summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/svm/nested.c
blob: 61738ff8ef33b6c85eac131273e83c4415910961 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * AMD SVM support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 */

#define pr_fmt(fmt) "SVM: " fmt

#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <linux/kernel.h>

#include <asm/msr-index.h>
#include <asm/debugreg.h>

#include "kvm_emulate.h"
#include "trace.h"
#include "mmu.h"
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
#include "svm.h"

#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK

static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
				       struct x86_exception *fault)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) {
		/*
		 * TODO: track the cause of the nested page fault, and
		 * correctly fill in the high bits of exit_info_1.
		 */
		svm->vmcb->control.exit_code = SVM_EXIT_NPF;
		svm->vmcb->control.exit_code_hi = 0;
		svm->vmcb->control.exit_info_1 = (1ULL << 32);
		svm->vmcb->control.exit_info_2 = fault->address;
	}

	svm->vmcb->control.exit_info_1 &= ~0xffffffffULL;
	svm->vmcb->control.exit_info_1 |= fault->error_code;

	nested_svm_vmexit(svm);
}

static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
       struct vcpu_svm *svm = to_svm(vcpu);
       WARN_ON(!is_guest_mode(vcpu));

       if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
	   !svm->nested.nested_run_pending) {
               svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR;
               svm->vmcb->control.exit_code_hi = 0;
               svm->vmcb->control.exit_info_1 = fault->error_code;
               svm->vmcb->control.exit_info_2 = fault->address;
               nested_svm_vmexit(svm);
       } else {
               kvm_inject_page_fault(vcpu, fault);
       }
}

static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	u64 cr3 = svm->nested.ctl.nested_cr3;
	u64 pdpte;
	int ret;

	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
				       offset_in_page(cr3) + index * 8, 8);
	if (ret)
		return 0;
	return pdpte;
}

static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	return svm->nested.ctl.nested_cr3;
}

static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	WARN_ON(mmu_is_nested(vcpu));

	vcpu->arch.mmu = &vcpu->arch.guest_mmu;

	/*
	 * The NPT format depends on L1's CR4 and EFER, which is in vmcb01.  Note,
	 * when called via KVM_SET_NESTED_STATE, that state may _not_ match current
	 * vCPU state.  CR0.WP is explicitly ignored, while CR0.PG is required.
	 */
	kvm_init_shadow_npt_mmu(vcpu, X86_CR0_PG, svm->vmcb01.ptr->save.cr4,
				svm->vmcb01.ptr->save.efer,
				svm->nested.ctl.nested_cr3);
	vcpu->arch.mmu->get_guest_pgd     = nested_svm_get_tdp_cr3;
	vcpu->arch.mmu->get_pdptr         = nested_svm_get_tdp_pdptr;
	vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
}

static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
	vcpu->arch.mmu = &vcpu->arch.root_mmu;
	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}

void recalc_intercepts(struct vcpu_svm *svm)
{
	struct vmcb_control_area *c, *h, *g;
	unsigned int i;

	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);

	if (!is_guest_mode(&svm->vcpu))
		return;

	c = &svm->vmcb->control;
	h = &svm->vmcb01.ptr->control;
	g = &svm->nested.ctl;

	for (i = 0; i < MAX_INTERCEPT; i++)
		c->intercepts[i] = h->intercepts[i];

	if (g->int_ctl & V_INTR_MASKING_MASK) {
		/* We only want the cr8 intercept bits of L1 */
		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);

		/*
		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
		 * affect any interrupt we may want to inject; therefore,
		 * interrupt window vmexits are irrelevant to L0.
		 */
		vmcb_clr_intercept(c, INTERCEPT_VINTR);
	}

	/* We don't want to see VMMCALLs from a nested guest */
	vmcb_clr_intercept(c, INTERCEPT_VMMCALL);

	for (i = 0; i < MAX_INTERCEPT; i++)
		c->intercepts[i] |= g->intercepts[i];

	/* If SMI is not intercepted, ignore guest SMI intercept as well  */
	if (!intercept_smi)
		vmcb_clr_intercept(c, INTERCEPT_SMI);
}

static void copy_vmcb_control_area(struct vmcb_control_area *dst,
				   struct vmcb_control_area *from)
{
	unsigned int i;

	for (i = 0; i < MAX_INTERCEPT; i++)
		dst->intercepts[i] = from->intercepts[i];

	dst->iopm_base_pa         = from->iopm_base_pa;
	dst->msrpm_base_pa        = from->msrpm_base_pa;
	dst->tsc_offset           = from->tsc_offset;
	/* asid not copied, it is handled manually for svm->vmcb.  */
	dst->tlb_ctl              = from->tlb_ctl;
	dst->int_ctl              = from->int_ctl;
	dst->int_vector           = from->int_vector;
	dst->int_state            = from->int_state;
	dst->exit_code            = from->exit_code;
	dst->exit_code_hi         = from->exit_code_hi;
	dst->exit_info_1          = from->exit_info_1;
	dst->exit_info_2          = from->exit_info_2;
	dst->exit_int_info        = from->exit_int_info;
	dst->exit_int_info_err    = from->exit_int_info_err;
	dst->nested_ctl           = from->nested_ctl;
	dst->event_inj            = from->event_inj;
	dst->event_inj_err        = from->event_inj_err;
	dst->nested_cr3           = from->nested_cr3;
	dst->virt_ext              = from->virt_ext;
	dst->pause_filter_count   = from->pause_filter_count;
	dst->pause_filter_thresh  = from->pause_filter_thresh;
}

static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
	/*
	 * This function merges the msr permission bitmaps of kvm and the
	 * nested vmcb. It is optimized in that it only merges the parts where
	 * the kvm msr permission bitmap may contain zero bits
	 */
	int i;

