summaryrefslogtreecommitdiffstats
path: root/Documentation/virtual/kvm/api.txt
blob: f670e4b9e7f33fdbb186d9b1c9186c6a2fbf7324 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
The Definitive KVM (Kernel-based Virtual Machine) API Documentation
===================================================================

1. General description
----------------------

The kvm API is a set of ioctls that are issued to control various aspects
of a virtual machine.  The ioctls belong to three classes

 - System ioctls: These query and set global attributes which affect the
   whole kvm subsystem.  In addition a system ioctl is used to create
   virtual machines

 - VM ioctls: These query and set attributes that affect an entire virtual
   machine, for example memory layout.  In addition a VM ioctl is used to
   create virtual cpus (vcpus).

   Only run VM ioctls from the same process (address space) that was used
   to create the VM.

 - vcpu ioctls: These query and set attributes that control the operation
   of a single virtual cpu.

   Only run vcpu ioctls from the same thread that was used to create the
   vcpu.


2. File descriptors
-------------------

The kvm API is centered around file descriptors.  An initial
open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
handle will create a VM file descriptor which can be used to issue VM
ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
fd can be used to control the vcpu, including the important task of
actually running guest code.

In general file descriptors can be migrated among processes by means
of fork() and the SCM_RIGHTS facility of unix domain socket.  These
kinds of tricks are explicitly not supported by kvm.  While they will
not cause harm to the host, their actual behavior is not guaranteed by
the API.  The only supported use is one virtual machine per process,
and one vcpu per thread.


3. Extensions
-------------

As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
incompatible change are allowed.  However, there is an extension
facility that allows backward-compatible extensions to the API to be
queried and used.

The extension mechanism is not based on the Linux version number.
Instead, kvm defines extension identifiers and a facility to query
whether a particular extension identifier is available.  If it is, a
set of ioctls is available for application use.


4. API description
------------------

This section describes ioctls that can be used to control kvm guests.
For each ioctl, the following information is provided along with a
description:

  Capability: which KVM extension provides this ioctl.  Can be 'basic',
      which means that is will be provided by any kernel that supports
      API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
      means availability needs to be checked with KVM_CHECK_EXTENSION
      (see section 4.4), or 'none' which means that while not all kernels
      support this ioctl, there's no capability bit to check its
      availability: for kernels that don't support the ioctl,
      the ioctl returns -ENOTTY.

  Architectures: which instruction set architectures provide this ioctl.
      x86 includes both i386 and x86_64.

  Type: system, vm, or vcpu.

  Parameters: what parameters are accepted by the ioctl.

  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
      are not detailed, but errors with specific meanings are.


4.1 KVM_GET_API_VERSION

Capability: basic
Architectures: all
Type: system ioctl
Parameters: none
Returns: the constant KVM_API_VERSION (=12)

This identifies the API version as the stable kvm API. It is not
expected that this number will change.  However, Linux 2.6.20 and
2.6.21 report earlier versions; these are not documented and not
supported.  Applications should refuse to run if KVM_GET_API_VERSION
returns a value other than 12.  If this check passes, all ioctls
described as 'basic' will be available.


4.2 KVM_CREATE_VM

Capability: basic
Architectures: all
Type: system ioctl
Parameters: machine type identifier (KVM_VM_*)
Returns: a VM fd that can be used to control the new virtual machine.

The new VM has no virtual cpus and no memory.
You probably want to use 0 as machine type.

In order to create user controlled virtual machines on S390, check
KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
privileged user (CAP_SYS_ADMIN).

To use hardware assisted virtualization on MIPS (VZ ASE) rather than
the default trap & emulate implementation (which changes the virtual
memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
flag KVM_VM_MIPS_VZ.


4.3 KVM_GET_MSR_INDEX_LIST

Capability: basic
Architectures: x86
Type: system
Parameters: struct kvm_msr_list (in/out)
Returns: 0 on success; -1 on error
Errors:
  E2BIG:     the msr index list is to be to fit in the array specified by
             the user.

struct kvm_msr_list {
	__u32 nmsrs; /* number of msrs in entries */
	__u32 indices[0];
};

This ioctl returns the guest msrs that are supported.  The list varies
by kvm version and host processor, but does not change otherwise.  The
user fills in the size of the indices array in nmsrs, and in return
kvm adjusts nmsrs to reflect the actual number of msrs and fills in
the indices array with their numbers.

Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
not returned in the MSR list, as different vcpus can have a different number
of banks, as set via the KVM_X86_SETUP_MCE ioctl.


4.4 KVM_CHECK_EXTENSION

Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
Architectures: all
Type: system ioctl, vm ioctl
Parameters: extension identifier (KVM_CAP_*)
Returns: 0 if unsupported; 1 (or some other positive integer) if supported

The API allows the application to query about extensions to the core
kvm API.  Userspace passes an extension identifier (an integer) and
receives an integer that describes the extension availability.
Generally 0 means no and 1 means yes, but some extensions may report
additional information in the integer return value.

Based on their initialization different VMs may have different capabilities.
It is thus encouraged to use the vm ioctl to query for capabilities (available
with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)

4.5 KVM_GET_VCPU_MMAP_SIZE

Capability: basic
Architectures: all
Type: system ioctl
Parameters: none
Returns: size of vcpu mmap area, in bytes

The KVM_RUN ioctl (cf.) communicates with userspace via a shared
memory region.  This ioctl returns the size of that region.  See the
KVM_RUN documentation for details.


4.6 KVM_SET_MEMORY_REGION

Capability: basic
Architectures: all
Type: vm ioctl
Parameters: struct kvm_memory_region (in)
Returns: 0 on success, -1 on error

This ioctl is obsolete and has been removed.


4.7 KVM_CREATE_VCPU

Capability: basic
Architectures: all
Type: vm ioctl
Parameters: vcpu id (apic id on x86)
Returns: vcpu fd on success, -1 on error

This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
The vcpu id is an integer in the range [0, max_vcpu_id).

The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
the KVM_CHECK_EXTENSION ioctl() at run-time.
The maximum possible value for max_vcpus can be retrieved using the
KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.

If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
cpus max.
If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
same as the value returned from KVM_CAP_NR_VCPUS.

The maximum possible value for max_vcpu_id can be retrieved using the
KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.

If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
is the same as the value returned from KVM_CAP_MAX_VCPUS.

On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
threads in one or more virtual CPU cores.  (This is because the
hardware requires all the hardware threads in a CPU core to be in the
same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
of vcpus per virtual core (vcore).  The vcore id is obtained by
dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
given vcore will always be in the same physical core as each other
(though that might be a different physical core from time to time).
Userspace can control the threading (SMT) mode of the guest by its
allocation of vcpu ids.  For example, if userspace wants
single-threaded guest vcpus, it should make all vcpu ids be a multiple
of the number of vcpus per vcore.

For virtual cpus that have been created with S390 user controlled virtual
machines, the resulting vcpu fd can be memory mapped at page offset
KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
cpu's hardware control block.


4.8 KVM_GET_DIRTY_LOG (vm ioctl)

Capability: basic
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_dirty_log (in/out)
Returns: 0 on success, -1 on error

/* for KVM_GET_DIRTY_LOG */
struct kvm_dirty_log {
	__u32 slot;
	__u32 padding;
	union {
		void __user *dirty_bitmap; /* one bit per page */
		__u64 padding;
	};
};

Given a memory slot, return a bitmap containing any pages dirtied
since the last call to this ioctl.  Bit 0 is the first page in the
memory slot.  Ensure the entire structure is cleared to avoid padding
issues.

If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
the address space for which you want to return the dirty bitmap.
They must be less than the value that KVM_CHECK_EXTENSION returns for
the KVM_CAP_MULTI_ADDRESS_SPACE capability.


4.9 KVM_SET_MEMORY_ALIAS

Capability: basic
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_memory_alias (in)
Returns: 0 (success), -1 (error)

This ioctl is obsolete and has been removed.


4.10 KVM_RUN

Capability: basic
Architectures: all
Type: vcpu ioctl
Parameters: none
Returns: 0 on success, -1 on error
Errors:
  EINTR:     an unmasked signal is pending

This ioctl is used to run a guest virtual cpu.  While there are no
explicit parameters, there is an implicit parameter block that can be
obtained by mmap()ing the vcpu fd at offset 0, with the size given by
KVM_GET_VCPU_MMAP_SIZE.  The parameter block is formatted as a 'struct
kvm_run' (see below).


4.11 KVM_GET_REGS

Capability: basic
Architectures: all except ARM, arm64
Type: vcpu ioctl
Parameters: struct kvm_regs (out)
Returns: 0 on success, -1 on error

Reads the general purpose registers from the vcpu.

/* x86 */
struct kvm_regs {
	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
	__u64 rax, rbx, rcx, rdx;
	__u64 rsi, rdi, rsp, rbp;
	__u64 r8,  r9,  r10, r11;
	__u64 r12, r13, r14, r15;
	__u64 rip, rflags;
};

/* mips */
struct kvm_regs {
	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
	__u64 gpr[32];
	__u64 hi;
	__u64 lo;
	__u64 pc;
};


4.12 KVM_SET_REGS

Capability: basic
Architectures: all except ARM, arm64
Type: vcpu ioctl
Parameters: struct kvm_regs (in)
Returns: 0 on success, -1 on error

Writes the general purpose registers into the vcpu.

See KVM_GET_REGS for the data structure.


4.13 KVM_GET_SREGS

Capability: basic
Architectures: x86, ppc
Type: vcpu ioctl
Parameters: struct kvm_sregs (out)
Returns: 0 on success, -1 on error

Reads special registers from the vcpu.

/* x86 */
struct kvm_sregs {
	struct kvm_segment cs, ds, es, fs, gs, ss;
	struct kvm_segment tr, ldt;
	struct kvm_dtable gdt, idt;
	__u64 cr0, cr2, cr3, cr4, cr8;
	__u64 efer;
	__u64 apic_base;
	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
};

/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */

interrupt_bitmap is a bitmap of pending external interrupts.  At most
one bit may be set.  This interrupt has been acknowledged by the APIC
but not yet injected into the cpu core.


4.14 KVM_SET_SREGS

Capability: basic
Architectures: x86, ppc
Type: vcpu ioctl
Parameters: struct kvm_sregs (in)
Returns: 0 on success, -1 on error

Writes special registers into the vcpu.  See KVM_GET_SREGS for the
data structures.


4.15 KVM_TRANSLATE

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_translation (in/out)
Returns: 0 on success, -1 on error

Translates a virtual address according to the vcpu's current address
translation mode.

struct kvm_translation {
	/* in */
	__u64 linear_address;

	/* out */
	__u64 physical_address;
	__u8  valid;
	__u8  writeable;
	__u8  usermode;
	__u8  pad[5];
};


4.16 KVM_INTERRUPT

Capability: basic
Architectures: x86, ppc, mips
Type: vcpu ioctl
Parameters: struct kvm_interrupt (in)
Returns: 0 on success, negative on failure.

Queues a hardware interrupt vector to be injected.

/* for KVM_INTERRUPT */
struct kvm_interrupt {
	/* in */
	__u32 irq;
};

X86:

Returns: 0 on success,
	 -EEXIST if an interrupt is already enqueued
	 -EINVAL the the irq number is invalid
	 -ENXIO if the PIC is in the kernel
	 -EFAULT if the pointer is invalid

Note 'irq' is an interrupt vector, not an interrupt pin or line. This
ioctl is useful if the in-kernel PIC is not used.

PPC:

Queues an external interrupt to be injected. This ioctl is overleaded
with 3 different irq values:

a) KVM_INTERRUPT_SET

  This injects an edge type external interrupt into the guest once it's ready
  to receive interrupts. When injected, the interrupt is done.

b) KVM_INTERRUPT_UNSET

  This unsets any pending interrupt.

  Only available with KVM_CAP_PPC_UNSET_IRQ.

c) KVM_INTERRUPT_SET_LEVEL

  This injects a level type external interrupt into the guest context. The
  interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
  is triggered.

  Only available with KVM_CAP_PPC_IRQ_LEVEL.

Note that any value for 'irq' other than the ones stated above is invalid
and incurs unexpected behavior.

MIPS:

Queues an external interrupt to be injected into the virtual CPU. A negative
interrupt number dequeues the interrupt.


4.17 KVM_DEBUG_GUEST

Capability: basic
Architectures: none
Type: vcpu ioctl
Parameters: none)
Returns: -1 on error

Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.


4.18 KVM_GET_MSRS

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_msrs (in/out)
Returns: 0 on success, -1 on error

Reads model-specific registers from the vcpu.  Supported msr indices can
be obtained using KVM_GET_MSR_INDEX_LIST.

struct kvm_msrs {
	__u32 nmsrs; /* number of msrs in entries */
	__u32 pad;

	struct kvm_msr_entry entries[0];
};

struct kvm_msr_entry {
	__u32 index;
	__u32 reserved;
	__u64 data;
};

Application code should set the 'nmsrs' member (which indicates the
size of the entries array) and the 'index' member of each array entry.
kvm will fill in the 'data' member.


4.19 KVM_SET_MSRS

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_msrs (in)
Returns: 0 on success, -1 on error

Writes model-specific registers to the vcpu.  See KVM_GET_MSRS for the
data structures.

Application code should set the 'nmsrs' member (which indicates the
size of the entries array), and the 'index' and 'data' members of each
array entry.


4.20 KVM_SET_CPUID

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_cpuid (in)
Returns: 0 on success, -1 on error

Defines the vcpu responses to the cpuid instruction.  Applications
should use the KVM_SET_CPUID2 ioctl if available.


struct kvm_cpuid_entry {
	__u32 function;
	__u32 eax;
	__u32 ebx;
	__u32 ecx;
	__u32 edx;
	__u32 padding;
};

/* for KVM_SET_CPUID */
struct kvm_cpuid {
	__u32 nent;
	__u32 padding;
	struct kvm_cpuid_entry entries[0];
};


4.21 KVM_SET_SIGNAL_MASK

Capability: basic
Architectures: all
Type: vcpu ioctl
Parameters: struct kvm_signal_mask (in)
Returns: 0 on success, -1 on error

Defines which signals are blocked during execution of KVM_RUN.  This
signal mask temporarily overrides the threads signal mask.  Any
unblocked signal received (except SIGKILL and SIGSTOP, which retain
their traditional behaviour) will cause KVM_RUN to return with -EINTR.

Note the signal will only be delivered if not blocked by the original
signal mask.

/* for KVM_SET_SIGNAL_MASK */
struct kvm_signal_mask {
	__u32 len;
	__u8  sigset[0];
};


4.22 KVM_GET_FPU

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_fpu (out)
Returns: 0 on success, -1 on error

Reads the floating point state from the vcpu.

/* for KVM_GET_FPU and KVM_SET_FPU */
struct kvm_fpu {
	__u8  fpr[8][16];
	__u16 fcw;
	__u16 fsw;
	__u8  ftwx;  /* in fxsave format */
	__u8  pad1;
	__u16 last_opcode;
	__u64 last_ip;
	__u64 last_dp;
	__u8  xmm[16][16];
	__u32 mxcsr;
	__u32 pad2;
};


4.23 KVM_SET_FPU

Capability: basic
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_fpu (in)
Returns: 0 on success, -1 on error

Writes the floating point state to the vcpu.

/* for KVM_GET_FPU and KVM_SET_FPU */
struct kvm_fpu {
	__u8  fpr[8][16];
	__u16 fcw;
	__u16 fsw;
	__u8  ftwx;  /* in fxsave format */
	__u8  pad1;
	__u16 last_opcode;
	__u64 last_ip;
	__u64 last_dp;
	__u8  xmm[16][16];
	__u32 mxcsr;
	__u32 pad2;
};


4.24 KVM_CREATE_IRQCHIP

Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
Architectures: x86, ARM, arm64, s390
Type: vm ioctl
Parameters: none
Returns: 0 on success, -1 on error

Creates an interrupt controller model in the kernel.
On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
future vcpus to have a local APIC.  IRQ routing for GSIs 0-15 is set to both
PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of
KVM_CREATE_DEVICE, which also supports creating a GICv2.  Using
KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
On s390, a dummy irq routing table is created.

Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
before KVM_CREATE_IRQCHIP can be used.


