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
|
#define pr_fmt(fmt) "SVM: " fmt
#include <linux/kvm_host.h>
#include "irq.h"
#include "mmu.h"
#include "kvm_cache_regs.h"
#include "x86.h"
#include "cpuid.h"
#include "pmu.h"
#include <linux/module.h>
#include <linux/mod_devicetable.h>
#include <linux/kernel.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/amd-iommu.h>
#include <linux/sched.h>
#include <linux/trace_events.h>
#include <linux/slab.h>
#include <linux/hashtable.h>
#include <linux/objtool.h>
#include <linux/psp-sev.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/rwsem.h>
#include <linux/cc_platform.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
#include <asm/tlbflush.h>
#include <asm/desc.h>
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
#include <asm/spec-ctrl.h>
#include <asm/cpu_device_id.h>
#include <asm/traps.h>
#include <asm/fpu/api.h>
#include <asm/virtext.h>
#include "trace.h"
#include "svm.h"
#include "svm_ops.h"
#include "kvm_onhyperv.h"
#include "svm_onhyperv.h"
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
#ifdef MODULE
static const struct x86_cpu_id svm_cpu_id[] = {
X86_MATCH_FEATURE(X86_FEATURE_SVM, NULL),
{}
};
MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
#endif
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
static bool erratum_383_found __read_mostly;
u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
/*
* Set osvw_len to higher value when updated Revision Guides
* are published and we know what the new status bits are
*/
static uint64_t osvw_len = 4, osvw_status;
static DEFINE_PER_CPU(u64, current_tsc_ratio);
static const struct svm_direct_access_msrs {
u32 index; /* Index of the MSR */
bool always; /* True if intercept is initially cleared */
} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
{ .index = MSR_STAR, .always = true },
{ .index = MSR_IA32_SYSENTER_CS, .always = true },
{ .index = MSR_IA32_SYSENTER_EIP, .always = false },
{ .index = MSR_IA32_SYSENTER_ESP, .always = false },
#ifdef CONFIG_X86_64
{ .index = MSR_GS_BASE, .always = true },
{ .index = MSR_FS_BASE, .always = true },
{ .index = MSR_KERNEL_GS_BASE, .always = true },
{ .index = MSR_LSTAR, .always = true },
{ .index = MSR_CSTAR, .always = true },
{ .index = MSR_SYSCALL_MASK, .always = true },
#endif
{ .index = MSR_IA32_SPEC_CTRL, .always = false },
{ .index = MSR_IA32_PRED_CMD, .always = false },
{ .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
{ .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
{ .index = MSR_IA32_LASTINTFROMIP, .always = false },
{ .index = MSR_IA32_LASTINTTOIP, .always = false },
{ .index = MSR_EFER, .always = false },
{ .index = MSR_IA32_CR_PAT, .always = false },
{ .index = MSR_AMD64_SEV_ES_GHCB, .always = true },
{ .index = MSR_TSC_AUX, .always = false },
{ .index = MSR_INVALID, .always = false },
};
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* pause_filter_count: On processors that support Pause filtering(indicated
* by CPUID Fn8000_000A_EDX), the VMCB provides a 16 bit pause filter
* count value. On VMRUN this value is loaded into an internal counter.
* Each time a pause instruction is executed, this counter is decremented
* until it reaches zero at which time a #VMEXIT is generated if pause
* intercept is enabled. Refer to AMD APM Vol 2 Section 15.14.4 Pause
* Intercept Filtering for more details.
* This also indicate if ple logic enabled.
*
* pause_filter_thresh: In addition, some processor families support advanced
* pause filtering (indicated by CPUID Fn8000_000A_EDX) upper bound on
* the amount of time a guest is allowed to execute in a pause loop.
* In this mode, a 16-bit pause filter threshold field is added in the
* VMCB. The threshold value is a cycle count that is used to reset the
* pause counter. As with simple pause filtering, VMRUN loads the pause
* count value from VMCB into an internal counter. Then, on each pause
* instruction the hardware checks the elapsed number of cycles since
* the most recent pause instruction against the pause filter threshold.
* If the elapsed cycle count is greater than the pause filter threshold,
* then the internal pause count is reloaded from the VMCB and execution
* continues. If the elapsed cycle count is less than the pause filter
* threshold, then the internal pause count is decremented. If the count
* value is less than zero and PAUSE intercept is enabled, a #VMEXIT is
* triggered. If advanced pause filtering is supported and pause filter
* threshold field is set to zero, the filter will operate in the simpler,
* count only mode.
*/
static unsigned short pause_filter_thresh = KVM_DEFAULT_PLE_GAP;
module_param(pause_filter_thresh, ushort, 0444);
static unsigned short pause_filter_count = KVM_SVM_DEFAULT_PLE_WINDOW;
module_param(pause_filter_count, ushort, 0444);
/* Default doubles per-vcpu window every exit. */
static unsigned short pause_filter_count_grow = KVM_DEFAULT_PLE_WINDOW_GROW;
module_param(pause_filter_count_grow, ushort, 0444);
/* Default resets per-vcpu window every exit to pause_filter_count. */
static unsigned short pause_filter_count_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK;
module_param(pause_filter_count_shrink, ushort, 0444);
/* Default is to compute the maximum so we can never overflow. */
static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
module_param(pause_filter_count_max, ushort, 0444);
/*
* Use nested page tables by default. Note, NPT may get forced off by
* svm_hardware_setup() if it's unsupported by hardware or the host kernel.
*/
bool npt_enabled = true;
module_param_named(npt, npt_enabled, bool, 0444);
/* allow nested virtualization in KVM/SVM */
static int nested = true;
module_param(nested, int, S_IRUGO);
/* enable/disable Next RIP Save */
static int nrips = true;
module_param(nrips, int, 0444);
/* enable/disable Virtual VMLOAD VMSAVE */
static int vls = true;
module_param(vls, int, 0444);
/* enable/disable Virtual GIF */
int vgif = true;
module_param(vgif, int, 0444);
/* enable/disable LBR virtualization */
static int lbrv = true;
module_param(lbrv, int, 0444);
static int tsc_scaling = true;
module_param(tsc_scaling, int, 0444);
/*
* enable / disable AVIC. Because the defaults differ for APICv
* support between VMX and SVM we cannot use module_param_named.
*/
static bool avic;
module_param(avic, bool, 0444);
static bool force_avic;
module_param_unsafe(force_avic, bool, 0444);
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
bool intercept_smi = true;
module_param(intercept_smi, bool, 0444);
static bool svm_gp_erratum_intercept = true;
static u8 rsm_ins_bytes[] = "\x0f\xaa";
static unsigned long iopm_base;
struct kvm_ldttss_desc {
u16 limit0;
u16 base0;
unsigned base1:8, type:5, dpl:2, p:1;
unsigned limit1:4, zero0:3, g:1, base2:8;
u32 base3;
u32 zero1;
} __attribute__((packed));
DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
/*
* Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via
* the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE.
*
* RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to
* defer the restoration of TSC_AUX until the CPU returns to userspace.
*/
static int tsc_aux_uret_slot __read_mostly = -1;
static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
u32 svm_msrpm_offset(u32 msr)
{
u32 offset;
int i;
for (i = 0; i < NUM_MSR_MAPS; i++) {
if (msr < msrpm_ranges[i] ||
msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
continue;
offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
offset += (i * MSRS_RANGE_SIZE); /* add range offset */
/* Now we have the u8 offset - but need the u32 offset */
return offset / 4;
}
/* MSR not in any range */
return MSR_INVALID;
}
static void svm_flush_tlb_current(struct kvm_vcpu *vcpu);
static int get_npt_level(void)
{
#ifdef CONFIG_X86_64
return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
#else
return PT32E_ROOT_LEVEL;
#endif
}
int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 old_efer = vcpu->arch.efer;
vcpu->arch.efer = efer;
if (!npt_enabled) {
/* Shadow paging assumes NX to be available. */
efer |= EFER_NX;
if (!(efer & EFER_LMA))
efer &= ~EFER_LME;
}
if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) {
if (!(efer & EFER_SVME)) {
svm_leave_nested(vcpu);
svm_set_gif(svm, true);
/* #GP intercept is still needed for vmware backdoor */
if (!enable_vmware_backdoor)
clr_exception_intercept(svm, GP_VECTOR);
/*
* Free the nested guest state, unless we are in SMM.
* In this case we will return to the nested guest
* as soon as we leave SMM.
*/
if (!is_smm(vcpu))
svm_free_nested(svm);
} else {
int ret = svm_allocate_nested(svm);
if (ret) {
vcpu->arch.efer = old_efer;
return ret;
}
/*
* Never intercept #GP for SEV guests, KVM can't
* decrypt guest memory to workaround the erratum.
*/
if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm))
set_exception_intercept(svm, GP_VECTOR);
}
}
svm->vmcb->save.efer = efer | EFER_SVME;
vmcb_mark_dirty(svm->vmcb, VMCB_CR);
return 0;
}
static int is_external_interrupt(u32 info)
{
info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
}
static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 ret = 0;
if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
ret = KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
return ret;
}
static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (mask == 0)
svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
else
svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
}
static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* SEV-ES does not expose the next RIP. The RIP update is controlled by
* the type of exit and the #VC handler in the guest.
*/
if (sev_es_guest(vcpu->kvm))
goto done;
if (nrips && svm->vmcb->control.next_rip != 0) {
WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
svm->next_rip = svm->vmcb->control.next_rip;
}
if (!svm->next_rip) {
if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
return 0;
} else {
kvm_rip_write(vcpu, svm->next_rip);
}
done:
svm_set_interrupt_shadow(vcpu, 0);
return 1;
}
static void svm_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(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;
kvm_deliver_exception_payload(vcpu);
if (nr == BP_VECTOR && !nrips) {
unsigned long rip, old_rip = kvm_rip_read(vcpu);
/*
* For guest debugging where we have to reinject #BP if some
* INT3 is guest-owned:
* Emulate nRIP by moving RIP forward. Will fail if injection
* raises a fault that is not intercepted. Still better than
* failing in all cases.
*/
(void)svm_skip_emulated_instruction(vcpu);
rip = kvm_rip_read(vcpu);
svm->int3_rip = rip + svm->vmcb->save.cs.base;
svm->int3_injected = rip - old_rip;
}
svm->vmcb->control.event_inj = nr
| SVM_EVTINJ_VALID
| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
| SVM_EVTINJ_TYPE_EXEPT;
svm->vmcb->control.event_inj_err = error_code;
}
static void svm_init_erratum_383(void)
{
u32 low, high;
int err;
u64 val;
if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
return;
/* Use _safe variants to not break nested virtualization */
val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
if (err)
return;
val |= (1ULL << 47);
low = lower_32_bits(val);
high = upper_32_bits(val);
native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
erratum_383_found = true;
}
static void svm_init_osvw(struct kvm_vcpu *vcpu)
{
/*
* Guests should see errata 400 and 415 as fixed (assuming that
* HLT and IO instructions are intercepted).
*/
vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3;
vcpu->arch.osvw.status = osvw_status & ~(6ULL);
/*
* By increasing VCPU's osvw.length to 3 we are telling the guest that
* all osvw.status bits inside that length, including bit 0 (which is
* reserved for erratum 298), are valid. However, if host processor's
* osvw_len is 0 then osvw_status[0] carries no information. We need to
* be conservative here and therefore we tell the guest that erratum 298
* is present (because we really don't know).
*/
if (osvw_len == 0 && boot_cpu_data.x86 == 0x10)
vcpu->arch.osvw.status |= 1;
}
static int has_svm(void)
{
const char *msg;
if (!cpu_has_svm(&msg)) {
printk(KERN_INFO "has_svm: %s\n", msg);
return 0;
}
if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
pr_info("KVM is unsupported when running as an SEV guest\n");
return 0;
}
return 1;
}
static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (tsc_scaling)
wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
cpu_svm_disable();
amd_pmu_disable_virt();
}
static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
uint64_t efer;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
rdmsrl(MSR_EFER, efer);
if (efer & EFER_SVME)
return -EBUSY;
if (!has_svm()) {
pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me);
return -EINVAL;
}
sd = per_cpu(svm_data, me);
if (!sd) {
pr_err("%s: svm_data is NULL on %d\n", __func__, me);
return -EINVAL;
}
sd->asid_generation = 1;
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
sd->min_asid = max_sev_asid + 1;
gdt = get_current_gdt_rw();
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
wrmsrl(MSR_EFER, efer | EFER_SVME);
wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area));
if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
/*
* Set the default value, even if we don't use TSC scaling
* to avoid having stale value in the msr
*/
wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
__this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT);
}
/*
* Get OSVW bits.
*
* Note that it is possible to have a system with mixed processor
* revisions and therefore different OSVW bits. If bits are not the same
* on different processors then choose the worst case (i.e. if erratum
* is present on one processor and not on another then assume that the
* erratum is present everywhere).
*/
if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
uint64_t len, status = 0;
int err;
len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
if (!err)
status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
&err);
if (err)
osvw_status = osvw_len = 0;
else {
if (len < osvw_len)
osvw_len = len;
osvw_status |= status;
osvw_status &= (1ULL << osvw_len) - 1;
}
} else
osvw_status = osvw_len = 0;
svm_init_erratum_383();
amd_pmu_enable_virt();
return 0;
}
static void svm_cpu_uninit(int cpu)
{
struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
if (!sd)
return;
per_cpu(svm_data, cpu) = NULL;
kfree(sd->sev_vmcbs);
__free_page(sd->save_area);
kfree(sd);
}
static int svm_cpu_init(int cpu)
{
struct svm_cpu_data *sd;
int ret = -ENOMEM;
sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
if (!sd)
return ret;
sd->cpu = cpu;
sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!sd->save_area)
goto free_cpu_data;
ret = sev_cpu_init(sd);
if (ret)
goto free_save_area;
per_cpu(svm_data, cpu) = sd;
return 0;
free_save_area:
__free_page(sd->save_area);
free_cpu_data:
kfree(sd);
return ret;
}
static int direct_access_msr_slot(u32 msr)
{
u32 i;
for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
if (direct_access_msrs[i].index == msr)
return i;
return -ENOENT;
}
static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read,
int write)
{
struct vcpu_svm *svm = to_svm(vcpu);
int slot = direct_access_msr_slot(msr);
if (slot == -ENOENT)
return;
/* Set the shadow bitmaps to the desired intercept states */
if (read)
set_bit(slot, svm->shadow_msr_intercept.read);
else
clear_bit(slot, svm->shadow_msr_intercept.read);
if (write)
set_bit(slot, svm->shadow_msr_intercept.write);
else
clear_bit(slot, svm->shadow_msr_intercept.write);
}
static bool valid_msr_intercept(u32 index)
{
return direct_access_msr_slot(index) != -ENOENT;
}
static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
{
u8 bit_write;
unsigned long tmp;
u32 offset;
u32 *msrpm;
msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
to_svm(vcpu)->msrpm;
offset = svm_msrpm_offset(msr);
bit_write = 2 * (msr & 0x0f) + 1;
tmp = msrpm[offset];
BUG_ON(offset == MSR_INVALID);
return !!test_bit(bit_write, &tmp);
}
static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
u32 msr, int read, int write)
{
struct vcpu_svm *svm = to_svm(vcpu);
u8 bit_read, bit_write;
unsigned long tmp;
u32 offset;
/*
* If this warning triggers extend the direct_access_msrs list at the
* beginning of the file
*/
WARN_ON(!valid_msr_intercept(msr));
/* Enforce non allowed MSRs to trap */
if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
read = 0;
if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
write = 0;
offset = svm_msrpm_offset(msr);
bit_read = 2 * (msr & 0x0f);
bit_write = 2 * (msr & 0x0f) + 1;
tmp = msrpm[offset];
BUG_ON(offset == MSR_INVALID);
read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp);
write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
msrpm[offset] = tmp;
svm_hv_vmcb_dirty_nested_enlightenments(vcpu);
svm->nested.force_msr_bitmap_recalc = true;
}
void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
int read, int write)
{
set_shadow_msr_intercept(vcpu, msr, read, write);
set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
}
u32 *svm_vcpu_alloc_msrpm(void)
{
unsigned int order = get_order(MSRPM_SIZE);
struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, order);
u32 *msrpm;
if (!pages)
return NULL;
msrpm = page_address(pages);
memset(msrpm, 0xff, PAGE_SIZE * (1 << order));
return msrpm;
}
void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
{
int i;
for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
if (!direct_access_msrs[i].always)
continue;
set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
}
}
void svm_vcpu_free_msrpm(u32 *msrpm)
{
__free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE));
}
static void svm_msr_filter_changed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 i;
/*
* Set intercept permissions for all direct access MSRs again. They
* will automatically get filtered through the MSR filter, so we are
* back in sync after this.
