summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/kvm/lib/kvm_util.c
blob: 9741a7ff6380fe4caf4b6545cb522bed4c18620c (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * tools/testing/selftests/kvm/lib/kvm_util.c
 *
 * Copyright (C) 2018, Google LLC.
 */

#define _GNU_SOURCE /* for program_invocation_name */
#include "test_util.h"
#include "kvm_util.h"
#include "processor.h"

#include <assert.h>
#include <sched.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <linux/kernel.h>

#define KVM_UTIL_MIN_PFN	2

static int vcpu_mmap_sz(void);

int open_path_or_exit(const char *path, int flags)
{
	int fd;

	fd = open(path, flags);
	__TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno);

	return fd;
}

/*
 * Open KVM_DEV_PATH if available, otherwise exit the entire program.
 *
 * Input Args:
 *   flags - The flags to pass when opening KVM_DEV_PATH.
 *
 * Return:
 *   The opened file descriptor of /dev/kvm.
 */
static int _open_kvm_dev_path_or_exit(int flags)
{
	return open_path_or_exit(KVM_DEV_PATH, flags);
}

int open_kvm_dev_path_or_exit(void)
{
	return _open_kvm_dev_path_or_exit(O_RDONLY);
}

static bool get_module_param_bool(const char *module_name, const char *param)
{
	const int path_size = 128;
	char path[path_size];
	char value;
	ssize_t r;
	int fd;

	r = snprintf(path, path_size, "/sys/module/%s/parameters/%s",
		     module_name, param);
	TEST_ASSERT(r < path_size,
		    "Failed to construct sysfs path in %d bytes.", path_size);

	fd = open_path_or_exit(path, O_RDONLY);

	r = read(fd, &value, 1);
	TEST_ASSERT(r == 1, "read(%s) failed", path);

	r = close(fd);
	TEST_ASSERT(!r, "close(%s) failed", path);

	if (value == 'Y')
		return true;
	else if (value == 'N')
		return false;

	TEST_FAIL("Unrecognized value '%c' for boolean module param", value);
}

bool get_kvm_param_bool(const char *param)
{
	return get_module_param_bool("kvm", param);
}

bool get_kvm_intel_param_bool(const char *param)
{
	return get_module_param_bool("kvm_intel", param);
}

bool get_kvm_amd_param_bool(const char *param)
{
	return get_module_param_bool("kvm_amd", param);
}

/*
 * Capability
 *
 * Input Args:
 *   cap - Capability
 *
 * Output Args: None
 *
 * Return:
 *   On success, the Value corresponding to the capability (KVM_CAP_*)
 *   specified by the value of cap.  On failure a TEST_ASSERT failure
 *   is produced.
 *
 * Looks up and returns the value corresponding to the capability
 * (KVM_CAP_*) given by cap.
 */
unsigned int kvm_check_cap(long cap)
{
	int ret;
	int kvm_fd;

	kvm_fd = open_kvm_dev_path_or_exit();
	ret = __kvm_ioctl(kvm_fd, KVM_CHECK_EXTENSION, (void *)cap);
	TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret));

	close(kvm_fd);

	return (unsigned int)ret;
}

void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
{
	if (vm_check_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL))
		vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL, ring_size);
	else
		vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING, ring_size);
	vm->dirty_ring_size = ring_size;
}

static void vm_open(struct kvm_vm *vm)
{
	vm->kvm_fd = _open_kvm_dev_path_or_exit(O_RDWR);

	TEST_REQUIRE(kvm_has_cap(KVM_CAP_IMMEDIATE_EXIT));

	vm->fd = __kvm_ioctl(vm->kvm_fd, KVM_CREATE_VM, (void *)vm->type);
	TEST_ASSERT(vm->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm->fd));
}

const char *vm_guest_mode_string(uint32_t i)
{
	static const char * const strings[] = {
		[VM_MODE_P52V48_4K]	= "PA-bits:52,  VA-bits:48,  4K pages",
		[VM_MODE_P52V48_64K]	= "PA-bits:52,  VA-bits:48, 64K pages",
		[VM_MODE_P48V48_4K]	= "PA-bits:48,  VA-bits:48,  4K pages",
		[VM_MODE_P48V48_16K]	= "PA-bits:48,  VA-bits:48, 16K pages",
		[VM_MODE_P48V48_64K]	= "PA-bits:48,  VA-bits:48, 64K pages",
		[VM_MODE_P40V48_4K]	= "PA-bits:40,  VA-bits:48,  4K pages",
		[VM_MODE_P40V48_16K]	= "PA-bits:40,  VA-bits:48, 16K pages",
		[VM_MODE_P40V48_64K]	= "PA-bits:40,  VA-bits:48, 64K pages",
		[VM_MODE_PXXV48_4K]	= "PA-bits:ANY, VA-bits:48,  4K pages",
		[VM_MODE_P47V64_4K]	= "PA-bits:47,  VA-bits:64,  4K pages",
		[VM_MODE_P44V64_4K]	= "PA-bits:44,  VA-bits:64,  4K pages",
		[VM_MODE_P36V48_4K]	= "PA-bits:36,  VA-bits:48,  4K pages",
		[VM_MODE_P36V48_16K]	= "PA-bits:36,  VA-bits:48, 16K pages",
		[VM_MODE_P36V48_64K]	= "PA-bits:36,  VA-bits:48, 64K pages",
		[VM_MODE_P36V47_16K]	= "PA-bits:36,  VA-bits:47, 16K pages",
	};
	_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
		       "Missing new mode strings?");

	TEST_ASSERT(i < NUM_VM_MODES, "Guest mode ID %d too big", i);

	return strings[i];
}

const struct vm_guest_mode_params vm_guest_mode_params[] = {
	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
	[VM_MODE_P48V48_16K]	= { 48, 48,  0x4000, 14 },
	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
	[VM_MODE_P40V48_16K]	= { 40, 48,  0x4000, 14 },
	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
	[VM_MODE_P36V48_4K]	= { 36, 48,  0x1000, 12 },
	[VM_MODE_P36V48_16K]	= { 36, 48,  0x4000, 14 },
	[VM_MODE_P36V48_64K]	= { 36, 48, 0x10000, 16 },
	[VM_MODE_P36V47_16K]	= { 36, 47,  0x4000, 14 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
	       "Missing new mode params?");

/*
 * Initializes vm->vpages_valid to match the canonical VA space of the
 * architecture.
 *
 * The default implementation is valid for architectures which split the
 * range addressed by a single page table into a low and high region
 * based on the MSB of the VA. On architectures with this behavior
 * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1].
 */
__weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
{
	sparsebit_set_num(vm->vpages_valid,
		0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
	sparsebit_set_num(vm->vpages_valid,
		(~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift,
		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
}

struct kvm_vm *____vm_create(enum vm_guest_mode mode)
{
	struct kvm_vm *vm;

	vm = calloc(1, sizeof(*vm));
	TEST_ASSERT(vm != NULL, "Insufficient Memory");