4.25 KVM_IRQ_LINE

Capability: KVM_CAP_IRQCHIP
Architectures: x86, arm, arm64
Type: vm ioctl
Parameters: struct kvm_irq_level
Returns: 0 on success, -1 on error

Sets the level of a GSI input to the interrupt controller model in the kernel.
On some architectures it is required that an interrupt controller model has
been previously created with KVM_CREATE_IRQCHIP.  Note that edge-triggered
interrupts require the level to be set to 1 and then back to 0.

On real hardware, interrupt pins can be active-low or active-high.  This
does not matter for the level field of struct kvm_irq_level: 1 always
means active (asserted), 0 means inactive (deasserted).

x86 allows the operating system to program the interrupt polarity
(active-low/active-high) for level-triggered interrupts, and KVM used
to consider the polarity.  However, due to bitrot in the handling of
active-low interrupts, the above convention is now valid on x86 too.
This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED.  Userspace
should not present interrupts to the guest as active-low unless this
capability is present (or unless it is not using the in-kernel irqchip,
of course).


ARM/arm64 can signal an interrupt either at the CPU level, or at the
in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
use PPIs designated for specific cpus.  The irq field is interpreted
like this:

  bits:  | 31 ... 24 | 23  ... 16 | 15    ...    0 |
  field: | irq_type  | vcpu_index |     irq_id     |

The irq_type field has the following values:
- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
               (the vcpu_index field is ignored)
- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)

(The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)

In both cases, level is used to assert/deassert the line.

struct kvm_irq_level {
	union {
		__u32 irq;     /* GSI */
		__s32 status;  /* not used for KVM_IRQ_LEVEL */
	};
	__u32 level;           /* 0 or 1 */
};


4.26 KVM_GET_IRQCHIP

Capability: KVM_CAP_IRQCHIP
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_irqchip (in/out)
Returns: 0 on success, -1 on error

Reads the state of a kernel interrupt controller created with
KVM_CREATE_IRQCHIP into a buffer provided by the caller.

struct kvm_irqchip {
	__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
	__u32 pad;
        union {
		char dummy[512];  /* reserving space */
		struct kvm_pic_state pic;
		struct kvm_ioapic_state ioapic;
	} chip;
};


4.27 KVM_SET_IRQCHIP

Capability: KVM_CAP_IRQCHIP
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_irqchip (in)
Returns: 0 on success, -1 on error

Sets the state of a kernel interrupt controller created with
KVM_CREATE_IRQCHIP from a buffer provided by the caller.

struct kvm_irqchip {
	__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
	__u32 pad;
        union {
		char dummy[512];  /* reserving space */
		struct kvm_pic_state pic;
		struct kvm_ioapic_state ioapic;
	} chip;
};


4.28 KVM_XEN_HVM_CONFIG

Capability: KVM_CAP_XEN_HVM
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_xen_hvm_config (in)
Returns: 0 on success, -1 on error

Sets the MSR that the Xen HVM guest uses to initialize its hypercall
page, and provides the starting address and size of the hypercall
blobs in userspace.  When the guest writes the MSR, kvm copies one
page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
memory.

struct kvm_xen_hvm_config {
	__u32 flags;
	__u32 msr;
	__u64 blob_addr_32;
	__u64 blob_addr_64;
	__u8 blob_size_32;
	__u8 blob_size_64;
	__u8 pad2[30];
};


4.29 KVM_GET_CLOCK

Capability: KVM_CAP_ADJUST_CLOCK
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_clock_data (out)
Returns: 0 on success, -1 on error

Gets the current timestamp of kvmclock as seen by the current guest. In
conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
such as migration.

When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
set of bits that KVM can return in struct kvm_clock_data's flag member.

The only flag defined now is KVM_CLOCK_TSC_STABLE.  If set, the returned
value is the exact kvmclock value seen by all VCPUs at the instant
when KVM_GET_CLOCK was called.  If clear, the returned value is simply
CLOCK_MONOTONIC plus a constant offset; the offset can be modified
with KVM_SET_CLOCK.  KVM will try to make all VCPUs follow this clock,
but the exact value read by each VCPU could differ, because the host
TSC is not stable.

struct kvm_clock_data {
	__u64 clock;  /* kvmclock current value */
	__u32 flags;
	__u32 pad[9];
};


4.30 KVM_SET_CLOCK

Capability: KVM_CAP_ADJUST_CLOCK
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_clock_data (in)
Returns: 0 on success, -1 on error

Sets the current timestamp of kvmclock to the value specified in its parameter.
In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
such as migration.

struct kvm_clock_data {
	__u64 clock;  /* kvmclock current value */
	__u32 flags;
	__u32 pad[9];
};


4.31 KVM_GET_VCPU_EVENTS

Capability: KVM_CAP_VCPU_EVENTS
Extended by: KVM_CAP_INTR_SHADOW
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_vcpu_event (out)
Returns: 0 on success, -1 on error

Gets currently pending exceptions, interrupts, and NMIs as well as related
states of the vcpu.

struct kvm_vcpu_events {
	struct {
		__u8 injected;
		__u8 nr;
		__u8 has_error_code;
		__u8 pad;
		__u32 error_code;
	} exception;
	struct {
		__u8 injected;
		__u8 nr;
		__u8 soft;
		__u8 shadow;
	} interrupt;
	struct {
		__u8 injected;
		__u8 pending;
		__u8 masked;
		__u8 pad;
	} nmi;
	__u32 sipi_vector;
	__u32 flags;
	struct {
		__u8 smm;
		__u8 pending;
		__u8 smm_inside_nmi;
		__u8 latched_init;
	} smi;
};

Only two fields are defined in the flags field:

- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
  interrupt.shadow contains a valid state.

- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
  smi contains a valid state.

4.32 KVM_SET_VCPU_EVENTS

Capability: KVM_CAP_VCPU_EVENTS
Extended by: KVM_CAP_INTR_SHADOW
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_vcpu_event (in)
Returns: 0 on success, -1 on error

Set pending exceptions, interrupts, and NMIs as well as related states of the
vcpu.

See KVM_GET_VCPU_EVENTS for the data structure.

Fields that may be modified asynchronously by running VCPUs can be excluded
from the update. These fields are nmi.pending, sipi_vector, smi.smm,
smi.pending. Keep the corresponding bits in the flags field cleared to
suppress overwriting the current in-kernel state. The bits are:

KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
KVM_VCPUEVENT_VALID_SMM         - transfer the smi sub-struct.

If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
the flags field to signal that interrupt.shadow contains a valid state and
shall be written into the VCPU.

KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.


4.33 KVM_GET_DEBUGREGS

Capability: KVM_CAP_DEBUGREGS
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_debugregs (out)
Returns: 0 on success, -1 on error

Reads debug registers from the vcpu.

struct kvm_debugregs {
	__u64 db[4];
	__u64 dr6;
	__u64 dr7;
	__u64 flags;
	__u64 reserved[9];
};


4.34 KVM_SET_DEBUGREGS

Capability: KVM_CAP_DEBUGREGS
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_debugregs (in)
Returns: 0 on success, -1 on error

Writes debug registers into the vcpu.

See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
yet and must be cleared on entry.


4.35 KVM_SET_USER_MEMORY_REGION

Capability: KVM_CAP_USER_MEM
Architectures: all
Type: vm ioctl
Parameters: struct kvm_userspace_memory_region (in)
Returns: 0 on success, -1 on error

struct kvm_userspace_memory_region {
	__u32 slot;
	__u32 flags;
	__u64 guest_phys_addr;
	__u64 memory_size; /* bytes */
	__u64 userspace_addr; /* start of the userspace allocated memory */
};

/* for kvm_memory_region::flags */
#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
#define KVM_MEM_READONLY	(1UL << 1)

This ioctl allows the user to create or modify a guest physical memory
slot.  When changing an existing slot, it may be moved in the guest
physical memory space, or its flags may be modified.  It may not be
resized.  Slots may not overlap in guest physical address space.
Bits 0-15 of "slot" specifies the slot id and this value should be
less than the maximum number of user memory slots supported per VM.
The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
if this capability is supported by the architecture.

If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
specifies the address space which is being modified.  They must be
less than the value that KVM_CHECK_EXTENSION returns for the
KVM_CAP_MULTI_ADDRESS_SPACE capability.  Slots in separate address spaces
are unrelated; the restriction on overlapping slots only applies within
each address space.

Memory for the region is taken starting at the address denoted by the
field userspace_addr, which must point at user addressable memory for
the entire memory slot size.  Any object may back this memory, including
anonymous memory, ordinary files, and hugetlbfs.

It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
be identical.  This allows large pages in the guest to be backed by large
pages in the host.

The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
KVM_MEM_READONLY.  The former can be set to instruct KVM to keep track of
writes to memory within the slot.  See KVM_GET_DIRTY_LOG ioctl to know how to
use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
to make a new slot read-only.  In this case, writes to this memory will be
posted to userspace as KVM_EXIT_MMIO exits.

When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
the memory region are automatically reflected into the guest.  For example, an
mmap() that affects the region will be made visible immediately.  Another
example is madvise(MADV_DROP).

It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
allocation and is deprecated.


4.36 KVM_SET_TSS_ADDR

Capability: KVM_CAP_SET_TSS_ADDR
Architectures: x86
Type: vm ioctl
Parameters: unsigned long tss_address (in)
Returns: 0 on success, -1 on error

This ioctl defines the physical address of a three-page region in the guest
physical address space.  The region must be within the first 4GB of the
guest physical address space and must not conflict with any memory slot
or any mmio address.  The guest may malfunction if it accesses this memory
region.

This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
because of a quirk in the virtualization implementation (see the internals
documentation when it pops into existence).


4.37 KVM_ENABLE_CAP

Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
	       mips (only KVM_CAP_ENABLE_CAP), ppc, s390
Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
Parameters: struct kvm_enable_cap (in)
Returns: 0 on success; -1 on error

+Not all extensions are enabled by default. Using this ioctl the application
can enable an extension, making it available to the guest.

On systems that do not support this ioctl, it always fails. On systems that
do support it, it only works for extensions that are supported for enablement.

To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
be used.

struct kvm_enable_cap {
       /* in */
       __u32 cap;

The capability that is supposed to get enabled.

       __u32 flags;

A bitfield indicating future enhancements. Has to be 0 for now.

       __u64 args[4];

Arguments for enabling a feature. If a feature needs initial values to
function properly, this is the place to put them.

       __u8  pad[64];
};

The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
for vm-wide capabilities.

4.38 KVM_GET_MP_STATE

Capability: KVM_CAP_MP_STATE
Architectures: x86, s390, arm, arm64
Type: vcpu ioctl
Parameters: struct kvm_mp_state (out)
Returns: 0 on success; -1 on error

struct kvm_mp_state {
	__u32 mp_state;
};

Returns the vcpu's current "multiprocessing state" (though also valid on
uniprocessor guests).

Possible values are:

 - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running [x86,arm/arm64]
 - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
                                 which has not yet received an INIT signal [x86]
 - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
                                 now ready for a SIPI [x86]
 - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
                                 is waiting for an interrupt [x86]
 - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
                                 accessible via KVM_GET_VCPU_EVENTS) [x86]
 - KVM_MP_STATE_STOPPED:         the vcpu is stopped [s390,arm/arm64]
 - KVM_MP_STATE_CHECK_STOP:      the vcpu is in a special error state [s390]
 - KVM_MP_STATE_OPERATING:       the vcpu is operating (running or halted)
                                 [s390]
 - KVM_MP_STATE_LOAD:            the vcpu is in a special load/startup state
                                 [s390]

On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
in-kernel irqchip, the multiprocessing state must be maintained by userspace on
these architectures.

For arm/arm64:

The only states that are valid are KVM_MP_STATE_STOPPED and
KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.

4.39 KVM_SET_MP_STATE

Capability: KVM_CAP_MP_STATE
Architectures: x86, s390, arm, arm64
Type: vcpu ioctl
Parameters: struct kvm_mp_state (in)
Returns: 0 on success; -1 on error

Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
arguments.

On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
in-kernel irqchip, the multiprocessing state must be maintained by userspace on
these architectures.

For arm/arm64:

The only states that are valid are KVM_MP_STATE_STOPPED and
KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.

4.40 KVM_SET_IDENTITY_MAP_ADDR

Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
Architectures: x86
Type: vm ioctl
Parameters: unsigned long identity (in)
Returns: 0 on success, -1 on error

This ioctl defines the physical address of a one-page region in the guest
physical address space.  The region must be within the first 4GB of the
guest physical address space and must not conflict with any memory slot
or any mmio address.  The guest may malfunction if it accesses this memory
region.

Setting the address to 0 will result in resetting the address to its default
(0xfffbc000).

This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
because of a quirk in the virtualization implementation (see the internals
documentation when it pops into existence).

Fails if any VCPU has already been created.

4.41 KVM_SET_BOOT_CPU_ID

Capability: KVM_CAP_SET_BOOT_CPU_ID
Architectures: x86
Type: vm ioctl
Parameters: unsigned long vcpu_id
Returns: 0 on success, -1 on error

Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
is vcpu 0.


4.42 KVM_GET_XSAVE

Capability: KVM_CAP_XSAVE
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_xsave (out)
Returns: 0 on success, -1 on error

struct kvm_xsave {
	__u32 region[1024];
};

This ioctl would copy current vcpu's xsave struct to the userspace.


4.43 KVM_SET_XSAVE

Capability: KVM_CAP_XSAVE
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_xsave (in)
Returns: 0 on success, -1 on error

struct kvm_xsave {
	__u32 region[1024];
};

This ioctl would copy userspace's xsave struct to the kernel.


4.44 KVM_GET_XCRS

Capability: KVM_CAP_XCRS
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_xcrs (out)
Returns: 0 on success, -1 on error

struct kvm_xcr {
	__u32 xcr;
	__u32 reserved;
	__u64 value;
};

struct kvm_xcrs {
	__u32 nr_xcrs;
	__u32 flags;
	struct kvm_xcr xcrs[KVM_MAX_XCRS];
	__u64 padding[16];
};

This ioctl would copy current vcpu's xcrs to the userspace.


4.45 KVM_SET_XCRS

Capability: KVM_CAP_XCRS
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_xcrs (in)
Returns: 0 on success, -1 on error

struct kvm_xcr {
	__u32 xcr;
	__u32 reserved;
	__u64 value;
};

struct kvm_xcrs {
	__u32 nr_xcrs;
	__u32 flags;
	struct kvm_xcr xcrs[KVM_MAX_XCRS];
	__u64 padding[16];
};

This ioctl would set vcpu's xcr to the value userspace specified.


4.46 KVM_GET_SUPPORTED_CPUID

Capability: KVM_CAP_EXT_CPUID
Architectures: x86
Type: system ioctl
Parameters: struct kvm_cpuid2 (in/out)
Returns: 0 on success, -1 on error

struct kvm_cpuid2 {
	__u32 nent;
	__u32 padding;
	struct kvm_cpuid_entry2 entries[0];
};

#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)

struct kvm_cpuid_entry2 {
	__u32 function;
	__u32 index;
	__u32 flags;
	__u32 eax;
	__u32 ebx;
	__u32 ecx;
	__u32 edx;
	__u32 padding[3];
};

This ioctl returns x86 cpuid features which are supported by both the hardware
and kvm.  Userspace can use the information returned by this ioctl to
construct cpuid information (for KVM_SET_CPUID2) that is consistent with
hardware, kernel, and userspace capabilities, and with user requirements (for
example, the user may wish to constrain cpuid to emulate older hardware,
or for feature consistency across a cluster).

Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
with the 'nent' field indicating the number of entries in the variable-size
array 'entries'.  If the number of entries is too low to describe the cpu
capabilities, an error (E2BIG) is returned.  If the number is too high,
the 'nent' field is adjusted and an error (ENOMEM) is returned.  If the
number is just right, the 'nent' field is adjusted to the number of valid
entries in the 'entries' array, which is then filled.

