summaryrefslogtreecommitdiffstats
path: root/arch/arm64/include/asm/kvm_host.h
blob: 36b8e97bf49ec4e742f58f1f8cccccf2ed015666 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2012,2013 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 *
 * Derived from arch/arm/include/asm/kvm_host.h:
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#ifndef __ARM64_KVM_HOST_H__
#define __ARM64_KVM_HOST_H__

#include <linux/arm-smccc.h>
#include <linux/bitmap.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <linux/kvm_types.h>
#include <linux/maple_tree.h>
#include <linux/percpu.h>
#include <linux/psci.h>
#include <asm/arch_gicv3.h>
#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/daifflags.h>
#include <asm/fpsimd.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
#include <asm/vncr_mapping.h>

#define __KVM_HAVE_ARCH_INTC_INITIALIZED

#define KVM_HALT_POLL_NS_DEFAULT 500000

#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
#include <kvm/arm_pmu.h>

#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS

#define KVM_VCPU_MAX_FEATURES 7
#define KVM_VCPU_VALID_FEATURES	(BIT(KVM_VCPU_MAX_FEATURES) - 1)

#define KVM_REQ_SLEEP \
	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
#define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
#define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
#define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)

#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
				     KVM_DIRTY_LOG_INITIALLY_SET)

#define KVM_HAVE_MMU_RWLOCK

/*
 * Mode of operation configurable with kvm-arm.mode early param.
 * See Documentation/admin-guide/kernel-parameters.txt for more information.
 */
enum kvm_mode {
	KVM_MODE_DEFAULT,
	KVM_MODE_PROTECTED,
	KVM_MODE_NV,
	KVM_MODE_NONE,
};
#ifdef CONFIG_KVM
enum kvm_mode kvm_get_mode(void);
#else
static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
#endif

DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

extern unsigned int __ro_after_init kvm_sve_max_vl;
extern unsigned int __ro_after_init kvm_host_sve_max_vl;
int __init kvm_arm_init_sve(void);

u32 __attribute_const__ kvm_target_cpu(void);
void kvm_reset_vcpu(struct kvm_vcpu *vcpu);
void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);

struct kvm_hyp_memcache {
	phys_addr_t head;
	unsigned long nr_pages;
};

static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
				     phys_addr_t *p,
				     phys_addr_t (*to_pa)(void *virt))
{
	*p = mc->head;
	mc->head = to_pa(p);
	mc->nr_pages++;
}

static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc,
				     void *(*to_va)(phys_addr_t phys))
{
	phys_addr_t *p = to_va(mc->head);

	if (!mc->nr_pages)
		return NULL;

	mc->head = *p;
	mc->nr_pages--;

	return p;
}

static inline int __topup_hyp_memcache(struct kvm_hyp_memcache *mc,
				       unsigned long min_pages,
				       void *(*alloc_fn)(void *arg),
				       phys_addr_t (*to_pa)(void *virt),
				       void *arg)
{
	while (mc->nr_pages < min_pages) {
		phys_addr_t *p = alloc_fn(arg);

		if (!p)
			return -ENOMEM;
		push_hyp_memcache(mc, p, to_pa);
	}

	return 0;
}

static inline void __free_hyp_memcache(struct kvm_hyp_memcache *mc,
				       void (*free_fn)(void *virt, void *arg),
				       void *(*to_va)(phys_addr_t phys),
				       void *arg)
{
	while (mc->nr_pages)
		free_fn(pop_hyp_memcache(mc, to_va), arg);
}

void free_hyp_memcache(struct kvm_hyp_memcache *mc);
int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages);

struct kvm_vmid {
	atomic64_t id;
};

struct kvm_s2_mmu {
	struct kvm_vmid vmid;

	/*
	 * stage2 entry level table
	 *
	 * Two kvm_s2_mmu structures in the same VM can point to the same
	 * pgd here.  This happens when running a guest using a
	 * translation regime that isn't affected by its own stage-2
	 * translation, such as a non-VHE hypervisor running at vEL2, or
	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
	 * canonical stage-2 page tables.
	 */
	phys_addr_t	pgd_phys;
	struct kvm_pgtable *pgt;

	/*
	 * VTCR value used on the host. For a non-NV guest (or a NV
	 * guest that runs in a context where its own S2 doesn't
	 * apply), its T0SZ value reflects that of the IPA size.
	 *
	 * For a shadow S2 MMU, T0SZ reflects the PARange exposed to
	 * the guest.
	 */
	u64	vtcr;

	/* The last vcpu id that ran on each physical CPU */
	int __percpu *last_vcpu_ran;

#define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0
	/*
	 * Memory cache used to split
	 * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It
	 * is used to allocate stage2 page tables while splitting huge
	 * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
	 * influences both the capacity of the split page cache, and
	 * how often KVM reschedules. Be wary of raising CHUNK_SIZE
	 * too high.
	 *
	 * Protected by kvm->slots_lock.
	 */
	struct kvm_mmu_memory_cache split_page_cache;
	uint64_t split_page_chunk_size;

	struct kvm_arch *arch;
};

struct kvm_arch_memory_slot {
};