	INIT_LIST_HEAD(&vm->vcpus);
	vm->regions.gpa_tree = RB_ROOT;
	vm->regions.hva_tree = RB_ROOT;
	hash_init(vm->regions.slot_hash);

	vm->mode = mode;
	vm->type = 0;

	vm->pa_bits = vm_guest_mode_params[mode].pa_bits;
	vm->va_bits = vm_guest_mode_params[mode].va_bits;
	vm->page_size = vm_guest_mode_params[mode].page_size;
	vm->page_shift = vm_guest_mode_params[mode].page_shift;

	/* Setup mode specific traits. */
	switch (vm->mode) {
	case VM_MODE_P52V48_4K:
		vm->pgtable_levels = 4;
		break;
	case VM_MODE_P52V48_64K:
		vm->pgtable_levels = 3;
		break;
	case VM_MODE_P48V48_4K:
		vm->pgtable_levels = 4;
		break;
	case VM_MODE_P48V48_64K:
		vm->pgtable_levels = 3;
		break;
	case VM_MODE_P40V48_4K:
	case VM_MODE_P36V48_4K:
		vm->pgtable_levels = 4;
		break;
	case VM_MODE_P40V48_64K:
	case VM_MODE_P36V48_64K:
		vm->pgtable_levels = 3;
		break;
	case VM_MODE_P48V48_16K:
	case VM_MODE_P40V48_16K:
	case VM_MODE_P36V48_16K:
		vm->pgtable_levels = 4;
		break;
	case VM_MODE_P36V47_16K:
		vm->pgtable_levels = 3;
		break;
	case VM_MODE_PXXV48_4K:
#ifdef __x86_64__
		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
		/*
		 * Ignore KVM support for 5-level paging (vm->va_bits == 57),
		 * it doesn't take effect unless a CR4.LA57 is set, which it
		 * isn't for this VM_MODE.
		 */
		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
			    "Linear address width (%d bits) not supported",
			    vm->va_bits);
		pr_debug("Guest physical address width detected: %d\n",
			 vm->pa_bits);
		vm->pgtable_levels = 4;
		vm->va_bits = 48;
#else
		TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
#endif
		break;
	case VM_MODE_P47V64_4K:
		vm->pgtable_levels = 5;
		break;
	case VM_MODE_P44V64_4K:
		vm->pgtable_levels = 5;
		break;
	default:
		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
	}

#ifdef __aarch64__
	if (vm->pa_bits != 40)
		vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits);
#endif

	vm_open(vm);

	/* Limit to VA-bit canonical virtual addresses. */
	vm->vpages_valid = sparsebit_alloc();
	vm_vaddr_populate_bitmap(vm);

	/* Limit physical addresses to PA-bits. */
	vm->max_gfn = vm_compute_max_gfn(vm);

	/* Allocate and setup memory for guest. */
	vm->vpages_mapped = sparsebit_alloc();

	return vm;
}

static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
				     uint32_t nr_runnable_vcpus,
				     uint64_t extra_mem_pages)
{
	uint64_t nr_pages;

	TEST_ASSERT(nr_runnable_vcpus,
		    "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");

	TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
		    "nr_vcpus = %d too large for host, max-vcpus = %d",
		    nr_runnable_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));

	/*
	 * Arbitrarily allocate 512 pages (2mb when page size is 4kb) for the
	 * test code and other per-VM assets that will be loaded into memslot0.
	 */
	nr_pages = 512;

	/* Account for the per-vCPU stacks on behalf of the test. */
	nr_pages += nr_runnable_vcpus * DEFAULT_STACK_PGS;

	/*
	 * Account for the number of pages needed for the page tables.  The
	 * maximum page table size for a memory region will be when the
	 * smallest page size is used. Considering each page contains x page
	 * table descriptors, the total extra size for page tables (for extra
	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
	 * than N/x*2.
	 */
	nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2;

	return vm_adjust_num_guest_pages(mode, nr_pages);
}

struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
			   uint64_t nr_extra_pages)
{
	uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
						 nr_extra_pages);
	struct userspace_mem_region *slot0;
	struct kvm_vm *vm;
	int i;

	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
		 vm_guest_mode_string(mode), nr_pages);

	vm = ____vm_create(mode);

	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
	for (i = 0; i < NR_MEM_REGIONS; i++)
		vm->memslots[i] = 0;

	kvm_vm_elf_load(vm, program_invocation_name);

	/*
	 * TODO: Add proper defines to protect the library's memslots, and then
	 * carve out memslot1 for the ucall MMIO address.  KVM treats writes to
	 * read-only memslots as MMIO, and creating a read-only memslot for the
	 * MMIO region would prevent silently clobbering the MMIO region.
	 */
	slot0 = memslot2region(vm, 0);
	ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);

	kvm_arch_vm_post_create(vm);

	return vm;
}

/*
 * VM Create with customized parameters
 *
 * Input Args:
 *   mode - VM Mode (e.g. VM_MODE_P52V48_4K)
 *   nr_vcpus - VCPU count
 *   extra_mem_pages - Non-slot0 physical memory total size
 *   guest_code - Guest entry point
 *   vcpuids - VCPU IDs
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to opaque structure that describes the created VM.
 *
 * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K).
 * extra_mem_pages is only used to calculate the maximum page table size,
 * no real memory allocation for non-slot0 memory in this function.
 */
struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
				      uint64_t extra_mem_pages,
				      void *guest_code, struct kvm_vcpu *vcpus[])
{
	struct kvm_vm *vm;
	int i;

	TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array");

	vm = __vm_create(mode, nr_vcpus, extra_mem_pages);

	for (i = 0; i < nr_vcpus; ++i)
		vcpus[i] = vm_vcpu_add(vm, i, guest_code);

	return vm;
}

struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
					 uint64_t extra_mem_pages,
					 void *guest_code)
{
	struct kvm_vcpu *vcpus[1];
	struct kvm_vm *vm;

	vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages,
				    guest_code, vcpus);

	*vcpu = vcpus[0];
	return vm;
}

/*
 * VM Restart
 *
 * Input Args:
 *   vm - VM that has been released before
 *
 * Output Args: None
 *
 * Reopens the file descriptors associated to the VM and reinstates the
 * global state, such as the irqchip and the memory regions that are mapped
 * into the guest.
 */
void kvm_vm_restart(struct kvm_vm *vmp)
{
	int ctr;
	struct userspace_mem_region *region;

	vm_open(vmp);
	if (vmp->has_irqchip)
		vm_create_irqchip(vmp);

	hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) {
		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
			    "  rc: %i errno: %i\n"
			    "  slot: %u flags: 0x%x\n"
			    "  guest_phys_addr: 0x%llx size: 0x%llx",
			    ret, errno, region->region.slot,
			    region->region.flags,
			    region->region.guest_phys_addr,
			    region->region.memory_size);
	}
}

__weak struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm,
					      uint32_t vcpu_id)
{
	return __vm_vcpu_add(vm, vcpu_id);
}

struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm)
{
	kvm_vm_restart(vm);

	return vm_vcpu_recreate(vm, 0);
}

void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
{
	cpu_set_t mask;
	int r;

	CPU_ZERO(&mask);
	CPU_SET(pcpu, &mask);
	r = sched_setaffinity(0, sizeof(mask), &mask);
	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
}

static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
{
	uint32_t pcpu = atoi_non_negative("CPU number", cpu_str);

	TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask),
		    "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu);
	return pcpu;
}

void kvm_print_vcpu_pinning_help(void)
{
	const char *name = program_invocation_name;

