summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/arm.c
blob: 14391826241c8ca689232506144d681295482996 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#include <linux/bug.h>
#include <linux/cpu_pm.h>
#include <linux/entry-kvm.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
#include <linux/kvm.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
#include <linux/sched/stat.h>
#include <linux/psci.h>
#include <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "trace_arm.h"

#include <linux/uaccess.h>
#include <asm/ptrace.h>
#include <asm/mman.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_pkvm.h>
#include <asm/kvm_emulate.h>
#include <asm/sections.h>

#include <kvm/arm_hypercalls.h>
#include <kvm/arm_pmu.h>
#include <kvm/arm_psci.h>

static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;

DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);

DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);

static bool vgic_present;

static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}

int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
			    struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
	case KVM_CAP_ARM_NISV_TO_USER:
		r = 0;
		set_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER,
			&kvm->arch.flags);
		break;
	case KVM_CAP_ARM_MTE:
		mutex_lock(&kvm->lock);
		if (!system_supports_mte() || kvm->created_vcpus) {
			r = -EINVAL;
		} else {
			r = 0;
			set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags);
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_CAP_ARM_SYSTEM_SUSPEND:
		r = 0;
		set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags);
		break;
	default:
		r = -EINVAL;
		break;
	}

	return r;
}

static int kvm_arm_default_max_vcpus(void)
{
	return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
}

static void set_default_spectre(struct kvm *kvm)
{
	/*
	 * The default is to expose CSV2 == 1 if the HW isn't affected.
	 * Although this is a per-CPU feature, we make it global because
	 * asymmetric systems are just a nuisance.
	 *
	 * Userspace can override this as long as it doesn't promise
	 * the impossible.
	 */
	if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
		kvm->arch.pfr0_csv2 = 1;
	if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED)
		kvm->arch.pfr0_csv3 = 1;
}

/**
 * kvm_arch_init_vm - initializes a VM data structure
 * @kvm:	pointer to the KVM struct
 */
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
	int ret;

	mutex_init(&kvm->arch.config_lock);

#ifdef CONFIG_LOCKDEP
	/* Clue in lockdep that the config_lock must be taken inside kvm->lock */
	mutex_lock(&kvm->lock);
	mutex_lock(&kvm->arch.config_lock);
	mutex_unlock(&kvm->arch.config_lock);
	mutex_unlock(&kvm->lock);
#endif

	ret = kvm_share_hyp(kvm, kvm + 1);
	if (ret)
		return ret;

	ret = pkvm_init_host_vm(kvm);
	if (ret)
		goto err_unshare_kvm;

	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) {
		ret = -ENOMEM;
		goto err_unshare_kvm;
	}
	cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask);

	ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu, type);
	if (ret)
		goto err_free_cpumask;

	kvm_vgic_early_init(kvm);

	kvm_timer_init_vm(kvm);

	/* The maximum number of VCPUs is limited by the host's GIC model */
	kvm->max_vcpus = kvm_arm_default_max_vcpus();

	set_default_spectre(kvm);
	kvm_arm_init_hypercalls(kvm);

	/*
	 * Initialise the default PMUver before there is a chance to
	 * create an actual PMU.
	 */
	kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit();

	return 0;

err_free_cpumask:
	free_cpumask_var(kvm->arch.supported_cpus);
err_unshare_kvm:
	kvm_unshare_hyp(kvm, kvm + 1);
	return ret;
}

vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
	return VM_FAULT_SIGBUS;
}


/**
 * kvm_arch_destroy_vm - destroy the VM data structure
 * @kvm:	pointer to the KVM struct
 */
void kvm_arch_destroy_vm(struct kvm *kvm)
{
	bitmap_free(kvm->arch.pmu_filter);
	free_cpumask_var(kvm->arch.supported_cpus);

	kvm_vgic_destroy(kvm);

	if (is_protected_kvm_enabled())
		pkvm_destroy_hyp_vm(kvm);

	kvm_destroy_vcpus(kvm);

	kvm_unshare_hyp(kvm, kvm + 1);

	kvm_arm_teardown_hypercalls(kvm);
}

int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
	int r;
	switch (ext) {
	case KVM_CAP_IRQCHIP:
		r = vgic_present;
		break;
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_DEVICE_CTRL:
	case KVM_CAP_USER_MEMORY:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
	case KVM_CAP_ONE_REG:
	case KVM_CAP_ARM_PSCI:
	case KVM_CAP_ARM_PSCI_0_2:
	case KVM_CAP_READONLY_MEM:
	case KVM_CAP_MP_STATE:
	case KVM_CAP_IMMEDIATE_EXIT:
	case KVM_CAP_VCPU_EVENTS:
	case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2:
	case KVM_CAP_ARM_NISV_TO_USER:
	case KVM_CAP_ARM_INJECT_EXT_DABT:
	case KVM_CAP_SET_GUEST_DEBUG:
	case KVM_CAP_VCPU_ATTRIBUTES:
	case KVM_CAP_PTP_KVM:
	case KVM_CAP_ARM_SYSTEM_SUSPEND:
	case KVM_CAP_IRQFD_RESAMPLE:
	case KVM_CAP_COUNTER_OFFSET:
		r = 1;
		break;
	case KVM_CAP_SET_GUEST_DEBUG2:
		return KVM_GUESTDBG_VALID_MASK;
	case KVM_CAP_ARM_SET_DEVICE_ADDR:
		r = 1;
		break;
	case KVM_CAP_NR_VCPUS:
		/*
		 * ARM64 treats KVM_CAP_NR_CPUS differently from all other
		 * architectures, as it does not always bound it to
		 * KVM_CAP_MAX_VCPUS. It should not matter much because
		 * this is just an advisory value.
		 */
		r = min_t(unsigned int, num_online_cpus(),
			  kvm_arm_default_max_vcpus());
		break;
	case KVM_CAP_MAX_VCPUS:
	case KVM_CAP_MAX_VCPU_ID:
		if (kvm)
			r = kvm->max_vcpus;
		else
			r = kvm_arm_default_max_vcpus();
		break;
	case KVM_CAP_MSI_DEVID:
		if (!kvm)
			r = -EINVAL;
		else
			r = kvm->arch.vgic.msis_require_devid;
		break;
	case KVM_CAP_ARM_USER_IRQ:
		/*
		 * 1: EL1_VTIMER, EL1_PTIMER, and PMU.
		 * (bump this number if adding more devices)
		 */
		r = 1;
		break;
	case KVM_CAP_ARM_MTE:
		r = system_supports_mte();
		break;
	case KVM_CAP_STEAL_TIME:
		r = kvm_arm_pvtime_supported();
		break;
	case KVM_CAP_ARM_EL1_32BIT:
		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
		break;
	case KVM_CAP_GUEST_DEBUG_HW_BPS:
		r = get_num_brps();
		break;
	case KVM_CAP_GUEST_DEBUG_HW_WPS:
		r = get_num_wrps();
		break;
	case KVM_CAP_ARM_PMU_V3:
		r = kvm_arm_support_pmu_v3();
		break;
	case KVM_CAP_ARM_INJECT_SERROR_ESR:
		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
		break;
	case KVM_CAP_ARM_VM_IPA_SIZE:
		r = get_kvm_ipa_limit();
		break;
	case KVM_CAP_ARM_SVE:
		r = system_supports_sve();
		break;
	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
	case KVM_CAP_ARM_PTRAUTH_GENERIC:
		r = system_has_full_ptr_auth();
		break;
	default:
		r = 0;
	}

	return r;
}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	return -EINVAL;
}

struct kvm *kvm_arch_alloc_vm(void)
{
	size_t sz = sizeof(struct kvm);

	if (!has_vhe())
		return kzalloc(sz, GFP_KERNEL_ACCOUNT);

	return __vmalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM | __GFP_ZERO);
}

int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
		return -EBUSY;

	if (id >= kvm->max_vcpus)
		return -EINVAL;

	return 0;
}

int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
	int err;

	spin_lock_init(&vcpu->arch.mp_state_lock);