/**
 * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests
 *
 * @std_bmap: Bitmap of standard secure service calls
 * @std_hyp_bmap: Bitmap of standard hypervisor service calls
 * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls
 */
struct kvm_smccc_features {
	unsigned long std_bmap;
	unsigned long std_hyp_bmap;
	unsigned long vendor_hyp_bmap;
};

typedef unsigned int pkvm_handle_t;

struct kvm_protected_vm {
	pkvm_handle_t handle;
	struct kvm_hyp_memcache teardown_mc;
	bool enabled;
};

struct kvm_mpidr_data {
	u64			mpidr_mask;
	DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx);
};

static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
{
	unsigned long index = 0, mask = data->mpidr_mask;
	unsigned long aff = mpidr & MPIDR_HWID_BITMASK;

	bitmap_gather(&index, &aff, &mask, fls(mask));

	return index;
}

struct kvm_sysreg_masks;

enum fgt_group_id {
	__NO_FGT_GROUP__,
	HFGxTR_GROUP,
	HDFGRTR_GROUP,
	HDFGWTR_GROUP = HDFGRTR_GROUP,
	HFGITR_GROUP,
	HAFGRTR_GROUP,

	/* Must be last */
	__NR_FGT_GROUP_IDS__
};

struct kvm_arch {
	struct kvm_s2_mmu mmu;

	/*
	 * Fine-Grained UNDEF, mimicking the FGT layout defined by the
	 * architecture. We track them globally, as we present the
	 * same feature-set to all vcpus.
	 *
	 * Index 0 is currently spare.
	 */
	u64 fgu[__NR_FGT_GROUP_IDS__];

	/* Interrupt controller */
	struct vgic_dist	vgic;

	/* Timers */
	struct arch_timer_vm_data timer_data;

	/* Mandated version of PSCI */
	u32 psci_version;

	/* Protects VM-scoped configuration data */
	struct mutex config_lock;

	/*
	 * If we encounter a data abort without valid instruction syndrome
	 * information, report this to user space.  User space can (and
	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
	 * supported.
	 */
#define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER	0
	/* Memory Tagging Extension enabled for the guest */
#define KVM_ARCH_FLAG_MTE_ENABLED			1
	/* At least one vCPU has ran in the VM */
#define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
	/* The vCPU feature set for the VM is configured */
#define KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED		3
	/* PSCI SYSTEM_SUSPEND enabled for the guest */
#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		4
	/* VM counter offset */
#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET			5
	/* Timer PPIs made immutable */
#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
	/* Initial ID reg values loaded */
#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
	/* Fine-Grained UNDEF initialised */
#define KVM_ARCH_FLAG_FGU_INITIALIZED			8
	unsigned long flags;

	/* VM-wide vCPU feature set */
	DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES);

	/* MPIDR to vcpu index mapping, optional */
	struct kvm_mpidr_data *mpidr_data;

	/*
	 * VM-wide PMU filter, implemented as a bitmap and big enough for
	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
	 */
	unsigned long *pmu_filter;
	struct arm_pmu *arm_pmu;

	cpumask_var_t supported_cpus;

	/* PMCR_EL0.N value for the guest */
	u8 pmcr_n;

	/* Iterator for idreg debugfs */
	u8	idreg_debugfs_iter;

	/* Hypercall features firmware registers' descriptor */
	struct kvm_smccc_features smccc_feat;
	struct maple_tree smccc_filter;

	/*
	 * Emulated CPU ID registers per VM
	 * (Op0, Op1, CRn, CRm, Op2) of the ID registers to be saved in it
	 * is (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8.
	 *
	 * These emulated idregs are VM-wide, but accessed from the context of a vCPU.
	 * Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
	 */
#define IDREG_IDX(id)		(((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
#define IDX_IDREG(idx)		sys_reg(3, 0, 0, ((idx) >> 3) + 1, (idx) & Op2_mask)
#define IDREG(kvm, id)		((kvm)->arch.id_regs[IDREG_IDX(id)])
#define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
	u64 id_regs[KVM_ARM_ID_REG_NUM];

	/* Masks for VNCR-baked sysregs */
	struct kvm_sysreg_masks	*sysreg_masks;

	/*
	 * For an untrusted host VM, 'pkvm.handle' is used to lookup
	 * the associated pKVM instance in the hypervisor.
	 */
	struct kvm_protected_vm pkvm;
};

struct kvm_vcpu_fault_info {
	u64 esr_el2;		/* Hyp Syndrom Register */
	u64 far_el2;		/* Hyp Fault Address Register */
	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
	u64 disr_el1;		/* Deferred [SError] Status Register */
};

