summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/kvm_host.h
blob: c25775fad4ed19d73452f530f4fecfb8d2373176 (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
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This header defines architecture specific interfaces, x86 version
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#ifndef _ASM_X86_KVM_HOST_H
#define _ASM_X86_KVM_HOST_H

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/tracepoint.h>
#include <linux/cpumask.h>
#include <linux/irq_work.h>

#include <linux/kvm.h>
#include <linux/kvm_para.h>
#include <linux/kvm_types.h>
#include <linux/perf_event.h>
#include <linux/pvclock_gtod.h>
#include <linux/clocksource.h>
#include <linux/irqbypass.h>
#include <linux/hyperv.h>

#include <asm/apic.h>
#include <asm/pvclock-abi.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
#include <asm/kvm_page_track.h>
#include <asm/hyperv-tlfs.h>

#define KVM_MAX_VCPUS 288
#define KVM_SOFT_MAX_VCPUS 240
#define KVM_MAX_VCPU_ID 1023
#define KVM_USER_MEM_SLOTS 509
/* memory slots that are not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 3
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)

#define KVM_HALT_POLL_NS_DEFAULT 200000

#define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS

/* x86-specific vcpu->requests bit members */
#define KVM_REQ_MIGRATE_TIMER		KVM_ARCH_REQ(0)
#define KVM_REQ_REPORT_TPR_ACCESS	KVM_ARCH_REQ(1)
#define KVM_REQ_TRIPLE_FAULT		KVM_ARCH_REQ(2)
#define KVM_REQ_MMU_SYNC		KVM_ARCH_REQ(3)
#define KVM_REQ_CLOCK_UPDATE		KVM_ARCH_REQ(4)
#define KVM_REQ_EVENT			KVM_ARCH_REQ(6)
#define KVM_REQ_APF_HALT		KVM_ARCH_REQ(7)
#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(8)
#define KVM_REQ_NMI			KVM_ARCH_REQ(9)
#define KVM_REQ_PMU			KVM_ARCH_REQ(10)
#define KVM_REQ_PMI			KVM_ARCH_REQ(11)
#define KVM_REQ_SMI			KVM_ARCH_REQ(12)
#define KVM_REQ_MASTERCLOCK_UPDATE	KVM_ARCH_REQ(13)
#define KVM_REQ_MCLOCK_INPROGRESS \
	KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_SCAN_IOAPIC \
	KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_GLOBAL_CLOCK_UPDATE	KVM_ARCH_REQ(16)
#define KVM_REQ_APIC_PAGE_RELOAD \
	KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HV_CRASH		KVM_ARCH_REQ(18)
#define KVM_REQ_IOAPIC_EOI_EXIT		KVM_ARCH_REQ(19)
#define KVM_REQ_HV_RESET		KVM_ARCH_REQ(20)
#define KVM_REQ_HV_EXIT			KVM_ARCH_REQ(21)
#define KVM_REQ_HV_STIMER		KVM_ARCH_REQ(22)
#define KVM_REQ_LOAD_EOI_EXITMAP	KVM_ARCH_REQ(23)

#define CR0_RESERVED_BITS                                               \
	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))

#define CR3_PCID_INVD		 BIT_64(63)
#define CR4_RESERVED_BITS                                               \
	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))

#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)



#define INVALID_PAGE (~(hpa_t)0)
#define VALID_PAGE(x) ((x) != INVALID_PAGE)

#define UNMAPPED_GVA (~(gpa_t)0)

/* KVM Hugepage definitions for x86 */
#define KVM_NR_PAGE_SIZES	3
#define KVM_HPAGE_GFN_SHIFT(x)	(((x) - 1) * 9)
#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
#define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)

static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
{
	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
}

#define KVM_PERMILLE_MMU_PAGES 20
#define KVM_MIN_ALLOC_MMU_PAGES 64
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 80
#define KVM_NR_FIXED_MTRR_REGION 88
#define KVM_NR_VAR_MTRR 8

#define ASYNC_PF_PER_VCPU 64

enum kvm_reg {
	VCPU_REGS_RAX = 0,
	VCPU_REGS_RCX = 1,
	VCPU_REGS_RDX = 2,
	VCPU_REGS_RBX = 3,
	VCPU_REGS_RSP = 4,
	VCPU_REGS_RBP = 5,
	VCPU_REGS_RSI = 6,
	VCPU_REGS_RDI = 7,
#ifdef CONFIG_X86_64
	VCPU_REGS_R8 = 8,
	VCPU_REGS_R9 = 9,
	VCPU_REGS_R10 = 10,
	VCPU_REGS_R11 = 11,
	VCPU_REGS_R12 = 12,
	VCPU_REGS_R13 = 13,
	VCPU_REGS_R14 = 14,
	VCPU_REGS_R15 = 15,
#endif
	VCPU_REGS_RIP,
	NR_VCPU_REGS
};

enum kvm_reg_ex {
	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
	VCPU_EXREG_CR3,
	VCPU_EXREG_RFLAGS,
	VCPU_EXREG_SEGMENTS,
};

enum {
	VCPU_SREG_ES,
	VCPU_SREG_CS,
	VCPU_SREG_SS,
	VCPU_SREG_DS,
	VCPU_SREG_FS,
	VCPU_SREG_GS,
	VCPU_SREG_TR,
	VCPU_SREG_LDTR,
};