#ifdef CONFIG_LOCKDEP
	/* Inform lockdep that the config_lock is acquired after vcpu->mutex */
	mutex_lock(&vcpu->mutex);
	mutex_lock(&vcpu->kvm->arch.config_lock);
	mutex_unlock(&vcpu->kvm->arch.config_lock);
	mutex_unlock(&vcpu->mutex);
#endif

	/* Force users to call KVM_ARM_VCPU_INIT */
	vcpu->arch.target = -1;
	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);

	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;

	/*
	 * Default value for the FP state, will be overloaded at load
	 * time if we support FP (pretty likely)
	 */
	vcpu->arch.fp_state = FP_STATE_FREE;

	/* Set up the timer */
	kvm_timer_vcpu_init(vcpu);

	kvm_pmu_vcpu_init(vcpu);

	kvm_arm_reset_debug_ptr(vcpu);

	kvm_arm_pvtime_vcpu_init(&vcpu->arch);

	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;

	err = kvm_vgic_vcpu_init(vcpu);
	if (err)
		return err;

	return kvm_share_hyp(vcpu, vcpu + 1);
}

void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	if (vcpu_has_run_once(vcpu) && unlikely(!irqchip_in_kernel(vcpu->kvm)))
		static_branch_dec(&userspace_irqchip_in_use);

	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
	kvm_timer_vcpu_terminate(vcpu);
	kvm_pmu_vcpu_destroy(vcpu);

	kvm_arm_vcpu_destroy(vcpu);
}

void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{

}

void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{

}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvm_s2_mmu *mmu;
	int *last_ran;

	mmu = vcpu->arch.hw_mmu;
	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);

	/*
	 * We guarantee that both TLBs and I-cache are private to each
	 * vcpu. If detecting that a vcpu from the same VM has
	 * previously run on the same physical CPU, call into the
	 * hypervisor code to nuke the relevant contexts.
	 *
	 * We might get preempted before the vCPU actually runs, but
	 * over-invalidation doesn't affect correctness.
	 */
	if (*last_ran != vcpu->vcpu_id) {
		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
		*last_ran = vcpu->vcpu_id;
	}

	vcpu->cpu = cpu;

	kvm_vgic_load(vcpu);
	kvm_timer_vcpu_load(vcpu);
	if (has_vhe())
		kvm_vcpu_load_sysregs_vhe(vcpu);
	kvm_arch_vcpu_load_fp(vcpu);
	kvm_vcpu_pmu_restore_guest(vcpu);
	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);

	if (single_task_running())
		vcpu_clear_wfx_traps(vcpu);
	else
		vcpu_set_wfx_traps(vcpu);

	if (vcpu_has_ptrauth(vcpu))
		vcpu_ptrauth_disable(vcpu);
	kvm_arch_vcpu_load_debug_state_flags(vcpu);

	if (!cpumask_test_cpu(smp_processor_id(), vcpu->kvm->arch.supported_cpus))
		vcpu_set_on_unsupported_cpu(vcpu);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_put_debug_state_flags(vcpu);
	kvm_arch_vcpu_put_fp(vcpu);
	if (has_vhe())
		kvm_vcpu_put_sysregs_vhe(vcpu);
	kvm_timer_vcpu_put(vcpu);
	kvm_vgic_put(vcpu);
	kvm_vcpu_pmu_restore_host(vcpu);
	kvm_arm_vmid_clear_active();

	vcpu_clear_on_unsupported_cpu(vcpu);
	vcpu->cpu = -1;
}

static void __kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu)
{
	WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
	kvm_make_request(KVM_REQ_SLEEP, vcpu);
	kvm_vcpu_kick(vcpu);
}

void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu)
{
	spin_lock(&vcpu->arch.mp_state_lock);
	__kvm_arm_vcpu_power_off(vcpu);
	spin_unlock(&vcpu->arch.mp_state_lock);
}

bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu)
{
	return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED;
}

static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu)
{
	WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_SUSPENDED);
	kvm_make_request(KVM_REQ_SUSPEND, vcpu);
	kvm_vcpu_kick(vcpu);
}

static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu)
{
	return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_SUSPENDED;
}

int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	*mp_state = READ_ONCE(vcpu->arch.mp_state);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	int ret = 0;

	spin_lock(&vcpu->arch.mp_state_lock);

	switch (mp_state->mp_state) {
	case KVM_MP_STATE_RUNNABLE:
		WRITE_ONCE(vcpu->arch.mp_state, *mp_state);
		break;
	case KVM_MP_STATE_STOPPED:
		__kvm_arm_vcpu_power_off(vcpu);
		break;
	case KVM_MP_STATE_SUSPENDED:
		kvm_arm_vcpu_suspend(vcpu);
		break;
	default:
		ret = -EINVAL;
	}

	spin_unlock(&vcpu->arch.mp_state_lock);

	return ret;
}

/**
 * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled
 * @v:		The VCPU pointer
 *
 * If the guest CPU is not waiting for interrupts or an interrupt line is
 * asserted, the CPU is by definition runnable.
 */
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
	bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF);
	return ((irq_lines || kvm_vgic_vcpu_pending_irq(v))
		&& !kvm_arm_vcpu_stopped(v) && !v->arch.pause);
}

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
	return vcpu_mode_priv(vcpu);
}

#ifdef CONFIG_GUEST_PERF_EVENTS
unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
{
	return *vcpu_pc(vcpu);
}
#endif

static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.target >= 0;
}

/*
 * Handle both the initialisation that is being done when the vcpu is
 * run for the first time, as well as the updates that must be
 * performed each time we get a new thread dealing with this vcpu.
 */
int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	int ret;

	if (!kvm_vcpu_initialized(vcpu))
		return -ENOEXEC;

	if (!kvm_arm_vcpu_is_finalized(vcpu))
		return -EPERM;

	ret = kvm_arch_vcpu_run_map_fp(vcpu);
	if (ret)
		return ret;

	if (likely(vcpu_has_run_once(vcpu)))
		return 0;

	kvm_arm_vcpu_init_debug(vcpu);

	if (likely(irqchip_in_kernel(kvm))) {
		/*
		 * Map the VGIC hardware resources before running a vcpu the
		 * first time on this VM.
		 */
		ret = kvm_vgic_map_resources(kvm);
		if (ret)
			return ret;
	}

	ret = kvm_timer_enable(vcpu);
	if (ret)
		return ret;

	ret = kvm_arm_pmu_v3_enable(vcpu);
	if (ret)
		return ret;

	if (is_protected_kvm_enabled()) {
		ret = pkvm_create_hyp_vm(kvm);
		if (ret)
			return ret;
	}

	if (!irqchip_in_kernel(kvm)) {
		/*
		 * Tell the rest of the code that there are userspace irqchip
		 * VMs in the wild.
		 */
		static_branch_inc(&userspace_irqchip_in_use);
	}

