL;
	if (!enable_ept || !cpu_has_vmx_intel_pt())
		pt_mode = PT_MODE_SYSTEM;

	if (nested) {
		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
					   vmx_capability.ept, enable_apicv);

		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
		if (r)
			return r;
	}

	r = alloc_kvm_area();
	if (r)
		nested_vmx_hardware_unsetup();
	return r;
}

static __exit void hardware_unsetup(void)
{
	if (nested)
		nested_vmx_hardware_unsetup();

	free_kvm_area();
}

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,
	.has_emulated_msr = vmx_has_emulated_msr,

	.vm_init = vmx_vm_init,
	.vm_alloc = vmx_vm_alloc,
	.vm_free = vmx_vm_free,

	.vcpu_create = vmx_create_vcpu,
	.vcpu_free = vmx_free_vcpu,
	.vcpu_reset = vmx_vcpu_reset,

	.prepare_guest_switch = vmx_prepare_switch_to_guest,
	.vcpu_load = vmx_vcpu_load,
	.vcpu_put = vmx_vcpu_put,

	.update_bp_intercept = update_exception_bitmap,
	.get_msr_feature = vmx_get_msr_feature,
	.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,
	.tlb_flush_gva = vmx_flush_tlb_gva,

	.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_apic_mode = vmx_set_virtual_apic_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,
	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
	.sync_pir_to_irr = vmx_sync_pir_to_irr,
	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,

	.set_tss_addr = vmx_set_tss_addr,
	.set_identity_map_addr = vmx_set_identity_map_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,

	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
	.write_l1_tsc_offset = vmx_write_l1_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,
	.umip_emulated = vmx_umip_emulated,
	.pt_supported = vmx_pt_supported,

	.request_immediate_exit = vmx_request_immediate_exit,

	.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,

	.smi_allowed = vmx_smi_allowed,
	.pre_enter_smm = vmx_pre_enter_smm,
	.pre_leave_smm = vmx_pre_leave_smm,
	.enable_smi_window = enable_smi_window,

	.check_nested_events = NULL,
	.get_nested_state = NULL,
	.set_nested_state = NULL,
	.get_vmcs12_pages = NULL,
	.nested_enable_evmcs = NULL,
	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
};

static void vmx_cleanup_l1d_flush(void)
{
	if (vmx_l1d_flush_pages) {
		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
		vmx_l1d_flush_pages = NULL;
	}
	/* Restore state so sysfs ignores VMX */
	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
}

static void vmx_exit(void)
{
#ifdef CONFIG_KEXEC_CORE
	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
	synchronize_rcu();
#endif

	kvm_exit();

#if IS_ENABLED(CONFIG_HYPERV)
	if (static_branch_unlikely(&enable_evmcs)) {
		int cpu;
		struct hv_vp_assist_page *vp_ap;
		/*
		 * Reset everything to support using non-enlightened VMCS
		 * access later (e.g. when we reload the module with
		 * enlightened_vmcs=0)
		 */
		for_each_online_cpu(cpu) {
			vp_ap =	hv_get_vp_assist_page(cpu);

			if (!vp_ap)
				continue;

			vp_ap->current_nested_vmcs = 0;
			vp_ap->enlighten_vmentry = 0;
		}

		static_branch_disable(&enable_evmcs);
	}
#endif
	vmx_cleanup_l1d_flush();
}
module_exit(vmx_exit);

static int __init vmx_init(void)
{
	int r;

#if IS_ENABLED(CONFIG_HYPERV)
	/*
	 * Enlightened VMCS usage should be recommended and the host needs
	 * to support eVMCS v1 or above. We can also disable eVMCS support
	 * with module parameter.
	 */
	if (enlightened_vmcs &&
	    ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED &&
	    (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >=
	    KVM_EVMCS_VERSION) {
		int cpu;

		/* Check that we have assist pages on all online CPUs */
		for_each_online_cpu(cpu) {
			if (!hv_get_vp_assist_page(cpu)) {
				enlightened_vmcs = false;
				break;
			}
		}

		if (enlightened_vmcs) {
			pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n");
			static_branch_enable(&enable_evmcs);
		}
	} else {
		enlightened_vmcs = false;
	}
#endif

	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
		     __alignof__(struct vcpu_vmx), THIS_MODULE);
	if (r)
		return r;

	/*
	 * Must be called after kvm_init() so enable_ept is properly set
	 * up. Hand the parameter mitigation value in which was stored in
	 * the pre module init parser. If no parameter was given, it will
	 * contain 'auto' which will be turned into the default 'cond'
	 * mitigation mode.
	 */
	if (boot_cpu_has(X86_BUG_L1TF)) {
		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
		if (r) {
			vmx_exit();
			return r;
		}
	}

#ifdef CONFIG_KEXEC_CORE
	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
			   crash_vmclear_local_loaded_vmcss);
#endif
	vmx_check_vmcs12_offsets();

	return 0;
}
module_init(vmx_init);