#include <asm/kvm_emulate.h>

#define KVM_NR_MEM_OBJS 40

#define KVM_NR_DB_REGS	4

#define DR6_BD		(1 << 13)
#define DR6_BS		(1 << 14)
#define DR6_RTM		(1 << 16)
#define DR6_FIXED_1	0xfffe0ff0
#define DR6_INIT	0xffff0ff0
#define DR6_VOLATILE	0x0001e00f

#define DR7_BP_EN_MASK	0x000000ff
#define DR7_GE		(1 << 9)
#define DR7_GD		(1 << 13)
#define DR7_FIXED_1	0x00000400
#define DR7_VOLATILE	0xffff2bff

#define PFERR_PRESENT_BIT 0
#define PFERR_WRITE_BIT 1
#define PFERR_USER_BIT 2
#define PFERR_RSVD_BIT 3
#define PFERR_FETCH_BIT 4
#define PFERR_PK_BIT 5
#define PFERR_GUEST_FINAL_BIT 32
#define PFERR_GUEST_PAGE_BIT 33

#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
#define PFERR_PK_MASK (1U << PFERR_PK_BIT)
#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)

#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
				 PFERR_WRITE_MASK |		\
				 PFERR_PRESENT_MASK)

/*
 * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
 * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting
 * with the SVE bit in EPT PTEs.
 */
#define SPTE_SPECIAL_MASK (1ULL << 62)

/* apic attention bits */
#define KVM_APIC_CHECK_VAPIC	0
/*
 * The following bit is set with PV-EOI, unset on EOI.
 * We detect PV-EOI changes by guest by comparing
 * this bit with PV-EOI in guest memory.
 * See the implementation in apic_update_pv_eoi.
 */
#define KVM_APIC_PV_EOI_PENDING	1

struct kvm_kernel_irq_routing_entry;

/*
 * We don't want allocation failures within the mmu code, so we preallocate
 * enough memory for a single page fault in a cache.
 */
struct kvm_mmu_memory_cache {
	int nobjs;
	void *objects[KVM_NR_MEM_OBJS];
};

/*
 * the pages used as guest page table on soft mmu are tracked by
 * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
 * by indirect shadow page can not be more than 15 bits.
 *
 * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
 * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
 */
union kvm_mmu_page_role {
	unsigned word;
	struct {
		unsigned level:4;
		unsigned cr4_pae:1;
		unsigned quadrant:2;
		unsigned direct:1;
		unsigned access:3;
		unsigned invalid:1;
		unsigned nxe:1;
		unsigned cr0_wp:1;
		unsigned smep_andnot_wp:1;
		unsigned smap_andnot_wp:1;
		unsigned ad_disabled:1;
		unsigned :7;

		/*
		 * This is left at the top of the word so that
		 * kvm_memslots_for_spte_role can extract it with a
		 * simple shift.  While there is room, give it a whole
		 * byte so it is also faster to load it from memory.
		 */
		unsigned smm:8;
	};
};

struct kvm_rmap_head {
	unsigned long val;
};

struct kvm_mmu_page {
	struct list_head link;
	struct hlist_node hash_link;

	/*
	 * The following two entries are used to key the shadow page in the
	 * hash table.
	 */
	gfn_t gfn;
	union kvm_mmu_page_role role;

	u64 *spt;
	/* hold the gfn of each spte inside spt */
	gfn_t *gfns;
	bool unsync;
	int root_count;          /* Currently serving as active root */
	unsigned int unsync_children;
	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */

	/* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen.  */
	unsigned long mmu_valid_gen;

	DECLARE_BITMAP(unsync_child_bitmap, 512);

#ifdef CONFIG_X86_32
	/*
	 * Used out of the mmu-lock to avoid reading spte values while an
	 * update is in progress; see the comments in __get_spte_lockless().
	 */
	int clear_spte_count;
#endif

	/* Number of writes since the last time traversal visited this page.  */
	atomic_t write_flooding_count;
};

struct kvm_pio_request {
	unsigned long count;
	int in;
	int port;
	int size;
};

#define PT64_ROOT_MAX_LEVEL 5

struct rsvd_bits_validate {
	u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL];
	u64 bad_mt_xwr;
};