	/*
	 * Initialize traps for protected VMs.
	 * NOTE: Move to run in EL2 directly, rather than via a hypercall, once
	 * the code is in place for first run initialization at EL2.
	 */
	if (kvm_vm_is_protected(kvm))
		kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);

	mutex_lock(&kvm->arch.config_lock);
	set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags);
	mutex_unlock(&kvm->arch.config_lock);

	return ret;
}

bool kvm_arch_intc_initialized(struct kvm *kvm)
{
	return vgic_initialized(kvm);
}

void kvm_arm_halt_guest(struct kvm *kvm)
{
	unsigned long i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm)
		vcpu->arch.pause = true;
	kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP);
}

void kvm_arm_resume_guest(struct kvm *kvm)
{
	unsigned long i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		vcpu->arch.pause = false;
		__kvm_vcpu_wake_up(vcpu);
	}
}

static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu)
{
	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);

	rcuwait_wait_event(wait,
			   (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause),
			   TASK_INTERRUPTIBLE);

	if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) {
		/* Awaken to handle a signal, request we sleep again later. */
		kvm_make_request(KVM_REQ_SLEEP, vcpu);
	}

	/*
	 * Make sure we will observe a potential reset request if we've
	 * observed a change to the power state. Pairs with the smp_wmb() in
	 * kvm_psci_vcpu_on().
	 */
	smp_rmb();
}

/**
 * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior
 * @vcpu:	The VCPU pointer
 *
 * Suspend execution of a vCPU until a valid wake event is detected, i.e. until
 * the vCPU is runnable.  The vCPU may or may not be scheduled out, depending
 * on when a wake event arrives, e.g. there may already be a pending wake event.
 */
void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
{
	/*
	 * Sync back the state of the GIC CPU interface so that we have
	 * the latest PMR and group enables. This ensures that
	 * kvm_arch_vcpu_runnable has up-to-date data to decide whether
	 * we have pending interrupts, e.g. when determining if the
	 * vCPU should block.
	 *
	 * For the same reason, we want to tell GICv4 that we need
	 * doorbells to be signalled, should an interrupt become pending.
	 */
	preempt_disable();
	kvm_vgic_vmcr_sync(vcpu);
	vgic_v4_put(vcpu, true);
	preempt_enable();

	kvm_vcpu_halt(vcpu);
	vcpu_clear_flag(vcpu, IN_WFIT);

	preempt_disable();
	vgic_v4_load(vcpu);
	preempt_enable();
}

static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
{
	if (!kvm_arm_vcpu_suspended(vcpu))
		return 1;

	kvm_vcpu_wfi(vcpu);

	/*
	 * The suspend state is sticky; we do not leave it until userspace
	 * explicitly marks the vCPU as runnable. Request that we suspend again
	 * later.
	 */
	kvm_make_request(KVM_REQ_SUSPEND, vcpu);

	/*
	 * Check to make sure the vCPU is actually runnable. If so, exit to
	 * userspace informing it of the wakeup condition.
	 */
	if (kvm_arch_vcpu_runnable(vcpu)) {
		memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
		vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP;
		vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
		return 0;
	}

	/*
	 * Otherwise, we were unblocked to process a different event, such as a
	 * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to
	 * process the event.
	 */
	return 1;
}

/**
 * check_vcpu_requests - check and handle pending vCPU requests
 * @vcpu:	the VCPU pointer
 *
 * Return: 1 if we should enter the guest
 *	   0 if we should exit to userspace
 *	   < 0 if we should exit to userspace, where the return value indicates
 *	   an error
 */
static int check_vcpu_requests(struct kvm_vcpu *vcpu)
{
	if (kvm_request_pending(vcpu)) {
		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
			kvm_vcpu_sleep(vcpu);

		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
			kvm_reset_vcpu(vcpu);

		/*
		 * Clear IRQ_PENDING requests that were made to guarantee
		 * that a VCPU sees new virtual interrupts.
		 */
		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);

		if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
			kvm_update_stolen_time(vcpu);

		if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) {
			/* The distributor enable bits were changed */
			preempt_disable();
			vgic_v4_put(vcpu, false);
			vgic_v4_load(vcpu);
			preempt_enable();
		}

		if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
			kvm_pmu_handle_pmcr(vcpu,
					    __vcpu_sys_reg(vcpu, PMCR_EL0));

		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
			return kvm_vcpu_suspend(vcpu);

		if (kvm_dirty_ring_check_request(vcpu))
			return 0;
	}

	return 1;
}

static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
{
	if (likely(!vcpu_mode_is_32bit(vcpu)))
		return false;

	return !kvm_supports_32bit_el0();
}

/**
 * kvm_vcpu_exit_request - returns true if the VCPU should *not* enter the guest
 * @vcpu:	The VCPU pointer
 * @ret:	Pointer to write optional return code
 *
 * Returns: true if the VCPU needs to return to a preemptible + interruptible
 *	    and skip guest entry.
 *
 * This function disambiguates between two different types of exits: exits to a
 * preemptible + interruptible kernel context and exits to userspace. For an
 * exit to userspace, this function will write the return code to ret and return
 * true. For an exit to preemptible + interruptible kernel context (i.e. check
 * for pending work and re-enter), return true without writing to ret.
 */
static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
{
	struct kvm_run *run = vcpu->run;

	/*
	 * If we're using a userspace irqchip, then check if we need
	 * to tell a userspace irqchip about timer or PMU level
	 * changes and if so, exit to userspace (the actual level
	 * state gets updated in kvm_timer_update_run and
	 * kvm_pmu_update_run below).
	 */
	if (static_branch_unlikely(&userspace_irqchip_in_use)) {
		if (kvm_timer_should_notify_user(vcpu) ||
		    kvm_pmu_should_notify_user(vcpu)) {
			*ret = -EINTR;
			run->exit_reason = KVM_EXIT_INTR;
			return true;
		}
	}

	if (unlikely(vcpu_on_unsupported_cpu(vcpu))) {
		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		run->fail_entry.hardware_entry_failure_reason = KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED;
		run->fail_entry.cpu = smp_processor_id();
		*ret = 0;
		return true;
	}

	return kvm_request_pending(vcpu) ||
			xfer_to_guest_mode_work_pending();
}

/*
 * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
 * the vCPU is running.
 *
 * This must be noinstr as instrumentation may make use of RCU, and this is not
 * safe during the EQS.
 */
static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
{
	int ret;

	guest_state_enter_irqoff();
	ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
	guest_state_exit_irqoff();

	return ret;
}

/**
 * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
 * @vcpu:	The VCPU pointer
 *
 * This function is called through the VCPU_RUN ioctl called from user space. It
 * will execute VM code in a loop until the time slice for the process is used
 * or some emulation is needed from user space in which case the function will
 * return with return value 0 and with the kvm_run structure filled in with the
 * required data for the requested emulation.
 */
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	int ret;

	if (run->exit_reason == KVM_EXIT_MMIO) {
		ret = kvm_handle_mmio_return(vcpu);
		if (ret)
			return ret;
	}

	vcpu_load(vcpu);

	if (run->immediate_exit) {
		ret = -EINTR;
		goto out;
	}

	kvm_sigset_activate(vcpu);

	ret = 1;
	run->exit_reason = KVM_EXIT_UNKNOWN;
	run->flags = 0;
	while (ret > 0) {
		/*
		 * Check conditions before entering the guest
		 */
		ret = xfer_to_guest_mode_handle_work(vcpu);
		if (!ret)
			ret = 1;

		if (ret > 0)
			ret = check_vcpu_requests(vcpu);