The entries returned are the host cpuid as returned by the cpuid instruction,
with unknown or unsupported features masked out.  Some features (for example,
x2apic), may not be present in the host cpu, but are exposed by kvm if it can
emulate them efficiently. The fields in each entry are defined as follows:

  function: the eax value used to obtain the entry
  index: the ecx value used to obtain the entry (for entries that are
         affected by ecx)
  flags: an OR of zero or more of the following:
        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
           if the index field is valid
        KVM_CPUID_FLAG_STATEFUL_FUNC:
           if cpuid for this function returns different values for successive
           invocations; there will be several entries with the same function,
           all with this flag set
        KVM_CPUID_FLAG_STATE_READ_NEXT:
           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
           the first entry to be read by a cpu
   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
         this function/index combination

The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
support.  Instead it is reported via

  ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)

if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
feature in userspace, then you can enable the feature for KVM_SET_CPUID2.


4.47 KVM_PPC_GET_PVINFO

Capability: KVM_CAP_PPC_GET_PVINFO
Architectures: ppc
Type: vm ioctl
Parameters: struct kvm_ppc_pvinfo (out)
Returns: 0 on success, !0 on error

struct kvm_ppc_pvinfo {
	__u32 flags;
	__u32 hcall[4];
	__u8  pad[108];
};

This ioctl fetches PV specific information that need to be passed to the guest
using the device tree or other means from vm context.

The hcall array defines 4 instructions that make up a hypercall.

If any additional field gets added to this structure later on, a bit for that
additional piece of information will be set in the flags bitmap.

The flags bitmap is defined as:

   /* the host supports the ePAPR idle hcall
   #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)

4.52 KVM_SET_GSI_ROUTING

Capability: KVM_CAP_IRQ_ROUTING
Architectures: x86 s390 arm arm64
Type: vm ioctl
Parameters: struct kvm_irq_routing (in)
Returns: 0 on success, -1 on error

Sets the GSI routing table entries, overwriting any previously set entries.

On arm/arm64, GSI routing has the following limitation:
- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.

struct kvm_irq_routing {
	__u32 nr;
	__u32 flags;
	struct kvm_irq_routing_entry entries[0];
};

No flags are specified so far, the corresponding field must be set to zero.

struct kvm_irq_routing_entry {
	__u32 gsi;
	__u32 type;
	__u32 flags;
	__u32 pad;
	union {
		struct kvm_irq_routing_irqchip irqchip;
		struct kvm_irq_routing_msi msi;
		struct kvm_irq_routing_s390_adapter adapter;
		struct kvm_irq_routing_hv_sint hv_sint;
		__u32 pad[8];
	} u;
};

/* gsi routing entry types */
#define KVM_IRQ_ROUTING_IRQCHIP 1
#define KVM_IRQ_ROUTING_MSI 2
#define KVM_IRQ_ROUTING_S390_ADAPTER 3
#define KVM_IRQ_ROUTING_HV_SINT 4

flags:
- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
  type, specifies that the devid field contains a valid value.  The per-VM
  KVM_CAP_MSI_DEVID capability advertises the requirement to provide
  the device ID.  If this capability is not available, userspace should
  never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
- zero otherwise

struct kvm_irq_routing_irqchip {
	__u32 irqchip;
	__u32 pin;
};

struct kvm_irq_routing_msi {
	__u32 address_lo;
	__u32 address_hi;
	__u32 data;
	union {
		__u32 pad;
		__u32 devid;
	};
};

If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
for the device that wrote the MSI message.  For PCI, this is usually a
BFD identifier in the lower 16 bits.

On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
address_hi must be zero.

struct kvm_irq_routing_s390_adapter {
	__u64 ind_addr;
	__u64 summary_addr;
	__u64 ind_offset;
	__u32 summary_offset;
	__u32 adapter_id;
};

struct kvm_irq_routing_hv_sint {
	__u32 vcpu;
	__u32 sint;
};


4.55 KVM_SET_TSC_KHZ

Capability: KVM_CAP_TSC_CONTROL
Architectures: x86
Type: vcpu ioctl
Parameters: virtual tsc_khz
Returns: 0 on success, -1 on error

Specifies the tsc frequency for the virtual machine. The unit of the
frequency is KHz.


4.56 KVM_GET_TSC_KHZ

Capability: KVM_CAP_GET_TSC_KHZ
Architectures: x86
Type: vcpu ioctl
Parameters: none
Returns: virtual tsc-khz on success, negative value on error

Returns the tsc frequency of the guest. The unit of the return value is
KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
error.


4.57 KVM_GET_LAPIC

Capability: KVM_CAP_IRQCHIP
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_lapic_state (out)
Returns: 0 on success, -1 on error

#define KVM_APIC_REG_SIZE 0x400
struct kvm_lapic_state {
	char regs[KVM_APIC_REG_SIZE];
};

Reads the Local APIC registers and copies them into the input argument.  The
data format and layout are the same as documented in the architecture manual.

If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
enabled, then the format of APIC_ID register depends on the APIC mode
(reported by MSR_IA32_APICBASE) of its VCPU.  x2APIC stores APIC ID in
the APIC_ID register (bytes 32-35).  xAPIC only allows an 8-bit APIC ID
which is stored in bits 31-24 of the APIC register, or equivalently in
byte 35 of struct kvm_lapic_state's regs field.  KVM_GET_LAPIC must then
be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.

If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
always uses xAPIC format.


4.58 KVM_SET_LAPIC

Capability: KVM_CAP_IRQCHIP
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_lapic_state (in)
Returns: 0 on success, -1 on error

#define KVM_APIC_REG_SIZE 0x400
struct kvm_lapic_state {
	char regs[KVM_APIC_REG_SIZE];
};

Copies the input argument into the Local APIC registers.  The data format
and layout are the same as documented in the architecture manual.

The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
See the note in KVM_GET_LAPIC.


4.59 KVM_IOEVENTFD

Capability: KVM_CAP_IOEVENTFD
Architectures: all
Type: vm ioctl
Parameters: struct kvm_ioeventfd (in)
Returns: 0 on success, !0 on error

This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
within the guest.  A guest write in the registered address will signal the
provided event instead of triggering an exit.

struct kvm_ioeventfd {
	__u64 datamatch;
	__u64 addr;        /* legal pio/mmio address */
	__u32 len;         /* 0, 1, 2, 4, or 8 bytes    */
	__s32 fd;
	__u32 flags;
	__u8  pad[36];
};

For the special case of virtio-ccw devices on s390, the ioevent is matched
to a subchannel/virtqueue tuple instead.

The following flags are defined:

#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
#define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
#define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
	(1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)

If datamatch flag is set, the event will be signaled only if the written value
to the registered address is equal to datamatch in struct kvm_ioeventfd.

For virtio-ccw devices, addr contains the subchannel id and datamatch the
virtqueue index.

With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
the kernel will ignore the length of guest write and may get a faster vmexit.
The speedup may only apply to specific architectures, but the ioeventfd will
work anyway.

4.60 KVM_DIRTY_TLB

Capability: KVM_CAP_SW_TLB
Architectures: ppc
Type: vcpu ioctl
Parameters: struct kvm_dirty_tlb (in)
Returns: 0 on success, -1 on error

struct kvm_dirty_tlb {
	__u64 bitmap;
	__u32 num_dirty;
};

This must be called whenever userspace has changed an entry in the shared
TLB, prior to calling KVM_RUN on the associated vcpu.

The "bitmap" field is the userspace address of an array.  This array
consists of a number of bits, equal to the total number of TLB entries as
determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
nearest multiple of 64.

Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
array.

The array is little-endian: the bit 0 is the least significant bit of the
first byte, bit 8 is the least significant bit of the second byte, etc.
This avoids any complications with differing word sizes.

The "num_dirty" field is a performance hint for KVM to determine whether it
should skip processing the bitmap and just invalidate everything.  It must
be set to the number of set bits in the bitmap.


4.62 KVM_CREATE_SPAPR_TCE

Capability: KVM_CAP_SPAPR_TCE
Architectures: powerpc
Type: vm ioctl
Parameters: struct kvm_create_spapr_tce (in)
Returns: file descriptor for manipulating the created TCE table

This creates a virtual TCE (translation control entry) table, which
is an IOMMU for PAPR-style virtual I/O.  It is used to translate
logical addresses used in virtual I/O into guest physical addresses,
and provides a scatter/gather capability for PAPR virtual I/O.

/* for KVM_CAP_SPAPR_TCE */
struct kvm_create_spapr_tce {
	__u64 liobn;
	__u32 window_size;
};

The liobn field gives the logical IO bus number for which to create a
TCE table.  The window_size field specifies the size of the DMA window
which this TCE table will translate - the table will contain one 64
bit TCE entry for every 4kiB of the DMA window.

When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
table has been created using this ioctl(), the kernel will handle it
in real mode, updating the TCE table.  H_PUT_TCE calls for other
liobns will cause a vm exit and must be handled by userspace.

The return value is a file descriptor which can be passed to mmap(2)
to map the created TCE table into userspace.  This lets userspace read
the entries written by kernel-handled H_PUT_TCE calls, and also lets
userspace update the TCE table directly which is useful in some
circumstances.


4.63 KVM_ALLOCATE_RMA

Capability: KVM_CAP_PPC_RMA
Architectures: powerpc
Type: vm ioctl
Parameters: struct kvm_allocate_rma (out)
Returns: file descriptor for mapping the allocated RMA

This allocates a Real Mode Area (RMA) from the pool allocated at boot
time by the kernel.  An RMA is a physically-contiguous, aligned region
of memory used on older POWER processors to provide the memory which
will be accessed by real-mode (MMU off) accesses in a KVM guest.
POWER processors support a set of sizes for the RMA that usually
includes 64MB, 128MB, 256MB and some larger powers of two.

/* for KVM_ALLOCATE_RMA */
struct kvm_allocate_rma {
	__u64 rma_size;
};

The return value is a file descriptor which can be passed to mmap(2)
to map the allocated RMA into userspace.  The mapped area can then be
passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
RMA for a virtual machine.  The size of the RMA in bytes (which is
fixed at host kernel boot time) is returned in the rma_size field of
the argument structure.

The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
is supported; 2 if the processor requires all virtual machines to have
an RMA, or 1 if the processor can use an RMA but doesn't require it,
because it supports the Virtual RMA (VRMA) facility.


4.64 KVM_NMI

Capability: KVM_CAP_USER_NMI
Architectures: x86
Type: vcpu ioctl
Parameters: none
Returns: 0 on success, -1 on error

Queues an NMI on the thread's vcpu.  Note this is well defined only
when KVM_CREATE_IRQCHIP has not been called, since this is an interface
between the virtual cpu core and virtual local APIC.  After KVM_CREATE_IRQCHIP
has been called, this interface is completely emulated within the kernel.

To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
following algorithm:

  - pause the vcpu
  - read the local APIC's state (KVM_GET_LAPIC)
  - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
  - if so, issue KVM_NMI
  - resume the vcpu

Some guests configure the LINT1 NMI input to cause a panic, aiding in
debugging.


4.65 KVM_S390_UCAS_MAP

Capability: KVM_CAP_S390_UCONTROL
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_ucas_mapping (in)
Returns: 0 in case of success

The parameter is defined like this:
	struct kvm_s390_ucas_mapping {
		__u64 user_addr;
		__u64 vcpu_addr;
		__u64 length;
	};

This ioctl maps the memory at "user_addr" with the length "length" to
the vcpu's address space starting at "vcpu_addr". All parameters need to
be aligned by 1 megabyte.


4.66 KVM_S390_UCAS_UNMAP

Capability: KVM_CAP_S390_UCONTROL
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_ucas_mapping (in)
Returns: 0 in case of success

The parameter is defined like this:
	struct kvm_s390_ucas_mapping {
		__u64 user_addr;
		__u64 vcpu_addr;
		__u64 length;
	};

This ioctl unmaps the memory in the vcpu's address space starting at
"vcpu_addr" with the length "length". The field "user_addr" is ignored.
All parameters need to be aligned by 1 megabyte.


4.67 KVM_S390_VCPU_FAULT

Capability: KVM_CAP_S390_UCONTROL
Architectures: s390
Type: vcpu ioctl
Parameters: vcpu absolute address (in)
Returns: 0 in case of success

This call creates a page table entry on the virtual cpu's address space
(for user controlled virtual machines) or the virtual machine's address
space (for regular virtual machines). This only works for minor faults,
thus it's recommended to access subject memory page via the user page
table upfront. This is useful to handle validity intercepts for user
controlled virtual machines to fault in the virtual cpu's lowcore pages
prior to calling the KVM_RUN ioctl.


4.68 KVM_SET_ONE_REG

Capability: KVM_CAP_ONE_REG
Architectures: all
Type: vcpu ioctl
Parameters: struct kvm_one_reg (in)
Returns: 0 on success, negative value on failure

struct kvm_one_reg {
       __u64 id;
       __u64 addr;
};

Using this ioctl, a single vcpu register can be set to a specific value
defined by user space with the passed in struct kvm_one_reg, where id
refers to the register identifier as described below and addr is a pointer
to a variable with the respective size. There can be architecture agnostic
and architecture specific registers. Each have their own range of operation
and their own constants and width. To keep track of the implemented
registers, find a list below:

  Arch  |           Register            | Width (bits)
        |                               |
  PPC   | KVM_REG_PPC_HIOR              | 64
  PPC   | KVM_REG_PPC_IAC1              | 64
  PPC   | KVM_REG_PPC_IAC2              | 64
  PPC   | KVM_REG_PPC_IAC3              | 64
  PPC   | KVM_REG_PPC_IAC4              | 64
  PPC   | KVM_REG_PPC_DAC1              | 64
  PPC   | KVM_REG_PPC_DAC2              | 64
  PPC   | KVM_REG_PPC_DABR              | 64
  PPC   | KVM_REG_PPC_DSCR              | 64
  PPC   | KVM_REG_PPC_PURR              | 64
  PPC   | KVM_REG_PPC_SPURR             | 64
  PPC   | KVM_REG_PPC_DAR               | 64
  PPC   | KVM_REG_PPC_DSISR             | 32
  PPC   | KVM_REG_PPC_AMR               | 64
  PPC   | KVM_REG_PPC_UAMOR             | 64
  PPC   | KVM_REG_PPC_MMCR0             | 64
  PPC   | KVM_REG_PPC_MMCR1             | 64
  PPC   | KVM_REG_PPC_MMCRA             | 64
  PPC   | KVM_REG_PPC_MMCR2             | 64
  PPC   | KVM_REG_PPC_MMCRS             | 64
  PPC   | KVM_REG_PPC_SIAR              | 64
  PPC   | KVM_REG_PPC_SDAR              | 64
  PPC   | KVM_REG_PPC_SIER              | 64
  PPC   | KVM_REG_PPC_PMC1              | 32
  PPC   | KVM_REG_PPC_PMC2              | 32
  PPC   | KVM_REG_PPC_PMC3              | 32
  PPC   | KVM_REG_PPC_PMC4              | 32
  PPC   | KVM_REG_PPC_PMC5              | 32
  PPC   | KVM_REG_PPC_PMC6              | 32
  PPC   | KVM_REG_PPC_PMC7              | 32
  PPC   | KVM_REG_PPC_PMC8              | 32
  PPC   | KVM_REG_PPC_FPR0              | 64
          ...
  PPC   | KVM_REG_PPC_FPR31             | 64
  PPC   | KVM_REG_PPC_VR0               | 128
          ...
  PPC   | KVM_REG_PPC_VR31              | 128
  PPC   | KVM_REG_PPC_VSR0              | 128
          ...
  PPC   | KVM_REG_PPC_VSR31             | 128
  PPC   | KVM_REG_PPC_FPSCR             | 64
  PPC   | KVM_REG_PPC_VSCR              | 32
  PPC   | KVM_REG_PPC_VPA_ADDR          | 64
  PPC   | KVM_REG_PPC_VPA_SLB           | 128
  PPC   | KVM_REG_PPC_VPA_DTL           | 128
  PPC   | KVM_REG_PPC_EPCR              | 32
  PPC   | KVM_REG_PPC_EPR               | 32
  PPC   | KVM_REG_PPC_TCR               | 32
  PPC   | KVM_REG_PPC_TSR               | 32
  PPC   | KVM_REG_PPC_OR_TSR            | 32
  PPC   | KVM_REG_PPC_CLEAR_TSR         | 32
  PPC   | KVM_REG_PPC_MAS0              | 32
  PPC   | KVM_REG_PPC_MAS1              | 32
  PPC   | KVM_REG_PPC_MAS2              | 64
  PPC   | KVM_REG_PPC_MAS7_3            | 64
  PPC   | KVM_REG_PPC_MAS4              | 32
  PPC   | KVM_REG_PPC_MAS6              | 32
  PPC   | KVM_REG_PPC_MMUCFG            | 32
  PPC   | KVM_REG_PPC_TLB0CFG           | 32
  PPC   | KVM_REG_PPC_TLB1CFG           | 32
  PPC   | KVM_REG_PPC_TLB2CFG           | 32
  PPC   | KVM_REG_PPC_TLB3CFG           | 32
  PPC   | KVM_REG_PPC_TLB0PS            | 32
  PPC   | KVM_REG_PPC_TLB1PS            | 32
  PPC   | KVM_REG_PPC_TLB2PS            | 32
  PPC   | KVM_REG_PPC_TLB3PS            | 32
  PPC   | KVM_REG_PPC_EPTCFG            | 32
  PPC   | KVM_REG_PPC_ICP_STATE         | 64
  PPC   | KVM_REG_PPC_TB_OFFSET         | 64
  PPC   | KVM_REG_PPC_SPMC1             | 32
  PPC   | KVM_REG_PPC_SPMC2             | 32
  PPC   | KVM_REG_PPC_IAMR              | 64
  PPC   | KVM_REG_PPC_TFHAR             | 64
  PPC   | KVM_REG_PPC_TFIAR             | 64
  PPC   | KVM_REG_PPC_TEXASR            | 64
  PPC   | KVM_REG_PPC_FSCR              | 64
  PPC   | KVM_REG_PPC_PSPB              | 32
  PPC   | KVM_REG_PPC_EBBHR             | 64
  PPC   | KVM_REG_PPC_EBBRR             | 64
  PPC   | KVM_REG_PPC_BESCR             | 64
  PPC   | KVM_REG_PPC_TAR               | 64
  PPC   | KVM_REG_PPC_DPDES             | 64
  PPC   | KVM_REG_PPC_DAWR              | 64
  PPC   | KVM_REG_PPC_DAWRX             | 64
  PPC   | KVM_REG_PPC_CIABR             | 64
  PPC   | KVM_REG_PPC_IC                | 64
  PPC   | KVM_REG_PPC_VTB               | 64
  PPC   | KVM_REG_PPC_CSIGR             | 64
  PPC   | KVM_REG_PPC_TACR              | 64
  PPC   | KVM_REG_PPC_TCSCR             | 64
  PPC   | KVM_REG_PPC_PID               | 64
  PPC   | KVM_REG_PPC_ACOP              | 64
  PPC   | KVM_REG_PPC_VRSAVE            | 32
  PPC   | KVM_REG_PPC_LPCR              | 32
  PPC   | KVM_REG_PPC_LPCR_64           | 64
  PPC   | KVM_REG_PPC_PPR               | 64
  PPC   | KVM_REG_PPC_ARCH_COMPAT       | 32
  PPC   | KVM_REG_PPC_DABRX             | 32
  PPC   | KVM_REG_PPC_WORT              | 64
  PPC	| KVM_REG_PPC_SPRG9             | 64
  PPC	| KVM_REG_PPC_DBSR              | 32
  PPC   | KVM_REG_PPC_TIDR              | 64
  PPC   | KVM_REG_PPC_PSSCR             | 64
  PPC   | KVM_REG_PPC_TM_GPR0           | 64
          ...
  PPC   | KVM_REG_PPC_TM_GPR31          | 64
  PPC   | KVM_REG_PPC_TM_VSR0           | 128
          ...
  PPC   | KVM_REG_PPC_TM_VSR63          | 128
  PPC   | KVM_REG_PPC_TM_CR             | 64
  PPC   | KVM_REG_PPC_TM_LR             | 64
  PPC   | KVM_REG_PPC_TM_CTR            | 64
  PPC   | KVM_REG_PPC_TM_FPSCR          | 64
  PPC   | KVM_REG_PPC_TM_AMR            | 64
  PPC   | KVM_REG_PPC_TM_PPR            | 64
  PPC   | KVM_REG_PPC_TM_VRSAVE         | 64
  PPC   | KVM_REG_PPC_TM_VSCR           | 32
  PPC   | KVM_REG_PPC_TM_DSCR           | 64
  PPC   | KVM_REG_PPC_TM_TAR            | 64
  PPC   | KVM_REG_PPC_TM_XER            | 64
        |                               |
  MIPS  | KVM_REG_MIPS_R0               | 64
          ...
  MIPS  | KVM_REG_MIPS_R31              | 64
  MIPS  | KVM_REG_MIPS_HI               | 64
  MIPS  | KVM_REG_MIPS_LO               | 64
  MIPS  | KVM_REG_MIPS_PC               | 64
  MIPS  | KVM_REG_MIPS_CP0_INDEX        | 32
  MIPS  | KVM_REG_MIPS_CP0_ENTRYLO0     | 64
  MIPS  | KVM_REG_MIPS_CP0_ENTRYLO1     | 64
  MIPS  | KVM_REG_MIPS_CP0_CONTEXT      | 64
  MIPS  | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32
  MIPS  | KVM_REG_MIPS_CP0_USERLOCAL    | 64
  MIPS  | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64
  MIPS  | KVM_REG_MIPS_CP0_PAGEMASK     | 32
  MIPS  | KVM_REG_MIPS_CP0_PAGEGRAIN    | 32
  MIPS  | KVM_REG_MIPS_CP0_SEGCTL0      | 64
  MIPS  | KVM_REG_MIPS_CP0_SEGCTL1      | 64
  MIPS  | KVM_REG_MIPS_CP0_SEGCTL2      | 64
  MIPS  | KVM_REG_MIPS_CP0_PWBASE       | 64
  MIPS  | KVM_REG_MIPS_CP0_PWFIELD      | 64
  MIPS  | KVM_REG_MIPS_CP0_PWSIZE       | 64
  MIPS  | KVM_REG_MIPS_CP0_WIRED        | 32
  MIPS  | KVM_REG_MIPS_CP0_PWCTL        | 32
  MIPS  | KVM_REG_MIPS_CP0_HWRENA       | 32
  MIPS  | KVM_REG_MIPS_CP0_BADVADDR     | 64
  MIPS  | KVM_REG_MIPS_CP0_BADINSTR     | 32
  MIPS  | KVM_REG_MIPS_CP0_BADINSTRP    | 32
  MIPS  | KVM_REG_MIPS_CP0_COUNT        | 32
  MIPS  | KVM_REG_MIPS_CP0_ENTRYHI      | 64
  MIPS  | KVM_REG_MIPS_CP0_COMPARE      | 32
  MIPS  | KVM_REG_MIPS_CP0_STATUS       | 32
  MIPS  | KVM_REG_MIPS_CP0_INTCTL       | 32
  MIPS  | KVM_REG_MIPS_CP0_CAUSE        | 32
  MIPS  | KVM_REG_MIPS_CP0_EPC          | 64
  MIPS  | KVM_REG_MIPS_CP0_PRID         | 32
  MIPS  | KVM_REG_MIPS_CP0_EBASE        | 64
  MIPS  | KVM_REG_MIPS_CP0_CONFIG       | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG1      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG2      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG3      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG4      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG5      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG7      | 32
  MIPS  | KVM_REG_MIPS_CP0_XCONTEXT     | 64
  MIPS  | KVM_REG_MIPS_CP0_ERROREPC     | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH1    | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH2    | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH3    | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH4    | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH5    | 64
  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH6    | 64
  MIPS  | KVM_REG_MIPS_CP0_MAAR(0..63)  | 64
  MIPS  | KVM_REG_MIPS_COUNT_CTL        | 64
  MIPS  | KVM_REG_MIPS_COUNT_RESUME     | 64
  MIPS  | KVM_REG_MIPS_COUNT_HZ         | 64
  MIPS  | KVM_REG_MIPS_FPR_32(0..31)    | 32
  MIPS  | KVM_REG_MIPS_FPR_64(0..31)    | 64
  MIPS  | KVM_REG_MIPS_VEC_128(0..31)   | 128
  MIPS  | KVM_REG_MIPS_FCR_IR           | 32
  MIPS  | KVM_REG_MIPS_FCR_CSR          | 32
  MIPS  | KVM_REG_MIPS_MSA_IR           | 32
  MIPS  | KVM_REG_MIPS_MSA_CSR          | 32

ARM registers are mapped using the lower 32 bits.  The upper 16 of that
is the register group type, or coprocessor number:

ARM core registers have the following id bit patterns:
  0x4020 0000 0010 <index into the kvm_regs struct:16>

ARM 32-bit CP15 registers have the following id bit patterns:
  0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>

ARM 64-bit CP15 registers have the following id bit patterns:
  0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>

ARM CCSIDR registers are demultiplexed by CSSELR value:
  0x4020 0000 0011 00 <csselr:8>

ARM 32-bit VFP control registers have the following id bit patterns:
  0x4020 0000 0012 1 <regno:12>

ARM 64-bit FP registers have the following id bit patterns:
  0x4030 0000 0012 0 <regno:12>


arm64 registers are mapped using the lower 32 bits. The upper 16 of
that is the register group type, or coprocessor number:

arm64 core/FP-SIMD registers have the following id bit patterns. Note
that the size of the access is variable, as the kvm_regs structure
contains elements ranging from 32 to 128 bits. The index is a 32bit
value in the kvm_regs structure seen as a 32bit array.
  0x60x0 0000 0010 <index into the kvm_regs struct:16>

arm64 CCSIDR registers are demultiplexed by CSSELR value:
  0x6020 0000 0011 00 <csselr:8>

arm64 system registers have the following id bit patterns:
  0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>


MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
the register group type:

MIPS core registers (see above) have the following id bit patterns:
  0x7030 0000 0000 <reg:16>

MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
patterns depending on whether they're 32-bit or 64-bit registers:
  0x7020 0000 0001 00 <reg:5> <sel:3>   (32-bit)
  0x7030 0000 0001 00 <reg:5> <sel:3>   (64-bit)

Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64
versions of the EntryLo registers regardless of the word size of the host
hardware, host kernel, guest, and whether XPA is present in the guest, i.e.
with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and
the PFNX field starting at bit 30.

MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit
patterns:
  0x7030 0000 0001 01 <reg:8>

MIPS KVM control registers (see above) have the following id bit patterns:
  0x7030 0000 0002 <reg:16>

MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
id bit patterns depending on the size of the register being accessed. They are
always accessed according to the current guest FPU mode (Status.FR and
Config5.FRE), i.e. as the guest would see them, and they become unpredictable
if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
overlap the FPU registers:
  0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
  0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
  0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)

MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
following id bit patterns:
  0x7020 0000 0003 01 <0:3> <reg:5>

MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
following id bit patterns:
  0x7020 0000 0003 02 <0:3> <reg:5>


4.69 KVM_GET_ONE_REG

Capability: KVM_CAP_ONE_REG
Architectures: all
Type: vcpu ioctl
Parameters: struct kvm_one_reg (in and out)
Returns: 0 on success, negative value on failure

This ioctl allows to receive the value of a single register implemented
in a vcpu. The register to read is indicated by the "id" field of the
kvm_one_reg struct passed in. On success, the register value can be found
at the memory location pointed to by "addr".

The list of registers accessible using this interface is identical to the
list in 4.68.


4.70 KVM_KVMCLOCK_CTRL

Capability: KVM_CAP_KVMCLOCK_CTRL
Architectures: Any that implement pvclocks (currently x86 only)
Type: vcpu ioctl
Parameters: None
Returns: 0 on success, -1 on error

This signals to the host kernel that the specified guest is being paused by
userspace.  The host will set a flag in the pvclock structure that is checked
from the soft lockup watchdog.  The flag is part of the pvclock structure that
is shared between guest and host, specifically the second bit of the flags
field of the pvclock_vcpu_time_info structure.  It will be set exclusively by
the host and read/cleared exclusively by the guest.  The guest operation of
checking and clearing the flag must an atomic operation so
load-link/store-conditional, or equivalent must be used.  There are two cases
where the guest will clear the flag: when the soft lockup watchdog timer resets
itself or when a soft lockup is detected.  This ioctl can be called any time
after pausing the vcpu, but before it is resumed.


4.71 KVM_SIGNAL_MSI

Capability: KVM_CAP_SIGNAL_MSI
Architectures: x86 arm arm64
Type: vm ioctl
Parameters: struct kvm_msi (in)
Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error

Directly inject a MSI message. Only valid with in-kernel irqchip that handles
MSI messages.

struct kvm_msi {
	__u32 address_lo;
	__u32 address_hi;
	__u32 data;
	__u32 flags;
	__u32 devid;
	__u8  pad[12];
};

flags: KVM_MSI_VALID_DEVID: devid contains a valid value.  The per-VM
  KVM_CAP_MSI_DEVID capability advertises the requirement to provide
  the device ID.  If this capability is not available, userspace
  should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.

If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
for the device that wrote the MSI message.  For PCI, this is usually a
BFD identifier in the lower 16 bits.

On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
address_hi must be zero.


4.71 KVM_CREATE_PIT2

Capability: KVM_CAP_PIT2
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_pit_config (in)
Returns: 0 on success, -1 on error

Creates an in-kernel device model for the i8254 PIT. This call is only valid
after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
parameters have to be passed:

struct kvm_pit_config {
	__u32 flags;
	__u32 pad[15];
};

Valid flags are:

#define KVM_PIT_SPEAKER_DUMMY     1 /* emulate speaker port stub */

PIT timer interrupts may use a per-VM kernel thread for injection. If it
exists, this thread will have a name of the following pattern:

kvm-pit/<owner-process-pid>

When running a guest with elevated priorities, the scheduling parameters of
this thread may have to be adjusted accordingly.

This IOCTL replaces the obsolete KVM_CREATE_PIT.


4.72 KVM_GET_PIT2

Capability: KVM_CAP_PIT_STATE2
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_pit_state2 (out)
Returns: 0 on success, -1 on error

Retrieves the state of the in-kernel PIT model. Only valid after
KVM_CREATE_PIT2. The state is returned in the following structure:

struct kvm_pit_state2 {
	struct kvm_pit_channel_state channels[3];
	__u32 flags;
	__u32 reserved[9];
};

Valid flags are:

/* disable PIT in HPET legacy mode */
#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001

This IOCTL replaces the obsolete KVM_GET_PIT.


4.73 KVM_SET_PIT2

Capability: KVM_CAP_PIT_STATE2
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_pit_state2 (in)
Returns: 0 on success, -1 on error

Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
See KVM_GET_PIT2 for details on struct kvm_pit_state2.

This IOCTL replaces the obsolete KVM_SET_PIT.


4.74 KVM_PPC_GET_SMMU_INFO

Capability: KVM_CAP_PPC_GET_SMMU_INFO
Architectures: powerpc
Type: vm ioctl
Parameters: None
Returns: 0 on success, -1 on error

This populates and returns a structure describing the features of
the "Server" class MMU emulation supported by KVM.
This can in turn be used by userspace to generate the appropriate
device-tree properties for the guest operating system.

The structure contains some global information, followed by an
array of supported segment page sizes:

      struct kvm_ppc_smmu_info {
	     __u64 flags;
	     __u32 slb_size;
	     __u32 pad;
	     struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
      };

The supported flags are:

    - KVM_PPC_PAGE_SIZES_REAL:
        When that flag is set, guest page sizes must "fit" the backing
        store page sizes. When not set, any page size in the list can
        be used regardless of how they are backed by userspace.

    - KVM_PPC_1T_SEGMENTS
        The emulated MMU supports 1T segments in addition to the
        standard 256M ones.

The "slb_size" field indicates how many SLB entries are supported

The "sps" array contains 8 entries indicating the supported base
page sizes for a segment in increasing order. Each entry is defined
as follow:

   struct kvm_ppc_one_seg_page_size {
	__u32 page_shift;	/* Base page shift of segment (or 0) */
	__u32 slb_enc;		/* SLB encoding for BookS */
	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
   };

An entry with a "page_shift" of 0 is unused. Because the array is
organized in increasing order, a lookup can stop when encoutering
such an entry.

The "slb_enc" field provides the encoding to use in the SLB for the
page size. The bits are in positions such as the value can directly
be OR'ed into the "vsid" argument of the slbmte instruction.