*/
for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
u32 msr = direct_access_msrs[i].index;
u32 read = test_bit(i, svm->shadow_msr_intercept.read);
u32 write = test_bit(i, svm->shadow_msr_intercept.write);
set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write);
}
}
static void add_msr_offset(u32 offset)
{
int i;
for (i = 0; i < MSRPM_OFFSETS; ++i) {
/* Offset already in list? */
if (msrpm_offsets[i] == offset)
return;
/* Slot used by another offset? */
if (msrpm_offsets[i] != MSR_INVALID)
continue;
/* Add offset to list */
msrpm_offsets[i] = offset;
return;
}
/*
* If this BUG triggers the msrpm_offsets table has an overflow. Just
* increase MSRPM_OFFSETS in this case.
*/
BUG();
}
static void init_msrpm_offsets(void)
{
int i;
memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
u32 offset;
offset = svm_msrpm_offset(direct_access_msrs[i].index);
BUG_ON(offset == MSR_INVALID);
add_msr_offset(offset);
}
}
void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
{
to_vmcb->save.dbgctl = from_vmcb->save.dbgctl;
to_vmcb->save.br_from = from_vmcb->save.br_from;
to_vmcb->save.br_to = from_vmcb->save.br_to;
to_vmcb->save.last_excp_from = from_vmcb->save.last_excp_from;
to_vmcb->save.last_excp_to = from_vmcb->save.last_excp_to;
vmcb_mark_dirty(to_vmcb, VMCB_LBR);
}
static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
if (is_guest_mode(vcpu))
svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
}
static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
/*
* Move the LBR msrs back to the vmcb01 to avoid copying them
* on nested guest entries.
*/
if (is_guest_mode(vcpu))
svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
}
static int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index)
{
/*
* If the LBR virtualization is disabled, the LBR msrs are always
* kept in the vmcb01 to avoid copying them on nested guest entries.
*
* If nested, and the LBR virtualization is enabled/disabled, the msrs
* are moved between the vmcb01 and vmcb02 as needed.
*/
struct vmcb *vmcb =
(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ?
svm->vmcb : svm->vmcb01.ptr;
switch (index) {
case MSR_IA32_DEBUGCTLMSR:
return vmcb->save.dbgctl;
case MSR_IA32_LASTBRANCHFROMIP:
return vmcb->save.br_from;
case MSR_IA32_LASTBRANCHTOIP:
return vmcb->save.br_to;
case MSR_IA32_LASTINTFROMIP:
return vmcb->save.last_excp_from;
case MSR_IA32_LASTINTTOIP:
return vmcb->save.last_excp_to;
default:
KVM_BUG(false, svm->vcpu.kvm,
"%s: Unknown MSR 0x%x", __func__, index);
return 0;
}
}
void svm_update_lbrv(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) &
DEBUGCTLMSR_LBR;
bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
LBR_CTL_ENABLE_MASK);
if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled))
if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))
enable_lbrv = true;
if (enable_lbrv == current_enable_lbrv)
return;
if (enable_lbrv)
svm_enable_lbrv(vcpu);
else
svm_disable_lbrv(vcpu);
}
void disable_nmi_singlestep(struct vcpu_svm *svm)
{
svm->nmi_singlestep = false;
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) {
/* Clear our flags if they were not set by the guest */
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
svm->vmcb->save.rflags &= ~X86_EFLAGS_TF;
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
svm->vmcb->save.rflags &= ~X86_EFLAGS_RF;
}
}
static void grow_ple_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;
if (kvm_pause_in_guest(vcpu->kvm) || !old)
return;
control->pause_filter_count = __grow_ple_window(old,
pause_filter_count,
pause_filter_count_grow,
pause_filter_count_max);
if (control->pause_filter_count != old) {
vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
trace_kvm_ple_window_update(vcpu->vcpu_id,
control->pause_filter_count, old);
}
}
static void shrink_ple_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;
if (kvm_pause_in_guest(vcpu->kvm) || !old)
return;
control->pause_filter_count =
__shrink_ple_window(old,
pause_filter_count,
pause_filter_count_shrink,
pause_filter_count);
if (control->pause_filter_count != old) {
vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
trace_kvm_ple_window_update(vcpu->vcpu_id,
control->pause_filter_count, old);
}
}
static void svm_hardware_unsetup(void)
{
int cpu;
sev_hardware_unsetup();
for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT),
get_order(IOPM_SIZE));
iopm_base = 0;
}
static void init_seg(struct vmcb_seg *seg)
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
seg->limit = 0xffff;
seg->base = 0;
}
static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | type;
seg->limit = 0xffff;
seg->base = 0;
}
static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
return svm->nested.ctl.tsc_offset;
}
static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
return svm->tsc_ratio_msr;
}
static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset;
svm->vmcb->control.tsc_offset = offset;
vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
}
void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
{
wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
}
/* Evaluate instruction intercepts that depend on guest CPUID features. */
static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
struct vcpu_svm *svm)
{
/*
* Intercept INVPCID if shadow paging is enabled to sync/free shadow
* roots, or if INVPCID is disabled in the guest to inject #UD.
*/
if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
if (!npt_enabled ||
!guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID))
svm_set_intercept(svm, INTERCEPT_INVPCID);
else
svm_clr_intercept(svm, INTERCEPT_INVPCID);
}
if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) {
if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
svm_clr_intercept(svm, INTERCEPT_RDTSCP);
else
svm_set_intercept(svm, INTERCEPT_RDTSCP);
}
}
static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (guest_cpuid_is_intel(vcpu)) {
/*
* We must intercept SYSENTER_EIP and SYSENTER_ESP
* accesses because the processor only stores 32 bits.
* For the same reason we cannot use virtual VMLOAD/VMSAVE.
*/
svm_set_intercept(svm, INTERCEPT_VMLOAD);
svm_set_intercept(svm, INTERCEPT_VMSAVE);
svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0);
svm->v_vmload_vmsave_enabled = false;
} else {
/*
* If hardware supports Virtual VMLOAD VMSAVE then enable it
* in VMCB and clear intercepts to avoid #VMEXIT.
*/
if (vls) {
svm_clr_intercept(svm, INTERCEPT_VMLOAD);
svm_clr_intercept(svm, INTERCEPT_VMSAVE);
svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
}
/* No need to intercept these MSRs */
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1);
}
}
static void init_vmcb(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb01.ptr;
struct vmcb_control_area *control = &vmcb->control;
struct vmcb_save_area *save = &vmcb->save;
svm_set_intercept(svm, INTERCEPT_CR0_READ);
svm_set_intercept(svm, INTERCEPT_CR3_READ);
svm_set_intercept(svm, INTERCEPT_CR4_READ);
svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
svm_set_intercept(svm, INTERCEPT_CR3_WRITE);
svm_set_intercept(svm, INTERCEPT_CR4_WRITE);
if (!kvm_vcpu_apicv_active(vcpu))
svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
set_dr_intercepts(svm);
set_exception_intercept(svm, PF_VECTOR);
set_exception_intercept(svm, UD_VECTOR);
set_exception_intercept(svm, MC_VECTOR);
set_exception_intercept(svm, AC_VECTOR);
set_exception_intercept(svm, DB_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. Don't intercept #GP for SEV guests as KVM can't
* decrypt guest memory to decode the faulting instruction.
*/
if (enable_vmware_backdoor && !sev_guest(vcpu->kvm))
set_exception_intercept(svm, GP_VECTOR);
svm_set_intercept(svm, INTERCEPT_INTR);
svm_set_intercept(svm, INTERCEPT_NMI);
if (intercept_smi)
svm_set_intercept(svm, INTERCEPT_SMI);
svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
svm_set_intercept(svm, INTERCEPT_RDPMC);
svm_set_intercept(svm, INTERCEPT_CPUID);
svm_set_intercept(svm, INTERCEPT_INVD);
svm_set_intercept(svm, INTERCEPT_INVLPG);
svm_set_intercept(svm, INTERCEPT_INVLPGA);
svm_set_intercept(svm, INTERCEPT_IOIO_PROT);
svm_set_intercept(svm, INTERCEPT_MSR_PROT);
svm_set_intercept(svm, INTERCEPT_TASK_SWITCH);
svm_set_intercept(svm, INTERCEPT_SHUTDOWN);
svm_set_intercept(svm, INTERCEPT_VMRUN);
svm_set_intercept(svm, INTERCEPT_VMMCALL);
svm_set_intercept(svm, INTERCEPT_VMLOAD);
svm_set_intercept(svm, INTERCEPT_VMSAVE);
svm_set_intercept(svm, INTERCEPT_STGI);
svm_set_intercept(svm, INTERCEPT_CLGI);
svm_set_intercept(svm, INTERCEPT_SKINIT);
svm_set_intercept(svm, INTERCEPT_WBINVD);
svm_set_intercept(svm, INTERCEPT_XSETBV);
svm_set_intercept(svm, INTERCEPT_RDPRU);
svm_set_intercept(svm, INTERCEPT_RSM);
if (!kvm_mwait_in_guest(vcpu->kvm)) {
svm_set_intercept(svm, INTERCEPT_MONITOR);
svm_set_intercept(svm, INTERCEPT_MWAIT);
}
if (!kvm_hlt_in_guest(vcpu->kvm))
svm_set_intercept(svm, INTERCEPT_HLT);
control->iopm_base_pa = __sme_set(iopm_base);
control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
control->int_ctl = V_INTR_MASKING_MASK;
init_seg(&save->es);
init_seg(&save->ss);
init_seg(&save->ds);
init_seg(&save->fs);
init_seg(&save->gs);
save->cs.selector = 0xf000;
save->cs.base = 0xffff0000;
/* Executable/Readable Code Segment */
save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK |
SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK;
save->cs.limit = 0xffff;
save->gdtr.base = 0;
save->gdtr.limit = 0xffff;
save->idtr.base = 0;
save->idtr.limit = 0xffff;
init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
if (npt_enabled) {
/* Setup VMCB for Nested Paging */
control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE;
svm_clr_intercept(svm, INTERCEPT_INVLPG);
clr_exception_intercept(svm, PF_VECTOR);
svm_clr_intercept(svm, INTERCEPT_CR3_READ);
svm_clr_intercept(svm, INTERCEPT_CR3_WRITE);
save->g_pat = vcpu->arch.pat;
save->cr3 = 0;
}
svm->current_vmcb->asid_generation = 0;
svm->asid = 0;
svm->nested.vmcb12_gpa = INVALID_GPA;
svm->nested.last_vmcb12_gpa = INVALID_GPA;
if (!kvm_pause_in_guest(vcpu->kvm)) {
control->pause_filter_count = pause_filter_count;
if (pause_filter_thresh)
control->pause_filter_thresh = pause_filter_thresh;
svm_set_intercept(svm, INTERCEPT_PAUSE);
} else {
svm_clr_intercept(svm, INTERCEPT_PAUSE);
}
svm_recalc_instruction_intercepts(vcpu, svm);
/*
* If the host supports V_SPEC_CTRL then disable the interception
* of MSR_IA32_SPEC_CTRL.
*/
if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL))
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
if (kvm_vcpu_apicv_active(vcpu))
avic_init_vmcb(svm, vmcb);
if (vgif) {
svm_clr_intercept(svm, INTERCEPT_STGI);
svm_clr_intercept(svm, INTERCEPT_CLGI);
svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
}
if (sev_guest(vcpu->kvm)) {
svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
clr_exception_intercept(svm, UD_VECTOR);
if (sev_es_guest(vcpu->kvm)) {
/* Perform SEV-ES specific VMCB updates */
sev_es_init_vmcb(svm);
}
}
svm_hv_init_vmcb(vmcb);
init_vmcb_after_set_cpuid(vcpu);
vmcb_mark_all_dirty(vmcb);
enable_gif(svm);
}
static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm_vcpu_init_msrpm(vcpu, svm->msrpm);
svm_init_osvw(vcpu);
vcpu->arch.microcode_version = 0x01000065;
svm->tsc_ratio_msr = kvm_default_tsc_scaling_ratio;
if (sev_es_guest(vcpu->kvm))
sev_es_vcpu_reset(svm);
}
static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->spec_ctrl = 0;
svm->virt_spec_ctrl = 0;
init_vmcb(vcpu);
if (!init_event)
__svm_vcpu_reset(vcpu);
}
void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb)
{
svm->current_vmcb = target_vmcb;
svm->vmcb = target_vmcb->ptr;
}
static int svm_vcpu_create(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm;
struct page *vmcb01_page;
struct page *vmsa_page = NULL;
int err;
BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
svm = to_svm(vcpu);
err = -ENOMEM;
vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!vmcb01_page)
goto out;
if (sev_es_guest(vcpu->kvm)) {
/*
* SEV-ES guests require a separate VMSA page used to contain
* the encrypted register state of the guest.
*/
vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!vmsa_page)
goto error_free_vmcb_page;
/*
* SEV-ES guests maintain an encrypted version of their FPU
* state which is restored and saved on VMRUN and VMEXIT.
* Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't
* do xsave/xrstor on it.
*/
fpstate_set_confidential(&vcpu->arch.guest_fpu);
}
err = avic_init_vcpu(svm);
if (err)
goto error_free_vmsa_page;
svm->msrpm = svm_vcpu_alloc_msrpm();
if (!svm->msrpm) {
err = -ENOMEM;
goto error_free_vmsa_page;
}
svm->vmcb01.ptr = page_address(vmcb01_page);
svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
svm_switch_vmcb(svm, &svm->vmcb01);
if (vmsa_page)
svm->sev_es.vmsa = page_address(vmsa_page);
svm->guest_state_loaded = false;
return 0;
error_free_vmsa_page:
if (vmsa_page)
__free_page(vmsa_page);
error_free_vmcb_page:
__free_page(vmcb01_page);
out:
return err;
}
static void svm_clear_current_vmcb(struct vmcb *vmcb)
{
int i;
for_each_online_cpu(i)
cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL);
}
static void svm_vcpu_free(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* The vmcb page can be recycled, causing a false negative in
* svm_vcpu_load(). So, ensure that no logical CPU has this
* vmcb page recorded as its current vmcb.
*/
svm_clear_current_vmcb(svm->vmcb);
svm_free_nested(svm);
sev_free_vcpu(vcpu);
__free_page(pfn_to_page(__sme_clr(svm->vmcb01.pa) >> PAGE_SHIFT));
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
if (sev_es_guest(vcpu->kvm))
sev_es_unmap_ghcb(svm);
if (svm->guest_state_loaded)
return;
/*
* Save additional host state that will be restored on VMEXIT (sev-es)
* or subsequent vmload of host save area.