		/*
		 * Preparing the interrupts to be injected also
		 * involves poking the GIC, which must be done in a
		 * non-preemptible context.
		 */
		preempt_disable();

		/*
		 * The VMID allocator only tracks active VMIDs per
		 * physical CPU, and therefore the VMID allocated may not be
		 * preserved on VMID roll-over if the task was preempted,
		 * making a thread's VMID inactive. So we need to call
		 * kvm_arm_vmid_update() in non-premptible context.
		 */
		kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid);

		kvm_pmu_flush_hwstate(vcpu);

		local_irq_disable();

		kvm_vgic_flush_hwstate(vcpu);

		kvm_pmu_update_vcpu_events(vcpu);

		/*
		 * Ensure we set mode to IN_GUEST_MODE after we disable
		 * interrupts and before the final VCPU requests check.
		 * See the comment in kvm_vcpu_exiting_guest_mode() and
		 * Documentation/virt/kvm/vcpu-requests.rst
		 */
		smp_store_mb(vcpu->mode, IN_GUEST_MODE);

		if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) {
			vcpu->mode = OUTSIDE_GUEST_MODE;
			isb(); /* Ensure work in x_flush_hwstate is committed */
			kvm_pmu_sync_hwstate(vcpu);
			if (static_branch_unlikely(&userspace_irqchip_in_use))
				kvm_timer_sync_user(vcpu);
			kvm_vgic_sync_hwstate(vcpu);
			local_irq_enable();
			preempt_enable();
			continue;
		}

		kvm_arm_setup_debug(vcpu);
		kvm_arch_vcpu_ctxflush_fp(vcpu);

		/**************************************************************
		 * Enter the guest
		 */
		trace_kvm_entry(*vcpu_pc(vcpu));
		guest_timing_enter_irqoff();

		ret = kvm_arm_vcpu_enter_exit(vcpu);

		vcpu->mode = OUTSIDE_GUEST_MODE;
		vcpu->stat.exits++;
		/*
		 * Back from guest
		 *************************************************************/

		kvm_arm_clear_debug(vcpu);

		/*
		 * We must sync the PMU state before the vgic state so
		 * that the vgic can properly sample the updated state of the
		 * interrupt line.
		 */
		kvm_pmu_sync_hwstate(vcpu);

		/*
		 * Sync the vgic state before syncing the timer state because
		 * the timer code needs to know if the virtual timer
		 * interrupts are active.
		 */
		kvm_vgic_sync_hwstate(vcpu);

		/*
		 * Sync the timer hardware state before enabling interrupts as
		 * we don't want vtimer interrupts to race with syncing the
		 * timer virtual interrupt state.
		 */
		if (static_branch_unlikely(&userspace_irqchip_in_use))
			kvm_timer_sync_user(vcpu);

		kvm_arch_vcpu_ctxsync_fp(vcpu);

		/*
		 * We must ensure that any pending interrupts are taken before
		 * we exit guest timing so that timer ticks are accounted as
		 * guest time. Transiently unmask interrupts so that any
		 * pending interrupts are taken.
		 *
		 * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other
		 * context synchronization event) is necessary to ensure that
		 * pending interrupts are taken.
		 */
		if (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_IRQ) {
			local_irq_enable();
			isb();
			local_irq_disable();
		}

		guest_timing_exit_irqoff();

		local_irq_enable();

		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));

		/* Exit types that need handling before we can be preempted */
		handle_exit_early(vcpu, ret);

		preempt_enable();

		/*
		 * The ARMv8 architecture doesn't give the hypervisor
		 * a mechanism to prevent a guest from dropping to AArch32 EL0
		 * if implemented by the CPU. If we spot the guest in such
		 * state and that we decided it wasn't supposed to do so (like
		 * with the asymmetric AArch32 case), return to userspace with
		 * a fatal error.
		 */
		if (vcpu_mode_is_bad_32bit(vcpu)) {
			/*
			 * As we have caught the guest red-handed, decide that
			 * it isn't fit for purpose anymore by making the vcpu
			 * invalid. The VMM can try and fix it by issuing  a
			 * KVM_ARM_VCPU_INIT if it really wants to.
			 */
			vcpu->arch.target = -1;
			ret = ARM_EXCEPTION_IL;
		}

		ret = handle_exit(vcpu, ret);
	}

	/* Tell userspace about in-kernel device output levels */
	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
		kvm_timer_update_run(vcpu);
		kvm_pmu_update_run(vcpu);
	}

	kvm_sigset_deactivate(vcpu);

out:
	/*
	 * In the unlikely event that we are returning to userspace
	 * with pending exceptions or PC adjustment, commit these
	 * adjustments in order to give userspace a consistent view of
	 * the vcpu state. Note that this relies on __kvm_adjust_pc()
	 * being preempt-safe on VHE.
	 */
	if (unlikely(vcpu_get_flag(vcpu, PENDING_EXCEPTION) ||
		     vcpu_get_flag(vcpu, INCREMENT_PC)))
		kvm_call_hyp(__kvm_adjust_pc, vcpu);

	vcpu_put(vcpu);
	return ret;
}

static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
{
	int bit_index;
	bool set;
	unsigned long *hcr;

	if (number == KVM_ARM_IRQ_CPU_IRQ)
		bit_index = __ffs(HCR_VI);
	else /* KVM_ARM_IRQ_CPU_FIQ */
		bit_index = __ffs(HCR_VF);

	hcr = vcpu_hcr(vcpu);
	if (level)
		set = test_and_set_bit(bit_index, hcr);
	else
		set = test_and_clear_bit(bit_index, hcr);

	/*
	 * If we didn't change anything, no need to wake up or kick other CPUs
	 */
	if (set == level)
		return 0;

	/*
	 * The vcpu irq_lines field was updated, wake up sleeping VCPUs and
	 * trigger a world-switch round on the running physical CPU to set the
	 * virtual IRQ/FIQ fields in the HCR appropriately.
	 */
	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
	kvm_vcpu_kick(vcpu);

	return 0;
}

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
			  bool line_status)
{
	u32 irq = irq_level->irq;
	unsigned int irq_type, vcpu_idx, irq_num;
	int nrcpus = atomic_read(&kvm->online_vcpus);
	struct kvm_vcpu *vcpu = NULL;
	bool level = irq_level->level;

	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
	vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1);
	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;

	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);

	switch (irq_type) {
	case KVM_ARM_IRQ_TYPE_CPU:
		if (irqchip_in_kernel(kvm))
			return -ENXIO;

		if (vcpu_idx >= nrcpus)
			return -EINVAL;

		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
		if (!vcpu)
			return -EINVAL;

		if (irq_num > KVM_ARM_IRQ_CPU_FIQ)
			return -EINVAL;

		return vcpu_interrupt_line(vcpu, irq_num, level);
	case KVM_ARM_IRQ_TYPE_PPI:
		if (!irqchip_in_kernel(kvm))
			return -ENXIO;

		if (vcpu_idx >= nrcpus)
			return -EINVAL;

		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
		if (!vcpu)
			return -EINVAL;

		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
			return -EINVAL;

		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL);
	case KVM_ARM_IRQ_TYPE_SPI:
		if (!irqchip_in_kernel(kvm))
			return -ENXIO;

		if (irq_num < VGIC_NR_PRIVATE_IRQS)
			return -EINVAL;

		return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL);
	}

	return -EINVAL;
}

static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
			       const struct kvm_vcpu_init *init)
{
	unsigned int i, ret;
	u32 phys_target = kvm_target_cpu();

	if (init->target != phys_target)
		return -EINVAL;