	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
		return true;

	for (i = 0; i < MSRPM_OFFSETS; i++) {
		u32 value, p;
		u64 offset;

		if (msrpm_offsets[i] == 0xffffffff)
			break;

		p      = msrpm_offsets[i];
		offset = svm->nested.ctl.msrpm_base_pa + (p * 4);

		if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
			return false;

		svm->nested.msrpm[p] = svm->msrpm[p] | value;
	}

	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));

	return true;
}

/*
 * Bits 11:0 of bitmap address are ignored by hardware
 */
static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size)
{
	u64 addr = PAGE_ALIGN(pa);

	return kvm_vcpu_is_legal_gpa(vcpu, addr) &&
	    kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1);
}

static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
				       struct vmcb_control_area *control)
{
	if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN)))
		return false;

	if (CC(control->asid == 0))
		return false;

	if (CC((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && !npt_enabled))
		return false;

	if (CC(!nested_svm_check_bitmap_pa(vcpu, control->msrpm_base_pa,
					   MSRPM_SIZE)))
		return false;
	if (CC(!nested_svm_check_bitmap_pa(vcpu, control->iopm_base_pa,
					   IOPM_SIZE)))
		return false;

	return true;
}

static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu,
				      struct vmcb_save_area *save)
{
	/*
	 * These checks are also performed by KVM_SET_SREGS,
	 * except that EFER.LMA is not checked by SVM against
	 * CR0.PG && EFER.LME.
	 */
	if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) {
		if (CC(!(save->cr4 & X86_CR4_PAE)) ||
		    CC(!(save->cr0 & X86_CR0_PE)) ||
		    CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3)))
			return false;
	}

	if (CC(!kvm_is_valid_cr4(vcpu, save->cr4)))
		return false;

	return true;
}

/* Common checks that apply to both L1 and L2 state.  */
static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu,
				    struct vmcb_save_area *save)
{
	/*
	 * FIXME: these should be done after copying the fields,
	 * to avoid TOC/TOU races.  For these save area checks
	 * the possible damage is limited since kvm_set_cr0 and
	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
	 * so it is force-set later in nested_prepare_vmcb_save.
	 */
	if (CC(!(save->efer & EFER_SVME)))
		return false;

	if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) ||
	    CC(save->cr0 & ~0xffffffffULL))
		return false;

	if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7)))
		return false;

	if (!nested_vmcb_check_cr3_cr4(vcpu, save))
		return false;

	if (CC(!kvm_valid_efer(vcpu, save->efer)))
		return false;

	return true;
}

void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
				     struct vmcb_control_area *control)
{
	copy_vmcb_control_area(&svm->nested.ctl, control);

	/* Copy it here because nested_svm_check_controls will check it.  */
	svm->nested.ctl.asid           = control->asid;
	svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL;
	svm->nested.ctl.iopm_base_pa  &= ~0x0fffULL;
}

/*
 * Synchronize fields that are written by the processor, so that
 * they can be copied back into the vmcb12.
 */
void nested_sync_control_from_vmcb02(struct vcpu_svm *svm)
{
	u32 mask;
	svm->nested.ctl.event_inj      = svm->vmcb->control.event_inj;
	svm->nested.ctl.event_inj_err  = svm->vmcb->control.event_inj_err;

	/* Only a few fields of int_ctl are written by the processor.  */
	mask = V_IRQ_MASK | V_TPR_MASK;
	if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) &&
	    svm_is_intercept(svm, INTERCEPT_VINTR)) {
		/*
		 * In order to request an interrupt window, L0 is usurping
		 * svm->vmcb->control.int_ctl and possibly setting V_IRQ
		 * even if it was clear in L1's VMCB.  Restoring it would be
		 * wrong.  However, in this case V_IRQ will remain true until
		 * interrupt_window_interception calls svm_clear_vintr and
		 * restores int_ctl.  We can just leave it aside.
		 */
		mask &= ~V_IRQ_MASK;
	}
	svm->nested.ctl.int_ctl        &= ~mask;
	svm->nested.ctl.int_ctl        |= svm->vmcb->control.int_ctl & mask;
}

/*
 * Transfer any event that L0 or L1 wanted to inject into L2 to
 * EXIT_INT_INFO.
 */
static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
						struct vmcb *vmcb12)
{
	struct kvm_vcpu *vcpu = &svm->vcpu;
	u32 exit_int_info = 0;
	unsigned int nr;

	if (vcpu->arch.exception.injected) {
		nr = vcpu->arch.exception.nr;
		exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT;

		if (vcpu->arch.exception.has_error_code) {
			exit_int_info |= SVM_EVTINJ_VALID_ERR;
			vmcb12->control.exit_int_info_err =
				vcpu->arch.exception.error_code;
		}

	} else if (vcpu->arch.nmi_injected) {
		exit_int_info = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;