*/
vmsave(__sme_page_pa(sd->save_area));
if (sev_es_guest(vcpu->kvm)) {
struct vmcb_save_area *hostsa;
hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
sev_es_prepare_switch_to_guest(hostsa);
}
if (tsc_scaling) {
u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
__this_cpu_write(current_tsc_ratio, tsc_ratio);
wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
}
}
if (likely(tsc_aux_uret_slot >= 0))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
svm->guest_state_loaded = true;
}
static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
{
to_svm(vcpu)->guest_state_loaded = false;
}
static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
if (sd->current_vmcb != svm->vmcb) {
sd->current_vmcb = svm->vmcb;
indirect_branch_prediction_barrier();
}
if (kvm_vcpu_apicv_active(vcpu))
__avic_vcpu_load(vcpu, cpu);
}
static void svm_vcpu_put(struct kvm_vcpu *vcpu)
{
if (kvm_vcpu_apicv_active(vcpu))
__avic_vcpu_put(vcpu);
svm_prepare_host_switch(vcpu);
++vcpu->stat.host_state_reload;
}
static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long rflags = svm->vmcb->save.rflags;
if (svm->nmi_singlestep) {
/* Hide our flags if they were not set by the guest */
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
rflags &= ~X86_EFLAGS_TF;
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
rflags &= ~X86_EFLAGS_RF;
}
return rflags;
}
static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
if (to_svm(vcpu)->nmi_singlestep)
rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
/*
* Any change of EFLAGS.VM is accompanied by a reload of SS
* (caused by either a task switch or an inter-privilege IRET),
* so we do not need to update the CPL here.
*/
to_svm(vcpu)->vmcb->save.rflags = rflags;
}
static bool svm_get_if_flag(struct kvm_vcpu *vcpu)
{
struct vmcb *vmcb = to_svm(vcpu)->vmcb;
return sev_es_guest(vcpu->kvm)
? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK
: kvm_get_rflags(vcpu) & X86_EFLAGS_IF;
}
static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
kvm_register_mark_available(vcpu, reg);
switch (reg) {
case VCPU_EXREG_PDPTR:
/*
* When !npt_enabled, mmu->pdptrs[] is already available since
* it is always updated per SDM when moving to CRs.
*/
if (npt_enabled)
load_pdptrs(vcpu, kvm_read_cr3(vcpu));
break;
default:
KVM_BUG_ON(1, vcpu->kvm);
}
}
static void svm_set_vintr(struct vcpu_svm *svm)
{
struct vmcb_control_area *control;
/*
* The following fields are ignored when AVIC is enabled
*/
WARN_ON(kvm_vcpu_apicv_activated(&svm->vcpu));
svm_set_intercept(svm, INTERCEPT_VINTR);
/*
* This is just a dummy VINTR to actually cause a vmexit to happen.
* Actual injection of virtual interrupts happens through EVENTINJ.
*/
control = &svm->vmcb->control;
control->int_vector = 0x0;
control->int_ctl &= ~V_INTR_PRIO_MASK;
control->int_ctl |= V_IRQ_MASK |
((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT);
vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
}
static void svm_clear_vintr(struct vcpu_svm *svm)
{
svm_clr_intercept(svm, INTERCEPT_VINTR);
/* Drop int_ctl fields related to VINTR injection. */
svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
if (is_guest_mode(&svm->vcpu)) {
svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
(svm->nested.ctl.int_ctl & V_TPR_MASK));
svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
V_IRQ_INJECTION_BITS_MASK;
svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
}
vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
}
static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg)
{
struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
struct vmcb_save_area *save01 = &to_svm(vcpu)->vmcb01.ptr->save;
switch (seg) {
case VCPU_SREG_CS: return &save->cs;
case VCPU_SREG_DS: return &save->ds;
case VCPU_SREG_ES: return &save->es;
case VCPU_SREG_FS: return &save01->fs;
case VCPU_SREG_GS: return &save01->gs;
case VCPU_SREG_SS: return &save->ss;
case VCPU_SREG_TR: return &save01->tr;
case VCPU_SREG_LDTR: return &save01->ldtr;
}
BUG();
return NULL;
}
static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct vmcb_seg *s = svm_seg(vcpu, seg);
return s->base;
}
static void svm_get_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
struct vmcb_seg *s = svm_seg(vcpu, seg);
var->base = s->base;
var->limit = s->limit;
var->selector = s->selector;
var->type = s->attrib & SVM_SELECTOR_TYPE_MASK;
var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1;
var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1;
var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1;
var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
/*
* AMD CPUs circa 2014 track the G bit for all segments except CS.
* However, the SVM spec states that the G bit is not observed by the
* CPU, and some VMware virtual CPUs drop the G bit for all segments.
* So let's synthesize a legal G bit for all segments, this helps
* running KVM nested. It also helps cross-vendor migration, because
* Intel's vmentry has a check on the 'G' bit.
*/
var->g = s->limit > 0xfffff;
/*
* AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
var->unusable = !var->present;
switch (seg) {
case VCPU_SREG_TR:
/*
* Work around a bug where the busy flag in the tr selector
* isn't exposed
*/
var->type |= 0x2;
break;
case VCPU_SREG_DS:
case VCPU_SREG_ES:
case VCPU_SREG_FS:
case VCPU_SREG_GS:
/*
* The accessed bit must always be set in the segment
* descriptor cache, although it can be cleared in the
* descriptor, the cached bit always remains at 1. Since
* Intel has a check on this, set it here to support
* cross-vendor migration.
*/
if (!var->unusable)
var->type |= 0x1;
break;
case VCPU_SREG_SS:
/*
* On AMD CPUs sometimes the DB bit in the segment
* descriptor is left as 1, although the whole segment has
* been made unusable. Clear it here to pass an Intel VMX
* entry check when cross vendor migrating.
*/
if (var->unusable)
var->db = 0;
/* This is symmetric with svm_set_segment() */
var->dpl = to_svm(vcpu)->vmcb->save.cpl;
break;
}
}
static int svm_get_cpl(struct kvm_vcpu *vcpu)
{
struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
return save->cpl;
}
static void svm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
struct kvm_segment cs;
svm_get_segment(vcpu, &cs, VCPU_SREG_CS);
*db = cs.db;
*l = cs.l;
}
static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
dt->size = svm->vmcb->save.idtr.limit;
dt->address = svm->vmcb->save.idtr.base;
}
static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->save.idtr.limit = dt->size;
svm->vmcb->save.idtr.base = dt->address ;
vmcb_mark_dirty(svm->vmcb, VMCB_DT);
}
static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
dt->size = svm->vmcb->save.gdtr.limit;
dt->address = svm->vmcb->save.gdtr.base;
}
static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->save.gdtr.limit = dt->size;
svm->vmcb->save.gdtr.base = dt->address ;
vmcb_mark_dirty(svm->vmcb, VMCB_DT);
}
static void sev_post_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* For guests that don't set guest_state_protected, the cr3 update is
* handled via kvm_mmu_load() while entering the guest. For guests
* that do (SEV-ES/SEV-SNP), the cr3 update needs to be written to
* VMCB save area now, since the save area will become the initial
* contents of the VMSA, and future VMCB save area updates won't be
* seen.
*/
if (sev_es_guest(vcpu->kvm)) {
svm->vmcb->save.cr3 = cr3;
vmcb_mark_dirty(svm->vmcb, VMCB_CR);
}
}
void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 hcr0 = cr0;
bool old_paging = is_paging(vcpu);
#ifdef CONFIG_X86_64
if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
vcpu->arch.efer |= EFER_LMA;
svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
}
if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
vcpu->arch.efer &= ~EFER_LMA;
svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
}
}
#endif
vcpu->arch.cr0 = cr0;
if (!npt_enabled) {
hcr0 |= X86_CR0_PG | X86_CR0_WP;
if (old_paging != is_paging(vcpu))
svm_set_cr4(vcpu, kvm_read_cr4(vcpu));
}
/*
* re-enable caching here because the QEMU bios
* does not do it - this results in some delay at
* reboot
*/
if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
hcr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = hcr0;
vmcb_mark_dirty(svm->vmcb, VMCB_CR);
/*
* SEV-ES guests must always keep the CR intercepts cleared. CR
* tracking is done using the CR write traps.
*/
if (sev_es_guest(vcpu->kvm))
return;
if (hcr0 == cr0) {
/* Selective CR0 write remains on. */
svm_clr_intercept(svm, INTERCEPT_CR0_READ);
svm_clr_intercept(svm, INTERCEPT_CR0_WRITE);
} else {
svm_set_intercept(svm, INTERCEPT_CR0_READ);
svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
}
}
static bool svm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
return true;
}
void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
unsigned long old_cr4 = vcpu->arch.cr4;
if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
svm_flush_tlb_current(vcpu);
vcpu->arch.cr4 = cr4;
if (!npt_enabled) {
cr4 |= X86_CR4_PAE;
if (!is_paging(vcpu))
cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
}
cr4 |= host_cr4_mce;
to_svm(vcpu)->vmcb->save.cr4 = cr4;
vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
kvm_update_cpuid_runtime(vcpu);
}
static void svm_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_seg *s = svm_seg(vcpu, seg);
s->base = var->base;
s->limit = var->limit;
s->selector = var->selector;
s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
/*
* This is always accurate, except if SYSRET returned to a segment
* with SS.DPL != 3. Intel does not have this quirk, and always
* forces SS.DPL to 3 on sysret, so we ignore that case; fixing it
* would entail passing the CPL to userspace and back.
*/
if (seg == VCPU_SREG_SS)
/* This is symmetric with svm_get_segment() */
svm->vmcb->save.cpl = (var->dpl & 3);
vmcb_mark_dirty(svm->vmcb, VMCB_SEG);
}
static void svm_update_exception_bitmap(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
clr_exception_intercept(svm, BP_VECTOR);
if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
set_exception_intercept(svm, BP_VECTOR);
}
}
static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
{
if (sd->next_asid > sd->max_asid) {
++sd->asid_generation;
sd->next_asid = sd->min_asid;
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
}
svm->current_vmcb->asid_generation = sd->asid_generation;
svm->asid = sd->next_asid++;
}
static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
{
struct vmcb *vmcb = svm->vmcb;
if (svm->vcpu.arch.guest_state_protected)
return;
if (unlikely(value != vmcb->save.dr6)) {
vmcb->save.dr6 = value;
vmcb_mark_dirty(vmcb, VMCB_DR);
}
}
static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (vcpu->arch.guest_state_protected)
return;
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);
/*
* We cannot reset svm->vmcb->save.dr6 to DR6_ACTIVE_LOW here,
* because db_interception might need it. We can do it before vmentry.
*/
vcpu->arch.dr6 = svm->vmcb->save.dr6;
vcpu->arch.dr7 = svm->vmcb->save.dr7;
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
set_dr_intercepts(svm);
}
static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (vcpu->arch.guest_state_protected)
return;
svm->vmcb->save.dr7 = value;
vmcb_mark_dirty(svm->vmcb, VMCB_DR);
}
static int pf_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
return kvm_handle_page_fault(vcpu, error_code, fault_address,
static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
svm->vmcb->control.insn_bytes : NULL,
svm->vmcb->control.insn_len);
}
static int npf_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
return kvm_mmu_page_fault(vcpu, fault_address, error_code,
static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
svm->vmcb->control.insn_bytes : NULL,
svm->vmcb->control.insn_len);
}
static int db_interception(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
struct vcpu_svm *svm = to_svm(vcpu);
if (!(vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
!svm->nmi_singlestep) {
u32 payload = svm->vmcb->save.dr6 ^ DR6_ACTIVE_LOW;
kvm_queue_exception_p(vcpu, DB_VECTOR, payload);
return 1;
}
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
/* Make sure we check for pending NMIs upon entry */
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6;
kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7;
kvm_run->debug.arch.pc =
svm->vmcb->save.cs.base + svm->vmcb->save.rip;
kvm_run->debug.arch.exception = DB_VECTOR;
return 0;
}
return 1;
}
static int bp_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_run *kvm_run = vcpu->run;
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
kvm_run->debug.arch.exception = BP_VECTOR;
return 0;
}
static int ud_interception(struct kvm_vcpu *vcpu)
{
return handle_ud(vcpu);
}
static int ac_interception(struct kvm_vcpu *vcpu)
{
kvm_queue_exception_e(vcpu, AC_VECTOR, 0);
return 1;
}
static bool is_erratum_383(void)
{
int err, i;
u64 value;
if (!erratum_383_found)
return false;
value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
if (err)
return false;
/* Bit 62 may or may not be set for this mce */
value &= ~(1ULL << 62);
if (value != 0xb600000000010015ULL)
return false;
/* Clear MCi_STATUS registers */
for (i = 0; i < 6; ++i)
native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
if (!err) {
u32 low, high;
value &= ~(1ULL << 2);
low = lower_32_bits(value);
high = upper_32_bits(value);
native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
}
/* Flush tlb to evict multi-match entries */
__flush_tlb_all();
return true;
}
static void svm_handle_mce(struct kvm_vcpu *vcpu)
{
if (is_erratum_383()) {
/*
* Erratum 383 triggered. Guest state is corrupt so kill the
* guest.
*/
pr_err("KVM: Guest triggered AMD Erratum 383\n");
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return;
}
/*
* On an #MC intercept the MCE handler is not called automatically in
* the host. So do it by hand here.
*/
kvm_machine_check();
}
static int mc_interception(struct kvm_vcpu *vcpu)
{
return 1;
}
static int shutdown_interception(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
struct vcpu_svm *svm = to_svm(vcpu);
/*
* The VM save area has already been encrypted so it
* cannot be reinitialized - just terminate.
*/
if (sev_es_guest(vcpu->kvm))
return -EINVAL;
/*
* VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put
* the VMCB in a known good state. Unfortuately, KVM doesn't have
* KVM_MP_STATE_SHUTDOWN and can't add it without potentially breaking
* userspace. At a platform view, INIT is acceptable behavior as
* there exist bare metal platforms that automatically INIT the CPU
* in response to shutdown.