	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
	       "     values (target pCPU), one for each vCPU, plus an optional\n"
	       "     entry for the main application task (specified via entry\n"
	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
	       "         %s -v 3 -c 22,23,24,50\n\n"
	       "     To leave the application task unpinned, drop the final entry:\n\n"
	       "         %s -v 3 -c 22,23,24\n\n"
	       "     (default: no pinning)\n", name, name);
}

void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
			    int nr_vcpus)
{
	cpu_set_t allowed_mask;
	char *cpu, *cpu_list;
	char delim[2] = ",";
	int i, r;

	cpu_list = strdup(pcpus_string);
	TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");

	r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
	TEST_ASSERT(!r, "sched_getaffinity() failed");

	cpu = strtok(cpu_list, delim);

	/* 1. Get all pcpus for vcpus. */
	for (i = 0; i < nr_vcpus; i++) {
		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
		vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
		cpu = strtok(NULL, delim);
	}

	/* 2. Check if the main worker needs to be pinned. */
	if (cpu) {
		kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask));
		cpu = strtok(NULL, delim);
	}

	TEST_ASSERT(!cpu, "pCPU list contains trailing garbage characters '%s'", cpu);
	free(cpu_list);
}

/*
 * Userspace Memory Region Find
 *
 * Input Args:
 *   vm - Virtual Machine
 *   start - Starting VM physical address
 *   end - Ending VM physical address, inclusive.
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to overlapping region, NULL if no such region.
 *
 * Searches for a region with any physical memory that overlaps with
 * any portion of the guest physical addresses from start to end
 * inclusive.  If multiple overlapping regions exist, a pointer to any
 * of the regions is returned.  Null is returned only when no overlapping
 * region exists.
 */
static struct userspace_mem_region *
userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
{
	struct rb_node *node;

	for (node = vm->regions.gpa_tree.rb_node; node; ) {
		struct userspace_mem_region *region =
			container_of(node, struct userspace_mem_region, gpa_node);
		uint64_t existing_start = region->region.guest_phys_addr;
		uint64_t existing_end = region->region.guest_phys_addr
			+ region->region.memory_size - 1;
		if (start <= existing_end && end >= existing_start)
			return region;

		if (start < existing_start)
			node = node->rb_left;
		else
			node = node->rb_right;
	}

	return NULL;
}

/*
 * KVM Userspace Memory Region Find
 *
 * Input Args:
 *   vm - Virtual Machine
 *   start - Starting VM physical address
 *   end - Ending VM physical address, inclusive.
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to overlapping region, NULL if no such region.
 *
 * Public interface to userspace_mem_region_find. Allows tests to look up
 * the memslot datastructure for a given range of guest physical memory.
 */
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
				 uint64_t end)
{
	struct userspace_mem_region *region;

	region = userspace_mem_region_find(vm, start, end);
	if (!region)
		return NULL;

	return &region->region;
}

__weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
{

}

/*
 * VM VCPU Remove
 *
 * Input Args:
 *   vcpu - VCPU to remove
 *
 * Output Args: None
 *
 * Return: None, TEST_ASSERT failures for all error conditions
 *
 * Removes a vCPU from a VM and frees its resources.
 */
static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
{
	int ret;

	if (vcpu->dirty_gfns) {
		ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
		vcpu->dirty_gfns = NULL;
	}

	ret = munmap(vcpu->run, vcpu_mmap_sz());
	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));

	ret = close(vcpu->fd);
	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));

	list_del(&vcpu->list);

	vcpu_arch_free(vcpu);
	free(vcpu);
}

void kvm_vm_release(struct kvm_vm *vmp)
{
	struct kvm_vcpu *vcpu, *tmp;
	int ret;

	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
		vm_vcpu_rm(vmp, vcpu);

	ret = close(vmp->fd);
	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));

	ret = close(vmp->kvm_fd);
	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
}

static void __vm_mem_region_delete(struct kvm_vm *vm,
				   struct userspace_mem_region *region,
				   bool unlink)
{
	int ret;

	if (unlink) {
		rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
		rb_erase(&region->hva_node, &vm->regions.hva_tree);
		hash_del(&region->slot_node);
	}

	region->region.memory_size = 0;
	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);

	sparsebit_free(&region->unused_phy_pages);
	ret = munmap(region->mmap_start, region->mmap_size);
	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
	if (region->fd >= 0) {
		/* There's an extra map when using shared memory. */
		ret = munmap(region->mmap_alias, region->mmap_size);
		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
		close(region->fd);
	}

	free(region);
}

/*
 * Destroys and frees the VM pointed to by vmp.
 */
void kvm_vm_free(struct kvm_vm *vmp)
{
	int ctr;
	struct hlist_node *node;
	struct userspace_mem_region *region;

	if (vmp == NULL)
		return;

	/* Free cached stats metadata and close FD */
	if (vmp->stats_fd) {
		free(vmp->stats_desc);
		close(vmp->stats_fd);
	}

	/* Free userspace_mem_regions. */
	hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
		__vm_mem_region_delete(vmp, region, false);

	/* Free sparsebit arrays. */
	sparsebit_free(&vmp->vpages_valid);
	sparsebit_free(&vmp->vpages_mapped);

	kvm_vm_release(vmp);

	/* Free the structure describing the VM. */
	free(vmp);
}

int kvm_memfd_alloc(size_t size, bool hugepages)
{
	int memfd_flags = MFD_CLOEXEC;
	int fd, r;

	if (hugepages)
		memfd_flags |= MFD_HUGETLB;

	fd = memfd_create("kvm_selftest", memfd_flags);
	TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd));

	r = ftruncate(fd, size);
	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("ftruncate()", r));

	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));

	return fd;
}

/*
 * Memory Compare, host virtual to guest virtual
 *
 * Input Args:
 *   hva - Starting host virtual address
 *   vm - Virtual Machine
 *   gva - Starting guest virtual address
 *   len - number of bytes to compare
 *
 * Output Args: None
 *
 * Input/Output Args: None
 *
 * Return:
 *   Returns 0 if the bytes starting at hva for a length of len
 *   are equal the guest virtual bytes starting at gva.  Returns
 *   a value < 0, if bytes at hva are less than those at gva.
 *   Otherwise a value > 0 is returned.
 *
 * Compares the bytes starting at the host virtual address hva, for
 * a length of len, to the guest bytes starting at the guest virtual
 * address given by gva.
 */
int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
{
	size_t amt;

	/*
	 * Compare a batch of bytes until either a match is found
	 * or all the bytes have been compared.
	 */
	for (uintptr_t offset = 0; offset < len; offset += amt) {
		uintptr_t ptr1 = (uintptr_t)hva + offset;

		/*
		 * Determine host address for guest virtual address
		 * at offset.
		 */
		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);

		/*
		 * Determine amount to compare on this pass.
		 * Don't allow the comparsion to cross a page boundary.
		 */
		amt = len - offset;
		if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift))
			amt = vm->page_size - (ptr1 % vm->page_size);
		if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift))
			amt = vm->page_size - (ptr2 % vm->page_size);

		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));

		/*
		 * Perform the comparison.  If there is a difference
		 * return that result to the caller, otherwise need
		 * to continue on looking for a mismatch.
		 */
		int ret = memcmp((void *)ptr1, (void *)ptr2, amt);
		if (ret != 0)
			return ret;
	}