/*
 * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
 * and 2-level 32-bit).  The kvm_mmu structure abstracts the details of the
 * current mmu mode.
 */
struct kvm_mmu {
	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
			  bool prefault);
	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
				  struct x86_exception *fault);
	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
			    struct x86_exception *exception);
	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
			       struct x86_exception *exception);
	int (*sync_page)(struct kvm_vcpu *vcpu,
			 struct kvm_mmu_page *sp);
	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
	void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			   u64 *spte, const void *pte);
	hpa_t root_hpa;
	union kvm_mmu_page_role base_role;
	u8 root_level;
	u8 shadow_root_level;
	u8 ept_ad;
	bool direct_map;

	/*
	 * Bitmap; bit set = permission fault
	 * Byte index: page fault error code [4:1]
	 * Bit index: pte permissions in ACC_* format
	 */
	u8 permissions[16];

	/*
	* The pkru_mask indicates if protection key checks are needed.  It
	* consists of 16 domains indexed by page fault error code bits [4:1],
	* with PFEC.RSVD replaced by ACC_USER_MASK from the page tables.
	* Each domain has 2 bits which are ANDed with AD and WD from PKRU.
	*/
	u32 pkru_mask;

	u64 *pae_root;
	u64 *lm_root;

	/*
	 * check zero bits on shadow page table entries, these
	 * bits include not only hardware reserved bits but also
	 * the bits spte never used.
	 */
	struct rsvd_bits_validate shadow_zero_check;

	struct rsvd_bits_validate guest_rsvd_check;

	/* Can have large pages at levels 2..last_nonleaf_level-1. */
	u8 last_nonleaf_level;

	bool nx;

	u64 pdptrs[4]; /* pae */
};

enum pmc_type {
	KVM_PMC_GP = 0,
	KVM_PMC_FIXED,
};

struct kvm_pmc {
	enum pmc_type type;
	u8 idx;
	u64 counter;
	u64 eventsel;
	struct perf_event *perf_event;
	struct kvm_vcpu *vcpu;
};

struct kvm_pmu {
	unsigned nr_arch_gp_counters;
	unsigned nr_arch_fixed_counters;
	unsigned available_event_types;
	u64 fixed_ctr_ctrl;
	u64 global_ctrl;
	u64 global_status;
	u64 global_ovf_ctrl;
	u64 counter_bitmask[2];
	u64 global_ctrl_mask;
	u64 reserved_bits;
	u8 version;
	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
	struct irq_work irq_work;
	u64 reprogram_pmi;
};

struct kvm_pmu_ops;

enum {
	KVM_DEBUGREG_BP_ENABLED = 1,
	KVM_DEBUGREG_WONT_EXIT = 2,
	KVM_DEBUGREG_RELOAD = 4,
};

struct kvm_mtrr_range {
	u64 base;
	u64 mask;
	struct list_head node;
};

struct kvm_mtrr {
	struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
	mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
	u64 deftype;

	struct list_head head;
};

/* Hyper-V SynIC timer */
struct kvm_vcpu_hv_stimer {
	struct hrtimer timer;
	int index;
	u64 config;
	u64 count;
	u64 exp_time;
	struct hv_message msg;
	bool msg_pending;
};

/* Hyper-V synthetic interrupt controller (SynIC)*/
struct kvm_vcpu_hv_synic {
	u64 version;
	u64 control;
	u64 msg_page;
	u64 evt_page;
	atomic64_t sint[HV_SYNIC_SINT_COUNT];
	atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT];
	DECLARE_BITMAP(auto_eoi_bitmap, 256);
	DECLARE_BITMAP(vec_bitmap, 256);
	bool active;
	bool dont_zero_synic_pages;
};

/* Hyper-V per vcpu emulation context */
struct kvm_vcpu_hv {
	u32 vp_index;
	u64 hv_vapic;
	s64 runtime_offset;
	struct kvm_vcpu_hv_synic synic;
	struct kvm_hyperv_exit exit;
	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
};

struct kvm_vcpu_arch {
	/*
	 * rip and regs accesses must go through
	 * kvm_{register,rip}_{read,write} functions.
	 */
	unsigned long regs[NR_VCPU_REGS];
	u32 regs_avail;
	u32 regs_dirty;

	unsigned long cr0;
	unsigned long cr0_guest_owned_bits;
	unsigned long cr2;
	unsigned long cr3;
	unsigned long cr4;
	unsigned long cr4_guest_owned_bits;
	unsigned long cr8;
	u32 pkru;
	u32 hflags;
	u64 efer;
	u64 apic_base;
	struct kvm_lapic *apic;    /* kernel irqchip context */
	bool apicv_active;
	bool load_eoi_exitmap_pending;
	DECLARE_BITMAP(ioapic_handled_vectors, 256);
	unsigned long apic_attention;
	int32_t apic_arb_prio;
	int mp_state;
	u64 ia32_misc_enable_msr;
	u64 smbase;
	u64 smi_count;
	bool tpr_access_reporting;
	u64 ia32_xss;
	u64 microcode_version;