*/
clear_page(svm->vmcb);
kvm_vcpu_reset(vcpu, true);
kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
}
static int io_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
int size, in, string;
unsigned port;
++vcpu->stat.io_exits;
string = (io_info & SVM_IOIO_STR_MASK) != 0;
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
port = io_info >> 16;
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
if (string) {
if (sev_es_guest(vcpu->kvm))
return sev_es_string_io(svm, size, port, in);
else
return kvm_emulate_instruction(vcpu, 0);
}
svm->next_rip = svm->vmcb->control.exit_info_2;
return kvm_fast_pio(vcpu, size, port, in);
}
static int nmi_interception(struct kvm_vcpu *vcpu)
{
return 1;
}
static int smi_interception(struct kvm_vcpu *vcpu)
{
return 1;
}
static int intr_interception(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
return 1;
}
static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb12;
struct kvm_host_map map;
int ret;
if (nested_svm_check_permissions(vcpu))
return 1;
ret = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
if (ret) {
if (ret == -EINVAL)
kvm_inject_gp(vcpu, 0);
return 1;
}
vmcb12 = map.hva;
ret = kvm_skip_emulated_instruction(vcpu);
if (vmload) {
svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
svm->sysenter_eip_hi = 0;
svm->sysenter_esp_hi = 0;
} else {
svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
}
kvm_vcpu_unmap(vcpu, &map, true);
return ret;
}
static int vmload_interception(struct kvm_vcpu *vcpu)
{
return vmload_vmsave_interception(vcpu, true);
}
static int vmsave_interception(struct kvm_vcpu *vcpu)
{
return vmload_vmsave_interception(vcpu, false);
}
static int vmrun_interception(struct kvm_vcpu *vcpu)
{
if (nested_svm_check_permissions(vcpu))
return 1;
return nested_svm_vmrun(vcpu);
}
enum {
NONE_SVM_INSTR,
SVM_INSTR_VMRUN,
SVM_INSTR_VMLOAD,
SVM_INSTR_VMSAVE,
};
/* Return NONE_SVM_INSTR if not SVM instrs, otherwise return decode result */
static int svm_instr_opcode(struct kvm_vcpu *vcpu)
{
struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
if (ctxt->b != 0x1 || ctxt->opcode_len != 2)
return NONE_SVM_INSTR;
switch (ctxt->modrm) {
case 0xd8: /* VMRUN */
return SVM_INSTR_VMRUN;
case 0xda: /* VMLOAD */
return SVM_INSTR_VMLOAD;
case 0xdb: /* VMSAVE */
return SVM_INSTR_VMSAVE;
default:
break;
}
return NONE_SVM_INSTR;
}
static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode)
{
const int guest_mode_exit_codes[] = {
[SVM_INSTR_VMRUN] = SVM_EXIT_VMRUN,
[SVM_INSTR_VMLOAD] = SVM_EXIT_VMLOAD,
[SVM_INSTR_VMSAVE] = SVM_EXIT_VMSAVE,
};
int (*const svm_instr_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_INSTR_VMRUN] = vmrun_interception,
[SVM_INSTR_VMLOAD] = vmload_interception,
[SVM_INSTR_VMSAVE] = vmsave_interception,
};
struct vcpu_svm *svm = to_svm(vcpu);
int ret;
if (is_guest_mode(vcpu)) {
/* Returns '1' or -errno on failure, '0' on success. */
ret = nested_svm_simple_vmexit(svm, guest_mode_exit_codes[opcode]);
if (ret)
return ret;
return 1;
}
return svm_instr_handlers[opcode](vcpu);
}
/*
* #GP handling code. Note that #GP can be triggered under the following two
* cases:
* 1) SVM VM-related instructions (VMRUN/VMSAVE/VMLOAD) that trigger #GP on
* some AMD CPUs when EAX of these instructions are in the reserved memory
* regions (e.g. SMM memory on host).
* 2) VMware backdoor
*/
static int gp_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 error_code = svm->vmcb->control.exit_info_1;
int opcode;
/* Both #GP cases have zero error_code */
if (error_code)
goto reinject;
/* Decode the instruction for usage later */
if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
goto reinject;
opcode = svm_instr_opcode(vcpu);
if (opcode == NONE_SVM_INSTR) {
if (!enable_vmware_backdoor)
goto reinject;
/*
* VMware backdoor emulation on #GP interception only handles
* IN{S}, OUT{S}, and RDPMC.
*/
if (!is_guest_mode(vcpu))
return kvm_emulate_instruction(vcpu,
EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE);
} else {
/* All SVM instructions expect page aligned RAX */
if (svm->vmcb->save.rax & ~PAGE_MASK)
goto reinject;
return emulate_svm_instr(vcpu, opcode);
}
reinject:
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
return 1;
}
void svm_set_gif(struct vcpu_svm *svm, bool value)
{
if (value) {
/*
* If VGIF is enabled, the STGI intercept is only added to
* detect the opening of the SMI/NMI window; remove it now.
* Likewise, clear the VINTR intercept, we will set it
* again while processing KVM_REQ_EVENT if needed.
*/
if (vgif)
svm_clr_intercept(svm, INTERCEPT_STGI);
if (svm_is_intercept(svm, INTERCEPT_VINTR))
svm_clear_vintr(svm);
enable_gif(svm);
if (svm->vcpu.arch.smi_pending ||
svm->vcpu.arch.nmi_pending ||
kvm_cpu_has_injectable_intr(&svm->vcpu))
kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
} else {
disable_gif(svm);
/*
* After a CLGI no interrupts should come. But if vGIF is
* in use, we still rely on the VINTR intercept (rather than
* STGI) to detect an open interrupt window.
*/
if (!vgif)
svm_clear_vintr(svm);
}
}
static int stgi_interception(struct kvm_vcpu *vcpu)
{
int ret;
if (nested_svm_check_permissions(vcpu))
return 1;
ret = kvm_skip_emulated_instruction(vcpu);
svm_set_gif(to_svm(vcpu), true);
return ret;
}
static int clgi_interception(struct kvm_vcpu *vcpu)
{
int ret;
if (nested_svm_check_permissions(vcpu))
return 1;
ret = kvm_skip_emulated_instruction(vcpu);
svm_set_gif(to_svm(vcpu), false);
return ret;
}
static int invlpga_interception(struct kvm_vcpu *vcpu)
{
gva_t gva = kvm_rax_read(vcpu);
u32 asid = kvm_rcx_read(vcpu);
/* FIXME: Handle an address size prefix. */
if (!is_long_mode(vcpu))
gva = (u32)gva;
trace_kvm_invlpga(to_svm(vcpu)->vmcb->save.rip, asid, gva);
/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
kvm_mmu_invlpg(vcpu, gva);
return kvm_skip_emulated_instruction(vcpu);
}
static int skinit_interception(struct kvm_vcpu *vcpu)
{
trace_kvm_skinit(to_svm(vcpu)->vmcb->save.rip, kvm_rax_read(vcpu));
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
static int task_switch_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u16 tss_selector;
int reason;
int int_type = svm->vmcb->control.exit_int_info &
SVM_EXITINTINFO_TYPE_MASK;
int int_vec = svm->vmcb->control.exit_int_info & SVM_EVTINJ_VEC_MASK;
uint32_t type =
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
uint32_t idt_v =
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
bool has_error_code = false;
u32 error_code = 0;
tss_selector = (u16)svm->vmcb->control.exit_info_1;
if (svm->vmcb->control.exit_info_2 &
(1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET))
reason = TASK_SWITCH_IRET;
else if (svm->vmcb->control.exit_info_2 &
(1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
reason = TASK_SWITCH_JMP;
else if (idt_v)
reason = TASK_SWITCH_GATE;
else
reason = TASK_SWITCH_CALL;
if (reason == TASK_SWITCH_GATE) {
switch (type) {
case SVM_EXITINTINFO_TYPE_NMI:
vcpu->arch.nmi_injected = false;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
if (svm->vmcb->control.exit_info_2 &
(1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
has_error_code = true;
error_code =
(u32)svm->vmcb->control.exit_info_2;
}
kvm_clear_exception_queue(vcpu);
break;
case SVM_EXITINTINFO_TYPE_INTR:
kvm_clear_interrupt_queue(vcpu);
break;
default:
break;
}
}
if (reason != TASK_SWITCH_GATE ||
int_type == SVM_EXITINTINFO_TYPE_SOFT ||
(int_type == SVM_EXITINTINFO_TYPE_EXEPT &&
(int_vec == OF_VECTOR || int_vec == BP_VECTOR))) {
if (!svm_skip_emulated_instruction(vcpu))
return 0;
}
if (int_type != SVM_EXITINTINFO_TYPE_SOFT)
int_vec = -1;
return kvm_task_switch(vcpu, tss_selector, int_vec, reason,
has_error_code, error_code);
}
static int iret_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
++vcpu->stat.nmi_window_exits;
vcpu->arch.hflags |= HF_IRET_MASK;
if (!sev_es_guest(vcpu->kvm)) {
svm_clr_intercept(svm, INTERCEPT_IRET);
svm->nmi_iret_rip = kvm_rip_read(vcpu);
}
kvm_make_request(KVM_REQ_EVENT, vcpu);
return 1;
}
static int invlpg_interception(struct kvm_vcpu *vcpu)
{
if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
return kvm_emulate_instruction(vcpu, 0);
kvm_mmu_invlpg(vcpu, to_svm(vcpu)->vmcb->control.exit_info_1);
return kvm_skip_emulated_instruction(vcpu);
}
static int emulate_on_interception(struct kvm_vcpu *vcpu)
{
return kvm_emulate_instruction(vcpu, 0);
}
static int rsm_interception(struct kvm_vcpu *vcpu)
{
return kvm_emulate_instruction_from_buffer(vcpu, rsm_ins_bytes, 2);
}
static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu,
unsigned long val)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long cr0 = vcpu->arch.cr0;
bool ret = false;
if (!is_guest_mode(vcpu) ||
(!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))))
return false;
cr0 &= ~SVM_CR0_SELECTIVE_MASK;
val &= ~SVM_CR0_SELECTIVE_MASK;
if (cr0 ^ val) {
svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE);
}
return ret;
}
#define CR_VALID (1ULL << 63)
static int cr_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
int reg, cr;
unsigned long val;
int err;
if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
return emulate_on_interception(vcpu);
if (unlikely((svm->vmcb->control.exit_info_1 & CR_VALID) == 0))
return emulate_on_interception(vcpu);
reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE)
cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0;
else
cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
err = 0;
if (cr >= 16) { /* mov to cr */
cr -= 16;
val = kvm_register_read(vcpu, reg);
trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
if (!check_selective_cr0_intercepted(vcpu, val))
err = kvm_set_cr0(vcpu, val);
else
return 1;
break;
case 3:
err = kvm_set_cr3(vcpu, val);
break;
case 4:
err = kvm_set_cr4(vcpu, val);
break;
case 8:
err = kvm_set_cr8(vcpu, val);
break;
default:
WARN(1, "unhandled write to CR%d", cr);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
} else { /* mov from cr */
switch (cr) {
case 0:
val = kvm_read_cr0(vcpu);
break;
case 2:
val = vcpu->arch.cr2;
break;
case 3:
val = kvm_read_cr3(vcpu);
break;
case 4:
val = kvm_read_cr4(vcpu);
break;
case 8:
val = kvm_get_cr8(vcpu);
break;
default:
WARN(1, "unhandled read from CR%d", cr);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
kvm_register_write(vcpu, reg, val);
trace_kvm_cr_read(cr, val);
}
return kvm_complete_insn_gp(vcpu, err);
}
static int cr_trap(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long old_value, new_value;
unsigned int cr;
int ret = 0;
new_value = (unsigned long)svm->vmcb->control.exit_info_1;
cr = svm->vmcb->control.exit_code - SVM_EXIT_CR0_WRITE_TRAP;
switch (cr) {
case 0:
old_value = kvm_read_cr0(vcpu);
svm_set_cr0(vcpu, new_value);
kvm_post_set_cr0(vcpu, old_value, new_value);
break;
case 4:
old_value = kvm_read_cr4(vcpu);
svm_set_cr4(vcpu, new_value);
kvm_post_set_cr4(vcpu, old_value, new_value);
break;
case 8:
ret = kvm_set_cr8(vcpu, new_value);
break;
default:
WARN(1, "unhandled CR%d write trap", cr);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
return kvm_complete_insn_gp(vcpu, ret);
}
static int dr_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
int reg, dr;
unsigned long val;
int err = 0;
if (vcpu->guest_debug == 0) {
/*
* 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.
*/
clr_dr_intercepts(svm);
vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
return 1;
}
if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS))
return emulate_on_interception(vcpu);
reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0;
if (dr >= 16) { /* mov to DRn */
dr -= 16;
val = kvm_register_read(vcpu, reg);
err = kvm_set_dr(vcpu, dr, val);
} else {
kvm_get_dr(vcpu, dr, &val);
kvm_register_write(vcpu, reg, val);
}
return kvm_complete_insn_gp(vcpu, err);
}
static int cr8_write_interception(struct kvm_vcpu *vcpu)
{
int r;
u8 cr8_prev = kvm_get_cr8(vcpu);
/* instruction emulation calls kvm_set_cr8() */
r = cr_interception(vcpu);
if (lapic_in_kernel(vcpu))
return r;
if (cr8_prev <= kvm_get_cr8(vcpu))
return r;
vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
return 0;
}
static int efer_trap(struct kvm_vcpu *vcpu)
{
struct msr_data msr_info;
int ret;
/*
* Clear the EFER_SVME bit from EFER. The SVM code always sets this
* bit in svm_set_efer(), but __kvm_valid_efer() checks it against
* whether the guest has X86_FEATURE_SVM - this avoids a failure if
* the guest doesn't have X86_FEATURE_SVM.
*/
msr_info.host_initiated = false;
msr_info.index = MSR_EFER;
msr_info.data = to_svm(vcpu)->vmcb->control.exit_info_1 & ~EFER_SVME;
ret = kvm_set_msr_common(vcpu, &msr_info);
return kvm_complete_insn_gp(vcpu, ret);
}
static int svm_get_msr_feature(struct kvm_msr_entry *msr)
{
msr->data = 0;
switch (msr->index) {
case MSR_F10H_DECFG:
if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
break;
case MSR_IA32_PERF_CAPABILITIES:
return 0;
default:
return KVM_MSR_RET_INVALID;
}
return 0;
}
static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_svm *svm = to_svm(vcpu);
switch (msr_info->index) {
case MSR_AMD64_TSC_RATIO:
if (!msr_info->host_initiated && !svm->tsc_scaling_enabled)
return 1;
msr_info->data = svm->tsc_ratio_msr;
break;
case MSR_STAR:
msr_info->data = svm->vmcb01.ptr->save.star;
break;
#ifdef CONFIG_X86_64
case MSR_LSTAR:
msr_info->data = svm->vmcb01.ptr->save.lstar;
break;
case MSR_CSTAR:
msr_info->data = svm->vmcb01.ptr->save.cstar;
break;
case MSR_KERNEL_GS_BASE:
msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base;
break;
case MSR_SYSCALL_MASK:
msr_info->data = svm->vmcb01.ptr->save.sfmask;
break;
#endif
case MSR_IA32_SYSENTER_CS:
msr_info->data = svm->vmcb01.ptr->save.sysenter_cs;
break;
case MSR_IA32_SYSENTER_EIP:
msr_info->data = (u32)svm->vmcb01.ptr->save.sysenter_eip;
if (guest_cpuid_is_intel(vcpu))
msr_info->data |= (u64)svm->sysenter_eip_hi << 32;
break;
case MSR_IA32_SYSENTER_ESP:
msr_info->data = svm->vmcb01.ptr->save.sysenter_esp;
if (guest_cpuid_is_intel(vcpu))
msr_info->data |= (u64)svm->sysenter_esp_hi << 32;
break;
case MSR_TSC_AUX:
msr_info->data = svm->tsc_aux;
break;
case MSR_IA32_DEBUGCTLMSR:
case MSR_IA32_LASTBRANCHFROMIP:
case MSR_IA32_LASTBRANCHTOIP:
case MSR_IA32_LASTINTFROMIP:
case MSR_IA32_LASTINTTOIP:
msr_info->data = svm_get_lbr_msr(svm, msr_info->index);
break;
case MSR_VM_HSAVE_PA:
msr_info->data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
msr_info->data = svm->nested.vm_cr_msr;
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
!guest_has_spec_ctrl_msr(vcpu))
return 1;
if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL))
msr_info->data = svm->vmcb->save.spec_ctrl;
else
msr_info->data = svm->spec_ctrl;
break;
case MSR_AMD64_VIRT_SPEC_CTRL:
if (!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
return 1;
msr_info->data = svm->virt_spec_ctrl;
break;
case MSR_F15H_IC_CFG: {
int family, model;
family = guest_cpuid_family(vcpu);
model = guest_cpuid_model(vcpu);
if (family < 0 || model < 0)
return kvm_get_msr_common(vcpu, msr_info);
msr_info->data = 0;
if (family == 0x15 &&
(model >= 0x2 && model < 0x20))
msr_info->data = 0x1E;
}
break;
case MSR_F10H_DECFG:
msr_info->data = svm->msr_decfg;
break;
default:
return kvm_get_msr_common(vcpu, msr_info);
}
return 0;
}
static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb))
return kvm_complete_insn_gp(vcpu, err);
ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1);
ghcb_set_sw_exit_info_2(svm->sev_es.ghcb,
X86_TRAP_GP |
SVM_EVTINJ_TYPE_EXEPT |
SVM_EVTINJ_VALID);
return 1;
}
static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
{
struct vcpu_svm *svm = to_svm(vcpu);
int svm_dis, chg_mask;
if (data & ~SVM_VM_CR_VALID_MASK)
return 1;
chg_mask = SVM_VM_CR_VALID_MASK;
if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
svm->nested.vm_cr_msr &= ~chg_mask;
svm->nested.vm_cr_msr |= (data & chg_mask);
svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
/* check for svm_disable while efer.svme is set */
if (svm_dis && (vcpu->arch.efer & EFER_SVME))
return 1;
return 0;
}
static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct vcpu_svm *svm = to_svm(vcpu);
int r;
u32 ecx = msr->index;
u64 data = msr->data;
switch (ecx) {
case MSR_AMD64_TSC_RATIO:
if (!svm->tsc_scaling_enabled) {
if (!msr->host_initiated)
return 1;
/*
* In case TSC scaling is not enabled, always
* leave this MSR at the default value.