	/*
	 * No mismatch found.  Let the caller know the two memory
	 * areas are equal.
	 */
	return 0;
}

static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree,
					       struct userspace_mem_region *region)
{
	struct rb_node **cur, *parent;

	for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) {
		struct userspace_mem_region *cregion;

		cregion = container_of(*cur, typeof(*cregion), gpa_node);
		parent = *cur;
		if (region->region.guest_phys_addr <
		    cregion->region.guest_phys_addr)
			cur = &(*cur)->rb_left;
		else {
			TEST_ASSERT(region->region.guest_phys_addr !=
				    cregion->region.guest_phys_addr,
				    "Duplicate GPA in region tree");

			cur = &(*cur)->rb_right;
		}
	}

	rb_link_node(&region->gpa_node, parent, cur);
	rb_insert_color(&region->gpa_node, gpa_tree);
}

static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
					       struct userspace_mem_region *region)
{
	struct rb_node **cur, *parent;

	for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) {
		struct userspace_mem_region *cregion;

		cregion = container_of(*cur, typeof(*cregion), hva_node);
		parent = *cur;
		if (region->host_mem < cregion->host_mem)
			cur = &(*cur)->rb_left;
		else {
			TEST_ASSERT(region->host_mem !=
				    cregion->host_mem,
				    "Duplicate HVA in region tree");

			cur = &(*cur)->rb_right;
		}
	}

	rb_link_node(&region->hva_node, parent, cur);
	rb_insert_color(&region->hva_node, hva_tree);
}


int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
				uint64_t gpa, uint64_t size, void *hva)
{
	struct kvm_userspace_memory_region region = {
		.slot = slot,
		.flags = flags,
		.guest_phys_addr = gpa,
		.memory_size = size,
		.userspace_addr = (uintptr_t)hva,
	};

	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region);
}

void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
			       uint64_t gpa, uint64_t size, void *hva)
{
	int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva);

	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)",
		    errno, strerror(errno));
}

/*
 * VM Userspace Memory Region Add
 *
 * Input Args:
 *   vm - Virtual Machine
 *   src_type - Storage source for this region.
 *              NULL to use anonymous memory.
 *   guest_paddr - Starting guest physical address
 *   slot - KVM region slot
 *   npages - Number of physical pages
 *   flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES)
 *
 * Output Args: None
 *
 * Return: None
 *
 * Allocates a memory area of the number of pages specified by npages
 * and maps it to the VM specified by vm, at a starting physical address
 * given by guest_paddr.  The region is created with a KVM region slot
 * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM.  The
 * region is created with the flags given by flags.
 */
void vm_userspace_mem_region_add(struct kvm_vm *vm,
	enum vm_mem_backing_src_type src_type,
	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
	uint32_t flags)
{
	int ret;
	struct userspace_mem_region *region;
	size_t backing_src_pagesz = get_backing_src_pagesz(src_type);
	size_t alignment;

	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
		"Number of guest pages is not compatible with the host. "
		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));

	TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
		"address not on a page boundary.\n"
		"  guest_paddr: 0x%lx vm->page_size: 0x%x",
		guest_paddr, vm->page_size);
	TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1)
		<= vm->max_gfn, "Physical range beyond maximum "
		"supported physical address,\n"
		"  guest_paddr: 0x%lx npages: 0x%lx\n"
		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
		guest_paddr, npages, vm->max_gfn, vm->page_size);

	/*
	 * Confirm a mem region with an overlapping address doesn't
	 * already exist.
	 */
	region = (struct userspace_mem_region *) userspace_mem_region_find(
		vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
	if (region != NULL)
		TEST_FAIL("overlapping userspace_mem_region already "
			"exists\n"
			"  requested guest_paddr: 0x%lx npages: 0x%lx "
			"page_size: 0x%x\n"
			"  existing guest_paddr: 0x%lx size: 0x%lx",
			guest_paddr, npages, vm->page_size,
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size);

	/* Confirm no region with the requested slot already exists. */
	hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
			       slot) {
		if (region->region.slot != slot)
			continue;

		TEST_FAIL("A mem region with the requested slot "
			"already exists.\n"
			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
			"  existing slot: %u paddr: 0x%lx size: 0x%lx",
			slot, guest_paddr, npages,
			region->region.slot,
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size);
	}

	/* Allocate and initialize new mem region structure. */
	region = calloc(1, sizeof(*region));
	TEST_ASSERT(region != NULL, "Insufficient Memory");
	region->mmap_size = npages * vm->page_size;

#ifdef __s390x__
	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
	alignment = 0x100000;
#else
	alignment = 1;
#endif

	/*
	 * When using THP mmap is not guaranteed to returned a hugepage aligned
	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
	 * because mmap will always return an address aligned to the HugeTLB
	 * page size.
	 */
	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
		alignment = max(backing_src_pagesz, alignment);

	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));

	/* Add enough memory to align up if necessary */
	if (alignment > 1)
		region->mmap_size += alignment;

	region->fd = -1;
	if (backing_src_is_shared(src_type))
		region->fd = kvm_memfd_alloc(region->mmap_size,
					     src_type == VM_MEM_SRC_SHARED_HUGETLB);

	region->mmap_start = mmap(NULL, region->mmap_size,
				  PROT_READ | PROT_WRITE,
				  vm_mem_backing_src_alias(src_type)->flag,
				  region->fd, 0);
	TEST_ASSERT(region->mmap_start != MAP_FAILED,
		    __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED));

	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
		    region->mmap_start, backing_src_pagesz);

	/* Align host address */
	region->host_mem = align_ptr_up(region->mmap_start, alignment);

	/* As needed perform madvise */
	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
	     src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) {
		ret = madvise(region->host_mem, npages * vm->page_size,
			      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
		TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s",
			    region->host_mem, npages * vm->page_size,
			    vm_mem_backing_src_alias(src_type)->name);
	}

	region->backing_src_type = src_type;
	region->unused_phy_pages = sparsebit_alloc();
	sparsebit_set_num(region->unused_phy_pages,
		guest_paddr >> vm->page_shift, npages);
	region->region.slot = slot;
	region->region.flags = flags;
	region->region.guest_phys_addr = guest_paddr;
	region->region.memory_size = npages * vm->page_size;
	region->region.userspace_addr = (uintptr_t) region->host_mem;
	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
		"  rc: %i errno: %i\n"
		"  slot: %u flags: 0x%x\n"
		"  guest_phys_addr: 0x%lx size: 0x%lx",
		ret, errno, slot, flags,
		guest_paddr, (uint64_t) region->region.memory_size);

	/* Add to quick lookup data structures */
	vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
	vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region);
	hash_add(vm->regions.slot_hash, &region->slot_node, slot);

	/* If shared memory, create an alias. */
	if (region->fd >= 0) {
		region->mmap_alias = mmap(NULL, region->mmap_size,
					  PROT_READ | PROT_WRITE,
					  vm_mem_backing_src_alias(src_type)->flag,
					  region->fd, 0);
		TEST_ASSERT(region->mmap_alias != MAP_FAILED,
			    __KVM_SYSCALL_ERROR("mmap()",  (int)(unsigned long)MAP_FAILED));