The "enc" array is a list which for each of those segment base page
size provides the list of supported actual page sizes (which can be
only larger or equal to the base page size), along with the
corresponding encoding in the hash PTE. Similarly, the array is
8 entries sorted by increasing sizes and an entry with a "0" shift
is an empty entry and a terminator:

   struct kvm_ppc_one_page_size {
	__u32 page_shift;	/* Page shift (or 0) */
	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
   };

The "pte_enc" field provides a value that can OR'ed into the hash
PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
into the hash PTE second double word).

4.75 KVM_IRQFD

Capability: KVM_CAP_IRQFD
Architectures: x86 s390 arm arm64
Type: vm ioctl
Parameters: struct kvm_irqfd (in)
Returns: 0 on success, -1 on error

Allows setting an eventfd to directly trigger a guest interrupt.
kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
kvm_irqfd.gsi specifies the irqchip pin toggled by this event.  When
an event is triggered on the eventfd, an interrupt is injected into
the guest using the specified gsi pin.  The irqfd is removed using
the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
and kvm_irqfd.gsi.

With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
mechanism allowing emulation of level-triggered, irqfd-based
interrupts.  When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
additional eventfd in the kvm_irqfd.resamplefd field.  When operating
in resample mode, posting of an interrupt through kvm_irq.fd asserts
the specified gsi in the irqchip.  When the irqchip is resampled, such
as from an EOI, the gsi is de-asserted and the user is notified via
kvm_irqfd.resamplefd.  It is the user's responsibility to re-queue
the interrupt if the device making use of it still requires service.
Note that closing the resamplefd is not sufficient to disable the
irqfd.  The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.

On arm/arm64, gsi routing being supported, the following can happen:
- in case no routing entry is associated to this gsi, injection fails
- in case the gsi is associated to an irqchip routing entry,
  irqchip.pin + 32 corresponds to the injected SPI ID.
- in case the gsi is associated to an MSI routing entry, the MSI
  message and device ID are translated into an LPI (support restricted
  to GICv3 ITS in-kernel emulation).

4.76 KVM_PPC_ALLOCATE_HTAB

Capability: KVM_CAP_PPC_ALLOC_HTAB
Architectures: powerpc
Type: vm ioctl
Parameters: Pointer to u32 containing hash table order (in/out)
Returns: 0 on success, -1 on error

This requests the host kernel to allocate an MMU hash table for a
guest using the PAPR paravirtualization interface.  This only does
anything if the kernel is configured to use the Book 3S HV style of
virtualization.  Otherwise the capability doesn't exist and the ioctl
returns an ENOTTY error.  The rest of this description assumes Book 3S
HV.

There must be no vcpus running when this ioctl is called; if there
are, it will do nothing and return an EBUSY error.

The parameter is a pointer to a 32-bit unsigned integer variable
containing the order (log base 2) of the desired size of the hash
table, which must be between 18 and 46.  On successful return from the
ioctl, the value will not be changed by the kernel.

If no hash table has been allocated when any vcpu is asked to run
(with the KVM_RUN ioctl), the host kernel will allocate a
default-sized hash table (16 MB).

If this ioctl is called when a hash table has already been allocated,
with a different order from the existing hash table, the existing hash
table will be freed and a new one allocated.  If this is ioctl is
called when a hash table has already been allocated of the same order
as specified, the kernel will clear out the existing hash table (zero
all HPTEs).  In either case, if the guest is using the virtualized
real-mode area (VRMA) facility, the kernel will re-create the VMRA
HPTEs on the next KVM_RUN of any vcpu.

4.77 KVM_S390_INTERRUPT

Capability: basic
Architectures: s390
Type: vm ioctl, vcpu ioctl
Parameters: struct kvm_s390_interrupt (in)
Returns: 0 on success, -1 on error

Allows to inject an interrupt to the guest. Interrupts can be floating
(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.

Interrupt parameters are passed via kvm_s390_interrupt:

struct kvm_s390_interrupt {
	__u32 type;
	__u32 parm;
	__u64 parm64;
};

type can be one of the following:

KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
KVM_S390_RESTART (vcpu) - restart
KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
			   parameters in parm and parm64
KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
    I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
    I/O interruption parameters in parm (subchannel) and parm64 (intparm,
    interruption subclass)
KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
                           machine check interrupt code in parm64 (note that
                           machine checks needing further payload are not
                           supported by this ioctl)

Note that the vcpu ioctl is asynchronous to vcpu execution.

4.78 KVM_PPC_GET_HTAB_FD

Capability: KVM_CAP_PPC_HTAB_FD
Architectures: powerpc
Type: vm ioctl
Parameters: Pointer to struct kvm_get_htab_fd (in)
Returns: file descriptor number (>= 0) on success, -1 on error

This returns a file descriptor that can be used either to read out the
entries in the guest's hashed page table (HPT), or to write entries to
initialize the HPT.  The returned fd can only be written to if the
KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
can only be read if that bit is clear.  The argument struct looks like
this:

/* For KVM_PPC_GET_HTAB_FD */
struct kvm_get_htab_fd {
	__u64	flags;
	__u64	start_index;
	__u64	reserved[2];
};

/* Values for kvm_get_htab_fd.flags */
#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
#define KVM_GET_HTAB_WRITE		((__u64)0x2)

The `start_index' field gives the index in the HPT of the entry at
which to start reading.  It is ignored when writing.

Reads on the fd will initially supply information about all
"interesting" HPT entries.  Interesting entries are those with the
bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
all entries.  When the end of the HPT is reached, the read() will
return.  If read() is called again on the fd, it will start again from
the beginning of the HPT, but will only return HPT entries that have
changed since they were last read.

Data read or written is structured as a header (8 bytes) followed by a
series of valid HPT entries (16 bytes) each.  The header indicates how
many valid HPT entries there are and how many invalid entries follow
the valid entries.  The invalid entries are not represented explicitly
in the stream.  The header format is:

struct kvm_get_htab_header {
	__u32	index;
	__u16	n_valid;
	__u16	n_invalid;
};

Writes to the fd create HPT entries starting at the index given in the
header; first `n_valid' valid entries with contents from the data
written, then `n_invalid' invalid entries, invalidating any previously
valid entries found.

4.79 KVM_CREATE_DEVICE

Capability: KVM_CAP_DEVICE_CTRL
Type: vm ioctl
Parameters: struct kvm_create_device (in/out)
Returns: 0 on success, -1 on error
Errors:
  ENODEV: The device type is unknown or unsupported
  EEXIST: Device already created, and this type of device may not
          be instantiated multiple times

  Other error conditions may be defined by individual device types or
  have their standard meanings.

Creates an emulated device in the kernel.  The file descriptor returned
in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.

If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
device type is supported (not necessarily whether it can be created
in the current vm).

Individual devices should not define flags.  Attributes should be used
for specifying any behavior that is not implied by the device type
number.

struct kvm_create_device {
	__u32	type;	/* in: KVM_DEV_TYPE_xxx */
	__u32	fd;	/* out: device handle */
	__u32	flags;	/* in: KVM_CREATE_DEVICE_xxx */
};

4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR

Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
Type: device ioctl, vm ioctl, vcpu ioctl
Parameters: struct kvm_device_attr
Returns: 0 on success, -1 on error
Errors:
  ENXIO:  The group or attribute is unknown/unsupported for this device
          or hardware support is missing.
  EPERM:  The attribute cannot (currently) be accessed this way
          (e.g. read-only attribute, or attribute that only makes
          sense when the device is in a different state)

  Other error conditions may be defined by individual device types.

Gets/sets a specified piece of device configuration and/or state.  The
semantics are device-specific.  See individual device documentation in
the "devices" directory.  As with ONE_REG, the size of the data
transferred is defined by the particular attribute.

struct kvm_device_attr {
	__u32	flags;		/* no flags currently defined */
	__u32	group;		/* device-defined */
	__u64	attr;		/* group-defined */
	__u64	addr;		/* userspace address of attr data */
};

4.81 KVM_HAS_DEVICE_ATTR

Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
Type: device ioctl, vm ioctl, vcpu ioctl
Parameters: struct kvm_device_attr
Returns: 0 on success, -1 on error
Errors:
  ENXIO:  The group or attribute is unknown/unsupported for this device
          or hardware support is missing.

Tests whether a device supports a particular attribute.  A successful
return indicates the attribute is implemented.  It does not necessarily
indicate that the attribute can be read or written in the device's
current state.  "addr" is ignored.

4.82 KVM_ARM_VCPU_INIT

Capability: basic
Architectures: arm, arm64
Type: vcpu ioctl
Parameters: struct kvm_vcpu_init (in)
Returns: 0 on success; -1 on error
Errors:
  EINVAL:    the target is unknown, or the combination of features is invalid.
  ENOENT:    a features bit specified is unknown.

This tells KVM what type of CPU to present to the guest, and what
optional features it should have.  This will cause a reset of the cpu
registers to their initial values.  If this is not called, KVM_RUN will
return ENOEXEC for that vcpu.

Note that because some registers reflect machine topology, all vcpus
should be created before this ioctl is invoked.

Userspace can call this function multiple times for a given vcpu, including
after the vcpu has been run. This will reset the vcpu to its initial
state. All calls to this function after the initial call must use the same
target and same set of feature flags, otherwise EINVAL will be returned.

Possible features:
	- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
	  Depends on KVM_CAP_ARM_PSCI.  If not set, the CPU will be powered on
	  and execute guest code when KVM_RUN is called.
	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
	  Depends on KVM_CAP_ARM_PSCI_0_2.
	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
	  Depends on KVM_CAP_ARM_PMU_V3.


4.83 KVM_ARM_PREFERRED_TARGET

Capability: basic
Architectures: arm, arm64
Type: vm ioctl
Parameters: struct struct kvm_vcpu_init (out)
Returns: 0 on success; -1 on error
Errors:
  ENODEV:    no preferred target available for the host

This queries KVM for preferred CPU target type which can be emulated
by KVM on underlying host.

The ioctl returns struct kvm_vcpu_init instance containing information
about preferred CPU target type and recommended features for it.  The
kvm_vcpu_init->features bitmap returned will have feature bits set if
the preferred target recommends setting these features, but this is
not mandatory.

The information returned by this ioctl can be used to prepare an instance
of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
in VCPU matching underlying host.


4.84 KVM_GET_REG_LIST

Capability: basic
Architectures: arm, arm64, mips
Type: vcpu ioctl
Parameters: struct kvm_reg_list (in/out)
Returns: 0 on success; -1 on error
Errors:
  E2BIG:     the reg index list is too big to fit in the array specified by
             the user (the number required will be written into n).

struct kvm_reg_list {
	__u64 n; /* number of registers in reg[] */
	__u64 reg[0];
};

This ioctl returns the guest registers that are supported for the
KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.


4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)

Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
Architectures: arm, arm64
Type: vm ioctl
Parameters: struct kvm_arm_device_address (in)
Returns: 0 on success, -1 on error
Errors:
  ENODEV: The device id is unknown
  ENXIO:  Device not supported on current system
  EEXIST: Address already set
  E2BIG:  Address outside guest physical address space
  EBUSY:  Address overlaps with other device range

struct kvm_arm_device_addr {
	__u64 id;
	__u64 addr;
};

Specify a device address in the guest's physical address space where guests
can access emulated or directly exposed devices, which the host kernel needs
to know about. The id field is an architecture specific identifier for a
specific device.

ARM/arm64 divides the id field into two parts, a device id and an
address type id specific to the individual device.

  bits:  | 63        ...       32 | 31    ...    16 | 15    ...    0 |
  field: |        0x00000000      |     device id   |  addr type id  |

ARM/arm64 currently only require this when using the in-kernel GIC
support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
as the device id.  When setting the base address for the guest's
mapping of the VGIC virtual CPU and distributor interface, the ioctl
must be called after calling KVM_CREATE_IRQCHIP, but before calling
KVM_RUN on any of the VCPUs.  Calling this ioctl twice for any of the
base addresses will return -EEXIST.

Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
should be used instead.


4.86 KVM_PPC_RTAS_DEFINE_TOKEN

Capability: KVM_CAP_PPC_RTAS
Architectures: ppc
Type: vm ioctl
Parameters: struct kvm_rtas_token_args
Returns: 0 on success, -1 on error

Defines a token value for a RTAS (Run Time Abstraction Services)
service in order to allow it to be handled in the kernel.  The
argument struct gives the name of the service, which must be the name
of a service that has a kernel-side implementation.  If the token
value is non-zero, it will be associated with that service, and
subsequent RTAS calls by the guest specifying that token will be
handled by the kernel.  If the token value is 0, then any token
associated with the service will be forgotten, and subsequent RTAS
calls by the guest for that service will be passed to userspace to be
handled.

4.87 KVM_SET_GUEST_DEBUG

Capability: KVM_CAP_SET_GUEST_DEBUG
Architectures: x86, s390, ppc, arm64
Type: vcpu ioctl
Parameters: struct kvm_guest_debug (in)
Returns: 0 on success; -1 on error

struct kvm_guest_debug {
       __u32 control;
       __u32 pad;
       struct kvm_guest_debug_arch arch;
};

Set up the processor specific debug registers and configure vcpu for
handling guest debug events. There are two parts to the structure, the
first a control bitfield indicates the type of debug events to handle
when running. Common control bits are:

  - KVM_GUESTDBG_ENABLE:        guest debugging is enabled
  - KVM_GUESTDBG_SINGLESTEP:    the next run should single-step

The top 16 bits of the control field are architecture specific control
flags which can include the following:

  - KVM_GUESTDBG_USE_SW_BP:     using software breakpoints [x86, arm64]
  - KVM_GUESTDBG_USE_HW_BP:     using hardware breakpoints [x86, s390, arm64]
  - KVM_GUESTDBG_INJECT_DB:     inject DB type exception [x86]
  - KVM_GUESTDBG_INJECT_BP:     inject BP type exception [x86]
  - KVM_GUESTDBG_EXIT_PENDING:  trigger an immediate guest exit [s390]

For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints
are enabled in memory so we need to ensure breakpoint exceptions are
correctly trapped and the KVM run loop exits at the breakpoint and not
running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP
we need to ensure the guest vCPUs architecture specific registers are
updated to the correct (supplied) values.

The second part of the structure is architecture specific and
typically contains a set of debug registers.

For arm64 the number of debug registers is implementation defined and
can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
indicating the number of supported registers.

When debug events exit the main run loop with the reason
KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
structure containing architecture specific debug information.

4.88 KVM_GET_EMULATED_CPUID

Capability: KVM_CAP_EXT_EMUL_CPUID
Architectures: x86
Type: system ioctl
Parameters: struct kvm_cpuid2 (in/out)
Returns: 0 on success, -1 on error

struct kvm_cpuid2 {
	__u32 nent;
	__u32 flags;
	struct kvm_cpuid_entry2 entries[0];
};

The member 'flags' is used for passing flags from userspace.

#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)

struct kvm_cpuid_entry2 {
	__u32 function;
	__u32 index;
	__u32 flags;
	__u32 eax;
	__u32 ebx;
	__u32 ecx;
	__u32 edx;
	__u32 padding[3];
};

This ioctl returns x86 cpuid features which are emulated by
kvm.Userspace can use the information returned by this ioctl to query
which features are emulated by kvm instead of being present natively.

Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
structure with the 'nent' field indicating the number of entries in
the variable-size array 'entries'. If the number of entries is too low
to describe the cpu capabilities, an error (E2BIG) is returned. If the
number is too high, the 'nent' field is adjusted and an error (ENOMEM)
is returned. If the number is just right, the 'nent' field is adjusted
to the number of valid entries in the 'entries' array, which is then
filled.

The entries returned are the set CPUID bits of the respective features
which kvm emulates, as returned by the CPUID instruction, with unknown
or unsupported feature bits cleared.

Features like x2apic, for example, may not be present in the host cpu
but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
emulated efficiently and thus not included here.