	/*
	 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
	 * use the same target.
	 */
	if (vcpu->arch.target != -1 && vcpu->arch.target != init->target)
		return -EINVAL;

	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
	for (i = 0; i < sizeof(init->features) * 8; i++) {
		bool set = (init->features[i / 32] & (1 << (i % 32)));

		if (set && i >= KVM_VCPU_MAX_FEATURES)
			return -ENOENT;

		/*
		 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
		 * use the same feature set.
		 */
		if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES &&
		    test_bit(i, vcpu->arch.features) != set)
			return -EINVAL;

		if (set)
			set_bit(i, vcpu->arch.features);
	}

	vcpu->arch.target = phys_target;

	/* Now we know what it is, we can reset it. */
	ret = kvm_reset_vcpu(vcpu);
	if (ret) {
		vcpu->arch.target = -1;
		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
	}

	return ret;
}

static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
					 struct kvm_vcpu_init *init)
{
	int ret;

	ret = kvm_vcpu_set_target(vcpu, init);
	if (ret)
		return ret;

	/*
	 * Ensure a rebooted VM will fault in RAM pages and detect if the
	 * guest MMU is turned off and flush the caches as needed.
	 *
	 * S2FWB enforces all memory accesses to RAM being cacheable,
	 * ensuring that the data side is always coherent. We still
	 * need to invalidate the I-cache though, as FWB does *not*
	 * imply CTR_EL0.DIC.
	 */
	if (vcpu_has_run_once(vcpu)) {
		if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
			stage2_unmap_vm(vcpu->kvm);
		else
			icache_inval_all_pou();
	}

	vcpu_reset_hcr(vcpu);
	vcpu->arch.cptr_el2 = CPTR_EL2_DEFAULT;

	/*
	 * Handle the "start in power-off" case.
	 */
	spin_lock(&vcpu->arch.mp_state_lock);

	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
		__kvm_arm_vcpu_power_off(vcpu);
	else
		WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE);

	spin_unlock(&vcpu->arch.mp_state_lock);

	return 0;
}

static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
		break;
	}

	return ret;
}

static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
		break;
	}

	return ret;
}

static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
		break;
	}

	return ret;
}

static int kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
				   struct kvm_vcpu_events *events)
{
	memset(events, 0, sizeof(*events));

	return __kvm_arm_vcpu_get_events(vcpu, events);
}

static int kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
				   struct kvm_vcpu_events *events)
{
	int i;

	/* check whether the reserved field is zero */
	for (i = 0; i < ARRAY_SIZE(events->reserved); i++)
		if (events->reserved[i])
			return -EINVAL;

	/* check whether the pad field is zero */
	for (i = 0; i < ARRAY_SIZE(events->exception.pad); i++)
		if (events->exception.pad[i])
			return -EINVAL;

	return __kvm_arm_vcpu_set_events(vcpu, events);
}

long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	struct kvm_device_attr attr;
	long r;

	switch (ioctl) {
	case KVM_ARM_VCPU_INIT: {
		struct kvm_vcpu_init init;

		r = -EFAULT;
		if (copy_from_user(&init, argp, sizeof(init)))
			break;

		r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
		break;
	}
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;

		r = -ENOEXEC;
		if (unlikely(!kvm_vcpu_initialized(vcpu)))
			break;

		r = -EFAULT;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			break;

		/*
		 * We could owe a reset due to PSCI. Handle the pending reset
		 * here to ensure userspace register accesses are ordered after
		 * the reset.
		 */
		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
			kvm_reset_vcpu(vcpu);

		if (ioctl == KVM_SET_ONE_REG)
			r = kvm_arm_set_reg(vcpu, &reg);
		else
			r = kvm_arm_get_reg(vcpu, &reg);
		break;
	}
	case KVM_GET_REG_LIST: {
		struct kvm_reg_list __user *user_list = argp;
		struct kvm_reg_list reg_list;
		unsigned n;

		r = -ENOEXEC;
		if (unlikely(!kvm_vcpu_initialized(vcpu)))
			break;

		r = -EPERM;
		if (!kvm_arm_vcpu_is_finalized(vcpu))
			break;

		r = -EFAULT;
		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
			break;
		n = reg_list.n;
		reg_list.n = kvm_arm_num_regs(vcpu);
		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
			break;
		r = -E2BIG;
		if (n < reg_list.n)
			break;
		r = kvm_arm_copy_reg_indices(vcpu, user_list->reg);
		break;
	}
	case KVM_SET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, argp, sizeof(attr)))
			break;
		r = kvm_arm_vcpu_set_attr(vcpu, &attr);
		break;
	}
	case KVM_GET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, argp, sizeof(attr)))
			break;
		r = kvm_arm_vcpu_get_attr(vcpu, &attr);
		break;
	}
	case KVM_HAS_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, argp, sizeof(attr)))
			break;
		r = kvm_arm_vcpu_has_attr(vcpu, &attr);
		break;
	}
	case KVM_GET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		if (kvm_arm_vcpu_get_events(vcpu, &events))
			return -EINVAL;

		if (copy_to_user(argp, &events, sizeof(events)))
			return -EFAULT;

		return 0;
	}
	case KVM_SET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		if (copy_from_user(&events, argp, sizeof(events)))
			return -EFAULT;

		return kvm_arm_vcpu_set_events(vcpu, &events);
	}
	case KVM_ARM_VCPU_FINALIZE: {
		int what;

		if (!kvm_vcpu_initialized(vcpu))
			return -ENOEXEC;

		if (get_user(what, (const int __user *)argp))
			return -EFAULT;

		return kvm_arm_vcpu_finalize(vcpu, what);
	}
	default:
		r = -EINVAL;
	}

	return r;
}

void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{

}

void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
					const struct kvm_memory_slot *memslot)
{
	kvm_flush_remote_tlbs(kvm);
}

static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
					struct kvm_arm_device_addr *dev_addr)
{
	switch (FIELD_GET(KVM_ARM_DEVICE_ID_MASK, dev_addr->id)) {
	case KVM_ARM_DEVICE_VGIC_V2:
		if (!vgic_present)
			return -ENXIO;
		return kvm_set_legacy_vgic_v2_addr(kvm, dev_addr);
	default:
		return -ENODEV;
	}
}

static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_ARM_VM_SMCCC_CTRL:
		return kvm_vm_smccc_has_attr(kvm, attr);
	default:
		return -ENXIO;
	}
}

static int kvm_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_ARM_VM_SMCCC_CTRL:
		return kvm_vm_smccc_set_attr(kvm, attr);
	default:
		return -ENXIO;
	}
}

int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	struct kvm_device_attr attr;

	switch (ioctl) {
	case KVM_CREATE_IRQCHIP: {
		int ret;
		if (!vgic_present)
			return -ENXIO;
		mutex_lock(&kvm->lock);
		ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
		mutex_unlock(&kvm->lock);
		return ret;
	}
	case KVM_ARM_SET_DEVICE_ADDR: {
		struct kvm_arm_device_addr dev_addr;

		if (copy_from_user(&dev_addr, argp, sizeof(dev_addr)))
			return -EFAULT;
		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
	}
	case KVM_ARM_PREFERRED_TARGET: {
		struct kvm_vcpu_init init;