		/* Align host alias address */
		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
	}
}

/*
 * Memslot to region
 *
 * Input Args:
 *   vm - Virtual Machine
 *   memslot - KVM memory slot ID
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to memory region structure that describe memory region
 *   using kvm memory slot ID given by memslot.  TEST_ASSERT failure
 *   on error (e.g. currently no memory region using memslot as a KVM
 *   memory slot ID).
 */
struct userspace_mem_region *
memslot2region(struct kvm_vm *vm, uint32_t memslot)
{
	struct userspace_mem_region *region;

	hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
			       memslot)
		if (region->region.slot == memslot)
			return region;

	fprintf(stderr, "No mem region with the requested slot found,\n"
		"  requested slot: %u\n", memslot);
	fputs("---- vm dump ----\n", stderr);
	vm_dump(stderr, vm, 2);
	TEST_FAIL("Mem region not found");
	return NULL;
}

/*
 * VM Memory Region Flags Set
 *
 * Input Args:
 *   vm - Virtual Machine
 *   flags - Starting guest physical address
 *
 * Output Args: None
 *
 * Return: None
 *
 * Sets the flags of the memory region specified by the value of slot,
 * to the values given by flags.
 */
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
{
	int ret;
	struct userspace_mem_region *region;

	region = memslot2region(vm, slot);

	region->region.flags = flags;

	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);

	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
		"  rc: %i errno: %i slot: %u flags: 0x%x",
		ret, errno, slot, flags);
}

/*
 * VM Memory Region Move
 *
 * Input Args:
 *   vm - Virtual Machine
 *   slot - Slot of the memory region to move
 *   new_gpa - Starting guest physical address
 *
 * Output Args: None
 *
 * Return: None
 *
 * Change the gpa of a memory region.
 */
void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
{
	struct userspace_mem_region *region;
	int ret;

	region = memslot2region(vm, slot);

	region->region.guest_phys_addr = new_gpa;

	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);

	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n"
		    "ret: %i errno: %i slot: %u new_gpa: 0x%lx",
		    ret, errno, slot, new_gpa);
}

/*
 * VM Memory Region Delete
 *
 * Input Args:
 *   vm - Virtual Machine
 *   slot - Slot of the memory region to delete
 *
 * Output Args: None
 *
 * Return: None
 *
 * Delete a memory region.
 */
void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
{
	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
}

/* Returns the size of a vCPU's kvm_run structure. */
static int vcpu_mmap_sz(void)
{
	int dev_fd, ret;

	dev_fd = open_kvm_dev_path_or_exit();

	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
	TEST_ASSERT(ret >= sizeof(struct kvm_run),
		    KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret));

	close(dev_fd);

	return ret;
}

static bool vcpu_exists(struct kvm_vm *vm, uint32_t vcpu_id)
{
	struct kvm_vcpu *vcpu;

	list_for_each_entry(vcpu, &vm->vcpus, list) {
		if (vcpu->id == vcpu_id)
			return true;
	}

	return false;
}

/*
 * Adds a virtual CPU to the VM specified by vm with the ID given by vcpu_id.
 * No additional vCPU setup is done.  Returns the vCPU.
 */
struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
{
	struct kvm_vcpu *vcpu;

	/* Confirm a vcpu with the specified id doesn't already exist. */
	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id);

	/* Allocate and initialize new vcpu structure. */
	vcpu = calloc(1, sizeof(*vcpu));
	TEST_ASSERT(vcpu != NULL, "Insufficient Memory");

	vcpu->vm = vm;
	vcpu->id = vcpu_id;
	vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id);
	TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd));

	TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size "
		"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
		vcpu_mmap_sz(), sizeof(*vcpu->run));
	vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(),
		PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);
	TEST_ASSERT(vcpu->run != MAP_FAILED,
		    __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED));

	/* Add to linked-list of VCPUs. */
	list_add(&vcpu->list, &vm->vcpus);

	return vcpu;
}

/*
 * VM Virtual Address Unused Gap
 *
 * Input Args:
 *   vm - Virtual Machine
 *   sz - Size (bytes)
 *   vaddr_min - Minimum Virtual Address
 *
 * Output Args: None
 *
 * Return:
 *   Lowest virtual address at or below vaddr_min, with at least
 *   sz unused bytes.  TEST_ASSERT failure if no area of at least
 *   size sz is available.
 *
 * Within the VM specified by vm, locates the lowest starting virtual
 * address >= vaddr_min, that has at least sz unallocated bytes.  A
 * TEST_ASSERT failure occurs for invalid input or no area of at least
 * sz unallocated bytes >= vaddr_min is available.
 */
vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
			       vm_vaddr_t vaddr_min)
{
	uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;

	/* Determine lowest permitted virtual page index. */
	uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
	if ((pgidx_start * vm->page_size) < vaddr_min)
		goto no_va_found;

	/* Loop over section with enough valid virtual page indexes. */
	if (!sparsebit_is_set_num(vm->vpages_valid,
		pgidx_start, pages))
		pgidx_start = sparsebit_next_set_num(vm->vpages_valid,
			pgidx_start, pages);
	do {
		/*
		 * Are there enough unused virtual pages available at
		 * the currently proposed starting virtual page index.
		 * If not, adjust proposed starting index to next
		 * possible.
		 */
		if (sparsebit_is_clear_num(vm->vpages_mapped,
			pgidx_start, pages))
			goto va_found;
		pgidx_start = sparsebit_next_clear_num(vm->vpages_mapped,
			pgidx_start, pages);
		if (pgidx_start == 0)
			goto no_va_found;

		/*
		 * If needed, adjust proposed starting virtual address,
		 * to next range of valid virtual addresses.
		 */
		if (!sparsebit_is_set_num(vm->vpages_valid,
			pgidx_start, pages)) {
			pgidx_start = sparsebit_next_set_num(
				vm->vpages_valid, pgidx_start, pages);
			if (pgidx_start == 0)
				goto no_va_found;
		}
	} while (pgidx_start != 0);

no_va_found:
	TEST_FAIL("No vaddr of specified pages available, pages: 0x%lx", pages);

	/* NOT REACHED */
	return -1;

va_found:
	TEST_ASSERT(sparsebit_is_set_num(vm->vpages_valid,
		pgidx_start, pages),
		"Unexpected, invalid virtual page index range,\n"
		"  pgidx_start: 0x%lx\n"
		"  pages: 0x%lx",
		pgidx_start, pages);
	TEST_ASSERT(sparsebit_is_clear_num(vm->vpages_mapped,
		pgidx_start, pages),
		"Unexpected, pages already mapped,\n"
		"  pgidx_start: 0x%lx\n"
		"  pages: 0x%lx",
		pgidx_start, pages);

	return pgidx_start * vm->page_size;
}

vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
			    enum kvm_mem_region_type type)
{
	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);

	virt_pgd_alloc(vm);
	vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
					      KVM_UTIL_MIN_PFN * vm->page_size,
					      vm->memslots[type]);

	/*
	 * Find an unused range of virtual page addresses of at least
	 * pages in length.
	 */
	vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);

	/* Map the virtual pages. */
	for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
		pages--, vaddr += vm->page_size, paddr += vm->page_size) {

		virt_pg_map(vm, vaddr, paddr);