*
* Due to bug in qemu 6.2.0, it would try to set
* this msr to 0 if tsc scaling is not enabled.
* Ignore this value as well.
*/
if (data != 0 && data != svm->tsc_ratio_msr)
return 1;
break;
}
if (data & SVM_TSC_RATIO_RSVD)
return 1;
svm->tsc_ratio_msr = data;
if (svm->tsc_scaling_enabled && is_guest_mode(vcpu))
nested_svm_update_tsc_ratio_msr(vcpu);
break;
case MSR_IA32_CR_PAT:
if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
return 1;
vcpu->arch.pat = data;
svm->vmcb01.ptr->save.g_pat = data;
if (is_guest_mode(vcpu))
nested_vmcb02_compute_g_pat(svm);
vmcb_mark_dirty(svm->vmcb, VMCB_NPT);
break;
case MSR_IA32_SPEC_CTRL:
if (!msr->host_initiated &&
!guest_has_spec_ctrl_msr(vcpu))
return 1;
if (kvm_spec_ctrl_test_value(data))
return 1;
if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL))
svm->vmcb->save.spec_ctrl = data;
else
svm->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_svm_vmrun_msrpm.
* We update the L1 MSR bit as well since it will end up
* touching the MSR anyway now.
*/
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
break;
case MSR_IA32_PRED_CMD:
if (!msr->host_initiated &&
!guest_has_pred_cmd_msr(vcpu))
return 1;
if (data & ~PRED_CMD_IBPB)
return 1;
if (!boot_cpu_has(X86_FEATURE_IBPB))
return 1;
if (!data)
break;
wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
break;
case MSR_AMD64_VIRT_SPEC_CTRL:
if (!msr->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
return 1;
if (data & ~SPEC_CTRL_SSBD)
return 1;
svm->virt_spec_ctrl = data;
break;
case MSR_STAR:
svm->vmcb01.ptr->save.star = data;
break;
#ifdef CONFIG_X86_64
case MSR_LSTAR:
svm->vmcb01.ptr->save.lstar = data;
break;
case MSR_CSTAR:
svm->vmcb01.ptr->save.cstar = data;
break;
case MSR_KERNEL_GS_BASE:
svm->vmcb01.ptr->save.kernel_gs_base = data;
break;
case MSR_SYSCALL_MASK:
svm->vmcb01.ptr->save.sfmask = data;
break;
#endif
case MSR_IA32_SYSENTER_CS:
svm->vmcb01.ptr->save.sysenter_cs = data;
break;
case MSR_IA32_SYSENTER_EIP:
svm->vmcb01.ptr->save.sysenter_eip = (u32)data;
/*
* We only intercept the MSR_IA32_SYSENTER_{EIP|ESP} msrs
* when we spoof an Intel vendor ID (for cross vendor migration).
* In this case we use this intercept to track the high
* 32 bit part of these msrs to support Intel's
* implementation of SYSENTER/SYSEXIT.
*/
svm->sysenter_eip_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0;
break;
case MSR_IA32_SYSENTER_ESP:
svm->vmcb01.ptr->save.sysenter_esp = (u32)data;
svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0;
break;
case MSR_TSC_AUX:
/*
* TSC_AUX is usually changed only during boot and never read
* directly. Intercept TSC_AUX instead of exposing it to the
* guest via direct_access_msrs, and switch it via user return.
*/
preempt_disable();
r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull);
preempt_enable();
if (r)
return 1;
svm->tsc_aux = data;
break;
case MSR_IA32_DEBUGCTLMSR:
if (!lbrv) {
vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n",
__func__, data);
break;
}
if (data & DEBUGCTL_RESERVED_BITS)
return 1;
if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK)
svm->vmcb->save.dbgctl = data;
else
svm->vmcb01.ptr->save.dbgctl = data;
svm_update_lbrv(vcpu);
break;
case MSR_VM_HSAVE_PA:
/*
* Old kernels did not validate the value written to
* MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid
* value to allow live migrating buggy or malicious guests
* originating from those kernels.
*/
if (!msr->host_initiated && !page_address_valid(vcpu, data))
return 1;
svm->nested.hsave_msr = data & PAGE_MASK;
break;
case MSR_VM_CR:
return svm_set_vm_cr(vcpu, data);
case MSR_VM_IGNNE:
vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
case MSR_F10H_DECFG: {
struct kvm_msr_entry msr_entry;
msr_entry.index = msr->index;
if (svm_get_msr_feature(&msr_entry))
return 1;
/* Check the supported bits */
if (data & ~msr_entry.data)
return 1;
/* Don't allow the guest to change a bit, #GP */
if (!msr->host_initiated && (data ^ msr_entry.data))
return 1;
svm->msr_decfg = data;
break;
}
default:
return kvm_set_msr_common(vcpu, msr);
}
return 0;
}
static int msr_interception(struct kvm_vcpu *vcpu)
{
if (to_svm(vcpu)->vmcb->control.exit_info_1)
return kvm_emulate_wrmsr(vcpu);
else
return kvm_emulate_rdmsr(vcpu);
}
static int interrupt_window_interception(struct kvm_vcpu *vcpu)
{
kvm_make_request(KVM_REQ_EVENT, vcpu);
svm_clear_vintr(to_svm(vcpu));
/*
* If not running nested, for AVIC, the only reason to end up here is ExtINTs.
* In this case AVIC was temporarily disabled for
* requesting the IRQ window and we have to re-enable it.
*
* If running nested, still remove the VM wide AVIC inhibit to
* support case in which the interrupt window was requested when the
* vCPU was not running nested.
* All vCPUs which run still run nested, will remain to have their
* AVIC still inhibited due to per-cpu AVIC inhibition.
*/
kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
++vcpu->stat.irq_window_exits;
return 1;
}
static int pause_interception(struct kvm_vcpu *vcpu)
{
bool in_kernel;
/*
* CPL is not made available for an SEV-ES guest, therefore
* vcpu->arch.preempted_in_kernel can never be true. Just
* set in_kernel to false as well.
*/
in_kernel = !sev_es_guest(vcpu->kvm) && svm_get_cpl(vcpu) == 0;
grow_ple_window(vcpu);
kvm_vcpu_on_spin(vcpu, in_kernel);
return kvm_skip_emulated_instruction(vcpu);
}
static int invpcid_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long type;
gva_t gva;
if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
/*
* For an INVPCID intercept:
* EXITINFO1 provides the linear address of the memory operand.
* EXITINFO2 provides the contents of the register operand.
*/
type = svm->vmcb->control.exit_info_2;
gva = svm->vmcb->control.exit_info_1;
return kvm_handle_invpcid(vcpu, type, gva);
}
static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_READ_CR0] = cr_interception,
[SVM_EXIT_READ_CR3] = cr_interception,
[SVM_EXIT_READ_CR4] = cr_interception,
[SVM_EXIT_READ_CR8] = cr_interception,
[SVM_EXIT_CR0_SEL_WRITE] = cr_interception,
[SVM_EXIT_WRITE_CR0] = cr_interception,
[SVM_EXIT_WRITE_CR3] = cr_interception,
[SVM_EXIT_WRITE_CR4] = cr_interception,
[SVM_EXIT_WRITE_CR8] = cr8_write_interception,
[SVM_EXIT_READ_DR0] = dr_interception,
[SVM_EXIT_READ_DR1] = dr_interception,
[SVM_EXIT_READ_DR2] = dr_interception,
[SVM_EXIT_READ_DR3] = dr_interception,
[SVM_EXIT_READ_DR4] = dr_interception,
[SVM_EXIT_READ_DR5] = dr_interception,
[SVM_EXIT_READ_DR6] = dr_interception,
[SVM_EXIT_READ_DR7] = dr_interception,
[SVM_EXIT_WRITE_DR0] = dr_interception,
[SVM_EXIT_WRITE_DR1] = dr_interception,
[SVM_EXIT_WRITE_DR2] = dr_interception,
[SVM_EXIT_WRITE_DR3] = dr_interception,
[SVM_EXIT_WRITE_DR4] = dr_interception,
[SVM_EXIT_WRITE_DR5] = dr_interception,
[SVM_EXIT_WRITE_DR6] = dr_interception,
[SVM_EXIT_WRITE_DR7] = dr_interception,
[SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
[SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
[SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
[SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception,
[SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception,
[SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
[SVM_EXIT_SMI] = smi_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
[SVM_EXIT_RDPMC] = kvm_emulate_rdpmc,
[SVM_EXIT_CPUID] = kvm_emulate_cpuid,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = kvm_emulate_invd,
[SVM_EXIT_PAUSE] = pause_interception,
[SVM_EXIT_HLT] = kvm_emulate_halt,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
[SVM_EXIT_IOIO] = io_interception,
[SVM_EXIT_MSR] = msr_interception,
[SVM_EXIT_TASK_SWITCH] = task_switch_interception,
[SVM_EXIT_SHUTDOWN] = shutdown_interception,
[SVM_EXIT_VMRUN] = vmrun_interception,
[SVM_EXIT_VMMCALL] = kvm_emulate_hypercall,
[SVM_EXIT_VMLOAD] = vmload_interception,
[SVM_EXIT_VMSAVE] = vmsave_interception,
[SVM_EXIT_STGI] = stgi_interception,
[SVM_EXIT_CLGI] = clgi_interception,
[SVM_EXIT_SKINIT] = skinit_interception,
[SVM_EXIT_RDTSCP] = kvm_handle_invalid_op,
[SVM_EXIT_WBINVD] = kvm_emulate_wbinvd,
[SVM_EXIT_MONITOR] = kvm_emulate_monitor,
[SVM_EXIT_MWAIT] = kvm_emulate_mwait,
[SVM_EXIT_XSETBV] = kvm_emulate_xsetbv,
[SVM_EXIT_RDPRU] = kvm_handle_invalid_op,
[SVM_EXIT_EFER_WRITE_TRAP] = efer_trap,
[SVM_EXIT_CR0_WRITE_TRAP] = cr_trap,
[SVM_EXIT_CR4_WRITE_TRAP] = cr_trap,
[SVM_EXIT_CR8_WRITE_TRAP] = cr_trap,
[SVM_EXIT_INVPCID] = invpcid_interception,
[SVM_EXIT_NPF] = npf_interception,
[SVM_EXIT_RSM] = rsm_interception,
[SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception,
[SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception,
[SVM_EXIT_VMGEXIT] = sev_handle_vmgexit,
};
static void dump_vmcb(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save;
if (!dump_invalid_vmcb) {
pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
return;
}
pr_err("VMCB %p, last attempted VMRUN on CPU %d\n",
svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
pr_err("VMCB Control Area:\n");
pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
pr_err("%-20s%04x\n", "dr_read:", control->intercepts[INTERCEPT_DR] & 0xffff);
pr_err("%-20s%04x\n", "dr_write:", control->intercepts[INTERCEPT_DR] >> 16);
pr_err("%-20s%08x\n", "exceptions:", control->intercepts[INTERCEPT_EXCEPTION]);
pr_err("%-20s%08x %08x\n", "intercepts:",
control->intercepts[INTERCEPT_WORD3],
control->intercepts[INTERCEPT_WORD4]);
pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count);
pr_err("%-20s%d\n", "pause filter threshold:",
control->pause_filter_thresh);
pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa);
pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa);
pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset);
pr_err("%-20s%d\n", "asid:", control->asid);
pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl);
pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl);
pr_err("%-20s%08x\n", "int_vector:", control->int_vector);
pr_err("%-20s%08x\n", "int_state:", control->int_state);
pr_err("%-20s%08x\n", "exit_code:", control->exit_code);
pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1);
pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2);
pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info);
pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err);
pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl);
pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3);
pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar);
pr_err("%-20s%016llx\n", "ghcb:", control->ghcb_gpa);
pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext);
pr_err("%-20s%016llx\n", "next_rip:", control->next_rip);
pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page);
pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa);
pr_err("VMCB State Save Area:\n");
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"es:",
save->es.selector, save->es.attrib,
save->es.limit, save->es.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"cs:",
save->cs.selector, save->cs.attrib,
save->cs.limit, save->cs.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"ss:",
save->ss.selector, save->ss.attrib,
save->ss.limit, save->ss.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"ds:",
save->ds.selector, save->ds.attrib,
save->ds.limit, save->ds.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"fs:",
save01->fs.selector, save01->fs.attrib,
save01->fs.limit, save01->fs.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"gs:",
save01->gs.selector, save01->gs.attrib,
save01->gs.limit, save01->gs.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"gdtr:",
save->gdtr.selector, save->gdtr.attrib,
save->gdtr.limit, save->gdtr.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"ldtr:",
save01->ldtr.selector, save01->ldtr.attrib,
save01->ldtr.limit, save01->ldtr.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"idtr:",
save->idtr.selector, save->idtr.attrib,
save->idtr.limit, save->idtr.base);
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"tr:",
save01->tr.selector, save01->tr.attrib,
save01->tr.limit, save01->tr.base);
pr_err("cpl: %d efer: %016llx\n",
save->cpl, save->efer);
pr_err("%-15s %016llx %-13s %016llx\n",
"cr0:", save->cr0, "cr2:", save->cr2);
pr_err("%-15s %016llx %-13s %016llx\n",
"cr3:", save->cr3, "cr4:", save->cr4);
pr_err("%-15s %016llx %-13s %016llx\n",
"dr6:", save->dr6, "dr7:", save->dr7);
pr_err("%-15s %016llx %-13s %016llx\n",
"rip:", save->rip, "rflags:", save->rflags);
pr_err("%-15s %016llx %-13s %016llx\n",
"rsp:", save->rsp, "rax:", save->rax);
pr_err("%-15s %016llx %-13s %016llx\n",
"star:", save01->star, "lstar:", save01->lstar);
pr_err("%-15s %016llx %-13s %016llx\n",
"cstar:", save01->cstar, "sfmask:", save01->sfmask);
pr_err("%-15s %016llx %-13s %016llx\n",
"kernel_gs_base:", save01->kernel_gs_base,
"sysenter_cs:", save01->sysenter_cs);
pr_err("%-15s %016llx %-13s %016llx\n",
"sysenter_esp:", save01->sysenter_esp,
"sysenter_eip:", save01->sysenter_eip);
pr_err("%-15s %016llx %-13s %016llx\n",
"gpat:", save->g_pat, "dbgctl:", save->dbgctl);
pr_err("%-15s %016llx %-13s %016llx\n",
"br_from:", save->br_from, "br_to:", save->br_to);
pr_err("%-15s %016llx %-13s %016llx\n",
"excp_from:", save->last_excp_from,
"excp_to:", save->last_excp_to);
}
static bool svm_check_exit_valid(u64 exit_code)
{
return (exit_code < ARRAY_SIZE(svm_exit_handlers) &&
svm_exit_handlers[exit_code]);
}
static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code)
{
vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code);
dump_vmcb(vcpu);
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
vcpu->run->internal.ndata = 2;
vcpu->run->internal.data[0] = exit_code;
vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
return 0;
}
int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
{
if (!svm_check_exit_valid(exit_code))
return svm_handle_invalid_exit(vcpu, exit_code);
#ifdef CONFIG_RETPOLINE
if (exit_code == SVM_EXIT_MSR)
return msr_interception(vcpu);
else if (exit_code == SVM_EXIT_VINTR)
return interrupt_window_interception(vcpu);
else if (exit_code == SVM_EXIT_INTR)
return intr_interception(vcpu);
else if (exit_code == SVM_EXIT_HLT)
return kvm_emulate_halt(vcpu);
else if (exit_code == SVM_EXIT_NPF)
return npf_interception(vcpu);
#endif
return svm_exit_handlers[exit_code](vcpu);
}
static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
u64 *info1, u64 *info2,
u32 *intr_info, u32 *error_code)
{
struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;
*reason = control->exit_code;
*info1 = control->exit_info_1;
*info2 = control->exit_info_2;
*intr_info = control->exit_int_info;
if ((*intr_info & SVM_EXITINTINFO_VALID) &&
(*intr_info & SVM_EXITINTINFO_VALID_ERR))
*error_code = control->exit_int_info_err;
else
*error_code = 0;
}
static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
trace_kvm_exit(vcpu, KVM_ISA_SVM);
/* SEV-ES guests must use the CR write traps to track CR registers. */
if (!sev_es_guest(vcpu->kvm)) {
if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE))
vcpu->arch.cr0 = svm->vmcb->save.cr0;
if (npt_enabled)
vcpu->arch.cr3 = svm->vmcb->save.cr3;
}
if (is_guest_mode(vcpu)) {
int vmexit;
trace_kvm_nested_vmexit(vcpu, KVM_ISA_SVM);
vmexit = nested_svm_exit_special(svm);
if (vmexit == NESTED_EXIT_CONTINUE)
vmexit = nested_svm_exit_handled(svm);
if (vmexit == NESTED_EXIT_DONE)
return 1;
}
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
= svm->vmcb->control.exit_code;
kvm_run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu;
dump_vmcb(vcpu);
return 0;
}
if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH &&
exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI)
printk(KERN_ERR "%s: unexpected exit_int_info 0x%x "
"exit_code 0x%x\n",
__func__, svm->vmcb->control.exit_int_info,
exit_code);
if (exit_fastpath != EXIT_FASTPATH_NONE)
return 1;
return svm_invoke_exit_handler(vcpu, exit_code);
}
static void reload_tss(struct kvm_vcpu *vcpu)
{
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
sd->tss_desc->type = 9; /* available 32/64-bit TSS */
load_TR_desc();
}
static void pre_svm_run(struct kvm_vcpu *vcpu)
{
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
struct vcpu_svm *svm = to_svm(vcpu);
/*
* If the previous vmrun of the vmcb occurred on a different physical
* cpu, then mark the vmcb dirty and assign a new asid. Hardware's
* vmcb clean bits are per logical CPU, as are KVM's asid assignments.