		kvm_vcpu_preferred_target(&init);

		if (copy_to_user(argp, &init, sizeof(init)))
			return -EFAULT;

		return 0;
	}
	case KVM_ARM_MTE_COPY_TAGS: {
		struct kvm_arm_copy_mte_tags copy_tags;

		if (copy_from_user(&copy_tags, argp, sizeof(copy_tags)))
			return -EFAULT;
		return kvm_vm_ioctl_mte_copy_tags(kvm, &copy_tags);
	}
	case KVM_ARM_SET_COUNTER_OFFSET: {
		struct kvm_arm_counter_offset offset;

		if (copy_from_user(&offset, argp, sizeof(offset)))
			return -EFAULT;
		return kvm_vm_ioctl_set_counter_offset(kvm, &offset);
	}
	case KVM_HAS_DEVICE_ATTR: {
		if (copy_from_user(&attr, argp, sizeof(attr)))
			return -EFAULT;

		return kvm_vm_has_attr(kvm, &attr);
	}
	case KVM_SET_DEVICE_ATTR: {
		if (copy_from_user(&attr, argp, sizeof(attr)))
			return -EFAULT;

		return kvm_vm_set_attr(kvm, &attr);
	}
	default:
		return -EINVAL;
	}
}

/* unlocks vcpus from @vcpu_lock_idx and smaller */
static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
{
	struct kvm_vcpu *tmp_vcpu;

	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
		tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
		mutex_unlock(&tmp_vcpu->mutex);
	}
}

void unlock_all_vcpus(struct kvm *kvm)
{
	lockdep_assert_held(&kvm->lock);

	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
}

/* Returns true if all vcpus were locked, false otherwise */
bool lock_all_vcpus(struct kvm *kvm)
{
	struct kvm_vcpu *tmp_vcpu;
	unsigned long c;

	lockdep_assert_held(&kvm->lock);

	/*
	 * Any time a vcpu is in an ioctl (including running), the
	 * core KVM code tries to grab the vcpu->mutex.
	 *
	 * By grabbing the vcpu->mutex of all VCPUs we ensure that no
	 * other VCPUs can fiddle with the state while we access it.
	 */
	kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
		if (!mutex_trylock(&tmp_vcpu->mutex)) {
			unlock_vcpus(kvm, c - 1);
			return false;
		}
	}

	return true;
}

static unsigned long nvhe_percpu_size(void)
{
	return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) -
		(unsigned long)CHOOSE_NVHE_SYM(__per_cpu_start);
}

static unsigned long nvhe_percpu_order(void)
{
	unsigned long size = nvhe_percpu_size();

	return size ? get_order(size) : 0;
}

/* A lookup table holding the hypervisor VA for each vector slot */
static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];

static void kvm_init_vector_slot(void *base, enum arm64_hyp_spectre_vector slot)
{
	hyp_spectre_vector_selector[slot] = __kvm_vector_slot2addr(base, slot);
}

static int kvm_init_vector_slots(void)
{
	int err;
	void *base;

	base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
	kvm_init_vector_slot(base, HYP_VECTOR_DIRECT);

	base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
	kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT);

	if (kvm_system_needs_idmapped_vectors() &&
	    !is_protected_kvm_enabled()) {
		err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs),
					       __BP_HARDEN_HYP_VECS_SZ, &base);
		if (err)
			return err;
	}

	kvm_init_vector_slot(base, HYP_VECTOR_INDIRECT);
	kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_INDIRECT);
	return 0;
}

static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
{
	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
	unsigned long tcr;

	/*
	 * Calculate the raw per-cpu offset without a translation from the
	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
	 * so that we can use adr_l to access per-cpu variables in EL2.
	 * Also drop the KASAN tag which gets in the way...
	 */
	params->tpidr_el2 = (unsigned long)kasan_reset_tag(per_cpu_ptr_nvhe_sym(__per_cpu_start, cpu)) -
			    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));

	params->mair_el2 = read_sysreg(mair_el1);

	tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1;
	tcr &= ~TCR_T0SZ_MASK;
	tcr |= TCR_T0SZ(hyp_va_bits);
	params->tcr_el2 = tcr;

	params->pgd_pa = kvm_mmu_get_httbr();
	if (is_protected_kvm_enabled())
		params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS;
	else
		params->hcr_el2 = HCR_HOST_NVHE_FLAGS;
	params->vttbr = params->vtcr = 0;

	/*
	 * Flush the init params from the data cache because the struct will
	 * be read while the MMU is off.
	 */
	kvm_flush_dcache_to_poc(params, sizeof(*params));
}

static void hyp_install_host_vector(void)
{
	struct kvm_nvhe_init_params *params;
	struct arm_smccc_res res;

	/* Switch from the HYP stub to our own HYP init vector */
	__hyp_set_vectors(kvm_get_idmap_vector());

	/*
	 * Call initialization code, and switch to the full blown HYP code.
	 * If the cpucaps haven't been finalized yet, something has gone very
	 * wrong, and hyp will crash and burn when it uses any
	 * cpus_have_const_cap() wrapper.
	 */
	BUG_ON(!system_capabilities_finalized());
	params = this_cpu_ptr_nvhe_sym(kvm_init_params);
	arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), virt_to_phys(params), &res);
	WARN_ON(res.a0 != SMCCC_RET_SUCCESS);
}

static void cpu_init_hyp_mode(void)
{
	hyp_install_host_vector();

	/*
	 * Disabling SSBD on a non-VHE system requires us to enable SSBS
	 * at EL2.
	 */
	if (this_cpu_has_cap(ARM64_SSBS) &&
	    arm64_get_spectre_v4_state() == SPECTRE_VULNERABLE) {
		kvm_call_hyp_nvhe(__kvm_enable_ssbs);
	}
}

static void cpu_hyp_reset(void)
{
	if (!is_kernel_in_hyp_mode())
		__hyp_reset_vectors();
}

/*
 * EL2 vectors can be mapped and rerouted in a number of ways,
 * depending on the kernel configuration and CPU present:
 *
 * - If the CPU is affected by Spectre-v2, the hardening sequence is
 *   placed in one of the vector slots, which is executed before jumping
 *   to the real vectors.
 *
 * - If the CPU also has the ARM64_SPECTRE_V3A cap, the slot
 *   containing the hardening sequence is mapped next to the idmap page,
 *   and executed before jumping to the real vectors.
 *
 * - If the CPU only has the ARM64_SPECTRE_V3A cap, then an
 *   empty slot is selected, mapped next to the idmap page, and
 *   executed before jumping to the real vectors.
 *
 * Note that ARM64_SPECTRE_V3A is somewhat incompatible with
 * VHE, as we don't have hypervisor-specific mappings. If the system
 * is VHE and yet selects this capability, it will be ignored.
 */
static void cpu_set_hyp_vector(void)
{
	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
	void *vector = hyp_spectre_vector_selector[data->slot];

	if (!is_protected_kvm_enabled())
		*this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)vector;
	else
		kvm_call_hyp_nvhe(__pkvm_cpu_set_vector, data->slot);
}

static void cpu_hyp_init_context(void)
{
	kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt);

	if (!is_kernel_in_hyp_mode())
		cpu_init_hyp_mode();
}

static void cpu_hyp_init_features(void)
{
	cpu_set_hyp_vector();
	kvm_arm_init_debug();

	if (is_kernel_in_hyp_mode())
		kvm_timer_init_vhe();

	if (vgic_present)
		kvm_vgic_init_cpu_hardware();
}

static void cpu_hyp_reinit(void)
{
	cpu_hyp_reset();
	cpu_hyp_init_context();
	cpu_hyp_init_features();
}

static void _kvm_arch_hardware_enable(void *discard)
{
	if (!__this_cpu_read(kvm_arm_hardware_enabled)) {
		cpu_hyp_reinit();
		__this_cpu_write(kvm_arm_hardware_enabled, 1);
	}
}

int kvm_arch_hardware_enable(void)
{
	int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);