		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
	}

	return vaddr_start;
}

/*
 * VM Virtual Address Allocate
 *
 * Input Args:
 *   vm - Virtual Machine
 *   sz - Size in bytes
 *   vaddr_min - Minimum starting virtual address
 *
 * Output Args: None
 *
 * Return:
 *   Starting guest virtual address
 *
 * Allocates at least sz bytes within the virtual address space of the vm
 * given by vm.  The allocated bytes are mapped to a virtual address >=
 * the address given by vaddr_min.  Note that each allocation uses a
 * a unique set of pages, with the minimum real allocation being at least
 * a page. The allocated physical space comes from the TEST_DATA memory region.
 */
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
{
	return __vm_vaddr_alloc(vm, sz, vaddr_min, MEM_REGION_TEST_DATA);
}

/*
 * VM Virtual Address Allocate Pages
 *
 * Input Args:
 *   vm - Virtual Machine
 *
 * Output Args: None
 *
 * Return:
 *   Starting guest virtual address
 *
 * Allocates at least N system pages worth of bytes within the virtual address
 * space of the vm.
 */
vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages)
{
	return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR);
}

vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type)
{
	return __vm_vaddr_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type);
}

/*
 * VM Virtual Address Allocate Page
 *
 * Input Args:
 *   vm - Virtual Machine
 *
 * Output Args: None
 *
 * Return:
 *   Starting guest virtual address
 *
 * Allocates at least one system page worth of bytes within the virtual address
 * space of the vm.
 */
vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm)
{
	return vm_vaddr_alloc_pages(vm, 1);
}

/*
 * Map a range of VM virtual address to the VM's physical address
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vaddr - Virtuall address to map
 *   paddr - VM Physical Address
 *   npages - The number of pages to map
 *
 * Output Args: None
 *
 * Return: None
 *
 * Within the VM given by @vm, creates a virtual translation for
 * @npages starting at @vaddr to the page range starting at @paddr.
 */
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
	      unsigned int npages)
{
	size_t page_size = vm->page_size;
	size_t size = npages * page_size;

	TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow");
	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");

	while (npages--) {
		virt_pg_map(vm, vaddr, paddr);
		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);

		vaddr += page_size;
		paddr += page_size;
	}
}

/*
 * Address VM Physical to Host Virtual
 *
 * Input Args:
 *   vm - Virtual Machine
 *   gpa - VM physical address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent host virtual address
 *
 * Locates the memory region containing the VM physical address given
 * by gpa, within the VM given by vm.  When found, the host virtual
 * address providing the memory to the vm physical address is returned.
 * A TEST_ASSERT failure occurs if no region containing gpa exists.
 */
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
{
	struct userspace_mem_region *region;

	region = userspace_mem_region_find(vm, gpa, gpa);
	if (!region) {
		TEST_FAIL("No vm physical memory at 0x%lx", gpa);
		return NULL;
	}

	return (void *)((uintptr_t)region->host_mem
		+ (gpa - region->region.guest_phys_addr));
}

/*
 * Address Host Virtual to VM Physical
 *
 * Input Args:
 *   vm - Virtual Machine
 *   hva - Host virtual address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent VM physical address
 *
 * Locates the memory region containing the host virtual address given
 * by hva, within the VM given by vm.  When found, the equivalent
 * VM physical address is returned. A TEST_ASSERT failure occurs if no
 * region containing hva exists.
 */
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
{
	struct rb_node *node;

	for (node = vm->regions.hva_tree.rb_node; node; ) {
		struct userspace_mem_region *region =
			container_of(node, struct userspace_mem_region, hva_node);

		if (hva >= region->host_mem) {
			if (hva <= (region->host_mem
				+ region->region.memory_size - 1))
				return (vm_paddr_t)((uintptr_t)
					region->region.guest_phys_addr
					+ (hva - (uintptr_t)region->host_mem));

			node = node->rb_right;
		} else
			node = node->rb_left;
	}

	TEST_FAIL("No mapping to a guest physical address, hva: %p", hva);
	return -1;
}

/*
 * Address VM physical to Host Virtual *alias*.
 *
 * Input Args:
 *   vm - Virtual Machine
 *   gpa - VM physical address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent address within the host virtual *alias* area, or NULL
 *   (without failing the test) if the guest memory is not shared (so
 *   no alias exists).
 *
 * Create a writable, shared virtual=>physical alias for the specific GPA.
 * The primary use case is to allow the host selftest to manipulate guest
 * memory without mapping said memory in the guest's address space. And, for
 * userfaultfd-based demand paging, to do so without triggering userfaults.
 */
void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa)
{
	struct userspace_mem_region *region;
	uintptr_t offset;

	region = userspace_mem_region_find(vm, gpa, gpa);
	if (!region)
		return NULL;

	if (!region->host_alias)
		return NULL;

	offset = gpa - region->region.guest_phys_addr;
	return (void *) ((uintptr_t) region->host_alias + offset);
}

/* Create an interrupt controller chip for the specified VM. */
void vm_create_irqchip(struct kvm_vm *vm)
{
	vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL);

	vm->has_irqchip = true;
}

int _vcpu_run(struct kvm_vcpu *vcpu)
{
	int rc;

	do {
		rc = __vcpu_run(vcpu);
	} while (rc == -1 && errno == EINTR);

	assert_on_unhandled_exception(vcpu);

	return rc;
}

/*
 * Invoke KVM_RUN on a vCPU until KVM returns something other than -EINTR.
 * Assert if the KVM returns an error (other than -EINTR).
 */
void vcpu_run(struct kvm_vcpu *vcpu)
{
	int ret = _vcpu_run(vcpu);

	TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_RUN, ret));
}

void vcpu_run_complete_io(struct kvm_vcpu *vcpu)
{
	int ret;

	vcpu->run->immediate_exit = 1;
	ret = __vcpu_run(vcpu);
	vcpu->run->immediate_exit = 0;

	TEST_ASSERT(ret == -1 && errno == EINTR,
		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
		    ret, errno);
}

/*
 * Get the list of guest registers which are supported for
 * KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls.  Returns a kvm_reg_list pointer,
 * it is the caller's responsibility to free the list.
 */
struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu)
{
	struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
	int ret;

	ret = __vcpu_ioctl(vcpu, KVM_GET_REG_LIST, &reg_list_n);
	TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");

	reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
	reg_list->n = reg_list_n.n;
	vcpu_ioctl(vcpu, KVM_GET_REG_LIST, reg_list);
	return reg_list;
}

void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu)
{
	uint32_t page_size = getpagesize();
	uint32_t size = vcpu->vm->dirty_ring_size;