	} else if (vcpu->arch.interrupt.injected) {
		nr = vcpu->arch.interrupt.nr;
		exit_int_info = nr | SVM_EVTINJ_VALID;

		if (vcpu->arch.interrupt.soft)
			exit_int_info |= SVM_EVTINJ_TYPE_SOFT;
		else
			exit_int_info |= SVM_EVTINJ_TYPE_INTR;
	}

	vmcb12->control.exit_int_info = exit_int_info;
}

static inline bool nested_npt_enabled(struct vcpu_svm *svm)
{
	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
}

static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
{
	/*
	 * TODO: optimize unconditional TLB flush/MMU sync.  A partial list of
	 * things to fix before this can be conditional:
	 *
	 *  - Flush TLBs for both L1 and L2 remote TLB flush
	 *  - Honor L1's request to flush an ASID on nested VMRUN
	 *  - Sync nested NPT MMU on VMRUN that flushes L2's ASID[*]
	 *  - Don't crush a pending TLB flush in vmcb02 on nested VMRUN
	 *  - Flush L1's ASID on KVM_REQ_TLB_FLUSH_GUEST
	 *
	 * [*] Unlike nested EPT, SVM's ASID management can invalidate nested
	 *     NPT guest-physical mappings on VMRUN.
	 */
	kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
	kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}

/*
 * Load guest's/host's cr3 on nested vmentry or vmexit. @nested_npt is true
 * if we are emulating VM-Entry into a guest with NPT enabled.
 */
static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
			       bool nested_npt, bool reload_pdptrs)
{
	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3)))
		return -EINVAL;

	if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) &&
	    CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)))
		return -EINVAL;

	if (!nested_npt)
		kvm_mmu_new_pgd(vcpu, cr3);

	vcpu->arch.cr3 = cr3;
	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);

	/* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */
	kvm_init_mmu(vcpu);

	return 0;
}

void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm)
{
	if (!svm->nested.vmcb02.ptr)
		return;

	/* FIXME: merge g_pat from vmcb01 and vmcb12.  */
	svm->nested.vmcb02.ptr->save.g_pat = svm->vmcb01.ptr->save.g_pat;
}

static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
{
	bool new_vmcb12 = false;

	nested_vmcb02_compute_g_pat(svm);

	/* Load the nested guest state */
	if (svm->nested.vmcb12_gpa != svm->nested.last_vmcb12_gpa) {
		new_vmcb12 = true;
		svm->nested.last_vmcb12_gpa = svm->nested.vmcb12_gpa;
	}

	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_SEG))) {
		svm->vmcb->save.es = vmcb12->save.es;
		svm->vmcb->save.cs = vmcb12->save.cs;
		svm->vmcb->save.ss = vmcb12->save.ss;
		svm->vmcb->save.ds = vmcb12->save.ds;
		svm->vmcb->save.cpl = vmcb12->save.cpl;
		vmcb_mark_dirty(svm->vmcb, VMCB_SEG);
	}

	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DT))) {
		svm->vmcb->save.gdtr = vmcb12->save.gdtr;
		svm->vmcb->save.idtr = vmcb12->save.idtr;
		vmcb_mark_dirty(svm->vmcb, VMCB_DT);
	}

	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);

	/*
	 * Force-set EFER_SVME even though it is checked earlier on the
	 * VMCB12, because the guest can flip the bit between the check
	 * and now.  Clearing EFER_SVME would call svm_free_nested.
	 */
	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);

	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);

	svm->vcpu.arch.cr2 = vmcb12->save.cr2;

	kvm_rax_write(&svm->vcpu, vmcb12->save.rax);
	kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp);
	kvm_rip_write(&svm->vcpu, vmcb12->save.rip);

	/* In case we don't even reach vcpu_run, the fields are not updated */
	svm->vmcb->save.rax = vmcb12->save.rax;
	svm->vmcb->save.rsp = vmcb12->save.rsp;
	svm->vmcb->save.rip = vmcb12->save.rip;

	/* These bits will be set properly on the first execution when new_vmc12 is true */
	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) {
		svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
		svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_ACTIVE_LOW;
		vmcb_mark_dirty(svm->vmcb, VMCB_DR);
	}
}

static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
{
	const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
	struct kvm_vcpu *vcpu = &svm->vcpu;

	/*
	 * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
	 * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes.
	 */

	/*
	 * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
	 * avic_physical_id.
	 */
	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));

	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
	svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
	svm->vmcb->control.iopm_base_pa = svm->vmcb01.ptr->control.iopm_base_pa;
	svm->vmcb->control.msrpm_base_pa = svm->vmcb01.ptr->control.msrpm_base_pa;

	/* Done at vmrun: asid.  */

	/* Also overwritten later if necessary.  */
	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;

	/* nested_cr3.  */
	if (nested_npt_enabled(svm))
		nested_svm_init_mmu_context(vcpu);

	svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset =
		vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;

	svm->vmcb->control.int_ctl             =
		(svm->nested.ctl.int_ctl & ~mask) |
		(svm->vmcb01.ptr->control.int_ctl & mask);

	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;
	svm->vmcb->control.int_state           = svm->nested.ctl.int_state;
	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
	svm->vmcb->control.event_inj_err       = svm->nested.ctl.event_inj_err;

	svm->vmcb->control.pause_filter_count  = svm->nested.ctl.pause_filter_count;
	svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh;

	nested_svm_transition_tlb_flush(vcpu);