The fields in each entry are defined as follows:

  function: the eax value used to obtain the entry
  index: the ecx value used to obtain the entry (for entries that are
         affected by ecx)
  flags: an OR of zero or more of the following:
        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
           if the index field is valid
        KVM_CPUID_FLAG_STATEFUL_FUNC:
           if cpuid for this function returns different values for successive
           invocations; there will be several entries with the same function,
           all with this flag set
        KVM_CPUID_FLAG_STATE_READ_NEXT:
           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
           the first entry to be read by a cpu
   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
         this function/index combination

4.89 KVM_S390_MEM_OP

Capability: KVM_CAP_S390_MEM_OP
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_mem_op (in)
Returns: = 0 on success,
         < 0 on generic error (e.g. -EFAULT or -ENOMEM),
         > 0 if an exception occurred while walking the page tables

Read or write data from/to the logical (virtual) memory of a VCPU.

Parameters are specified via the following structure:

struct kvm_s390_mem_op {
	__u64 gaddr;		/* the guest address */
	__u64 flags;		/* flags */
	__u32 size;		/* amount of bytes */
	__u32 op;		/* type of operation */
	__u64 buf;		/* buffer in userspace */
	__u8 ar;		/* the access register number */
	__u8 reserved[31];	/* should be set to 0 */
};

The type of operation is specified in the "op" field. It is either
KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
whether the corresponding memory access would create an access exception
(without touching the data in the memory at the destination). In case an
access exception occurred while walking the MMU tables of the guest, the
ioctl returns a positive error number to indicate the type of exception.
This exception is also raised directly at the corresponding VCPU if the
flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.

The start address of the memory region has to be specified in the "gaddr"
field, and the length of the region in the "size" field. "buf" is the buffer
supplied by the userspace application where the read data should be written
to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
register number to be used.

The "reserved" field is meant for future extensions. It is not used by
KVM with the currently defined set of flags.

4.90 KVM_S390_GET_SKEYS

Capability: KVM_CAP_S390_SKEYS
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_skeys
Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
         keys, negative value on error

This ioctl is used to get guest storage key values on the s390
architecture. The ioctl takes parameters via the kvm_s390_skeys struct.

struct kvm_s390_skeys {
	__u64 start_gfn;
	__u64 count;
	__u64 skeydata_addr;
	__u32 flags;
	__u32 reserved[9];
};

The start_gfn field is the number of the first guest frame whose storage keys
you want to get.

The count field is the number of consecutive frames (starting from start_gfn)
whose storage keys to get. The count field must be at least 1 and the maximum
allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
will cause the ioctl to return -EINVAL.

The skeydata_addr field is the address to a buffer large enough to hold count
bytes. This buffer will be filled with storage key data by the ioctl.

4.91 KVM_S390_SET_SKEYS

Capability: KVM_CAP_S390_SKEYS
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_skeys
Returns: 0 on success, negative value on error

This ioctl is used to set guest storage key values on the s390
architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
See section on KVM_S390_GET_SKEYS for struct definition.

The start_gfn field is the number of the first guest frame whose storage keys
you want to set.

The count field is the number of consecutive frames (starting from start_gfn)
whose storage keys to get. The count field must be at least 1 and the maximum
allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
will cause the ioctl to return -EINVAL.

The skeydata_addr field is the address to a buffer containing count bytes of
storage keys. Each byte in the buffer will be set as the storage key for a
single frame starting at start_gfn for count frames.

Note: If any architecturally invalid key value is found in the given data then
the ioctl will return -EINVAL.

4.92 KVM_S390_IRQ

Capability: KVM_CAP_S390_INJECT_IRQ
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_irq (in)
Returns: 0 on success, -1 on error
Errors:
  EINVAL: interrupt type is invalid
          type is KVM_S390_SIGP_STOP and flag parameter is invalid value
          type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
            than the maximum of VCPUs
  EBUSY:  type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
          type is KVM_S390_SIGP_STOP and a stop irq is already pending
          type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
            is already pending

Allows to inject an interrupt to the guest.

Using struct kvm_s390_irq as a parameter allows
to inject additional payload which is not
possible via KVM_S390_INTERRUPT.

Interrupt parameters are passed via kvm_s390_irq:

struct kvm_s390_irq {
	__u64 type;
	union {
		struct kvm_s390_io_info io;
		struct kvm_s390_ext_info ext;
		struct kvm_s390_pgm_info pgm;
		struct kvm_s390_emerg_info emerg;
		struct kvm_s390_extcall_info extcall;
		struct kvm_s390_prefix_info prefix;
		struct kvm_s390_stop_info stop;
		struct kvm_s390_mchk_info mchk;
		char reserved[64];
	} u;
};

type can be one of the following:

KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
KVM_S390_PROGRAM_INT - program check; parameters in .pgm
KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
KVM_S390_RESTART - restart; no parameters
KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
KVM_S390_MCHK - machine check interrupt; parameters in .mchk


Note that the vcpu ioctl is asynchronous to vcpu execution.

4.94 KVM_S390_GET_IRQ_STATE

Capability: KVM_CAP_S390_IRQ_STATE
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_irq_state (out)
Returns: >= number of bytes copied into buffer,
         -EINVAL if buffer size is 0,
         -ENOBUFS if buffer size is too small to fit all pending interrupts,
         -EFAULT if the buffer address was invalid

This ioctl allows userspace to retrieve the complete state of all currently
pending interrupts in a single buffer. Use cases include migration
and introspection. The parameter structure contains the address of a
userspace buffer and its length:

struct kvm_s390_irq_state {
	__u64 buf;
	__u32 flags;
	__u32 len;
	__u32 reserved[4];
};

Userspace passes in the above struct and for each pending interrupt a
struct kvm_s390_irq is copied to the provided buffer.

If -ENOBUFS is returned the buffer provided was too small and userspace
may retry with a bigger buffer.

4.95 KVM_S390_SET_IRQ_STATE

Capability: KVM_CAP_S390_IRQ_STATE
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_irq_state (in)
Returns: 0 on success,
         -EFAULT if the buffer address was invalid,
         -EINVAL for an invalid buffer length (see below),
         -EBUSY if there were already interrupts pending,
         errors occurring when actually injecting the
          interrupt. See KVM_S390_IRQ.

This ioctl allows userspace to set the complete state of all cpu-local
interrupts currently pending for the vcpu. It is intended for restoring
interrupt state after a migration. The input parameter is a userspace buffer
containing a struct kvm_s390_irq_state:

struct kvm_s390_irq_state {
	__u64 buf;
	__u32 len;
	__u32 pad;
};

The userspace memory referenced by buf contains a struct kvm_s390_irq
for each interrupt to be injected into the guest.
If one of the interrupts could not be injected for some reason the
ioctl aborts.

len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
which is the maximum number of possibly pending cpu-local interrupts.

4.96 KVM_SMI

Capability: KVM_CAP_X86_SMM
Architectures: x86
Type: vcpu ioctl
Parameters: none
Returns: 0 on success, -1 on error

Queues an SMI on the thread's vcpu.

4.97 KVM_CAP_PPC_MULTITCE

Capability: KVM_CAP_PPC_MULTITCE
Architectures: ppc
Type: vm

This capability means the kernel is capable of handling hypercalls
H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
space. This significantly accelerates DMA operations for PPC KVM guests.
User space should expect that its handlers for these hypercalls
are not going to be called if user space previously registered LIOBN
in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).

In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
user space might have to advertise it for the guest. For example,
IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
present in the "ibm,hypertas-functions" device-tree property.

The hypercalls mentioned above may or may not be processed successfully
in the kernel based fast path. If they can not be handled by the kernel,
they will get passed on to user space. So user space still has to have
an implementation for these despite the in kernel acceleration.

This capability is always enabled.

4.98 KVM_CREATE_SPAPR_TCE_64

Capability: KVM_CAP_SPAPR_TCE_64
Architectures: powerpc
Type: vm ioctl
Parameters: struct kvm_create_spapr_tce_64 (in)
Returns: file descriptor for manipulating the created TCE table

This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
windows, described in 4.62 KVM_CREATE_SPAPR_TCE

This capability uses extended struct in ioctl interface:

/* for KVM_CAP_SPAPR_TCE_64 */
struct kvm_create_spapr_tce_64 {
	__u64 liobn;
	__u32 page_shift;
	__u32 flags;
	__u64 offset;	/* in pages */
	__u64 size; 	/* in pages */
};

The aim of extension is to support an additional bigger DMA window with
a variable page size.
KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
a bus offset of the corresponding DMA window, @size and @offset are numbers
of IOMMU pages.

@flags are not used at the moment.

The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.

4.99 KVM_REINJECT_CONTROL

Capability: KVM_CAP_REINJECT_CONTROL
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_reinject_control (in)
Returns: 0 on success,
         -EFAULT if struct kvm_reinject_control cannot be read,
         -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.

i8254 (PIT) has two modes, reinject and !reinject.  The default is reinject,
where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
vector(s) that i8254 injects.  Reinject mode dequeues a tick and injects its
interrupt whenever there isn't a pending interrupt from i8254.
!reinject mode injects an interrupt as soon as a tick arrives.

struct kvm_reinject_control {
	__u8 pit_reinject;
	__u8 reserved[31];
};

pit_reinject = 0 (!reinject mode) is recommended, unless running an old
operating system that uses the PIT for timing (e.g. Linux 2.4.x).

4.100 KVM_PPC_CONFIGURE_V3_MMU

Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
Architectures: ppc
Type: vm ioctl
Parameters: struct kvm_ppc_mmuv3_cfg (in)
Returns: 0 on success,
         -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
         -EINVAL if the configuration is invalid

This ioctl controls whether the guest will use radix or HPT (hashed
page table) translation, and sets the pointer to the process table for
the guest.

struct kvm_ppc_mmuv3_cfg {
	__u64	flags;
	__u64	process_table;
};

There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and
KVM_PPC_MMUV3_GTSE.  KVM_PPC_MMUV3_RADIX, if set, configures the guest
to use radix tree translation, and if clear, to use HPT translation.
KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest
to be able to use the global TLB and SLB invalidation instructions;
if clear, the guest may not use these instructions.

The process_table field specifies the address and size of the guest
process table, which is in the guest's space.  This field is formatted
as the second doubleword of the partition table entry, as defined in
the Power ISA V3.00, Book III section 5.7.6.1.

4.101 KVM_PPC_GET_RMMU_INFO

Capability: KVM_CAP_PPC_RADIX_MMU
Architectures: ppc
Type: vm ioctl
Parameters: struct kvm_ppc_rmmu_info (out)
Returns: 0 on success,
	 -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
	 -EINVAL if no useful information can be returned

This ioctl returns a structure containing two things: (a) a list
containing supported radix tree geometries, and (b) a list that maps
page sizes to put in the "AP" (actual page size) field for the tlbie
(TLB invalidate entry) instruction.

struct kvm_ppc_rmmu_info {
	struct kvm_ppc_radix_geom {
		__u8	page_shift;
		__u8	level_bits[4];
		__u8	pad[3];
	}	geometries[8];
	__u32	ap_encodings[8];
};

The geometries[] field gives up to 8 supported geometries for the
radix page table, in terms of the log base 2 of the smallest page
size, and the number of bits indexed at each level of the tree, from
the PTE level up to the PGD level in that order.  Any unused entries
will have 0 in the page_shift field.

The ap_encodings gives the supported page sizes and their AP field
encodings, encoded with the AP value in the top 3 bits and the log
base 2 of the page size in the bottom 6 bits.

4.102 KVM_PPC_RESIZE_HPT_PREPARE

Capability: KVM_CAP_SPAPR_RESIZE_HPT
Architectures: powerpc
Type: vm ioctl
Parameters: struct kvm_ppc_resize_hpt (in)
Returns: 0 on successful completion,
	 >0 if a new HPT is being prepared, the value is an estimated
             number of milliseconds until preparation is complete
         -EFAULT if struct kvm_reinject_control cannot be read,
	 -EINVAL if the supplied shift or flags are invalid
	 -ENOMEM if unable to allocate the new HPT
	 -ENOSPC if there was a hash collision when moving existing
                  HPT entries to the new HPT
	 -EIO on other error conditions

Used to implement the PAPR extension for runtime resizing of a guest's
Hashed Page Table (HPT).  Specifically this starts, stops or monitors
the preparation of a new potential HPT for the guest, essentially
implementing the H_RESIZE_HPT_PREPARE hypercall.

If called with shift > 0 when there is no pending HPT for the guest,
this begins preparation of a new pending HPT of size 2^(shift) bytes.
It then returns a positive integer with the estimated number of
milliseconds until preparation is complete.

If called when there is a pending HPT whose size does not match that
requested in the parameters, discards the existing pending HPT and
creates a new one as above.

If called when there is a pending HPT of the size requested, will:
  * If preparation of the pending HPT is already complete, return 0
  * If preparation of the pending HPT has failed, return an error
    code, then discard the pending HPT.
  * If preparation of the pending HPT is still in progress, return an
    estimated number of milliseconds until preparation is complete.

If called with shift == 0, discards any currently pending HPT and
returns 0 (i.e. cancels any in-progress preparation).

flags is reserved for future expansion, currently setting any bits in
flags will result in an -EINVAL.

Normally this will be called repeatedly with the same parameters until
it returns <= 0.  The first call will initiate preparation, subsequent
ones will monitor preparation until it completes or fails.

struct kvm_ppc_resize_hpt {
	__u64 flags;
	__u32 shift;
	__u32 pad;
};

4.103 KVM_PPC_RESIZE_HPT_COMMIT

Capability: KVM_CAP_SPAPR_RESIZE_HPT
Architectures: powerpc
Type: vm ioctl
Parameters: struct kvm_ppc_resize_hpt (in)
Returns: 0 on successful completion,
         -EFAULT if struct kvm_reinject_control cannot be read,
	 -EINVAL if the supplied shift or flags are invalid
	 -ENXIO is there is no pending HPT, or the pending HPT doesn't
                 have the requested size
	 -EBUSY if the pending HPT is not fully prepared
	 -ENOSPC if there was a hash collision when moving existing
                  HPT entries to the new HPT
	 -EIO on other error conditions

Used to implement the PAPR extension for runtime resizing of a guest's
Hashed Page Table (HPT).  Specifically this requests that the guest be
transferred to working with the new HPT, essentially implementing the
H_RESIZE_HPT_COMMIT hypercall.

This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has
returned 0 with the same parameters.  In other cases
KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or
-EBUSY, though others may be possible if the preparation was started,
but failed).

This will have undefined effects on the guest if it has not already
placed itself in a quiescent state where no vcpu will make MMU enabled
memory accesses.

On succsful completion, the pending HPT will become the guest's active
HPT and the previous HPT will be discarded.

On failure, the guest will still be operating on its previous HPT.

struct kvm_ppc_resize_hpt {
	__u64 flags;
	__u32 shift;
	__u32 pad;
};

4.104 KVM_X86_GET_MCE_CAP_SUPPORTED

Capability: KVM_CAP_MCE
Architectures: x86
Type: system ioctl
Parameters: u64 mce_cap (out)
Returns: 0 on success, -1 on error

Returns supported MCE capabilities. The u64 mce_cap parameter
has the same format as the MSR_IA32_MCG_CAP register. Supported
capabilities will have the corresponding bits set.

4.105 KVM_X86_SETUP_MCE

Capability: KVM_CAP_MCE
Architectures: x86
Type: vcpu ioctl
Parameters: u64 mcg_cap (in)
Returns: 0 on success,
         -EFAULT if u64 mcg_cap cannot be read,
         -EINVAL if the requested number of banks is invalid,
         -EINVAL if requested MCE capability is not supported.

Initializes MCE support for use. The u64 mcg_cap parameter
has the same format as the MSR_IA32_MCG_CAP register and
specifies which capabilities should be enabled. The maximum
supported number of error-reporting banks can be retrieved when
checking for KVM_CAP_MCE. The supported capabilities can be
retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.

4.106 KVM_X86_SET_MCE

Capability: KVM_CAP_MCE
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_x86_mce (in)
Returns: 0 on success,
         -EFAULT if struct kvm_x86_mce cannot be read,
         -EINVAL if the bank number is invalid,
         -EINVAL if VAL bit is not set in status field.

Inject a machine check error (MCE) into the guest. The input
parameter is:

struct kvm_x86_mce {
	__u64 status;
	__u64 addr;
	__u64 misc;
	__u64 mcg_status;
	__u8 bank;
	__u8 pad1[7];
	__u64 pad2[3];
};

If the MCE being reported is an uncorrected error, KVM will
inject it as an MCE exception into the guest. If the guest
MCG_STATUS register reports that an MCE is in progress, KVM
causes an KVM_EXIT_SHUTDOWN vmexit.