	/*
	 * Paging state of the vcpu
	 *
	 * If the vcpu runs in guest mode with two level paging this still saves
	 * the paging mode of the l1 guest. This context is always used to
	 * handle faults.
	 */
	struct kvm_mmu mmu;

	/*
	 * Paging state of an L2 guest (used for nested npt)
	 *
	 * This context will save all necessary information to walk page tables
	 * of the an L2 guest. This context is only initialized for page table
	 * walking and not for faulting since we never handle l2 page faults on
	 * the host.
	 */
	struct kvm_mmu nested_mmu;

	/*
	 * Pointer to the mmu context currently used for
	 * gva_to_gpa translations.
	 */
	struct kvm_mmu *walk_mmu;

	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
	struct kvm_mmu_memory_cache mmu_page_cache;
	struct kvm_mmu_memory_cache mmu_page_header_cache;

	/*
	 * QEMU userspace and the guest each have their own FPU state.
	 * In vcpu_run, we switch between the user and guest FPU contexts.
	 * While running a VCPU, the VCPU thread will have the guest FPU
	 * context.
	 *
	 * Note that while the PKRU state lives inside the fpu registers,
	 * it is switched out separately at VMENTER and VMEXIT time. The
	 * "guest_fpu" state here contains the guest FPU context, with the
	 * host PRKU bits.
	 */
	struct fpu user_fpu;
	struct fpu guest_fpu;

	u64 xcr0;
	u64 guest_supported_xcr0;
	u32 guest_xstate_size;

	struct kvm_pio_request pio;
	void *pio_data;

	u8 event_exit_inst_len;

	struct kvm_queued_exception {
		bool pending;
		bool injected;
		bool has_error_code;
		u8 nr;
		u32 error_code;
		u8 nested_apf;
	} exception;

	struct kvm_queued_interrupt {
		bool injected;
		bool soft;
		u8 nr;
	} interrupt;

	int halt_request; /* real mode on Intel only */

	int cpuid_nent;
	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];

	int maxphyaddr;

	/* emulate context */

	struct x86_emulate_ctxt emulate_ctxt;
	bool emulate_regs_need_sync_to_vcpu;
	bool emulate_regs_need_sync_from_vcpu;
	int (*complete_userspace_io)(struct kvm_vcpu *vcpu);

	gpa_t time;
	struct pvclock_vcpu_time_info hv_clock;
	unsigned int hw_tsc_khz;
	struct gfn_to_hva_cache pv_time;
	bool pv_time_enabled;
	/* set guest stopped flag in pvclock flags field */
	bool pvclock_set_guest_stopped_request;

	struct {
		u64 msr_val;
		u64 last_steal;
		struct gfn_to_hva_cache stime;
		struct kvm_steal_time steal;
	} st;

	u64 tsc_offset;
	u64 last_guest_tsc;
	u64 last_host_tsc;
	u64 tsc_offset_adjustment;
	u64 this_tsc_nsec;
	u64 this_tsc_write;
	u64 this_tsc_generation;
	bool tsc_catchup;
	bool tsc_always_catchup;
	s8 virtual_tsc_shift;
	u32 virtual_tsc_mult;
	u32 virtual_tsc_khz;
	s64 ia32_tsc_adjust_msr;
	u64 tsc_scaling_ratio;

	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
	unsigned nmi_pending; /* NMI queued after currently running handler */
	bool nmi_injected;    /* Trying to inject an NMI this entry */
	bool smi_pending;    /* SMI queued after currently running handler */

	struct kvm_mtrr mtrr_state;
	u64 pat;

	unsigned switch_db_regs;
	unsigned long db[KVM_NR_DB_REGS];
	unsigned long dr6;
	unsigned long dr7;
	unsigned long eff_db[KVM_NR_DB_REGS];
	unsigned long guest_debug_dr7;
	u64 msr_platform_info;
	u64 msr_misc_features_enables;

	u64 mcg_cap;
	u64 mcg_status;
	u64 mcg_ctl;
	u64 mcg_ext_ctl;
	u64 *mce_banks;

	/* Cache MMIO info */
	u64 mmio_gva;
	unsigned access;
	gfn_t mmio_gfn;
	u64 mmio_gen;

	struct kvm_pmu pmu;

	/* used for guest single stepping over the given code position */
	unsigned long singlestep_rip;

	struct kvm_vcpu_hv hyperv;

	cpumask_var_t wbinvd_dirty_mask;

	unsigned long last_retry_eip;
	unsigned long last_retry_addr;

	struct {
		bool halted;
		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
		struct gfn_to_hva_cache data;
		u64 msr_val;
		u32 id;
		bool send_user_only;
		u32 host_apf_reason;
		unsigned long nested_apf_token;
		bool delivery_as_pf_vmexit;
	} apf;