	/* Enter Guest-Mode */
	enter_guest_mode(vcpu);

	/*
	 * Merge guest and host intercepts - must be called with vcpu in
	 * guest-mode to take effect.
	 */
	recalc_intercepts(svm);
}

static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
{
	/*
	 * Some VMCB state is shared between L1 and L2 and thus has to be
	 * moved at the time of nested vmrun and vmexit.
	 *
	 * VMLOAD/VMSAVE state would also belong in this category, but KVM
	 * always performs VMLOAD and VMSAVE from the VMCB01.
	 */
	to_vmcb->save.spec_ctrl = from_vmcb->save.spec_ctrl;
}

int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
			 struct vmcb *vmcb12)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	int ret;

	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa,
			       vmcb12->save.rip,
			       vmcb12->control.int_ctl,
			       vmcb12->control.event_inj,
			       vmcb12->control.nested_ctl);

	trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff,
				    vmcb12->control.intercepts[INTERCEPT_CR] >> 16,
				    vmcb12->control.intercepts[INTERCEPT_EXCEPTION],
				    vmcb12->control.intercepts[INTERCEPT_WORD3],
				    vmcb12->control.intercepts[INTERCEPT_WORD4],
				    vmcb12->control.intercepts[INTERCEPT_WORD5]);


	svm->nested.vmcb12_gpa = vmcb12_gpa;

	WARN_ON(svm->vmcb == svm->nested.vmcb02.ptr);

	nested_svm_copy_common_state(svm->vmcb01.ptr, svm->nested.vmcb02.ptr);

	svm_switch_vmcb(svm, &svm->nested.vmcb02);
	nested_vmcb02_prepare_control(svm);
	nested_vmcb02_prepare_save(svm, vmcb12);

	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
				  nested_npt_enabled(svm), true);
	if (ret)
		return ret;

	if (!npt_enabled)
		vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;

	svm_set_gif(svm, true);

	return 0;
}

int nested_svm_vmrun(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	int ret;
	struct vmcb *vmcb12;
	struct kvm_host_map map;
	u64 vmcb12_gpa;

	if (!svm->nested.hsave_msr) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	if (is_smm(vcpu)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	vmcb12_gpa = svm->vmcb->save.rax;
	ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map);
	if (ret == -EINVAL) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	} else if (ret) {
		return kvm_skip_emulated_instruction(vcpu);
	}

	ret = kvm_skip_emulated_instruction(vcpu);

	vmcb12 = map.hva;

	if (WARN_ON_ONCE(!svm->nested.initialized))
		return -EINVAL;

	nested_load_control_from_vmcb12(svm, &vmcb12->control);

	if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) ||
	    !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) {
		vmcb12->control.exit_code    = SVM_EXIT_ERR;
		vmcb12->control.exit_code_hi = 0;
		vmcb12->control.exit_info_1  = 0;
		vmcb12->control.exit_info_2  = 0;
		goto out;
	}


	/* Clear internal status */
	kvm_clear_exception_queue(vcpu);
	kvm_clear_interrupt_queue(vcpu);

	/*
	 * Since vmcb01 is not in use, we can use it to store some of the L1
	 * state.
	 */
	svm->vmcb01.ptr->save.efer   = vcpu->arch.efer;
	svm->vmcb01.ptr->save.cr0    = kvm_read_cr0(vcpu);
	svm->vmcb01.ptr->save.cr4    = vcpu->arch.cr4;
	svm->vmcb01.ptr->save.rflags = kvm_get_rflags(vcpu);
	svm->vmcb01.ptr->save.rip    = kvm_rip_read(vcpu);

	if (!npt_enabled)
		svm->vmcb01.ptr->save.cr3 = kvm_read_cr3(vcpu);

	svm->nested.nested_run_pending = 1;

	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12))
		goto out_exit_err;

	if (nested_svm_vmrun_msrpm(svm))
		goto out;

out_exit_err:
	svm->nested.nested_run_pending = 0;

	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
	svm->vmcb->control.exit_code_hi = 0;
	svm->vmcb->control.exit_info_1  = 0;
	svm->vmcb->control.exit_info_2  = 0;

	nested_svm_vmexit(svm);

out:
	kvm_vcpu_unmap(vcpu, &map, true);

	return ret;
}

/* Copy state save area fields which are handled by VMRUN */
void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
			  struct vmcb_save_area *from_save)
{
	to_save->es = from_save->es;
	to_save->cs = from_save->cs;
	to_save->ss = from_save->ss;
	to_save->ds = from_save->ds;
	to_save->gdtr = from_save->gdtr;
	to_save->idtr = from_save->idtr;
	to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED;
	to_save->efer = from_save->efer;
	to_save->cr0 = from_save->cr0;
	to_save->cr3 = from_save->cr3;
	to_save->cr4 = from_save->cr4;
	to_save->rax = from_save->rax;
	to_save->rsp = from_save->rsp;
	to_save->rip = from_save->rip;
	to_save->cpl = 0;
}

void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
{
	to_vmcb->save.fs = from_vmcb->save.fs;
	to_vmcb->save.gs = from_vmcb->save.gs;
	to_vmcb->save.tr = from_vmcb->save.tr;
	to_vmcb->save.ldtr = from_vmcb->save.ldtr;
	to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base;
	to_vmcb->save.star = from_vmcb->save.star;
	to_vmcb->save.lstar = from_vmcb->save.lstar;
	to_vmcb->save.cstar = from_vmcb->save.cstar;
	to_vmcb->save.sfmask = from_vmcb->save.sfmask;
	to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
	to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
}

int nested_svm_vmexit(struct vcpu_svm *svm)
{
	struct kvm_vcpu *vcpu = &svm->vcpu;
	struct vmcb *vmcb12;
	struct vmcb *vmcb = svm->vmcb;
	struct kvm_host_map map;
	int rc;