Otherwise, if the MCE is a corrected error, KVM will just
store it in the corresponding bank (provided this bank is
not holding a previously reported uncorrected error).

4.107 KVM_S390_GET_CMMA_BITS

Capability: KVM_CAP_S390_CMMA_MIGRATION
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_cmma_log (in, out)
Returns: 0 on success, a negative value on error

This ioctl is used to get the values of the CMMA bits on the s390
architecture. It is meant to be used in two scenarios:
- During live migration to save the CMMA values. Live migration needs
  to be enabled via the KVM_REQ_START_MIGRATION VM property.
- To non-destructively peek at the CMMA values, with the flag
  KVM_S390_CMMA_PEEK set.

The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired
values are written to a buffer whose location is indicated via the "values"
member in the kvm_s390_cmma_log struct.  The values in the input struct are
also updated as needed.
Each CMMA value takes up one byte.

struct kvm_s390_cmma_log {
	__u64 start_gfn;
	__u32 count;
	__u32 flags;
	union {
		__u64 remaining;
		__u64 mask;
	};
	__u64 values;
};

start_gfn is the number of the first guest frame whose CMMA values are
to be retrieved,

count is the length of the buffer in bytes,

values points to the buffer where the result will be written to.

If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be
KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
other ioctls.

The result is written in the buffer pointed to by the field values, and
the values of the input parameter are updated as follows.

Depending on the flags, different actions are performed. The only
supported flag so far is KVM_S390_CMMA_PEEK.

The default behaviour if KVM_S390_CMMA_PEEK is not set is:
start_gfn will indicate the first page frame whose CMMA bits were dirty.
It is not necessarily the same as the one passed as input, as clean pages
are skipped.

count will indicate the number of bytes actually written in the buffer.
It can (and very often will) be smaller than the input value, since the
buffer is only filled until 16 bytes of clean values are found (which
are then not copied in the buffer). Since a CMMA migration block needs
the base address and the length, for a total of 16 bytes, we will send
back some clean data if there is some dirty data afterwards, as long as
the size of the clean data does not exceed the size of the header. This
allows to minimize the amount of data to be saved or transferred over
the network at the expense of more roundtrips to userspace. The next
invocation of the ioctl will skip over all the clean values, saving
potentially more than just the 16 bytes we found.

If KVM_S390_CMMA_PEEK is set:
the existing storage attributes are read even when not in migration
mode, and no other action is performed;

the output start_gfn will be equal to the input start_gfn,

the output count will be equal to the input count, except if the end of
memory has been reached.

In both cases:
the field "remaining" will indicate the total number of dirty CMMA values
still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is
not enabled.

mask is unused.

values points to the userspace buffer where the result will be stored.

This ioctl can fail with -ENOMEM if not enough memory can be allocated to
complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with
-EFAULT if the userspace address is invalid or if no page table is
present for the addresses (e.g. when using hugepages).

4.108 KVM_S390_SET_CMMA_BITS

Capability: KVM_CAP_S390_CMMA_MIGRATION
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_cmma_log (in)
Returns: 0 on success, a negative value on error

This ioctl is used to set the values of the CMMA bits on the s390
architecture. It is meant to be used during live migration to restore
the CMMA values, but there are no restrictions on its use.
The ioctl takes parameters via the kvm_s390_cmma_values struct.
Each CMMA value takes up one byte.

struct kvm_s390_cmma_log {
	__u64 start_gfn;
	__u32 count;
	__u32 flags;
	union {
		__u64 remaining;
		__u64 mask;
	};
	__u64 values;
};

start_gfn indicates the starting guest frame number,

count indicates how many values are to be considered in the buffer,

flags is not used and must be 0.

mask indicates which PGSTE bits are to be considered.

remaining is not used.

values points to the buffer in userspace where to store the values.

This ioctl can fail with -ENOMEM if not enough memory can be allocated to
complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or
if the flags field was not 0, with -EFAULT if the userspace address is
invalid, if invalid pages are written to (e.g. after the end of memory)
or if no page table is present for the addresses (e.g. when using
hugepages).

5. The kvm_run structure
------------------------

Application code obtains a pointer to the kvm_run structure by
mmap()ing a vcpu fd.  From that point, application code can control
execution by changing fields in kvm_run prior to calling the KVM_RUN
ioctl, and obtain information about the reason KVM_RUN returned by
looking up structure members.

struct kvm_run {
	/* in */
	__u8 request_interrupt_window;

Request that KVM_RUN return when it becomes possible to inject external
interrupts into the guest.  Useful in conjunction with KVM_INTERRUPT.

	__u8 immediate_exit;

This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
exits immediately, returning -EINTR.  In the common scenario where a
signal is used to "kick" a VCPU out of KVM_RUN, this field can be used
to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability.
Rather than blocking the signal outside KVM_RUN, userspace can set up
a signal handler that sets run->immediate_exit to a non-zero value.

This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.

	__u8 padding1[6];

	/* out */
	__u32 exit_reason;

When KVM_RUN has returned successfully (return value 0), this informs
application code why KVM_RUN has returned.  Allowable values for this
field are detailed below.

	__u8 ready_for_interrupt_injection;

If request_interrupt_window has been specified, this field indicates
an interrupt can be injected now with KVM_INTERRUPT.

	__u8 if_flag;

The value of the current interrupt flag.  Only valid if in-kernel
local APIC is not used.

	__u16 flags;

More architecture-specific flags detailing state of the VCPU that may
affect the device's behavior.  The only currently defined flag is
KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
VCPU is in system management mode.

	/* in (pre_kvm_run), out (post_kvm_run) */
	__u64 cr8;

The value of the cr8 register.  Only valid if in-kernel local APIC is
not used.  Both input and output.

	__u64 apic_base;

The value of the APIC BASE msr.  Only valid if in-kernel local
APIC is not used.  Both input and output.

	union {
		/* KVM_EXIT_UNKNOWN */
		struct {
			__u64 hardware_exit_reason;
		} hw;

If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
reasons.  Further architecture-specific information is available in
hardware_exit_reason.

		/* KVM_EXIT_FAIL_ENTRY */
		struct {
			__u64 hardware_entry_failure_reason;
		} fail_entry;

If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
to unknown reasons.  Further architecture-specific information is
available in hardware_entry_failure_reason.

		/* KVM_EXIT_EXCEPTION */
		struct {
			__u32 exception;
			__u32 error_code;
		} ex;

Unused.

		/* KVM_EXIT_IO */
		struct {
#define KVM_EXIT_IO_IN  0
#define KVM_EXIT_IO_OUT 1
			__u8 direction;
			__u8 size; /* bytes */
			__u16 port;
			__u32 count;
			__u64 data_offset; /* relative to kvm_run start */
		} io;

If exit_reason is KVM_EXIT_IO, then the vcpu has
executed a port I/O instruction which could not be satisfied by kvm.
data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
where kvm expects application code to place the data for the next
KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.

		/* KVM_EXIT_DEBUG */
		struct {
			struct kvm_debug_exit_arch arch;
		} debug;

If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
for which architecture specific information is returned.

		/* KVM_EXIT_MMIO */
		struct {
			__u64 phys_addr;
			__u8  data[8];
			__u32 len;
			__u8  is_write;
		} mmio;

If exit_reason is KVM_EXIT_MMIO, then the vcpu has
executed a memory-mapped I/O instruction which could not be satisfied
by kvm.  The 'data' member contains the written data if 'is_write' is
true, and should be filled by application code otherwise.

The 'data' member contains, in its first 'len' bytes, the value as it would
appear if the VCPU performed a load or store of the appropriate width directly
to the byte array.

NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
      KVM_EXIT_EPR the corresponding
operations are complete (and guest state is consistent) only after userspace
has re-entered the kernel with KVM_RUN.  The kernel side will first finish
incomplete operations and then check for pending signals.  Userspace
can re-enter the guest with an unmasked signal pending to complete
pending operations.

		/* KVM_EXIT_HYPERCALL */
		struct {
			__u64 nr;
			__u64 args[6];
			__u64 ret;
			__u32 longmode;
			__u32 pad;
		} hypercall;

Unused.  This was once used for 'hypercall to userspace'.  To implement
such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.

		/* KVM_EXIT_TPR_ACCESS */
		struct {
			__u64 rip;
			__u32 is_write;
			__u32 pad;
		} tpr_access;

To be documented (KVM_TPR_ACCESS_REPORTING).

		/* KVM_EXIT_S390_SIEIC */
		struct {
			__u8 icptcode;
			__u64 mask; /* psw upper half */
			__u64 addr; /* psw lower half */
			__u16 ipa;
			__u32 ipb;
		} s390_sieic;

s390 specific.

		/* KVM_EXIT_S390_RESET */
#define KVM_S390_RESET_POR       1
#define KVM_S390_RESET_CLEAR     2
#define KVM_S390_RESET_SUBSYSTEM 4
#define KVM_S390_RESET_CPU_INIT  8
#define KVM_S390_RESET_IPL       16
		__u64 s390_reset_flags;

s390 specific.

		/* KVM_EXIT_S390_UCONTROL */
		struct {
			__u64 trans_exc_code;
			__u32 pgm_code;
		} s390_ucontrol;

s390 specific. A page fault has occurred for a user controlled virtual
machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
resolved by the kernel.
The program code and the translation exception code that were placed
in the cpu's lowcore are presented here as defined by the z Architecture
Principles of Operation Book in the Chapter for Dynamic Address Translation
(DAT)

		/* KVM_EXIT_DCR */
		struct {
			__u32 dcrn;
			__u32 data;
			__u8  is_write;
		} dcr;

Deprecated - was used for 440 KVM.

		/* KVM_EXIT_OSI */
		struct {
			__u64 gprs[32];
		} osi;

MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
hypercalls and exit with this exit struct that contains all the guest gprs.

If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
Userspace can now handle the hypercall and when it's done modify the gprs as
necessary. Upon guest entry all guest GPRs will then be replaced by the values
in this struct.

		/* KVM_EXIT_PAPR_HCALL */
		struct {
			__u64 nr;
			__u64 ret;
			__u64 args[9];
		} papr_hcall;

This is used on 64-bit PowerPC when emulating a pSeries partition,
e.g. with the 'pseries' machine type in qemu.  It occurs when the
guest does a hypercall using the 'sc 1' instruction.  The 'nr' field
contains the hypercall number (from the guest R3), and 'args' contains
the arguments (from the guest R4 - R12).  Userspace should put the
return code in 'ret' and any extra returned values in args[].
The possible hypercalls are defined in the Power Architecture Platform
Requirements (PAPR) document available from www.power.org (free
developer registration required to access it).

		/* KVM_EXIT_S390_TSCH */
		struct {
			__u16 subchannel_id;
			__u16 subchannel_nr;
			__u32 io_int_parm;
			__u32 io_int_word;
			__u32 ipb;
			__u8 dequeued;
		} s390_tsch;

s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
interrupt for the target subchannel has been dequeued and subchannel_id,
subchannel_nr, io_int_parm and io_int_word contain the parameters for that
interrupt. ipb is needed for instruction parameter decoding.

		/* KVM_EXIT_EPR */
		struct {
			__u32 epr;
		} epr;

On FSL BookE PowerPC chips, the interrupt controller has a fast patch
interrupt acknowledge path to the core. When the core successfully
delivers an interrupt, it automatically populates the EPR register with
the interrupt vector number and acknowledges the interrupt inside
the interrupt controller.

In case the interrupt controller lives in user space, we need to do
the interrupt acknowledge cycle through it to fetch the next to be
delivered interrupt vector using this exit.

It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
external interrupt has just been delivered into the guest. User space
should put the acknowledged interrupt vector into the 'epr' field.

		/* KVM_EXIT_SYSTEM_EVENT */
		struct {
#define KVM_SYSTEM_EVENT_SHUTDOWN       1
#define KVM_SYSTEM_EVENT_RESET          2
#define KVM_SYSTEM_EVENT_CRASH          3
			__u32 type;
			__u64 flags;
		} system_event;

If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
a system-level event using some architecture specific mechanism (hypercall
or some special instruction). In case of ARM/ARM64, this is triggered using
HVC instruction based PSCI call from the vcpu. The 'type' field describes
the system-level event type. The 'flags' field describes architecture
specific flags for the system-level event.

Valid values for 'type' are:
  KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
   VM. Userspace is not obliged to honour this, and if it does honour
   this does not need to destroy the VM synchronously (ie it may call
   KVM_RUN again before shutdown finally occurs).
  KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
   As with SHUTDOWN, userspace can choose to ignore the request, or
   to schedule the reset to occur in the future and may call KVM_RUN again.
  KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
   has requested a crash condition maintenance. Userspace can choose
   to ignore the request, or to gather VM memory core dump and/or
   reset/shutdown of the VM.

		/* KVM_EXIT_IOAPIC_EOI */
		struct {
			__u8 vector;
		} eoi;

Indicates that the VCPU's in-kernel local APIC received an EOI for a
level-triggered IOAPIC interrupt.  This exit only triggers when the
IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
the userspace IOAPIC should process the EOI and retrigger the interrupt if
it is still asserted.  Vector is the LAPIC interrupt vector for which the
EOI was received.

		struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC          1
#define KVM_EXIT_HYPERV_HCALL          2
			__u32 type;
			union {
				struct {
					__u32 msr;
					__u64 control;
					__u64 evt_page;
					__u64 msg_page;
				} synic;
				struct {
					__u64 input;
					__u64 result;
					__u64 params[2];
				} hcall;
			} u;
		};
		/* KVM_EXIT_HYPERV */
                struct kvm_hyperv_exit hyperv;
Indicates that the VCPU exits into userspace to process some tasks
related to Hyper-V emulation.
Valid values for 'type' are:
	KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
Hyper-V SynIC state change. Notification is used to remap SynIC
event/message pages and to enable/disable SynIC messages/events processing
in userspace.

		/* Fix the size of the union. */
		char padding[256];
	};

	/*
	 * shared registers between kvm and userspace.
	 * kvm_valid_regs specifies the register classes set by the host
	 * kvm_dirty_regs specified the register classes dirtied by userspace
	 * struct kvm_sync_regs is architecture specific, as well as the
	 * bits for kvm_valid_regs and kvm_dirty_regs
	 */
	__u64 kvm_valid_regs;
	__u64 kvm_dirty_regs;
	union {
		struct kvm_sync_regs regs;
		char padding[1024];
	} s;

If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
certain guest registers without having to call SET/GET_*REGS. Thus we can
avoid some system call overhead if userspace has to handle the exit.
Userspace can query the validity of the structure by checking
kvm_valid_regs for specific bits. These bits are architecture specific
and usually define the validity of a groups of registers. (e.g. one bit
 for general purpose registers)

Please note that the kernel is allowed to use the kvm_run structure as the
primary storage for certain register types. Therefore, the kernel may use the
values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.

};



6. Capabilities that can be enabled on vCPUs
--------------------------------------------

There are certain capabilities that change the behavior of the virtual CPU or
the virtual machine when enabled. To enable them, please see section 4.37.
Below you can find a list of capabilities and what their effect on the vCPU or
the virtual machine is when enabling them.

The following information is provided along with the description:

  Architectures: which instruction set architectures provide this ioctl.
      x86 includes both i386 and x86_64.

  Target: whether this is a per-vcpu or per-vm capability.

  Parameters: what parameters are accepted by the capability.

  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
      are not detailed, but errors with specific meanings are.


6.1 KVM_CAP_PPC_OSI

Architectures: ppc
Target: vcpu
Parameters: none
Returns: 0 on success; -1 on error

This capability enables interception of OSI hypercalls that otherwise would
be treated as normal system calls to be injected into the guest. OSI hypercalls
were invented by Mac-on-Linux to have a standardized communication mechanism
between the guest and the host.

When this capability is enabled, KVM_EXIT_OSI can occur.


6.2 KVM_CAP_PPC_PAPR

Architectures: ppc
Target: vcpu
Parameters: none
Returns: 0 on success; -1 on error

This capability enables interception of PAPR hypercalls. PAPR hypercalls are
done using the hypercall instruction "sc 1".

It also sets the guest privilege level to "supervisor" mode. Usually the guest
runs in "hypervisor" privilege mode with a few missing features.