*/
if (unlikely(svm->current_vmcb->cpu != vcpu->cpu)) {
svm->current_vmcb->asid_generation = 0;
vmcb_mark_all_dirty(svm->vmcb);
svm->current_vmcb->cpu = vcpu->cpu;
}
if (sev_guest(vcpu->kvm))
return pre_sev_run(svm, vcpu->cpu);
/* FIXME: handle wraparound of asid_generation */
if (svm->current_vmcb->asid_generation != sd->asid_generation)
new_asid(svm, sd);
}
static void svm_inject_nmi(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
vcpu->arch.hflags |= HF_NMI_MASK;
if (!sev_es_guest(vcpu->kvm))
svm_set_intercept(svm, INTERCEPT_IRET);
++vcpu->stat.nmi_injections;
}
static void svm_inject_irq(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
BUG_ON(!(gif_set(svm)));
trace_kvm_inj_virq(vcpu->arch.interrupt.nr);
++vcpu->stat.irq_injections;
svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
}
void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
int trig_mode, int vector)
{
/*
* vcpu->arch.apicv_active must be read after vcpu->mode.
* Pairs with smp_store_release in vcpu_enter_guest.
*/
bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE);
if (!READ_ONCE(vcpu->arch.apicv_active)) {
/* Process the interrupt via inject_pending_event */
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
return;
}
trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector);
if (in_guest_mode) {
/*
* Signal the doorbell to tell hardware to inject the IRQ. If
* the vCPU exits the guest before the doorbell chimes, hardware
* will automatically process AVIC interrupts at the next VMRUN.
*/
avic_ring_doorbell(vcpu);
} else {
/*
* Wake the vCPU if it was blocking. KVM will then detect the
* pending IRQ when checking if the vCPU has a wake event.
*/
kvm_vcpu_wake_up(vcpu);
}
}
static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
int trig_mode, int vector)
{
kvm_lapic_set_irr(vector, apic);
/*
* Pairs with the smp_mb_*() after setting vcpu->guest_mode in
* vcpu_enter_guest() to ensure the write to the vIRR is ordered before
* the read of guest_mode. This guarantees that either VMRUN will see
* and process the new vIRR entry, or that svm_complete_interrupt_delivery
* will signal the doorbell if the CPU has already entered the guest.
*/
smp_mb__after_atomic();
svm_complete_interrupt_delivery(apic->vcpu, delivery_mode, trig_mode, vector);
}
static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* SEV-ES guests must always keep the CR intercepts cleared. CR
* tracking is done using the CR write traps.
*/
if (sev_es_guest(vcpu->kvm))
return;
if (nested_svm_virtualize_tpr(vcpu))
return;
svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
if (irr == -1)
return;
if (tpr >= irr)
svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
}
bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
bool ret;
if (!gif_set(svm))
return true;
if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm))
return false;
ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
(vcpu->arch.hflags & HF_NMI_MASK);
return ret;
}
static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->nested.nested_run_pending)
return -EBUSY;
if (svm_nmi_blocked(vcpu))
return 0;
/* An NMI must not be injected into L2 if it's supposed to VM-Exit. */
if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm))
return -EBUSY;
return 1;
}
static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
{
return !!(vcpu->arch.hflags & HF_NMI_MASK);
}
static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (masked) {
vcpu->arch.hflags |= HF_NMI_MASK;
if (!sev_es_guest(vcpu->kvm))
svm_set_intercept(svm, INTERCEPT_IRET);
} else {
vcpu->arch.hflags &= ~HF_NMI_MASK;
if (!sev_es_guest(vcpu->kvm))
svm_clr_intercept(svm, INTERCEPT_IRET);
}
}
bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
if (!gif_set(svm))
return true;
if (is_guest_mode(vcpu)) {
/* As long as interrupts are being delivered... */
if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)
: !(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
return true;
/* ... vmexits aren't blocked by the interrupt shadow */
if (nested_exit_on_intr(svm))
return false;
} else {
if (!svm_get_if_flag(vcpu))
return true;
}
return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK);
}
static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->nested.nested_run_pending)
return -EBUSY;
if (svm_interrupt_blocked(vcpu))
return 0;
/*
* An IRQ must not be injected into L2 if it's supposed to VM-Exit,
* e.g. if the IRQ arrived asynchronously after checking nested events.
*/
if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm))
return -EBUSY;
return 1;
}
static void svm_enable_irq_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
* 1, because that's a separate STGI/VMRUN intercept. The next time we
* get that intercept, this function will be called again though and
* we'll get the vintr intercept. However, if the vGIF feature is
* enabled, the STGI interception will not occur. Enable the irq
* window under the assumption that the hardware will set the GIF.
*/
if (vgif || gif_set(svm)) {
/*
* IRQ window is not needed when AVIC is enabled,
* unless we have pending ExtINT since it cannot be injected
* via AVIC. In such case, KVM needs to temporarily disable AVIC,
* and fallback to injecting IRQ via V_IRQ.
*
* If running nested, AVIC is already locally inhibited
* on this vCPU, therefore there is no need to request
* the VM wide AVIC inhibition.
*/
if (!is_guest_mode(vcpu))
kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
svm_set_vintr(svm);
}
}
static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if ((vcpu->arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK)
return; /* IRET will cause a vm exit */
if (!gif_set(svm)) {
if (vgif)
svm_set_intercept(svm, INTERCEPT_STGI);
return; /* STGI will cause a vm exit */
}
/*
* Something prevents NMI from been injected. Single step over possible
* problem (IRET or exception injection or interrupt shadow)
*/
svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu);
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
}
static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* Flush only the current ASID even if the TLB flush was invoked via
* kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all
* ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and
* unconditionally does a TLB flush on both nested VM-Enter and nested
* VM-Exit (via kvm_mmu_reset_context()).
*/
if (static_cpu_has(X86_FEATURE_FLUSHBYASID))
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
else
svm->current_vmcb->asid_generation--;
}
static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
{
struct vcpu_svm *svm = to_svm(vcpu);
invlpga(gva, svm->vmcb->control.asid);
}
static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (nested_svm_virtualize_tpr(vcpu))
return;
if (!svm_is_intercept(svm, INTERCEPT_CR8_WRITE)) {
int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
kvm_set_cr8(vcpu, cr8);
}
}
static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 cr8;
if (nested_svm_virtualize_tpr(vcpu) ||
kvm_vcpu_apicv_active(vcpu))
return;
cr8 = kvm_get_cr8(vcpu);
svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
}
static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u8 vector;
int type;
u32 exitintinfo = svm->vmcb->control.exit_int_info;
unsigned int3_injected = svm->int3_injected;
svm->int3_injected = 0;
/*
* If we've made progress since setting HF_IRET_MASK, we've
* executed an IRET and can allow NMI injection.
*/
if ((vcpu->arch.hflags & HF_IRET_MASK) &&
(sev_es_guest(vcpu->kvm) ||
kvm_rip_read(vcpu) != svm->nmi_iret_rip)) {
vcpu->arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
vcpu->arch.nmi_injected = false;
kvm_clear_exception_queue(vcpu);
kvm_clear_interrupt_queue(vcpu);
if (!(exitintinfo & SVM_EXITINTINFO_VALID))
return;
kvm_make_request(KVM_REQ_EVENT, vcpu);
vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK;
type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK;
switch (type) {
case SVM_EXITINTINFO_TYPE_NMI:
vcpu->arch.nmi_injected = true;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
/*
* Never re-inject a #VC exception.
*/
if (vector == X86_TRAP_VC)
break;
/*
* In case of software exceptions, do not reinject the vector,
* but re-execute the instruction instead. Rewind RIP first
* if we emulated INT3 before.
*/
if (kvm_exception_is_soft(vector)) {
if (vector == BP_VECTOR && int3_injected &&
kvm_is_linear_rip(vcpu, svm->int3_rip))
kvm_rip_write(vcpu,
kvm_rip_read(vcpu) - int3_injected);
break;
}
if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
u32 err = svm->vmcb->control.exit_int_info_err;
kvm_requeue_exception_e(vcpu, vector, err);
} else
kvm_requeue_exception(vcpu, vector);
break;
case SVM_EXITINTINFO_TYPE_INTR:
kvm_queue_interrupt(vcpu, vector, false);
break;
default:
break;
}
}
static void svm_cancel_injection(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_control_area *control = &svm->vmcb->control;
control->exit_int_info = control->event_inj;
control->exit_int_info_err = control->event_inj_err;
control->event_inj = 0;
svm_complete_interrupts(vcpu);
}
static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
{
return 1;
}
static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
{
if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
to_svm(vcpu)->vmcb->control.exit_info_1)
return handle_fastpath_set_msr_irqoff(vcpu);
return EXIT_FASTPATH_NONE;
}
static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long vmcb_pa = svm->current_vmcb->pa;
guest_state_enter_irqoff();
if (sev_es_guest(vcpu->kvm)) {
__svm_sev_es_vcpu_run(vmcb_pa);
} else {
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
/*
* Use a single vmcb (vmcb01 because it's always valid) for
* context switching guest state via VMLOAD/VMSAVE, that way
* the state doesn't need to be copied between vmcb01 and
* vmcb02 when switching vmcbs for nested virtualization.
*/
vmload(svm->vmcb01.pa);
__svm_vcpu_run(vmcb_pa, (unsigned long *)&vcpu->arch.regs);
vmsave(svm->vmcb01.pa);
vmload(__sme_page_pa(sd->save_area));
}
guest_state_exit_irqoff();
}
static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
trace_kvm_entry(vcpu);
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
/*
* Disable singlestep if we're injecting an interrupt/exception.
* We don't want our modified rflags to be pushed on the stack where
* we might not be able to easily reset them if we disabled NMI
* singlestep later.
*/
if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
/*
* Event injection happens before external interrupts cause a
* vmexit and interrupts are disabled here, so smp_send_reschedule
* is enough to force an immediate vmexit.
*/
disable_nmi_singlestep(svm);
smp_send_reschedule(vcpu->cpu);
}
pre_svm_run(vcpu);
sync_lapic_to_cr8(vcpu);
if (unlikely(svm->asid != svm->vmcb->control.asid)) {
svm->vmcb->control.asid = svm->asid;
vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
}
svm->vmcb->save.cr2 = vcpu->arch.cr2;
svm_hv_update_vp_id(svm->vmcb, vcpu);
/*
* Run with all-zero DR6 unless needed, so that we can get the exact cause
* of a #DB.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
svm_set_dr6(svm, vcpu->arch.dr6);
else
svm_set_dr6(svm, DR6_ACTIVE_LOW);
clgi();
kvm_load_guest_xsave_state(vcpu);
kvm_wait_lapic_expire(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.