	_kvm_arch_hardware_enable(NULL);

	if (!was_enabled) {
		kvm_vgic_cpu_up();
		kvm_timer_cpu_up();
	}

	return 0;
}

static void _kvm_arch_hardware_disable(void *discard)
{
	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
		cpu_hyp_reset();
		__this_cpu_write(kvm_arm_hardware_enabled, 0);
	}
}

void kvm_arch_hardware_disable(void)
{
	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
		kvm_timer_cpu_down();
		kvm_vgic_cpu_down();
	}

	if (!is_protected_kvm_enabled())
		_kvm_arch_hardware_disable(NULL);
}

#ifdef CONFIG_CPU_PM
static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
				    unsigned long cmd,
				    void *v)
{
	/*
	 * kvm_arm_hardware_enabled is left with its old value over
	 * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should
	 * re-enable hyp.
	 */
	switch (cmd) {
	case CPU_PM_ENTER:
		if (__this_cpu_read(kvm_arm_hardware_enabled))
			/*
			 * don't update kvm_arm_hardware_enabled here
			 * so that the hardware will be re-enabled
			 * when we resume. See below.
			 */
			cpu_hyp_reset();

		return NOTIFY_OK;
	case CPU_PM_ENTER_FAILED:
	case CPU_PM_EXIT:
		if (__this_cpu_read(kvm_arm_hardware_enabled))
			/* The hardware was enabled before suspend. */
			cpu_hyp_reinit();

		return NOTIFY_OK;

	default:
		return NOTIFY_DONE;
	}
}

static struct notifier_block hyp_init_cpu_pm_nb = {
	.notifier_call = hyp_init_cpu_pm_notifier,
};

static void __init hyp_cpu_pm_init(void)
{
	if (!is_protected_kvm_enabled())
		cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
}
static void __init hyp_cpu_pm_exit(void)
{
	if (!is_protected_kvm_enabled())
		cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
}
#else
static inline void __init hyp_cpu_pm_init(void)
{
}
static inline void __init hyp_cpu_pm_exit(void)
{
}
#endif

static void __init init_cpu_logical_map(void)
{
	unsigned int cpu;

	/*
	 * Copy the MPIDR <-> logical CPU ID mapping to hyp.
	 * Only copy the set of online CPUs whose features have been checked
	 * against the finalized system capabilities. The hypervisor will not
	 * allow any other CPUs from the `possible` set to boot.
	 */
	for_each_online_cpu(cpu)
		hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu);
}

#define init_psci_0_1_impl_state(config, what)	\
	config.psci_0_1_ ## what ## _implemented = psci_ops.what

static bool __init init_psci_relay(void)
{
	/*
	 * If PSCI has not been initialized, protected KVM cannot install
	 * itself on newly booted CPUs.
	 */
	if (!psci_ops.get_version) {
		kvm_err("Cannot initialize protected mode without PSCI\n");
		return false;
	}

	kvm_host_psci_config.version = psci_ops.get_version();

	if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) {
		kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids();
		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend);
		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on);
		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off);
		init_psci_0_1_impl_state(kvm_host_psci_config, migrate);
	}
	return true;
}

static int __init init_subsystems(void)
{
	int err = 0;

	/*
	 * Enable hardware so that subsystem initialisation can access EL2.
	 */
	on_each_cpu(_kvm_arch_hardware_enable, NULL, 1);

	/*
	 * Register CPU lower-power notifier
	 */
	hyp_cpu_pm_init();

	/*
	 * Init HYP view of VGIC
	 */
	err = kvm_vgic_hyp_init();
	switch (err) {
	case 0:
		vgic_present = true;
		break;
	case -ENODEV:
	case -ENXIO:
		vgic_present = false;
		err = 0;
		break;
	default:
		goto out;
	}

	/*
	 * Init HYP architected timer support
	 */
	err = kvm_timer_hyp_init(vgic_present);
	if (err)
		goto out;

	kvm_register_perf_callbacks(NULL);

out:
	if (err)
		hyp_cpu_pm_exit();

	if (err || !is_protected_kvm_enabled())
		on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);

	return err;
}

static void __init teardown_subsystems(void)
{
	kvm_unregister_perf_callbacks();
	hyp_cpu_pm_exit();
}

static void __init teardown_hyp_mode(void)
{
	int cpu;

	free_hyp_pgds();
	for_each_possible_cpu(cpu) {
		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
	}
}

static int __init do_pkvm_init(u32 hyp_va_bits)
{
	void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base));
	int ret;

	preempt_disable();
	cpu_hyp_init_context();
	ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size,
				num_possible_cpus(), kern_hyp_va(per_cpu_base),
				hyp_va_bits);
	cpu_hyp_init_features();

	/*
	 * The stub hypercalls are now disabled, so set our local flag to
	 * prevent a later re-init attempt in kvm_arch_hardware_enable().
	 */
	__this_cpu_write(kvm_arm_hardware_enabled, 1);
	preempt_enable();

	return ret;
}

static u64 get_hyp_id_aa64pfr0_el1(void)
{
	/*
	 * Track whether the system isn't affected by spectre/meltdown in the
	 * hypervisor's view of id_aa64pfr0_el1, used for protected VMs.
	 * Although this is per-CPU, we make it global for simplicity, e.g., not
	 * to have to worry about vcpu migration.
	 *
	 * Unlike for non-protected VMs, userspace cannot override this for
	 * protected VMs.
	 */
	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);

	val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) |
		 ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3));

	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2),
			  arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED);
	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3),
			  arm64_get_meltdown_state() == SPECTRE_UNAFFECTED);

	return val;
}

static void kvm_hyp_init_symbols(void)
{
	kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1();
	kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
	kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1);
	kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1);
	kvm_nvhe_sym(id_aa64isar2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
	kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
	kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1);
	kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1);
	kvm_nvhe_sym(__icache_flags) = __icache_flags;
	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
}

static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
{
	void *addr = phys_to_virt(hyp_mem_base);
	int ret;

	ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP);
	if (ret)
		return ret;

	ret = do_pkvm_init(hyp_va_bits);
	if (ret)
		return ret;

	free_hyp_pgds();

	return 0;
}

/* Inits Hyp-mode on all online CPUs */
static int __init init_hyp_mode(void)
{
	u32 hyp_va_bits;
	int cpu;
	int err = -ENOMEM;

	/*
	 * The protected Hyp-mode cannot be initialized if the memory pool
	 * allocation has failed.
	 */
	if (is_protected_kvm_enabled() && !hyp_mem_base)
		goto out_err;

	/*
	 * Allocate Hyp PGD and setup Hyp identity mapping
	 */
	err = kvm_mmu_init(&hyp_va_bits);
	if (err)
		goto out_err;

	/*
	 * Allocate stack pages for Hypervisor-mode
	 */
	for_each_possible_cpu(cpu) {
		unsigned long stack_page;

		stack_page = __get_free_page(GFP_KERNEL);
		if (!stack_page) {
			err = -ENOMEM;
			goto out_err;
		}