	/* OSVW MSRs (AMD only) */
	struct {
		u64 length;
		u64 status;
	} osvw;

	struct {
		u64 msr_val;
		struct gfn_to_hva_cache data;
	} pv_eoi;

	/*
	 * Indicate whether the access faults on its page table in guest
	 * which is set when fix page fault and used to detect unhandeable
	 * instruction.
	 */
	bool write_fault_to_shadow_pgtable;

	/* set at EPT violation at this point */
	unsigned long exit_qualification;

	/* pv related host specific info */
	struct {
		bool pv_unhalted;
	} pv;

	int pending_ioapic_eoi;
	int pending_external_vector;

	/* GPA available */
	bool gpa_available;
	gpa_t gpa_val;

	/* be preempted when it's in kernel-mode(cpl=0) */
	bool preempted_in_kernel;
};

struct kvm_lpage_info {
	int disallow_lpage;
};

struct kvm_arch_memory_slot {
	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
};

/*
 * We use as the mode the number of bits allocated in the LDR for the
 * logical processor ID.  It happens that these are all powers of two.
 * This makes it is very easy to detect cases where the APICs are
 * configured for multiple modes; in that case, we cannot use the map and
 * hence cannot use kvm_irq_delivery_to_apic_fast either.
 */
#define KVM_APIC_MODE_XAPIC_CLUSTER          4
#define KVM_APIC_MODE_XAPIC_FLAT             8
#define KVM_APIC_MODE_X2APIC                16

struct kvm_apic_map {
	struct rcu_head rcu;
	u8 mode;
	u32 max_apic_id;
	union {
		struct kvm_lapic *xapic_flat_map[8];
		struct kvm_lapic *xapic_cluster_map[16][4];
	};
	struct kvm_lapic *phys_map[];
};

/* Hyper-V emulation context */
struct kvm_hv {
	struct mutex hv_lock;
	u64 hv_guest_os_id;
	u64 hv_hypercall;
	u64 hv_tsc_page;

	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
	u64 hv_crash_ctl;

	HV_REFERENCE_TSC_PAGE tsc_ref;

	struct idr conn_to_evt;

	u64 hv_reenlightenment_control;
	u64 hv_tsc_emulation_control;
	u64 hv_tsc_emulation_status;
};

enum kvm_irqchip_mode {
	KVM_IRQCHIP_NONE,
	KVM_IRQCHIP_KERNEL,       /* created with KVM_CREATE_IRQCHIP */
	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
};

struct kvm_arch {
	unsigned int n_used_mmu_pages;
	unsigned int n_requested_mmu_pages;
	unsigned int n_max_mmu_pages;
	unsigned int indirect_shadow_pages;
	unsigned long mmu_valid_gen;
	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
	/*
	 * Hash table of struct kvm_mmu_page.
	 */
	struct list_head active_mmu_pages;
	struct list_head zapped_obsolete_pages;
	struct kvm_page_track_notifier_node mmu_sp_tracker;
	struct kvm_page_track_notifier_head track_notifier_head;

	struct list_head assigned_dev_head;
	struct iommu_domain *iommu_domain;
	bool iommu_noncoherent;
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
	atomic_t noncoherent_dma_count;
#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
	atomic_t assigned_device_count;
	struct kvm_pic *vpic;
	struct kvm_ioapic *vioapic;
	struct kvm_pit *vpit;
	atomic_t vapics_in_nmi_mode;
	struct mutex apic_map_lock;
	struct kvm_apic_map *apic_map;

	bool apic_access_page_done;

	gpa_t wall_clock;

	bool mwait_in_guest;
	bool hlt_in_guest;
	bool pause_in_guest;

	unsigned long irq_sources_bitmap;
	s64 kvmclock_offset;
	raw_spinlock_t tsc_write_lock;
	u64 last_tsc_nsec;
	u64 last_tsc_write;
	u32 last_tsc_khz;
	u64 cur_tsc_nsec;
	u64 cur_tsc_write;
	u64 cur_tsc_offset;
	u64 cur_tsc_generation;
	int nr_vcpus_matched_tsc;

	spinlock_t pvclock_gtod_sync_lock;
	bool use_master_clock;
	u64 master_kernel_ns;
	u64 master_cycle_now;
	struct delayed_work kvmclock_update_work;
	struct delayed_work kvmclock_sync_work;

	struct kvm_xen_hvm_config xen_hvm_config;

	/* reads protected by irq_srcu, writes by irq_lock */
	struct hlist_head mask_notifier_list;

	struct kvm_hv hyperv;