*/
if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL))
x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
svm_vcpu_enter_exit(vcpu);
/*
* 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 (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL) &&
unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
if (!sev_es_guest(vcpu->kvm))
reload_tss(vcpu);
if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL))
x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
if (!sev_es_guest(vcpu->kvm)) {
vcpu->arch.cr2 = svm->vmcb->save.cr2;
vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
}
vcpu->arch.regs_dirty = 0;
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
kvm_load_host_xsave_state(vcpu);
stgi();
/* Any pending NMI will happen here */
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_after_interrupt(vcpu);
sync_cr8_to_lapic(vcpu);
svm->next_rip = 0;
if (is_guest_mode(vcpu)) {
nested_sync_control_from_vmcb02(svm);
/* Track VMRUNs that have made past consistency checking */
if (svm->nested.nested_run_pending &&
svm->vmcb->control.exit_code != SVM_EXIT_ERR)
++vcpu->stat.nested_run;
svm->nested.nested_run_pending = 0;
}
svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
vmcb_mark_all_clean(svm->vmcb);
/* if exit due to PF check for async PF */
if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
vcpu->arch.apf.host_apf_flags =
kvm_read_and_reset_apf_flags();
vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET;
/*
* We need to handle MC intercepts here before the vcpu has a chance to
* change the physical cpu
*/
if (unlikely(svm->vmcb->control.exit_code ==
SVM_EXIT_EXCP_BASE + MC_VECTOR))
svm_handle_mce(vcpu);
svm_complete_interrupts(vcpu);
if (is_guest_mode(vcpu))
return EXIT_FASTPATH_NONE;
return svm_exit_handlers_fastpath(vcpu);
}
static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
int root_level)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long cr3;
if (npt_enabled) {
svm->vmcb->control.nested_cr3 = __sme_set(root_hpa);
vmcb_mark_dirty(svm->vmcb, VMCB_NPT);
hv_track_root_tdp(vcpu, root_hpa);
cr3 = vcpu->arch.cr3;
} else if (vcpu->arch.mmu->root_role.level >= PT64_ROOT_4LEVEL) {
cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu);
} else {
/* PCID in the guest should be impossible with a 32-bit MMU. */
WARN_ON_ONCE(kvm_get_active_pcid(vcpu));
cr3 = root_hpa;
}
svm->vmcb->save.cr3 = cr3;
vmcb_mark_dirty(svm->vmcb, VMCB_CR);
}
static int is_disabled(void)
{
u64 vm_cr;
rdmsrl(MSR_VM_CR, vm_cr);
if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE))
return 1;
return 0;
}
static void
svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
{
/*
* Patch in the VMMCALL instruction:
*/
hypercall[0] = 0x0f;
hypercall[1] = 0x01;
hypercall[2] = 0xd9;
}
static int __init svm_check_processor_compat(void)
{
return 0;
}
/*
* The kvm parameter can be NULL (module initialization, or invocation before
* VM creation). Be sure to check the kvm parameter before using it.
*/
static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
{
switch (index) {
case MSR_IA32_MCG_EXT_CTL:
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
return false;
case MSR_IA32_SMBASE:
/* SEV-ES guests do not support SMM, so report false */
if (kvm && sev_es_guest(kvm))
return false;
break;
default:
break;
}
return true;
}
static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
return 0;
}
static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_cpuid_entry2 *best;
struct kvm *kvm = vcpu->kvm;
vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
boot_cpu_has(X86_FEATURE_XSAVE) &&
boot_cpu_has(X86_FEATURE_XSAVES);
/* Update nrips enabled cache */
svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
guest_cpuid_has(vcpu, X86_FEATURE_NRIPS);
svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR);
svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) &&
guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER);
svm->pause_threshold_enabled = kvm_cpu_cap_has(X86_FEATURE_PFTHRESHOLD) &&
guest_cpuid_has(vcpu, X86_FEATURE_PFTHRESHOLD);
svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
svm_recalc_instruction_intercepts(vcpu, svm);
/* For sev guests, the memory encryption bit is not reserved in CR3. */
if (sev_guest(vcpu->kvm)) {
best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
if (best)
vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
}
if (kvm_vcpu_apicv_active(vcpu)) {
/*
* AVIC does not work with an x2APIC mode guest. If the X2APIC feature
* is exposed to the guest, disable AVIC.
*/
if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC))
kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC);
}
init_vmcb_after_set_cpuid(vcpu);
}
static bool svm_has_wbinvd_exit(void)
{
return true;
}
#define PRE_EX(exit) { .exit_code = (exit), \
.stage = X86_ICPT_PRE_EXCEPT, }
#define POST_EX(exit) { .exit_code = (exit), \
.stage = X86_ICPT_POST_EXCEPT, }
#define POST_MEM(exit) { .exit_code = (exit), \
.stage = X86_ICPT_POST_MEMACCESS, }
static const struct __x86_intercept {
u32 exit_code;
enum x86_intercept_stage stage;
} x86_intercept_map[] = {
[x86_intercept_cr_read] = POST_EX(SVM_EXIT_READ_CR0),
[x86_intercept_cr_write] = POST_EX(SVM_EXIT_WRITE_CR0),
[x86_intercept_clts] = POST_EX(SVM_EXIT_WRITE_CR0),
[x86_intercept_lmsw] = POST_EX(SVM_EXIT_WRITE_CR0),
[x86_intercept_smsw] = POST_EX(SVM_EXIT_READ_CR0),
[x86_intercept_dr_read] = POST_EX(SVM_EXIT_READ_DR0),
[x86_intercept_dr_write] = POST_EX(SVM_EXIT_WRITE_DR0),
[x86_intercept_sldt] = POST_EX(SVM_EXIT_LDTR_READ),
[x86_intercept_str] = POST_EX(SVM_EXIT_TR_READ),
[x86_intercept_lldt] = POST_EX(SVM_EXIT_LDTR_WRITE),
[x86_intercept_ltr] = POST_EX(SVM_EXIT_TR_WRITE),
[x86_intercept_sgdt] = POST_EX(SVM_EXIT_GDTR_READ),
[x86_intercept_sidt] = POST_EX(SVM_EXIT_IDTR_READ),
[x86_intercept_lgdt] = POST_EX(SVM_EXIT_GDTR_WRITE),
[x86_intercept_lidt] = POST_EX(SVM_EXIT_IDTR_WRITE),
[x86_intercept_vmrun] = POST_EX(SVM_EXIT_VMRUN),
[x86_intercept_vmmcall] = POST_EX(SVM_EXIT_VMMCALL),
[x86_intercept_vmload] = POST_EX(SVM_EXIT_VMLOAD),
[x86_intercept_vmsave] = POST_EX(SVM_EXIT_VMSAVE),
[x86_intercept_stgi] = POST_EX(SVM_EXIT_STGI),
[x86_intercept_clgi] = POST_EX(SVM_EXIT_CLGI),
[x86_intercept_skinit] = POST_EX(SVM_EXIT_SKINIT),
[x86_intercept_invlpga] = POST_EX(SVM_EXIT_INVLPGA),
[x86_intercept_rdtscp] = POST_EX(SVM_EXIT_RDTSCP),
[x86_intercept_monitor] = POST_MEM(SVM_EXIT_MONITOR),
[x86_intercept_mwait] = POST_EX(SVM_EXIT_MWAIT),
[x86_intercept_invlpg] = POST_EX(SVM_EXIT_INVLPG),
[x86_intercept_invd] = POST_EX(SVM_EXIT_INVD),
[x86_intercept_wbinvd] = POST_EX(SVM_EXIT_WBINVD),
[x86_intercept_wrmsr] = POST_EX(SVM_EXIT_MSR),
[x86_intercept_rdtsc] = POST_EX(SVM_EXIT_RDTSC),
[x86_intercept_rdmsr] = POST_EX(SVM_EXIT_MSR),
[x86_intercept_rdpmc] = POST_EX(SVM_EXIT_RDPMC),
[x86_intercept_cpuid] = PRE_EX(SVM_EXIT_CPUID),
[x86_intercept_rsm] = PRE_EX(SVM_EXIT_RSM),
[x86_intercept_pause] = PRE_EX(SVM_EXIT_PAUSE),
[x86_intercept_pushf] = PRE_EX(SVM_EXIT_PUSHF),
[x86_intercept_popf] = PRE_EX(SVM_EXIT_POPF),
[x86_intercept_intn] = PRE_EX(SVM_EXIT_SWINT),
[x86_intercept_iret] = PRE_EX(SVM_EXIT_IRET),
[x86_intercept_icebp] = PRE_EX(SVM_EXIT_ICEBP),
[x86_intercept_hlt] = POST_EX(SVM_EXIT_HLT),
[x86_intercept_in] = POST_EX(SVM_EXIT_IOIO),
[x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO),
[x86_intercept_out] = POST_EX(SVM_EXIT_IOIO),
[x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO),
[x86_intercept_xsetbv] = PRE_EX(SVM_EXIT_XSETBV),
};
#undef PRE_EX
#undef POST_EX
#undef POST_MEM
static int svm_check_intercept(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage,
struct x86_exception *exception)
{
struct vcpu_svm *svm = to_svm(vcpu);
int vmexit, ret = X86EMUL_CONTINUE;
struct __x86_intercept icpt_info;
struct vmcb *vmcb = svm->vmcb;
if (info->intercept >= ARRAY_SIZE(x86_intercept_map))
goto out;
icpt_info = x86_intercept_map[info->intercept];
if (stage != icpt_info.stage)
goto out;
switch (icpt_info.exit_code) {
case SVM_EXIT_READ_CR0:
if (info->intercept == x86_intercept_cr_read)
icpt_info.exit_code += info->modrm_reg;
break;
case SVM_EXIT_WRITE_CR0: {
unsigned long cr0, val;
if (info->intercept == x86_intercept_cr_write)
icpt_info.exit_code += info->modrm_reg;
if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 ||
info->intercept == x86_intercept_clts)
break;
if (!(vmcb12_is_intercept(&svm->nested.ctl,
INTERCEPT_SELECTIVE_CR0)))
break;
cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK;
val = info->src_val & ~SVM_CR0_SELECTIVE_MASK;
if (info->intercept == x86_intercept_lmsw) {
cr0 &= 0xfUL;
val &= 0xfUL;
/* lmsw can't clear PE - catch this here */
if (cr0 & X86_CR0_PE)
val |= X86_CR0_PE;
}
if (cr0 ^ val)
icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE;
break;
}
case SVM_EXIT_READ_DR0:
case SVM_EXIT_WRITE_DR0:
icpt_info.exit_code += info->modrm_reg;
break;
case SVM_EXIT_MSR:
if (info->intercept == x86_intercept_wrmsr)
vmcb->control.exit_info_1 = 1;
else
vmcb->control.exit_info_1 = 0;
break;
case SVM_EXIT_PAUSE:
/*
* We get this for NOP only, but pause
* is rep not, check this here
*/
if (info->rep_prefix != REPE_PREFIX)
goto out;
break;
case SVM_EXIT_IOIO: {
u64 exit_info;
u32 bytes;
if (info->intercept == x86_intercept_in ||
info->intercept == x86_intercept_ins) {
exit_info = ((info->src_val & 0xffff) << 16) |
SVM_IOIO_TYPE_MASK;
bytes = info->dst_bytes;
} else {
exit_info = (info->dst_val & 0xffff) << 16;
bytes = info->src_bytes;
}
if (info->intercept == x86_intercept_outs ||
info->intercept == x86_intercept_ins)
exit_info |= SVM_IOIO_STR_MASK;
if (info->rep_prefix)
exit_info |= SVM_IOIO_REP_MASK;
bytes = min(bytes, 4u);
exit_info |= bytes << SVM_IOIO_SIZE_SHIFT;
exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1);
vmcb->control.exit_info_1 = exit_info;
vmcb->control.exit_info_2 = info->next_rip;
break;
}
default:
break;
}
/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
if (static_cpu_has(X86_FEATURE_NRIPS))
vmcb->control.next_rip = info->next_rip;
vmcb->control.exit_code = icpt_info.exit_code;
vmexit = nested_svm_exit_handled(svm);
ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED
: X86EMUL_CONTINUE;
out:
return ret;
}
static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
{
}
static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
if (!kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
}
static void svm_setup_mce(struct kvm_vcpu *vcpu)
{
/* [63:9] are reserved. */
vcpu->arch.mcg_cap &= 0x1ff;
}
bool svm_smi_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/* Per APM Vol.2 15.22.2 "Response to SMI" */
if (!gif_set(svm))
return true;
return is_smm(vcpu);
}
static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->nested.nested_run_pending)
return -EBUSY;
if (svm_smi_blocked(vcpu))
return 0;
/* An SMI must not be injected into L2 if it's supposed to VM-Exit. */
if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm))
return -EBUSY;
return 1;
}
static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map_save;
int ret;
if (!is_guest_mode(vcpu))
return 0;
/* FED8h - SVM Guest */
put_smstate(u64, smstate, 0x7ed8, 1);
/* FEE0h - SVM Guest VMCB Physical Address */
put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
ret = nested_svm_simple_vmexit(svm, SVM_EXIT_SW);
if (ret)
return ret;
/*
* KVM uses VMCB01 to store L1 host state while L2 runs but
* VMCB01 is going to be used during SMM and thus the state will
* be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
* area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
* format of the area is identical to guest save area offsetted
* by 0x400 (matches the offset of 'struct vmcb_save_area'
* within 'struct vmcb'). Note: HSAVE area may also be used by
* L1 hypervisor to save additional host context (e.g. KVM does
* that, see svm_prepare_switch_to_guest()) which must be
* preserved.
*/
if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
&map_save) == -EINVAL)
return 1;
BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
svm_copy_vmrun_state(map_save.hva + 0x400,
&svm->vmcb01.ptr->save);
kvm_vcpu_unmap(vcpu, &map_save, true);
return 0;
}
static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
u64 saved_efer, vmcb12_gpa;
struct vmcb *vmcb12;
int ret;
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
/* Non-zero if SMI arrived while vCPU was in guest mode. */
if (!GET_SMSTATE(u64, smstate, 0x7ed8))
return 0;
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return 1;
saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
if (!(saved_efer & EFER_SVME))
return 1;
vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
return 1;
ret = 1;
if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
goto unmap_map;
if (svm_allocate_nested(svm))
goto unmap_save;
/*
* Restore L1 host state from L1 HSAVE area as VMCB01 was
* used during SMM (see svm_enter_smm())
*/
svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400);
/*
* Enter the nested guest now
*/
vmcb_mark_all_dirty(svm->vmcb01.ptr);
vmcb12 = map.hva;
nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
if (ret)
goto unmap_save;
svm->nested.nested_run_pending = 1;
unmap_save:
kvm_vcpu_unmap(vcpu, &map_save, true);
unmap_map:
kvm_vcpu_unmap(vcpu, &map, true);
return ret;
}
static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (!gif_set(svm)) {
if (vgif)
svm_set_intercept(svm, INTERCEPT_STGI);
/* STGI will cause a vm exit */
} else {
/* We must be in SMM; RSM will cause a vmexit anyway. */
}
}
static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
void *insn, int insn_len)
{
bool smep, smap, is_user;
unsigned long cr4;
u64 error_code;
/* Emulation is always possible when KVM has access to all guest state. */
if (!sev_guest(vcpu->kvm))
return true;
/* #UD and #GP should never be intercepted for SEV guests. */
WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD |
EMULTYPE_TRAP_UD_FORCED |
EMULTYPE_VMWARE_GP));
/*
* Emulation is impossible for SEV-ES guests as KVM doesn't have access
* to guest register state.
*/
if (sev_es_guest(vcpu->kvm))
return false;
/*
* Emulation is possible if the instruction is already decoded, e.g.
* when completing I/O after returning from userspace.
*/
if (emul_type & EMULTYPE_NO_DECODE)
return true;
/*
* Emulation is possible for SEV guests if and only if a prefilled
* buffer containing the bytes of the intercepted instruction is
* available. SEV guest memory is encrypted with a guest specific key
* and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
* decode garbage.
*
* Inject #UD if KVM reached this point without an instruction buffer.
* In practice, this path should never be hit by a well-behaved guest,
* e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path
* is still theoretically reachable, e.g. via unaccelerated fault-like
* AVIC access, and needs to be handled by KVM to avoid putting the
* guest into an infinite loop. Injecting #UD is somewhat arbitrary,
* but its the least awful option given lack of insight into the guest.
*/
if (unlikely(!insn)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return false;
}
/*
* Emulate for SEV guests if the insn buffer is not empty. The buffer
* will be empty if the DecodeAssist microcode cannot fetch bytes for
* the faulting instruction because the code fetch itself faulted, e.g.
* the guest attempted to fetch from emulated MMIO or a guest page
* table used to translate CS:RIP resides in emulated MMIO.