	/* Triple faults in L2 should never escape. */
	WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu));

	rc = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map);
	if (rc) {
		if (rc == -EINVAL)
			kvm_inject_gp(vcpu, 0);
		return 1;
	}

	vmcb12 = map.hva;

	/* Exit Guest-Mode */
	leave_guest_mode(vcpu);
	svm->nested.vmcb12_gpa = 0;
	WARN_ON_ONCE(svm->nested.nested_run_pending);

	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);

	/* in case we halted in L2 */
	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;

	/* Give the current vmcb to the guest */

	vmcb12->save.es     = vmcb->save.es;
	vmcb12->save.cs     = vmcb->save.cs;
	vmcb12->save.ss     = vmcb->save.ss;
	vmcb12->save.ds     = vmcb->save.ds;
	vmcb12->save.gdtr   = vmcb->save.gdtr;
	vmcb12->save.idtr   = vmcb->save.idtr;
	vmcb12->save.efer   = svm->vcpu.arch.efer;
	vmcb12->save.cr0    = kvm_read_cr0(vcpu);
	vmcb12->save.cr3    = kvm_read_cr3(vcpu);
	vmcb12->save.cr2    = vmcb->save.cr2;
	vmcb12->save.cr4    = svm->vcpu.arch.cr4;
	vmcb12->save.rflags = kvm_get_rflags(vcpu);
	vmcb12->save.rip    = kvm_rip_read(vcpu);
	vmcb12->save.rsp    = kvm_rsp_read(vcpu);
	vmcb12->save.rax    = kvm_rax_read(vcpu);
	vmcb12->save.dr7    = vmcb->save.dr7;
	vmcb12->save.dr6    = svm->vcpu.arch.dr6;
	vmcb12->save.cpl    = vmcb->save.cpl;

	vmcb12->control.int_state         = vmcb->control.int_state;
	vmcb12->control.exit_code         = vmcb->control.exit_code;
	vmcb12->control.exit_code_hi      = vmcb->control.exit_code_hi;
	vmcb12->control.exit_info_1       = vmcb->control.exit_info_1;
	vmcb12->control.exit_info_2       = vmcb->control.exit_info_2;

	if (vmcb12->control.exit_code != SVM_EXIT_ERR)
		nested_save_pending_event_to_vmcb12(svm, vmcb12);

	if (svm->nrips_enabled)
		vmcb12->control.next_rip  = vmcb->control.next_rip;

	vmcb12->control.int_ctl           = svm->nested.ctl.int_ctl;
	vmcb12->control.tlb_ctl           = svm->nested.ctl.tlb_ctl;
	vmcb12->control.event_inj         = svm->nested.ctl.event_inj;
	vmcb12->control.event_inj_err     = svm->nested.ctl.event_inj_err;

	vmcb12->control.pause_filter_count =
		svm->vmcb->control.pause_filter_count;
	vmcb12->control.pause_filter_thresh =
		svm->vmcb->control.pause_filter_thresh;

	nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);

	svm_switch_vmcb(svm, &svm->vmcb01);

	/*
	 * On vmexit the  GIF is set to false and
	 * no event can be injected in L1.
	 */
	svm_set_gif(svm, false);
	svm->vmcb->control.exit_int_info = 0;

	svm->vcpu.arch.tsc_offset = svm->vcpu.arch.l1_tsc_offset;
	if (svm->vmcb->control.tsc_offset != svm->vcpu.arch.tsc_offset) {
		svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
		vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
	}

	svm->nested.ctl.nested_cr3 = 0;

	/*
	 * Restore processor state that had been saved in vmcb01
	 */
	kvm_set_rflags(vcpu, svm->vmcb->save.rflags);
	svm_set_efer(vcpu, svm->vmcb->save.efer);
	svm_set_cr0(vcpu, svm->vmcb->save.cr0 | X86_CR0_PE);
	svm_set_cr4(vcpu, svm->vmcb->save.cr4);
	kvm_rax_write(vcpu, svm->vmcb->save.rax);
	kvm_rsp_write(vcpu, svm->vmcb->save.rsp);
	kvm_rip_write(vcpu, svm->vmcb->save.rip);

	svm->vcpu.arch.dr7 = DR7_FIXED_1;
	kvm_update_dr7(&svm->vcpu);

	trace_kvm_nested_vmexit_inject(vmcb12->control.exit_code,
				       vmcb12->control.exit_info_1,
				       vmcb12->control.exit_info_2,
				       vmcb12->control.exit_int_info,
				       vmcb12->control.exit_int_info_err,
				       KVM_ISA_SVM);

	kvm_vcpu_unmap(vcpu, &map, true);

	nested_svm_transition_tlb_flush(vcpu);

	nested_svm_uninit_mmu_context(vcpu);

	rc = nested_svm_load_cr3(vcpu, svm->vmcb->save.cr3, false, true);
	if (rc)
		return 1;