	#ifdef CONFIG_KVM_MMU_AUDIT
	int audit_point;
	#endif

	bool backwards_tsc_observed;
	bool boot_vcpu_runs_old_kvmclock;
	u32 bsp_vcpu_id;

	u64 disabled_quirks;

	enum kvm_irqchip_mode irqchip_mode;
	u8 nr_reserved_ioapic_pins;

	bool disabled_lapic_found;

	bool x2apic_format;
	bool x2apic_broadcast_quirk_disabled;
};

struct kvm_vm_stat {
	ulong mmu_shadow_zapped;
	ulong mmu_pte_write;
	ulong mmu_pte_updated;
	ulong mmu_pde_zapped;
	ulong mmu_flooded;
	ulong mmu_recycled;
	ulong mmu_cache_miss;
	ulong mmu_unsync;
	ulong remote_tlb_flush;
	ulong lpages;
	ulong max_mmu_page_hash_collisions;
};

struct kvm_vcpu_stat {
	u64 pf_fixed;
	u64 pf_guest;
	u64 tlb_flush;
	u64 invlpg;

	u64 exits;
	u64 io_exits;
	u64 mmio_exits;
	u64 signal_exits;
	u64 irq_window_exits;
	u64 nmi_window_exits;
	u64 halt_exits;
	u64 halt_successful_poll;
	u64 halt_attempted_poll;
	u64 halt_poll_invalid;
	u64 halt_wakeup;
	u64 request_irq_exits;
	u64 irq_exits;
	u64 host_state_reload;
	u64 fpu_reload;
	u64 insn_emulation;
	u64 insn_emulation_fail;
	u64 hypercalls;
	u64 irq_injections;
	u64 nmi_injections;
	u64 req_event;
};

struct x86_instruction_info;

struct msr_data {
	bool host_initiated;
	u32 index;
	u64 data;
};

struct kvm_lapic_irq {
	u32 vector;
	u16 delivery_mode;
	u16 dest_mode;
	bool level;
	u16 trig_mode;
	u32 shorthand;
	u32 dest_id;
	bool msi_redir_hint;
};

struct kvm_x86_ops {
	int (*cpu_has_kvm_support)(void);          /* __init */
	int (*disabled_by_bios)(void);             /* __init */
	int (*hardware_enable)(void);
	void (*hardware_disable)(void);
	void (*check_processor_compatibility)(void *rtn);
	int (*hardware_setup)(void);               /* __init */
	void (*hardware_unsetup)(void);            /* __exit */
	bool (*cpu_has_accelerated_tpr)(void);
	bool (*cpu_has_high_real_mode_segbase)(void);
	void (*cpuid_update)(struct kvm_vcpu *vcpu);

	struct kvm *(*vm_alloc)(void);
	void (*vm_free)(struct kvm *);
	int (*vm_init)(struct kvm *kvm);
	void (*vm_destroy)(struct kvm *kvm);

	/* Create, but do not attach this VCPU */
	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
	void (*vcpu_free)(struct kvm_vcpu *vcpu);
	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);

	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
	void (*vcpu_put)(struct kvm_vcpu *vcpu);

	void (*update_bp_intercept)(struct kvm_vcpu *vcpu);
	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
	void (*get_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
	int (*get_cpl)(struct kvm_vcpu *vcpu);
	void (*set_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
	void (*decache_cr3)(struct kvm_vcpu *vcpu);
	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
	int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
	void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
	u64 (*get_dr6)(struct kvm_vcpu *vcpu);
	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);

	void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);

	void (*run)(struct kvm_vcpu *vcpu);
	int (*handle_exit)(struct kvm_vcpu *vcpu);
	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
				unsigned char *hypercall_addr);
	void (*set_irq)(struct kvm_vcpu *vcpu);
	void (*set_nmi)(struct kvm_vcpu *vcpu);
	void (*queue_exception)(struct kvm_vcpu *vcpu);
	void (*cancel_injection)(struct kvm_vcpu *vcpu);
	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
	bool (*get_enable_apicv)(struct kvm_vcpu *vcpu);
	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
	int (*get_lpage_level)(void);
	bool (*rdtscp_supported)(void);
	bool (*invpcid_supported)(void);

	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);

	void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);

	bool (*has_wbinvd_exit)(void);

	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);

	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);

	int (*check_intercept)(struct kvm_vcpu *vcpu,
			       struct x86_instruction_info *info,
			       enum x86_intercept_stage stage);
	void (*handle_external_intr)(struct kvm_vcpu *vcpu);
	bool (*mpx_supported)(void);
	bool (*xsaves_supported)(void);
	bool (*umip_emulated)(void);

	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);

	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);