*/
if (likely(insn_len))
return true;
/*
* Detect and workaround Errata 1096 Fam_17h_00_0Fh.
*
* Errata:
* When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is
* possible that CPU microcode implementing DecodeAssist will fail to
* read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly
* be '0'. This happens because microcode reads CS:RIP using a _data_
* loap uop with CPL=0 privileges. If the load hits a SMAP #PF, ucode
* gives up and does not fill the instruction bytes buffer.
*
* As above, KVM reaches this point iff the VM is an SEV guest, the CPU
* supports DecodeAssist, a #NPF was raised, KVM's page fault handler
* triggered emulation (e.g. for MMIO), and the CPU returned 0 in the
* GuestIntrBytes field of the VMCB.
*
* This does _not_ mean that the erratum has been encountered, as the
* DecodeAssist will also fail if the load for CS:RIP hits a legitimate
* #PF, e.g. if the guest attempt to execute from emulated MMIO and
* encountered a reserved/not-present #PF.
*
* To hit the erratum, the following conditions must be true:
* 1. CR4.SMAP=1 (obviously).
* 2. CR4.SMEP=0 || CPL=3. If SMEP=1 and CPL<3, the erratum cannot
* have been hit as the guest would have encountered a SMEP
* violation #PF, not a #NPF.
* 3. The #NPF is not due to a code fetch, in which case failure to
* retrieve the instruction bytes is legitimate (see abvoe).
*
* In addition, don't apply the erratum workaround if the #NPF occurred
* while translating guest page tables (see below).
*/
error_code = to_svm(vcpu)->vmcb->control.exit_info_1;
if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK))
goto resume_guest;
cr4 = kvm_read_cr4(vcpu);
smep = cr4 & X86_CR4_SMEP;
smap = cr4 & X86_CR4_SMAP;
is_user = svm_get_cpl(vcpu) == 3;
if (smap && (!smep || is_user)) {
pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
/*
* If the fault occurred in userspace, arbitrarily inject #GP
* to avoid killing the guest and to hopefully avoid confusing
* the guest kernel too much, e.g. injecting #PF would not be
* coherent with respect to the guest's page tables. Request
* triple fault if the fault occurred in the kernel as there's
* no fault that KVM can inject without confusing the guest.
* In practice, the triple fault is moot as no sane SEV kernel
* will execute from user memory while also running with SMAP=1.
*/
if (is_user)
kvm_inject_gp(vcpu, 0);
else
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
}
resume_guest:
/*
* If the erratum was not hit, simply resume the guest and let it fault
* again. While awful, e.g. the vCPU may get stuck in an infinite loop
* if the fault is at CPL=0, it's the lesser of all evils. Exiting to
* userspace will kill the guest, and letting the emulator read garbage
* will yield random behavior and potentially corrupt the guest.
*
* Simply resuming the guest is technically not a violation of the SEV
* architecture. AMD's APM states that all code fetches and page table
* accesses for SEV guest are encrypted, regardless of the C-Bit. The
* APM also states that encrypted accesses to MMIO are "ignored", but
* doesn't explicitly define "ignored", i.e. doing nothing and letting
* the guest spin is technically "ignoring" the access.
*/
return false;
}
static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
/*
* TODO: Last condition latch INIT signals on vCPU when
* vCPU is in guest-mode and vmcb12 defines intercept on INIT.
* To properly emulate the INIT intercept,
* svm_check_nested_events() should call nested_svm_vmexit()
* if an INIT signal is pending.
*/
return !gif_set(svm) ||
(vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
}
static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
{
if (!sev_es_guest(vcpu->kvm))
return kvm_vcpu_deliver_sipi_vector(vcpu, vector);
sev_vcpu_deliver_sipi_vector(vcpu, vector);
}
static void svm_vm_destroy(struct kvm *kvm)
{
avic_vm_destroy(kvm);
sev_vm_destroy(kvm);
}
static int svm_vm_init(struct kvm *kvm)
{
if (!pause_filter_count || !pause_filter_thresh)
kvm->arch.pause_in_guest = true;
if (enable_apicv) {
int ret = avic_vm_init(kvm);
if (ret)
return ret;
}
return 0;
}
static struct kvm_x86_ops svm_x86_ops __initdata = {
.name = "kvm_amd",
.hardware_unsetup = svm_hardware_unsetup,
.hardware_enable = svm_hardware_enable,
.hardware_disable = svm_hardware_disable,
.has_emulated_msr = svm_has_emulated_msr,
.vcpu_create = svm_vcpu_create,
.vcpu_free = svm_vcpu_free,
.vcpu_reset = svm_vcpu_reset,
.vm_size = sizeof(struct kvm_svm),
.vm_init = svm_vm_init,
.vm_destroy = svm_vm_destroy,
.prepare_switch_to_guest = svm_prepare_switch_to_guest,
.vcpu_load = svm_vcpu_load,
.vcpu_put = svm_vcpu_put,
.vcpu_blocking = avic_vcpu_blocking,
.vcpu_unblocking = avic_vcpu_unblocking,
.update_exception_bitmap = svm_update_exception_bitmap,
.get_msr_feature = svm_get_msr_feature,
.get_msr = svm_get_msr,
.set_msr = svm_set_msr,
.get_segment_base = svm_get_segment_base,
.get_segment = svm_get_segment,
.set_segment = svm_set_segment,
.get_cpl = svm_get_cpl,
.get_cs_db_l_bits = svm_get_cs_db_l_bits,
.set_cr0 = svm_set_cr0,
.post_set_cr3 = sev_post_set_cr3,
.is_valid_cr4 = svm_is_valid_cr4,
.set_cr4 = svm_set_cr4,
.set_efer = svm_set_efer,
.get_idt = svm_get_idt,
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
.set_dr7 = svm_set_dr7,
.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
.get_if_flag = svm_get_if_flag,
.flush_tlb_all = svm_flush_tlb_current,
.flush_tlb_current = svm_flush_tlb_current,
.flush_tlb_gva = svm_flush_tlb_gva,
.flush_tlb_guest = svm_flush_tlb_current,
.vcpu_pre_run = svm_vcpu_pre_run,
.vcpu_run = svm_vcpu_run,
.handle_exit = svm_handle_exit,
.skip_emulated_instruction = svm_skip_emulated_instruction,
.update_emulated_instruction = NULL,
.set_interrupt_shadow = svm_set_interrupt_shadow,
.get_interrupt_shadow = svm_get_interrupt_shadow,
.patch_hypercall = svm_patch_hypercall,
.inject_irq = svm_inject_irq,
.inject_nmi = svm_inject_nmi,
.queue_exception = svm_queue_exception,
.cancel_injection = svm_cancel_injection,
.interrupt_allowed = svm_interrupt_allowed,
.nmi_allowed = svm_nmi_allowed,
.get_nmi_mask = svm_get_nmi_mask,
.set_nmi_mask = svm_set_nmi_mask,
.enable_nmi_window = svm_enable_nmi_window,
.enable_irq_window = svm_enable_irq_window,
.update_cr8_intercept = svm_update_cr8_intercept,
.refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl,
.check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons,
.apicv_post_state_restore = avic_apicv_post_state_restore,
.get_mt_mask = svm_get_mt_mask,
.get_exit_info = svm_get_exit_info,
.vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid,
.has_wbinvd_exit = svm_has_wbinvd_exit,
.get_l2_tsc_offset = svm_get_l2_tsc_offset,
.get_l2_tsc_multiplier = svm_get_l2_tsc_multiplier,
.write_tsc_offset = svm_write_tsc_offset,
.write_tsc_multiplier = svm_write_tsc_multiplier,
.load_mmu_pgd = svm_load_mmu_pgd,
.check_intercept = svm_check_intercept,
.handle_exit_irqoff = svm_handle_exit_irqoff,
.request_immediate_exit = __kvm_request_immediate_exit,
.sched_in = svm_sched_in,
.nested_ops = &svm_nested_ops,
.deliver_interrupt = svm_deliver_interrupt,
.pi_update_irte = avic_pi_update_irte,
.setup_mce = svm_setup_mce,
.smi_allowed = svm_smi_allowed,
.enter_smm = svm_enter_smm,
.leave_smm = svm_leave_smm,
.enable_smi_window = svm_enable_smi_window,
.mem_enc_ioctl = sev_mem_enc_ioctl,
.mem_enc_register_region = sev_mem_enc_register_region,
.mem_enc_unregister_region = sev_mem_enc_unregister_region,
.vm_copy_enc_context_from = sev_vm_copy_enc_context_from,
.vm_move_enc_context_from = sev_vm_move_enc_context_from,
.can_emulate_instruction = svm_can_emulate_instruction,
.apic_init_signal_blocked = svm_apic_init_signal_blocked,
.msr_filter_changed = svm_msr_filter_changed,
.complete_emulated_msr = svm_complete_emulated_msr,
.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
};
/*
* The default MMIO mask is a single bit (excluding the present bit),
* which could conflict with the memory encryption bit. Check for
* memory encryption support and override the default MMIO mask if
* memory encryption is enabled.
*/
static __init void svm_adjust_mmio_mask(void)
{
unsigned int enc_bit, mask_bit;
u64 msr, mask;
/* If there is no memory encryption support, use existing mask */
if (cpuid_eax(0x80000000) < 0x8000001f)
return;
/* If memory encryption is not enabled, use existing mask */
rdmsrl(MSR_AMD64_SYSCFG, msr);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
return;
enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
mask_bit = boot_cpu_data.x86_phys_bits;
/* Increment the mask bit if it is the same as the encryption bit */
if (enc_bit == mask_bit)
mask_bit++;
/*
* If the mask bit location is below 52, then some bits above the
* physical addressing limit will always be reserved, so use the
* rsvd_bits() function to generate the mask. This mask, along with
* the present bit, will be used to generate a page fault with
* PFER.RSV = 1.
*
* If the mask bit location is 52 (or above), then clear the mask.
*/
mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
}
static __init void svm_set_cpu_caps(void)
{
kvm_set_cpu_caps();
supported_xss = 0;
/* CPUID 0x80000001 and 0x8000000A (SVM features) */
if (nested) {
kvm_cpu_cap_set(X86_FEATURE_SVM);
kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN);
if (nrips)
kvm_cpu_cap_set(X86_FEATURE_NRIPS);
if (npt_enabled)
kvm_cpu_cap_set(X86_FEATURE_NPT);
if (tsc_scaling)
kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
if (vls)
kvm_cpu_cap_set(X86_FEATURE_V_VMSAVE_VMLOAD);
if (lbrv)
kvm_cpu_cap_set(X86_FEATURE_LBRV);
if (boot_cpu_has(X86_FEATURE_PAUSEFILTER))
kvm_cpu_cap_set(X86_FEATURE_PAUSEFILTER);
if (boot_cpu_has(X86_FEATURE_PFTHRESHOLD))
kvm_cpu_cap_set(X86_FEATURE_PFTHRESHOLD);
if (vgif)
kvm_cpu_cap_set(X86_FEATURE_VGIF);
/* Nested VM can receive #VMEXIT instead of triggering #GP */
kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
}
/* CPUID 0x80000008 */
if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
boot_cpu_has(X86_FEATURE_AMD_SSBD))
kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
/* AMD PMU PERFCTR_CORE CPUID */
if (enable_pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE);
/* CPUID 0x8000001F (SME/SEV features) */
sev_set_cpu_caps();
}
static __init int svm_hardware_setup(void)
{
int cpu;
struct page *iopm_pages;
void *iopm_va;
int r;
unsigned int order = get_order(IOPM_SIZE);
/*
* NX is required for shadow paging and for NPT if the NX huge pages
* mitigation is enabled.
*/
if (!boot_cpu_has(X86_FEATURE_NX)) {
pr_err_ratelimited("NX (Execute Disable) not supported\n");
return -EOPNOTSUPP;
}
kvm_enable_efer_bits(EFER_NX);
iopm_pages = alloc_pages(GFP_KERNEL, order);
if (!iopm_pages)
return -ENOMEM;
iopm_va = page_address(iopm_pages);
memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
init_msrpm_offsets();
supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
kvm_enable_efer_bits(EFER_FFXSR);
if (tsc_scaling) {
if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
tsc_scaling = false;
} else {
pr_info("TSC scaling supported\n");
kvm_has_tsc_control = true;
}
}
kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX;
kvm_tsc_scaling_ratio_frac_bits = 32;
tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
/* Check for pause filtering support */
if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
pause_filter_count = 0;
pause_filter_thresh = 0;
} else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
pause_filter_thresh = 0;
}
if (nested) {
printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
}
/*
* KVM's MMU doesn't support using 2-level paging for itself, and thus
* NPT isn't supported if the host is using 2-level paging since host
* CR4 is unchanged on VMRUN.
*/
if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
npt_enabled = false;
if (!boot_cpu_has(X86_FEATURE_NPT))
npt_enabled = false;
/* Force VM NPT level equal to the host's paging level */
kvm_configure_mmu(npt_enabled, get_npt_level(),
get_npt_level(), PG_LEVEL_1G);
pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
/* Note, SEV setup consumes npt_enabled. */
sev_hardware_setup();
svm_hv_hardware_setup();
svm_adjust_mmio_mask();
for_each_possible_cpu(cpu) {
r = svm_cpu_init(cpu);
if (r)
goto err;
}
if (nrips) {
if (!boot_cpu_has(X86_FEATURE_NRIPS))
nrips = false;
}
enable_apicv = avic = avic && npt_enabled && (boot_cpu_has(X86_FEATURE_AVIC) || force_avic);
if (enable_apicv) {
if (!boot_cpu_has(X86_FEATURE_AVIC)) {
pr_warn("AVIC is not supported in CPUID but force enabled");
pr_warn("Your system might crash and burn");
} else
pr_info("AVIC enabled\n");
amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
} else {
svm_x86_ops.vcpu_blocking = NULL;
svm_x86_ops.vcpu_unblocking = NULL;
svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
}
if (vls) {
if (!npt_enabled ||
!boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
!IS_ENABLED(CONFIG_X86_64)) {
vls = false;
} else {
pr_info("Virtual VMLOAD VMSAVE supported\n");
}
}
if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK))
svm_gp_erratum_intercept = false;
if (vgif) {
if (!boot_cpu_has(X86_FEATURE_VGIF))
vgif = false;
else
pr_info("Virtual GIF supported\n");
}
if (lbrv) {
if (!boot_cpu_has(X86_FEATURE_LBRV))
lbrv = false;
else
pr_info("LBR virtualization supported\n");
}
if (!enable_pmu)
pr_info("PMU virtualization is disabled\n");
svm_set_cpu_caps();
/*
* It seems that on AMD processors PTE's accessed bit is
* being set by the CPU hardware before the NPF vmexit.
* This is not expected behaviour and our tests fail because
* of it.
* A workaround here is to disable support for
* GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
* In this case userspace can know if there is support using
* KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
* it
* If future AMD CPU models change the behaviour described above,
* this variable can be changed accordingly
*/
allow_smaller_maxphyaddr = !npt_enabled;
return 0;
err:
svm_hardware_unsetup();
return r;
}
static struct kvm_x86_init_ops svm_init_ops __initdata = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
.check_processor_compatibility = svm_check_processor_compat,
.runtime_ops = &svm_x86_ops,
.pmu_ops = &amd_pmu_ops,
};
static int __init svm_init(void)
{
__unused_size_checks();
return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm),
__alignof__(struct vcpu_svm), THIS_MODULE);
}
static void __exit svm_exit(void)
{
kvm_exit();
}
module_init(svm_init)
module_exit(svm_exit)
|