	TEST_ASSERT(size > 0, "Should enable dirty ring first");

	if (!vcpu->dirty_gfns) {
		void *addr;

		addr = mmap(NULL, size, PROT_READ, MAP_PRIVATE, vcpu->fd,
			    page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private");

		addr = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_PRIVATE, vcpu->fd,
			    page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec");

		addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd,
			    page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
		TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed");

		vcpu->dirty_gfns = addr;
		vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn);
	}

	return vcpu->dirty_gfns;
}

/*
 * Device Ioctl
 */

int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr)
{
	struct kvm_device_attr attribute = {
		.group = group,
		.attr = attr,
		.flags = 0,
	};

	return ioctl(dev_fd, KVM_HAS_DEVICE_ATTR, &attribute);
}

int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type)
{
	struct kvm_create_device create_dev = {
		.type = type,
		.flags = KVM_CREATE_DEVICE_TEST,
	};

	return __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev);
}

int __kvm_create_device(struct kvm_vm *vm, uint64_t type)
{
	struct kvm_create_device create_dev = {
		.type = type,
		.fd = -1,
		.flags = 0,
	};
	int err;

	err = __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev);
	TEST_ASSERT(err <= 0, "KVM_CREATE_DEVICE shouldn't return a positive value");
	return err ? : create_dev.fd;
}

int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val)
{
	struct kvm_device_attr kvmattr = {
		.group = group,
		.attr = attr,
		.flags = 0,
		.addr = (uintptr_t)val,
	};

	return __kvm_ioctl(dev_fd, KVM_GET_DEVICE_ATTR, &kvmattr);
}

int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val)
{
	struct kvm_device_attr kvmattr = {
		.group = group,
		.attr = attr,
		.flags = 0,
		.addr = (uintptr_t)val,
	};

	return __kvm_ioctl(dev_fd, KVM_SET_DEVICE_ATTR, &kvmattr);
}

/*
 * IRQ related functions.
 */

int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
{
	struct kvm_irq_level irq_level = {
		.irq    = irq,
		.level  = level,
	};

	return __vm_ioctl(vm, KVM_IRQ_LINE, &irq_level);
}

void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
{
	int ret = _kvm_irq_line(vm, irq, level);

	TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret));
}

struct kvm_irq_routing *kvm_gsi_routing_create(void)
{
	struct kvm_irq_routing *routing;
	size_t size;

	size = sizeof(struct kvm_irq_routing);
	/* Allocate space for the max number of entries: this wastes 196 KBs. */
	size += KVM_MAX_IRQ_ROUTES * sizeof(struct kvm_irq_routing_entry);
	routing = calloc(1, size);
	assert(routing);

	return routing;
}

void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
		uint32_t gsi, uint32_t pin)
{
	int i;

	assert(routing);
	assert(routing->nr < KVM_MAX_IRQ_ROUTES);

	i = routing->nr;
	routing->entries[i].gsi = gsi;
	routing->entries[i].type = KVM_IRQ_ROUTING_IRQCHIP;
	routing->entries[i].flags = 0;
	routing->entries[i].u.irqchip.irqchip = 0;
	routing->entries[i].u.irqchip.pin = pin;
	routing->nr++;
}

int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
{
	int ret;

	assert(routing);
	ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing);
	free(routing);

	return ret;
}

void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
{
	int ret;

	ret = _kvm_gsi_routing_write(vm, routing);
	TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_GSI_ROUTING, ret));
}

/*
 * VM Dump
 *
 * Input Args:
 *   vm - Virtual Machine
 *   indent - Left margin indent amount
 *
 * Output Args:
 *   stream - Output FILE stream
 *
 * Return: None
 *
 * Dumps the current state of the VM given by vm, to the FILE stream
 * given by stream.
 */
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
	int ctr;
	struct userspace_mem_region *region;
	struct kvm_vcpu *vcpu;

	fprintf(stream, "%*smode: 0x%x\n", indent, "", vm->mode);
	fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
	fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
	fprintf(stream, "%*sMem Regions:\n", indent, "");
	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) {
		fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
			"host_virt: %p\n", indent + 2, "",
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size,
			region->host_mem);
		fprintf(stream, "%*sunused_phy_pages: ", indent + 2, "");
		sparsebit_dump(stream, region->unused_phy_pages, 0);
	}
	fprintf(stream, "%*sMapped Virtual Pages:\n", indent, "");
	sparsebit_dump(stream, vm->vpages_mapped, indent + 2);
	fprintf(stream, "%*spgd_created: %u\n", indent, "",
		vm->pgd_created);
	if (vm->pgd_created) {
		fprintf(stream, "%*sVirtual Translation Tables:\n",
			indent + 2, "");
		virt_dump(stream, vm, indent + 4);
	}
	fprintf(stream, "%*sVCPUs:\n", indent, "");

	list_for_each_entry(vcpu, &vm->vcpus, list)
		vcpu_dump(stream, vcpu, indent + 2);
}

#define KVM_EXIT_STRING(x) {KVM_EXIT_##x, #x}

/* Known KVM exit reasons */
static struct exit_reason {
	unsigned int reason;
	const char *name;
} exit_reasons_known[] = {
	KVM_EXIT_STRING(UNKNOWN),
	KVM_EXIT_STRING(EXCEPTION),
	KVM_EXIT_STRING(IO),
	KVM_EXIT_STRING(HYPERCALL),
	KVM_EXIT_STRING(DEBUG),
	KVM_EXIT_STRING(HLT),
	KVM_EXIT_STRING(MMIO),
	KVM_EXIT_STRING(IRQ_WINDOW_OPEN),
	KVM_EXIT_STRING(SHUTDOWN),
	KVM_EXIT_STRING(FAIL_ENTRY),
	KVM_EXIT_STRING(INTR),
	KVM_EXIT_STRING(SET_TPR),
	KVM_EXIT_STRING(TPR_ACCESS),
	KVM_EXIT_STRING(S390_SIEIC),
	KVM_EXIT_STRING(S390_RESET),
	KVM_EXIT_STRING(DCR),
	KVM_EXIT_STRING(NMI),
	KVM_EXIT_STRING(INTERNAL_ERROR),
	KVM_EXIT_STRING(OSI),
	KVM_EXIT_STRING(PAPR_HCALL),
	KVM_EXIT_STRING(S390_UCONTROL),
	KVM_EXIT_STRING(WATCHDOG),
	KVM_EXIT_STRING(S390_TSCH),
	KVM_EXIT_STRING(EPR),
	KVM_EXIT_STRING(SYSTEM_EVENT),
	KVM_EXIT_STRING(S390_STSI),
	KVM_EXIT_STRING(IOAPIC_EOI),
	KVM_EXIT_STRING(HYPERV),
	KVM_EXIT_STRING(ARM_NISV),
	KVM_EXIT_STRING(X86_RDMSR),
	KVM_EXIT_STRING(X86_WRMSR),
	KVM_EXIT_STRING(DIRTY_RING_FULL),
	KVM_EXIT_STRING(AP_RESET_HOLD),
	KVM_EXIT_STRING(X86_BUS_LOCK),
	KVM_EXIT_STRING(XEN),
	KVM_EXIT_STRING(RISCV_SBI),
	KVM_EXIT_STRING(RISCV_CSR),
	KVM_EXIT_STRING(NOTIFY),
#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
	KVM_EXIT_STRING(MEMORY_NOT_PRESENT),
#endif
};