		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
	}

	/*
	 * Allocate and initialize pages for Hypervisor-mode percpu regions.
	 */
	for_each_possible_cpu(cpu) {
		struct page *page;
		void *page_addr;

		page = alloc_pages(GFP_KERNEL, nvhe_percpu_order());
		if (!page) {
			err = -ENOMEM;
			goto out_err;
		}

		page_addr = page_address(page);
		memcpy(page_addr, CHOOSE_NVHE_SYM(__per_cpu_start), nvhe_percpu_size());
		kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu] = (unsigned long)page_addr;
	}

	/*
	 * Map the Hyp-code called directly from the host
	 */
	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
				  kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
	if (err) {
		kvm_err("Cannot map world-switch code\n");
		goto out_err;
	}

	err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
				  kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
	if (err) {
		kvm_err("Cannot map .hyp.rodata section\n");
		goto out_err;
	}

	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
	if (err) {
		kvm_err("Cannot map rodata section\n");
		goto out_err;
	}

	/*
	 * .hyp.bss is guaranteed to be placed at the beginning of the .bss
	 * section thanks to an assertion in the linker script. Map it RW and
	 * the rest of .bss RO.
	 */
	err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_start),
				  kvm_ksym_ref(__hyp_bss_end), PAGE_HYP);
	if (err) {
		kvm_err("Cannot map hyp bss section: %d\n", err);
		goto out_err;
	}

	err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_end),
				  kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
	if (err) {
		kvm_err("Cannot map bss section\n");
		goto out_err;
	}

	/*
	 * Map the Hyp stack pages
	 */
	for_each_possible_cpu(cpu) {
		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
		unsigned long hyp_addr;

		/*
		 * Allocate a contiguous HYP private VA range for the stack
		 * and guard page. The allocation is also aligned based on
		 * the order of its size.
		 */
		err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
		if (err) {
			kvm_err("Cannot allocate hyp stack guard page\n");
			goto out_err;
		}

		/*
		 * Since the stack grows downwards, map the stack to the page
		 * at the higher address and leave the lower guard page
		 * unbacked.
		 *
		 * Any valid stack address now has the PAGE_SHIFT bit as 1
		 * and addresses corresponding to the guard page have the
		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
		 */
		err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE,
					    __pa(stack_page), PAGE_HYP);
		if (err) {
			kvm_err("Cannot map hyp stack\n");
			goto out_err;
		}

		/*
		 * Save the stack PA in nvhe_init_params. This will be needed
		 * to recreate the stack mapping in protected nVHE mode.
		 * __hyp_pa() won't do the right thing there, since the stack
		 * has been mapped in the flexible private VA space.
		 */
		params->stack_pa = __pa(stack_page);

		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
	}

	for_each_possible_cpu(cpu) {
		char *percpu_begin = (char *)kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu];
		char *percpu_end = percpu_begin + nvhe_percpu_size();

		/* Map Hyp percpu pages */
		err = create_hyp_mappings(percpu_begin, percpu_end, PAGE_HYP);
		if (err) {
			kvm_err("Cannot map hyp percpu region\n");
			goto out_err;
		}

		/* Prepare the CPU initialization parameters */
		cpu_prepare_hyp_mode(cpu, hyp_va_bits);
	}

	kvm_hyp_init_symbols();

	if (is_protected_kvm_enabled()) {
		init_cpu_logical_map();

		if (!init_psci_relay()) {
			err = -ENODEV;
			goto out_err;
		}

		err = kvm_hyp_init_protection(hyp_va_bits);
		if (err) {
			kvm_err("Failed to init hyp memory protection\n");
			goto out_err;
		}
	}

	return 0;

out_err:
	teardown_hyp_mode();
	kvm_err("error initializing Hyp mode: %d\n", err);
	return err;
}

struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;

	mpidr &= MPIDR_HWID_BITMASK;
	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
			return vcpu;
	}
	return NULL;
}

bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
{
	return irqchip_in_kernel(kvm);
}

bool kvm_arch_has_irq_bypass(void)
{
	return true;
}

int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
				      struct irq_bypass_producer *prod)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);

	return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq,
					  &irqfd->irq_entry);
}
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
				      struct irq_bypass_producer *prod)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);

	kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq,
				     &irqfd->irq_entry);
}

void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);

	kvm_arm_halt_guest(irqfd->kvm);
}

void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);

	kvm_arm_resume_guest(irqfd->kvm);
}

/* Initialize Hyp-mode and memory mappings on all CPUs */
static __init int kvm_arm_init(void)
{
	int err;
	bool in_hyp_mode;

	if (!is_hyp_mode_available()) {
		kvm_info("HYP mode not available\n");
		return -ENODEV;
	}

	if (kvm_get_mode() == KVM_MODE_NONE) {
		kvm_info("KVM disabled from command line\n");
		return -ENODEV;
	}

	err = kvm_sys_reg_table_init();
	if (err) {
		kvm_info("Error initializing system register tables");
		return err;
	}

	in_hyp_mode = is_kernel_in_hyp_mode();

	if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) ||
	    cpus_have_final_cap(ARM64_WORKAROUND_1508412))
		kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
			 "Only trusted guests should be used on this system.\n");

	err = kvm_set_ipa_limit();
	if (err)
		return err;

	err = kvm_arm_init_sve();
	if (err)
		return err;

	err = kvm_arm_vmid_alloc_init();
	if (err) {
		kvm_err("Failed to initialize VMID allocator.\n");
		return err;
	}

	if (!in_hyp_mode) {
		err = init_hyp_mode();
		if (err)
			goto out_err;
	}

	err = kvm_init_vector_slots();
	if (err) {
		kvm_err("Cannot initialise vector slots\n");
		goto out_hyp;
	}

	err = init_subsystems();
	if (err)
		goto out_hyp;

	if (is_protected_kvm_enabled()) {
		kvm_info("Protected nVHE mode initialized successfully\n");
	} else if (in_hyp_mode) {
		kvm_info("VHE mode initialized successfully\n");
	} else {
		kvm_info("Hyp mode initialized successfully\n");
	}

	/*
	 * FIXME: Do something reasonable if kvm_init() fails after pKVM
	 * hypervisor protection is finalized.
	 */
	err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
	if (err)
		goto out_subs;

	return 0;

out_subs:
	teardown_subsystems();
out_hyp:
	if (!in_hyp_mode)
		teardown_hyp_mode();
out_err:
	kvm_arm_vmid_alloc_free();
	return err;
}

static int __init early_kvm_mode_cfg(char *arg)
{
	if (!arg)
		return -EINVAL;

	if (strcmp(arg, "none") == 0) {
		kvm_mode = KVM_MODE_NONE;
		return 0;
	}

	if (!is_hyp_mode_available()) {
		pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n");
		return 0;
	}

	if (strcmp(arg, "protected") == 0) {
		if (!is_kernel_in_hyp_mode())
			kvm_mode = KVM_MODE_PROTECTED;
		else
			pr_warn_once("Protected KVM not available with VHE\n");

		return 0;
	}

	if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) {
		kvm_mode = KVM_MODE_DEFAULT;
		return 0;
	}

	if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) {
		kvm_mode = KVM_MODE_NV;
		return 0;
	}

	return -EINVAL;
}
early_param("kvm-arm.mode", early_kvm_mode_cfg);

enum kvm_mode kvm_get_mode(void)
{
	return kvm_mode;
}

module_init(kvm_arm_init);