	/*
	 * Arch-specific dirty logging hooks. These hooks are only supposed to
	 * be valid if the specific arch has hardware-accelerated dirty logging
	 * mechanism. Currently only for PML on VMX.
	 *
	 *  - slot_enable_log_dirty:
	 *	called when enabling log dirty mode for the slot.
	 *  - slot_disable_log_dirty:
	 *	called when disabling log dirty mode for the slot.
	 *	also called when slot is created with log dirty disabled.
	 *  - flush_log_dirty:
	 *	called before reporting dirty_bitmap to userspace.
	 *  - enable_log_dirty_pt_masked:
	 *	called when reenabling log dirty for the GFNs in the mask after
	 *	corresponding bits are cleared in slot->dirty_bitmap.
	 */
	void (*slot_enable_log_dirty)(struct kvm *kvm,
				      struct kvm_memory_slot *slot);
	void (*slot_disable_log_dirty)(struct kvm *kvm,
				       struct kvm_memory_slot *slot);
	void (*flush_log_dirty)(struct kvm *kvm);
	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
					   struct kvm_memory_slot *slot,
					   gfn_t offset, unsigned long mask);
	int (*write_log_dirty)(struct kvm_vcpu *vcpu);

	/* pmu operations of sub-arch */
	const struct kvm_pmu_ops *pmu_ops;

	/*
	 * Architecture specific hooks for vCPU blocking due to
	 * HLT instruction.
	 * Returns for .pre_block():
	 *    - 0 means continue to block the vCPU.
	 *    - 1 means we cannot block the vCPU since some event
	 *        happens during this period, such as, 'ON' bit in
	 *        posted-interrupts descriptor is set.
	 */
	int (*pre_block)(struct kvm_vcpu *vcpu);
	void (*post_block)(struct kvm_vcpu *vcpu);

	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
	void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);

	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
			      uint32_t guest_irq, bool set);
	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);

	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);

	void (*setup_mce)(struct kvm_vcpu *vcpu);

	int (*smi_allowed)(struct kvm_vcpu *vcpu);
	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
	int (*enable_smi_window)(struct kvm_vcpu *vcpu);

	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);

	int (*get_msr_feature)(struct kvm_msr_entry *entry);
};

struct kvm_arch_async_pf {
	u32 token;
	gfn_t gfn;
	unsigned long cr3;
	bool direct_map;
};

extern struct kvm_x86_ops *kvm_x86_ops;

#define __KVM_HAVE_ARCH_VM_ALLOC
static inline struct kvm *kvm_arch_alloc_vm(void)
{
	return kvm_x86_ops->vm_alloc();
}

static inline void kvm_arch_free_vm(struct kvm *kvm)
{
	return kvm_x86_ops->vm_free(kvm);
}

int kvm_mmu_module_init(void);
void kvm_mmu_module_exit(void);

void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
void kvm_mmu_setup(struct kvm_vcpu *vcpu);
void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
		u64 acc_track_mask, u64 me_mask);

void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
				      struct kvm_memory_slot *memslot);
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
				   const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
				   struct kvm_memory_slot *memslot);
void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
					struct kvm_memory_slot *memslot);
void kvm_mmu_slot_set_dirty(struct kvm *kvm,
			    struct kvm_memory_slot *memslot);
void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
				   struct kvm_memory_slot *slot,
				   gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots);
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);

int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);

int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
			  const void *val, int bytes);

struct kvm_irq_mask_notifier {
	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
	int irq;
	struct hlist_node link;
};

void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
				    struct kvm_irq_mask_notifier *kimn);
void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
				      struct kvm_irq_mask_notifier *kimn);
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
			     bool mask);

extern bool tdp_enabled;

u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);

/* control of guest tsc rate supported? */
extern bool kvm_has_tsc_control;
/* maximum supported tsc_khz for guests */
extern u32  kvm_max_guest_tsc_khz;
/* number of bits of the fractional part of the TSC scaling ratio */
extern u8   kvm_tsc_scaling_ratio_frac_bits;
/* maximum allowed value of TSC scaling ratio */
extern u64  kvm_max_tsc_scaling_ratio;
/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
extern u64  kvm_default_tsc_scaling_ratio;

extern u64 kvm_mce_cap_supported;

enum emulation_result {
	EMULATE_DONE,         /* no further processing */
	EMULATE_USER_EXIT,    /* kvm_run ready for userspace exit */
	EMULATE_FAIL,         /* can't emulate this instruction */
};