	/*
	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
	 * doesn't end up in L1.
	 */
	svm->vcpu.arch.nmi_injected = false;
	kvm_clear_exception_queue(vcpu);
	kvm_clear_interrupt_queue(vcpu);

	/*
	 * If we are here following the completion of a VMRUN that
	 * is being single-stepped, queue the pending #DB intercept
	 * right now so that it an be accounted for before we execute
	 * L1's next instruction.
	 */
	if (unlikely(svm->vmcb->save.rflags & X86_EFLAGS_TF))
		kvm_queue_exception(&(svm->vcpu), DB_VECTOR);

	return 0;
}

static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
{
	nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN);
}

int svm_allocate_nested(struct vcpu_svm *svm)
{
	struct page *vmcb02_page;

	if (svm->nested.initialized)
		return 0;

	vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
	if (!vmcb02_page)
		return -ENOMEM;
	svm->nested.vmcb02.ptr = page_address(vmcb02_page);
	svm->nested.vmcb02.pa = __sme_set(page_to_pfn(vmcb02_page) << PAGE_SHIFT);

	svm->nested.msrpm = svm_vcpu_alloc_msrpm();
	if (!svm->nested.msrpm)
		goto err_free_vmcb02;
	svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm);

	svm->nested.initialized = true;
	return 0;

err_free_vmcb02:
	__free_page(vmcb02_page);
	return -ENOMEM;
}

void svm_free_nested(struct vcpu_svm *svm)
{
	if (!svm->nested.initialized)
		return;

	svm_vcpu_free_msrpm(svm->nested.msrpm);
	svm->nested.msrpm = NULL;

	__free_page(virt_to_page(svm->nested.vmcb02.ptr));
	svm->nested.vmcb02.ptr = NULL;

	/*
	 * When last_vmcb12_gpa matches the current vmcb12 gpa,
	 * some vmcb12 fields are not loaded if they are marked clean
	 * in the vmcb12, since in this case they are up to date already.
	 *
	 * When the vmcb02 is freed, this optimization becomes invalid.
	 */
	svm->nested.last_vmcb12_gpa = INVALID_GPA;

	svm->nested.initialized = false;
}

/*
 * Forcibly leave nested mode in order to be able to reset the VCPU later on.
 */
void svm_leave_nested(struct vcpu_svm *svm)
{
	struct kvm_vcpu *vcpu = &svm->vcpu;

	if (is_guest_mode(vcpu)) {
		svm->nested.nested_run_pending = 0;
		svm->nested.vmcb12_gpa = INVALID_GPA;

		leave_guest_mode(vcpu);

		svm_switch_vmcb(svm, &svm->vmcb01);

		nested_svm_uninit_mmu_context(vcpu);
		vmcb_mark_all_dirty(svm->vmcb);
	}

	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
}

static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
{
	u32 offset, msr, value;
	int write, mask;

	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
		return NESTED_EXIT_HOST;

	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
	offset = svm_msrpm_offset(msr);
	write  = svm->vmcb->control.exit_info_1 & 1;
	mask   = 1 << ((2 * (msr & 0xf)) + write);

	if (offset == MSR_INVALID)
		return NESTED_EXIT_DONE;

	/* Offset is in 32 bit units but need in 8 bit units */
	offset *= 4;

	if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4))
		return NESTED_EXIT_DONE;

	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}

static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
{
	unsigned port, size, iopm_len;
	u16 val, mask;
	u8 start_bit;
	u64 gpa;

	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT)))
		return NESTED_EXIT_HOST;

	port = svm->vmcb->control.exit_info_1 >> 16;
	size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >>
		SVM_IOIO_SIZE_SHIFT;
	gpa  = svm->nested.ctl.iopm_base_pa + (port / 8);
	start_bit = port % 8;
	iopm_len = (start_bit + size > 8) ? 2 : 1;
	mask = (0xf >> (4 - size)) << start_bit;
	val = 0;

	if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len))
		return NESTED_EXIT_DONE;

	return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}

static int nested_svm_intercept(struct vcpu_svm *svm)
{
	u32 exit_code = svm->vmcb->control.exit_code;
	int vmexit = NESTED_EXIT_HOST;

	switch (exit_code) {
	case SVM_EXIT_MSR:
		vmexit = nested_svm_exit_handled_msr(svm);
		break;
	case SVM_EXIT_IOIO:
		vmexit = nested_svm_intercept_ioio(svm);
		break;
	case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: {
		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
			vmexit = NESTED_EXIT_DONE;
		break;
	}
	case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: {
		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
			vmexit = NESTED_EXIT_DONE;
		break;
	}
	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
		/*
		 * Host-intercepted exceptions have been checked already in
		 * nested_svm_exit_special.  There is nothing to do here,
		 * the vmexit is injected by svm_check_nested_events.
		 */
		vmexit = NESTED_EXIT_DONE;
		break;
	}
	case SVM_EXIT_ERR: {
		vmexit = NESTED_EXIT_DONE;
		break;
	}
	default: {
		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
			vmexit = NESTED_EXIT_DONE;
	}
	}

	return vmexit;
}

int nested_svm_exit_handled(struct vcpu_svm *svm)
{
	int vmexit;

	vmexit = nested_svm_intercept(svm);

	if (vmexit == NESTED_EXIT_DONE)
		nested_svm_vmexit(svm);

	return vmexit;
}

int nested_svm_check_permissions(struct kvm_vcpu *vcpu)
{
	if (!(vcpu->arch.efer & EFER_SVME) || !is_paging(vcpu)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}

	if (to_svm(vcpu)->vmcb->save.cpl) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	return 0;
}

static bool nested_exit_on_exception(struct vcpu_svm *svm)
{
	unsigned int nr = svm->vcpu.arch.exception.nr;

	return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(nr));
}

static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm)
{
	unsigned int nr = svm->vcpu.arch.exception.nr;