/*
 * Exit Reason String
 *
 * Input Args:
 *   exit_reason - Exit reason
 *
 * Output Args: None
 *
 * Return:
 *   Constant string pointer describing the exit reason.
 *
 * Locates and returns a constant string that describes the KVM exit
 * reason given by exit_reason.  If no such string is found, a constant
 * string of "Unknown" is returned.
 */
const char *exit_reason_str(unsigned int exit_reason)
{
	unsigned int n1;

	for (n1 = 0; n1 < ARRAY_SIZE(exit_reasons_known); n1++) {
		if (exit_reason == exit_reasons_known[n1].reason)
			return exit_reasons_known[n1].name;
	}

	return "Unknown";
}

/*
 * Physical Contiguous Page Allocator
 *
 * Input Args:
 *   vm - Virtual Machine
 *   num - number of pages
 *   paddr_min - Physical address minimum
 *   memslot - Memory region to allocate page from
 *
 * Output Args: None
 *
 * Return:
 *   Starting physical address
 *
 * Within the VM specified by vm, locates a range of available physical
 * pages at or above paddr_min. If found, the pages are marked as in use
 * and their base address is returned. A TEST_ASSERT failure occurs if
 * not enough pages are available at or above paddr_min.
 */
vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
			      vm_paddr_t paddr_min, uint32_t memslot)
{
	struct userspace_mem_region *region;
	sparsebit_idx_t pg, base;

	TEST_ASSERT(num > 0, "Must allocate at least one page");

	TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
		"not divisible by page size.\n"
		"  paddr_min: 0x%lx page_size: 0x%x",
		paddr_min, vm->page_size);

	region = memslot2region(vm, memslot);
	base = pg = paddr_min >> vm->page_shift;

	do {
		for (; pg < base + num; ++pg) {
			if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
				base = pg = sparsebit_next_set(region->unused_phy_pages, pg);
				break;
			}
		}
	} while (pg && pg != base + num);

	if (pg == 0) {
		fprintf(stderr, "No guest physical page available, "
			"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
			paddr_min, vm->page_size, memslot);
		fputs("---- vm dump ----\n", stderr);
		vm_dump(stderr, vm, 2);
		abort();
	}

	for (pg = base; pg < base + num; ++pg)
		sparsebit_clear(region->unused_phy_pages, pg);

	return base * vm->page_size;
}

vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
			     uint32_t memslot)
{
	return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
}

vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm)
{
	return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR,
				 vm->memslots[MEM_REGION_PT]);
}

/*
 * Address Guest Virtual to Host Virtual
 *
 * Input Args:
 *   vm - Virtual Machine
 *   gva - VM virtual address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent host virtual address
 */
void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
{
	return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
}

unsigned long __weak vm_compute_max_gfn(struct kvm_vm *vm)
{
	return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
}

static unsigned int vm_calc_num_pages(unsigned int num_pages,
				      unsigned int page_shift,
				      unsigned int new_page_shift,
				      bool ceil)
{
	unsigned int n = 1 << (new_page_shift - page_shift);

	if (page_shift >= new_page_shift)
		return num_pages * (1 << (page_shift - new_page_shift));

	return num_pages / n + !!(ceil && num_pages % n);
}

static inline int getpageshift(void)
{
	return __builtin_ffs(getpagesize()) - 1;
}

unsigned int
vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
{
	return vm_calc_num_pages(num_guest_pages,
				 vm_guest_mode_params[mode].page_shift,
				 getpageshift(), true);
}

unsigned int
vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages)
{
	return vm_calc_num_pages(num_host_pages, getpageshift(),
				 vm_guest_mode_params[mode].page_shift, false);
}

unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size)
{
	unsigned int n;
	n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size);
	return vm_adjust_num_guest_pages(mode, n);
}

/*
 * Read binary stats descriptors
 *
 * Input Args:
 *   stats_fd - the file descriptor for the binary stats file from which to read
 *   header - the binary stats metadata header corresponding to the given FD
 *
 * Output Args: None
 *
 * Return:
 *   A pointer to a newly allocated series of stat descriptors.
 *   Caller is responsible for freeing the returned kvm_stats_desc.
 *
 * Read the stats descriptors from the binary stats interface.
 */
struct kvm_stats_desc *read_stats_descriptors(int stats_fd,
					      struct kvm_stats_header *header)
{
	struct kvm_stats_desc *stats_desc;
	ssize_t desc_size, total_size, ret;

	desc_size = get_stats_descriptor_size(header);
	total_size = header->num_desc * desc_size;

	stats_desc = calloc(header->num_desc, desc_size);
	TEST_ASSERT(stats_desc, "Allocate memory for stats descriptors");

	ret = pread(stats_fd, stats_desc, total_size, header->desc_offset);
	TEST_ASSERT(ret == total_size, "Read KVM stats descriptors");

	return stats_desc;
}

/*
 * Read stat data for a particular stat
 *
 * Input Args:
 *   stats_fd - the file descriptor for the binary stats file from which to read
 *   header - the binary stats metadata header corresponding to the given FD
 *   desc - the binary stat metadata for the particular stat to be read
 *   max_elements - the maximum number of 8-byte values to read into data
 *
 * Output Args:
 *   data - the buffer into which stat data should be read
 *
 * Read the data values of a specified stat from the binary stats interface.
 */
void read_stat_data(int stats_fd, struct kvm_stats_header *header,
		    struct kvm_stats_desc *desc, uint64_t *data,
		    size_t max_elements)
{
	size_t nr_elements = min_t(ssize_t, desc->size, max_elements);
	size_t size = nr_elements * sizeof(*data);
	ssize_t ret;

	TEST_ASSERT(desc->size, "No elements in stat '%s'", desc->name);
	TEST_ASSERT(max_elements, "Zero elements requested for stat '%s'", desc->name);

	ret = pread(stats_fd, data, size,
		    header->data_offset + desc->offset);

	TEST_ASSERT(ret >= 0, "pread() failed on stat '%s', errno: %i (%s)",
		    desc->name, errno, strerror(errno));
	TEST_ASSERT(ret == size,
		    "pread() on stat '%s' read %ld bytes, wanted %lu bytes",
		    desc->name, size, ret);
}

/*
 * Read the data of the named stat
 *
 * Input Args:
 *   vm - the VM for which the stat should be read
 *   stat_name - the name of the stat to read
 *   max_elements - the maximum number of 8-byte values to read into data
 *
 * Output Args:
 *   data - the buffer into which stat data should be read
 *
 * Read the data values of a specified stat from the binary stats interface.
 */
void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
		   size_t max_elements)
{
	struct kvm_stats_desc *desc;
	size_t size_desc;
	int i;

	if (!vm->stats_fd) {
		vm->stats_fd = vm_get_stats_fd(vm);
		read_stats_header(vm->stats_fd, &vm->stats_header);
		vm->stats_desc = read_stats_descriptors(vm->stats_fd,
							&vm->stats_header);
	}

	size_desc = get_stats_descriptor_size(&vm->stats_header);

	for (i = 0; i < vm->stats_header.num_desc; ++i) {
		desc = (void *)vm->stats_desc + (i * size_desc);

		if (strcmp(desc->name, stat_name))
			continue;

		read_stat_data(vm->stats_fd, &vm->stats_header, desc,
			       data, max_elements);

		break;
	}
}

__weak void kvm_arch_vm_post_create(struct kvm_vm *vm)
{
}

__weak void kvm_selftest_arch_init(void)
{
}

void __attribute((constructor)) kvm_selftest_init(void)
{
	/* Tell stdout not to buffer its content. */
	setbuf(stdout, NULL);

	kvm_selftest_arch_init();
}