In addition to the above, it changes the semantics of SDR1. In this mode, the
HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
HTAB invisible to the guest.

When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.


6.3 KVM_CAP_SW_TLB

Architectures: ppc
Target: vcpu
Parameters: args[0] is the address of a struct kvm_config_tlb
Returns: 0 on success; -1 on error

struct kvm_config_tlb {
	__u64 params;
	__u64 array;
	__u32 mmu_type;
	__u32 array_len;
};

Configures the virtual CPU's TLB array, establishing a shared memory area
between userspace and KVM.  The "params" and "array" fields are userspace
addresses of mmu-type-specific data structures.  The "array_len" field is an
safety mechanism, and should be set to the size in bytes of the memory that
userspace has reserved for the array.  It must be at least the size dictated
by "mmu_type" and "params".

While KVM_RUN is active, the shared region is under control of KVM.  Its
contents are undefined, and any modification by userspace results in
boundedly undefined behavior.

On return from KVM_RUN, the shared region will reflect the current state of
the guest's TLB.  If userspace makes any changes, it must call KVM_DIRTY_TLB
to tell KVM which entries have been changed, prior to calling KVM_RUN again
on this vcpu.

For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
 - The "array" field points to an array of type "struct
   kvm_book3e_206_tlb_entry".
 - The array consists of all entries in the first TLB, followed by all
   entries in the second TLB.
 - Within a TLB, entries are ordered first by increasing set number.  Within a
   set, entries are ordered by way (increasing ESEL).
 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
   where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
   hardware ignores this value for TLB0.

6.4 KVM_CAP_S390_CSS_SUPPORT

Architectures: s390
Target: vcpu
Parameters: none
Returns: 0 on success; -1 on error

This capability enables support for handling of channel I/O instructions.

TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
handled in-kernel, while the other I/O instructions are passed to userspace.

When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
SUBCHANNEL intercepts.

Note that even though this capability is enabled per-vcpu, the complete
virtual machine is affected.

6.5 KVM_CAP_PPC_EPR

Architectures: ppc
Target: vcpu
Parameters: args[0] defines whether the proxy facility is active
Returns: 0 on success; -1 on error

This capability enables or disables the delivery of interrupts through the
external proxy facility.

When enabled (args[0] != 0), every time the guest gets an external interrupt
delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
to receive the topmost interrupt vector.

When disabled (args[0] == 0), behavior is as if this facility is unsupported.

When this capability is enabled, KVM_EXIT_EPR can occur.

6.6 KVM_CAP_IRQ_MPIC

Architectures: ppc
Parameters: args[0] is the MPIC device fd
            args[1] is the MPIC CPU number for this vcpu

This capability connects the vcpu to an in-kernel MPIC device.

6.7 KVM_CAP_IRQ_XICS

Architectures: ppc
Target: vcpu
Parameters: args[0] is the XICS device fd
            args[1] is the XICS CPU number (server ID) for this vcpu

This capability connects the vcpu to an in-kernel XICS device.

6.8 KVM_CAP_S390_IRQCHIP

Architectures: s390
Target: vm
Parameters: none

This capability enables the in-kernel irqchip for s390. Please refer to
"4.24 KVM_CREATE_IRQCHIP" for details.

6.9 KVM_CAP_MIPS_FPU

Architectures: mips
Target: vcpu
Parameters: args[0] is reserved for future use (should be 0).

This capability allows the use of the host Floating Point Unit by the guest. It
allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed
(depending on the current guest FPU register mode), and the Status.FR,
Config5.FRE bits are accessible via the KVM API and also from the guest,
depending on them being supported by the FPU.

6.10 KVM_CAP_MIPS_MSA

Architectures: mips
Target: vcpu
Parameters: args[0] is reserved for future use (should be 0).

This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
the guest.

7. Capabilities that can be enabled on VMs
------------------------------------------

There are certain capabilities that change the behavior of the virtual
machine when enabled. To enable them, please see section 4.37. Below
you can find a list of capabilities and what their effect on the VM
is when enabling them.

The following information is provided along with the description:

  Architectures: which instruction set architectures provide this ioctl.
      x86 includes both i386 and x86_64.

  Parameters: what parameters are accepted by the capability.

  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
      are not detailed, but errors with specific meanings are.


7.1 KVM_CAP_PPC_ENABLE_HCALL

Architectures: ppc
Parameters: args[0] is the sPAPR hcall number
	    args[1] is 0 to disable, 1 to enable in-kernel handling

This capability controls whether individual sPAPR hypercalls (hcalls)
get handled by the kernel or not.  Enabling or disabling in-kernel
handling of an hcall is effective across the VM.  On creation, an
initial set of hcalls are enabled for in-kernel handling, which
consists of those hcalls for which in-kernel handlers were implemented
before this capability was implemented.  If disabled, the kernel will
not to attempt to handle the hcall, but will always exit to userspace
to handle it.  Note that it may not make sense to enable some and
disable others of a group of related hcalls, but KVM does not prevent
userspace from doing that.

If the hcall number specified is not one that has an in-kernel
implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
error.

7.2 KVM_CAP_S390_USER_SIGP

Architectures: s390
Parameters: none

This capability controls which SIGP orders will be handled completely in user
space. With this capability enabled, all fast orders will be handled completely
in the kernel:
- SENSE
- SENSE RUNNING
- EXTERNAL CALL
- EMERGENCY SIGNAL
- CONDITIONAL EMERGENCY SIGNAL

All other orders will be handled completely in user space.

Only privileged operation exceptions will be checked for in the kernel (or even
in the hardware prior to interception). If this capability is not enabled, the
old way of handling SIGP orders is used (partially in kernel and user space).

7.3 KVM_CAP_S390_VECTOR_REGISTERS

Architectures: s390
Parameters: none
Returns: 0 on success, negative value on error

Allows use of the vector registers introduced with z13 processor, and
provides for the synchronization between host and user space.  Will
return -EINVAL if the machine does not support vectors.

7.4 KVM_CAP_S390_USER_STSI

Architectures: s390
Parameters: none

This capability allows post-handlers for the STSI instruction. After
initial handling in the kernel, KVM exits to user space with
KVM_EXIT_S390_STSI to allow user space to insert further data.

Before exiting to userspace, kvm handlers should fill in s390_stsi field of
vcpu->run:
struct {
	__u64 addr;
	__u8 ar;
	__u8 reserved;
	__u8 fc;
	__u8 sel1;
	__u16 sel2;
} s390_stsi;

@addr - guest address of STSI SYSIB
@fc   - function code
@sel1 - selector 1
@sel2 - selector 2
@ar   - access register number

KVM handlers should exit to userspace with rc = -EREMOTE.

7.5 KVM_CAP_SPLIT_IRQCHIP

Architectures: x86
Parameters: args[0] - number of routes reserved for userspace IOAPICs
Returns: 0 on success, -1 on error

Create a local apic for each processor in the kernel. This can be used
instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
IOAPIC and PIC (and also the PIT, even though this has to be enabled
separately).

This capability also enables in kernel routing of interrupt requests;
when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
used in the IRQ routing table.  The first args[0] MSI routes are reserved
for the IOAPIC pins.  Whenever the LAPIC receives an EOI for these routes,
a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.

Fails if VCPU has already been created, or if the irqchip is already in the
kernel (i.e. KVM_CREATE_IRQCHIP has already been called).

7.6 KVM_CAP_S390_RI

Architectures: s390
Parameters: none

Allows use of runtime-instrumentation introduced with zEC12 processor.
Will return -EINVAL if the machine does not support runtime-instrumentation.
Will return -EBUSY if a VCPU has already been created.

7.7 KVM_CAP_X2APIC_API

Architectures: x86
Parameters: args[0] - features that should be enabled
Returns: 0 on success, -EINVAL when args[0] contains invalid features

Valid feature flags in args[0] are

#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)

Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
allowing the use of 32-bit APIC IDs.  See KVM_CAP_X2APIC_API in their
respective sections.

KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
in logical mode or with more than 255 VCPUs.  Otherwise, KVM treats 0xff
as a broadcast even in x2APIC mode in order to support physical x2APIC
without interrupt remapping.  This is undesirable in logical mode,
where 0xff represents CPUs 0-7 in cluster 0.

7.8 KVM_CAP_S390_USER_INSTR0

Architectures: s390
Parameters: none

With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
be intercepted and forwarded to user space. User space can use this
mechanism e.g. to realize 2-byte software breakpoints. The kernel will
not inject an operating exception for these instructions, user space has
to take care of that.

This capability can be enabled dynamically even if VCPUs were already
created and are running.

7.9 KVM_CAP_S390_GS

Architectures: s390
Parameters: none
Returns: 0 on success; -EINVAL if the machine does not support
	 guarded storage; -EBUSY if a VCPU has already been created.

Allows use of guarded storage for the KVM guest.

7.10 KVM_CAP_S390_AIS

Architectures: s390
Parameters: none

Allow use of adapter-interruption suppression.
Returns: 0 on success; -EBUSY if a VCPU has already been created.

7.11 KVM_CAP_PPC_SMT

Architectures: ppc
Parameters: vsmt_mode, flags

Enabling this capability on a VM provides userspace with a way to set
the desired virtual SMT mode (i.e. the number of virtual CPUs per
virtual core).  The virtual SMT mode, vsmt_mode, must be a power of 2
between 1 and 8.  On POWER8, vsmt_mode must also be no greater than
the number of threads per subcore for the host.  Currently flags must
be 0.  A successful call to enable this capability will result in
vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is
subsequently queried for the VM.  This capability is only supported by
HV KVM, and can only be set before any VCPUs have been created.
The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT
modes are available.

7.12 KVM_CAP_PPC_FWNMI

Architectures: ppc
Parameters: none

With this capability a machine check exception in the guest address
space will cause KVM to exit the guest with NMI exit reason. This
enables QEMU to build error log and branch to guest kernel registered
machine check handling routine. Without this capability KVM will
branch to guests' 0x200 interrupt vector.

8. Other capabilities.
----------------------

This section lists capabilities that give information about other
features of the KVM implementation.

8.1 KVM_CAP_PPC_HWRNG

Architectures: ppc

This capability, if KVM_CHECK_EXTENSION indicates that it is
available, means that that the kernel has an implementation of the
H_RANDOM hypercall backed by a hardware random-number generator.
If present, the kernel H_RANDOM handler can be enabled for guest use
with the KVM_CAP_PPC_ENABLE_HCALL capability.

8.2 KVM_CAP_HYPERV_SYNIC

Architectures: x86
This capability, if KVM_CHECK_EXTENSION indicates that it is
available, means that that the kernel has an implementation of the
Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
used to support Windows Hyper-V based guest paravirt drivers(VMBus).

In order to use SynIC, it has to be activated by setting this
capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
will disable the use of APIC hardware virtualization even if supported
by the CPU, as it's incompatible with SynIC auto-EOI behavior.

8.3 KVM_CAP_PPC_RADIX_MMU

Architectures: ppc

This capability, if KVM_CHECK_EXTENSION indicates that it is
available, means that that the kernel can support guests using the
radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
processor).

8.4 KVM_CAP_PPC_HASH_MMU_V3

Architectures: ppc

This capability, if KVM_CHECK_EXTENSION indicates that it is
available, means that that the kernel can support guests using the
hashed page table MMU defined in Power ISA V3.00 (as implemented in
the POWER9 processor), including in-memory segment tables.

8.5 KVM_CAP_MIPS_VZ

Architectures: mips

This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
it is available, means that full hardware assisted virtualization capabilities
of the hardware are available for use through KVM. An appropriate
KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
utilises it.

If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
available, it means that the VM is using full hardware assisted virtualization
capabilities of the hardware. This is useful to check after creating a VM with
KVM_VM_MIPS_DEFAULT.

The value returned by KVM_CHECK_EXTENSION should be compared against known
values (see below). All other values are reserved. This is to allow for the
possibility of other hardware assisted virtualization implementations which
may be incompatible with the MIPS VZ ASE.

 0: The trap & emulate implementation is in use to run guest code in user
    mode. Guest virtual memory segments are rearranged to fit the guest in the
    user mode address space.

 1: The MIPS VZ ASE is in use, providing full hardware assisted
    virtualization, including standard guest virtual memory segments.

8.6 KVM_CAP_MIPS_TE

Architectures: mips

This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
it is available, means that the trap & emulate implementation is available to
run guest code in user mode, even if KVM_CAP_MIPS_VZ indicates that hardware
assisted virtualisation is also available. KVM_VM_MIPS_TE (0) must be passed
to KVM_CREATE_VM to create a VM which utilises it.

If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
available, it means that the VM is using trap & emulate.

8.7 KVM_CAP_MIPS_64BIT

Architectures: mips

This capability indicates the supported architecture type of the guest, i.e. the
supported register and address width.

The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
be checked specifically against known values (see below). All other values are
reserved.

 0: MIPS32 or microMIPS32.
    Both registers and addresses are 32-bits wide.
    It will only be possible to run 32-bit guest code.

 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
    Registers are 64-bits wide, but addresses are 32-bits wide.
    64-bit guest code may run but cannot access MIPS64 memory segments.
    It will also be possible to run 32-bit guest code.

 2: MIPS64 or microMIPS64 with access to all address segments.
    Both registers and addresses are 64-bits wide.
    It will be possible to run 64-bit or 32-bit guest code.

8.8 KVM_CAP_X86_GUEST_MWAIT

Architectures: x86

This capability indicates that guest using memory monotoring instructions
(MWAIT/MWAITX) to stop the virtual CPU will not cause a VM exit.  As such time
spent while virtual CPU is halted in this way will then be accounted for as
guest running time on the host (as opposed to e.g. HLT).

8.9 KVM_CAP_ARM_USER_IRQ

Architectures: arm, arm64
This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
that if userspace creates a VM without an in-kernel interrupt controller, it
will be notified of changes to the output level of in-kernel emulated devices,
which can generate virtual interrupts, presented to the VM.
For such VMs, on every return to userspace, the kernel
updates the vcpu's run->s.regs.device_irq_level field to represent the actual
output level of the device.

Whenever kvm detects a change in the device output level, kvm guarantees at
least one return to userspace before running the VM.  This exit could either
be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
userspace can always sample the device output level and re-compute the state of
the userspace interrupt controller.  Userspace should always check the state
of run->s.regs.device_irq_level on every kvm exit.
The value in run->s.regs.device_irq_level can represent both level and edge
triggered interrupt signals, depending on the device.  Edge triggered interrupt
signals will exit to userspace with the bit in run->s.regs.device_irq_level
set exactly once per edge signal.

The field run->s.regs.device_irq_level is available independent of
run->kvm_valid_regs or run->kvm_dirty_regs bits.

If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
number larger than 0 indicating the version of this capability is implemented
and thereby which bits in in run->s.regs.device_irq_level can signal values.

Currently the following bits are defined for the device_irq_level bitmap:

  KVM_CAP_ARM_USER_IRQ >= 1:

    KVM_ARM_DEV_EL1_VTIMER -  EL1 virtual timer
    KVM_ARM_DEV_EL1_PTIMER -  EL1 physical timer
    KVM_ARM_DEV_PMU        -  ARM PMU overflow interrupt signal

Future versions of kvm may implement additional events. These will get
indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
listed above.

8.10 KVM_CAP_PPC_SMT_POSSIBLE

Architectures: ppc

Querying this capability returns a bitmap indicating the possible
virtual SMT modes that can be set using KVM_CAP_PPC_SMT.  If bit N
(counting from the right) is set, then a virtual SMT mode of 2^N is
available.

8.11 KVM_CAP_HYPERV_SYNIC2

Architectures: x86

This capability enables a newer version of Hyper-V Synthetic interrupt
controller (SynIC).  The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
doesn't clear SynIC message and event flags pages when they are enabled by
writing to the respective MSRs.

8.12 KVM_CAP_HYPERV_VP_INDEX

Architectures: x86

This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr.  Its
value is used to denote the target vcpu for a SynIC interrupt.  For
compatibilty, KVM initializes this msr to KVM's internal vcpu index.  When this
capability is absent, userspace can still query this msr's value.

8.13 KVM_CAP_S390_AIS_MIGRATION

Architectures: s390
Parameters: none

This capability indicates if the flic device will be able to get/set the
AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
to discover this without having to create a flic device.