	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
	svm->vmcb->control.exit_code_hi = 0;

	if (svm->vcpu.arch.exception.has_error_code)
		svm->vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code;

	/*
	 * EXITINFO2 is undefined for all exception intercepts other
	 * than #PF.
	 */
	if (nr == PF_VECTOR) {
		if (svm->vcpu.arch.exception.nested_apf)
			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
		else if (svm->vcpu.arch.exception.has_payload)
			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
		else
			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
	} else if (nr == DB_VECTOR) {
		/* See inject_pending_event.  */
		kvm_deliver_exception_payload(&svm->vcpu);
		if (svm->vcpu.arch.dr7 & DR7_GD) {
			svm->vcpu.arch.dr7 &= ~DR7_GD;
			kvm_update_dr7(&svm->vcpu);
		}
	} else
		WARN_ON(svm->vcpu.arch.exception.has_payload);

	nested_svm_vmexit(svm);
}

static inline bool nested_exit_on_init(struct vcpu_svm *svm)
{
	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT);
}

static int svm_check_nested_events(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	bool block_nested_events =
		kvm_event_needs_reinjection(vcpu) || svm->nested.nested_run_pending;
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (lapic_in_kernel(vcpu) &&
	    test_bit(KVM_APIC_INIT, &apic->pending_events)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_init(svm))
			return 0;
		nested_svm_simple_vmexit(svm, SVM_EXIT_INIT);
		return 0;
	}

	if (vcpu->arch.exception.pending) {
		/*
		 * Only a pending nested run can block a pending exception.
		 * Otherwise an injected NMI/interrupt should either be
		 * lost or delivered to the nested hypervisor in the EXITINTINFO
		 * vmcb field, while delivering the pending exception.
		 */
		if (svm->nested.nested_run_pending)
                        return -EBUSY;
		if (!nested_exit_on_exception(svm))
			return 0;
		nested_svm_inject_exception_vmexit(svm);
		return 0;
	}

	if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_smi(svm))
			return 0;
		nested_svm_simple_vmexit(svm, SVM_EXIT_SMI);
		return 0;
	}

	if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_nmi(svm))
			return 0;
		nested_svm_simple_vmexit(svm, SVM_EXIT_NMI);
		return 0;
	}

	if (kvm_cpu_has_interrupt(vcpu) && !svm_interrupt_blocked(vcpu)) {
		if (block_nested_events)
			return -EBUSY;
		if (!nested_exit_on_intr(svm))
			return 0;
		trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
		nested_svm_simple_vmexit(svm, SVM_EXIT_INTR);
		return 0;
	}

	return 0;
}

int nested_svm_exit_special(struct vcpu_svm *svm)
{
	u32 exit_code = svm->vmcb->control.exit_code;

	switch (exit_code) {
	case SVM_EXIT_INTR:
	case SVM_EXIT_NMI:
	case SVM_EXIT_NPF:
		return NESTED_EXIT_HOST;
	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);

		if (svm->vmcb01.ptr->control.intercepts[INTERCEPT_EXCEPTION] &
		    excp_bits)
			return NESTED_EXIT_HOST;
		else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR &&
			 svm->vcpu.arch.apf.host_apf_flags)
			/* Trap async PF even if not shadowing */
			return NESTED_EXIT_HOST;
		break;
	}
	default:
		break;
	}

	return NESTED_EXIT_CONTINUE;
}

static int svm_get_nested_state(struct kvm_vcpu *vcpu,
				struct kvm_nested_state __user *user_kvm_nested_state,
				u32 user_data_size)
{
	struct vcpu_svm *svm;
	struct kvm_nested_state kvm_state = {
		.flags = 0,
		.format = KVM_STATE_NESTED_FORMAT_SVM,
		.size = sizeof(kvm_state),
	};
	struct vmcb __user *user_vmcb = (struct vmcb __user *)
		&user_kvm_nested_state->data.svm[0];

	if (!vcpu)
		return kvm_state.size + KVM_STATE_NESTED_SVM_VMCB_SIZE;

	svm = to_svm(vcpu);

	if (user_data_size < kvm_state.size)
		goto out;

	/* First fill in the header and copy it out.  */
	if (is_guest_mode(vcpu)) {
		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb12_gpa;
		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;

		if (svm->nested.nested_run_pending)
			kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
	}

	if (gif_set(svm))
		kvm_state.flags |= KVM_STATE_NESTED_GIF_SET;

	if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
		return -EFAULT;

	if (!is_guest_mode(vcpu))
		goto out;