#define EMULTYPE_NO_DECODE	    (1 << 0)
#define EMULTYPE_TRAP_UD	    (1 << 1)
#define EMULTYPE_SKIP		    (1 << 2)
#define EMULTYPE_RETRY		    (1 << 3)
#define EMULTYPE_NO_REEXECUTE	    (1 << 4)
#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 5)
#define EMULTYPE_VMWARE		    (1 << 6)
int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
			    int emulation_type, void *insn, int insn_len);

static inline int emulate_instruction(struct kvm_vcpu *vcpu,
			int emulation_type)
{
	return x86_emulate_instruction(vcpu, 0,
			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
}

void kvm_enable_efer_bits(u64);
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);

struct x86_emulate_ctxt;

int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in);
int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);

void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);

int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
		    int reason, bool has_error_code, u32 error_code);

int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);

int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);

unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
bool kvm_rdpmc(struct kvm_vcpu *vcpu);

void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
			    gfn_t gfn, void *data, int offset, int len,
			    u32 access);
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr);

static inline int __kvm_irq_line_state(unsigned long *irq_state,
				       int irq_source_id, int level)
{
	/* Logical OR for level trig interrupt */
	if (level)
		__set_bit(irq_source_id, irq_state);
	else
		__clear_bit(irq_source_id, irq_state);

	return !!(*irq_state);
}

int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);

void kvm_inject_nmi(struct kvm_vcpu *vcpu);

int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
			   struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
			      struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
			       struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
			       struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
				struct x86_exception *exception);

void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);

int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);

int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
		       void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu);

void kvm_enable_tdp(void);
void kvm_disable_tdp(void);

static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
				  struct x86_exception *exception)
{
	return gpa;
}

static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
{
	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);

	return (struct kvm_mmu_page *)page_private(page);
}

static inline u16 kvm_read_ldt(void)
{
	u16 ldt;
	asm("sldt %0" : "=g"(ldt));
	return ldt;
}

static inline void kvm_load_ldt(u16 sel)
{
	asm("lldt %0" : : "rm"(sel));
}

#ifdef CONFIG_X86_64
static inline unsigned long read_msr(unsigned long msr)
{
	u64 value;

	rdmsrl(msr, value);
	return value;
}
#endif

static inline u32 get_rdx_init_val(void)
{
	return 0x600; /* P6 family */
}

static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
{
	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}

#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
#define TSS_REDIRECTION_SIZE (256 / 8)
#define RMODE_TSS_SIZE							\
	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)

enum {
	TASK_SWITCH_CALL = 0,
	TASK_SWITCH_IRET = 1,
	TASK_SWITCH_JMP = 2,
	TASK_SWITCH_GATE = 3,
};

#define HF_GIF_MASK		(1 << 0)
#define HF_HIF_MASK		(1 << 1)
#define HF_VINTR_MASK		(1 << 2)
#define HF_NMI_MASK		(1 << 3)
#define HF_IRET_MASK		(1 << 4)
#define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
#define HF_SMM_MASK		(1 << 6)
#define HF_SMM_INSIDE_NMI_MASK	(1 << 7)

#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
#define KVM_ADDRESS_SPACE_NUM 2

#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)

/*
 * Hardware virtualization extension instructions may fault if a
 * reboot turns off virtualization while processes are running.
 * Trap the fault and ignore the instruction if that happens.
 */
asmlinkage void kvm_spurious_fault(void);

#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn)	\
	"666: " insn "\n\t" \
	"668: \n\t"                           \
	".pushsection .fixup, \"ax\" \n" \
	"667: \n\t" \
	cleanup_insn "\n\t"		      \
	"cmpb $0, kvm_rebooting \n\t"	      \
	"jne 668b \n\t"      		      \
	__ASM_SIZE(push) " $666b \n\t"	      \
	"call kvm_spurious_fault \n\t"	      \
	".popsection \n\t" \
	_ASM_EXTABLE(666b, 667b)

#define __kvm_handle_fault_on_reboot(insn)		\
	____kvm_handle_fault_on_reboot(insn, "")

#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);

void kvm_define_shared_msr(unsigned index, u32 msr);
int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);

u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc);
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);

unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);

void kvm_make_mclock_inprogress_request(struct kvm *kvm);
void kvm_make_scan_ioapic_request(struct kvm *kvm);

void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
				     struct kvm_async_pf *work);
void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
				 struct kvm_async_pf *work);
void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
			       struct kvm_async_pf *work);
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);

int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);

int kvm_is_in_guest(void);

int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);

bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
			     struct kvm_vcpu **dest_vcpu);

void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
		     struct kvm_lapic_irq *irq);

static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
	if (kvm_x86_ops->vcpu_blocking)
		kvm_x86_ops->vcpu_blocking(vcpu);
}

static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{
	if (kvm_x86_ops->vcpu_unblocking)
		kvm_x86_ops->vcpu_unblocking(vcpu);
}

static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}

static inline int kvm_cpu_get_apicid(int mps_cpu)
{
#ifdef CONFIG_X86_LOCAL_APIC
	return default_cpu_present_to_apicid(mps_cpu);
#else
	WARN_ON_ONCE(1);
	return BAD_APICID;
#endif
}

#define put_smstate(type, buf, offset, val)                      \
	*(type *)((buf) + (offset) - 0x7e00) = val

#endif /* _ASM_X86_KVM_HOST_H */