	/*
	 * Copy over the full size of the VMCB rather than just the size
	 * of the structs.
	 */
	if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE))
		return -EFAULT;
	if (copy_to_user(&user_vmcb->control, &svm->nested.ctl,
			 sizeof(user_vmcb->control)))
		return -EFAULT;
	if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save,
			 sizeof(user_vmcb->save)))
		return -EFAULT;
out:
	return kvm_state.size;
}

static int svm_set_nested_state(struct kvm_vcpu *vcpu,
				struct kvm_nested_state __user *user_kvm_nested_state,
				struct kvm_nested_state *kvm_state)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	struct vmcb __user *user_vmcb = (struct vmcb __user *)
		&user_kvm_nested_state->data.svm[0];
	struct vmcb_control_area *ctl;
	struct vmcb_save_area *save;
	unsigned long cr0;
	int ret;

	BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) >
		     KVM_STATE_NESTED_SVM_VMCB_SIZE);

	if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM)
		return -EINVAL;

	if (kvm_state->flags & ~(KVM_STATE_NESTED_GUEST_MODE |
				 KVM_STATE_NESTED_RUN_PENDING |
				 KVM_STATE_NESTED_GIF_SET))
		return -EINVAL;

	/*
	 * If in guest mode, vcpu->arch.efer actually refers to the L2 guest's
	 * EFER.SVME, but EFER.SVME still has to be 1 for VMRUN to succeed.
	 */
	if (!(vcpu->arch.efer & EFER_SVME)) {
		/* GIF=1 and no guest mode are required if SVME=0.  */
		if (kvm_state->flags != KVM_STATE_NESTED_GIF_SET)
			return -EINVAL;
	}

	/* SMM temporarily disables SVM, so we cannot be in guest mode.  */
	if (is_smm(vcpu) && (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
		return -EINVAL;

	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) {
		svm_leave_nested(svm);
		svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
		return 0;
	}

	if (!page_address_valid(vcpu, kvm_state->hdr.svm.vmcb_pa))
		return -EINVAL;
	if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE)
		return -EINVAL;

	ret  = -ENOMEM;
	ctl  = kzalloc(sizeof(*ctl),  GFP_KERNEL_ACCOUNT);
	save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT);
	if (!ctl || !save)
		goto out_free;

	ret = -EFAULT;
	if (copy_from_user(ctl, &user_vmcb->control, sizeof(*ctl)))
		goto out_free;
	if (copy_from_user(save, &user_vmcb->save, sizeof(*save)))
		goto out_free;

	ret = -EINVAL;
	if (!nested_vmcb_check_controls(vcpu, ctl))
		goto out_free;

	/*
	 * Processor state contains L2 state.  Check that it is
	 * valid for guest mode (see nested_vmcb_check_save).
	 */
	cr0 = kvm_read_cr0(vcpu);
        if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW))
		goto out_free;

	/*
	 * Validate host state saved from before VMRUN (see
	 * nested_svm_check_permissions).
	 */
	if (!(save->cr0 & X86_CR0_PG) ||
	    !(save->cr0 & X86_CR0_PE) ||
	    (save->rflags & X86_EFLAGS_VM) ||
	    !nested_vmcb_valid_sregs(vcpu, save))
		goto out_free;

	/*
	 * While the nested guest CR3 is already checked and set by
	 * KVM_SET_SREGS, it was set when nested state was yet loaded,
	 * thus MMU might not be initialized correctly.
	 * Set it again to fix this.
	 */

	ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3,
				  nested_npt_enabled(svm), false);
	if (WARN_ON_ONCE(ret))
		goto out_free;


	/*
	 * All checks done, we can enter guest mode. Userspace provides
	 * vmcb12.control, which will be combined with L1 and stored into
	 * vmcb02, and the L1 save state which we store in vmcb01.
	 * L2 registers if needed are moved from the current VMCB to VMCB02.
	 */

	if (is_guest_mode(vcpu))
		svm_leave_nested(svm);
	else
		svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save;

	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));

	svm->nested.nested_run_pending =
		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);

	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;

	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
	nested_load_control_from_vmcb12(svm, ctl);

	svm_switch_vmcb(svm, &svm->nested.vmcb02);
	nested_vmcb02_prepare_control(svm);
	kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
	ret = 0;
out_free:
	kfree(save);
	kfree(ctl);

	return ret;
}

static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	if (WARN_ON(!is_guest_mode(vcpu)))
		return true;

	if (!vcpu->arch.pdptrs_from_userspace &&
	    !nested_npt_enabled(svm) && is_pae_paging(vcpu))
		/*
		 * Reload the guest's PDPTRs since after a migration
		 * the guest CR3 might be restored prior to setting the nested
		 * state which can lead to a load of wrong PDPTRs.
		 */
		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3)))
			return false;

	if (!nested_svm_vmrun_msrpm(svm)) {
		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		vcpu->run->internal.suberror =
			KVM_INTERNAL_ERROR_EMULATION;
		vcpu->run->internal.ndata = 0;
		return false;
	}

	return true;
}

struct kvm_x86_nested_ops svm_nested_ops = {
	.check_events = svm_check_nested_events,
	.triple_fault = nested_svm_triple_fault,
	.get_nested_state_pages = svm_get_nested_state_pages,
	.get_state = svm_get_nested_state,
	.set_state = svm_set_nested_state,
};