/*
 * VNCR() just places the VNCR_capable registers in the enum after
 * __VNCR_START__, and the value (after correction) to be an 8-byte offset
 * from the VNCR base. As we don't require the enum to be otherwise ordered,
 * we need the terrible hack below to ensure that we correctly size the
 * sys_regs array, no matter what.
 *
 * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful
 * treasure trove of bit hacks:
 * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
 */
#define __MAX__(x,y)	((x) ^ (((x) ^ (y)) & -((x) < (y))))
#define VNCR(r)						\
	__before_##r,					\
	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
	__after_##r = __MAX__(__before_##r - 1, r)

enum vcpu_sysreg {
	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
	MPIDR_EL1,	/* MultiProcessor Affinity Register */
	CLIDR_EL1,	/* Cache Level ID Register */
	CSSELR_EL1,	/* Cache Size Selection Register */
	TPIDR_EL0,	/* Thread ID, User R/W */
	TPIDRRO_EL0,	/* Thread ID, User R/O */
	TPIDR_EL1,	/* Thread ID, Privileged */
	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
	PAR_EL1,	/* Physical Address Register */
	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
	OSLSR_EL1,	/* OS Lock Status Register */
	DISR_EL1,	/* Deferred Interrupt Status Register */

	/* Performance Monitors Registers */
	PMCR_EL0,	/* Control Register */
	PMSELR_EL0,	/* Event Counter Selection Register */
	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
	PMCCNTR_EL0,	/* Cycle Counter Register */
	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
	PMCNTENSET_EL0,	/* Count Enable Set Register */
	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
	PMUSERENR_EL0,	/* User Enable Register */

	/* Pointer Authentication Registers in a strict increasing order. */
	APIAKEYLO_EL1,
	APIAKEYHI_EL1,
	APIBKEYLO_EL1,
	APIBKEYHI_EL1,
	APDAKEYLO_EL1,
	APDAKEYHI_EL1,
	APDBKEYLO_EL1,
	APDBKEYHI_EL1,
	APGAKEYLO_EL1,
	APGAKEYHI_EL1,

	/* Memory Tagging Extension registers */
	RGSR_EL1,	/* Random Allocation Tag Seed Register */
	GCR_EL1,	/* Tag Control Register */
	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */

	/* 32bit specific registers. */
	DACR32_EL2,	/* Domain Access Control Register */
	IFSR32_EL2,	/* Instruction Fault Status Register */
	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
	DBGVCR32_EL2,	/* Debug Vector Catch Register */

	/* EL2 registers */
	SCTLR_EL2,	/* System Control Register (EL2) */
	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
	TCR_EL2,	/* Translation Control Register (EL2) */
	SPSR_EL2,	/* EL2 saved program status register */
	ELR_EL2,	/* EL2 exception link register */
	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
	AFSR1_EL2,	/* Auxiliary Fault Status Register 1 (EL2) */
	ESR_EL2,	/* Exception Syndrome Register (EL2) */
	FAR_EL2,	/* Fault Address Register (EL2) */
	HPFAR_EL2,	/* Hypervisor IPA Fault Address Register */
	MAIR_EL2,	/* Memory Attribute Indirection Register (EL2) */
	AMAIR_EL2,	/* Auxiliary Memory Attribute Indirection Register (EL2) */
	VBAR_EL2,	/* Vector Base Address Register (EL2) */
	RVBAR_EL2,	/* Reset Vector Base Address Register */
	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
	SP_EL2,		/* EL2 Stack Pointer */
	CNTHP_CTL_EL2,
	CNTHP_CVAL_EL2,
	CNTHV_CTL_EL2,
	CNTHV_CVAL_EL2,

	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */

	VNCR(SCTLR_EL1),/* System Control Register */
	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
	VNCR(CPACR_EL1),/* Coprocessor Access Control */
	VNCR(ZCR_EL1),	/* SVE Control */
	VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */
	VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */
	VNCR(TCR_EL1),	/* Translation Control Register */
	VNCR(TCR2_EL1),	/* Extended Translation Control Register */
	VNCR(ESR_EL1),	/* Exception Syndrome Register */
	VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */
	VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */
	VNCR(FAR_EL1),	/* Fault Address Register */
	VNCR(MAIR_EL1),	/* Memory Attribute Indirection Register */
	VNCR(VBAR_EL1),	/* Vector Base Address Register */
	VNCR(CONTEXTIDR_EL1),	/* Context ID Register */
	VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */
	VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */
	VNCR(ELR_EL1),
	VNCR(SP_EL1),
	VNCR(SPSR_EL1),
	VNCR(TFSR_EL1),	/* Tag Fault Status Register (EL1) */
	VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */
	VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */
	VNCR(HCR_EL2),	/* Hypervisor Configuration Register */
	VNCR(HSTR_EL2),	/* Hypervisor System Trap Register */
	VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */
	VNCR(VTCR_EL2),	/* Virtualization Translation Control Register */
	VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */
	VNCR(HCRX_EL2),	/* Extended Hypervisor Configuration Register */

	/* Permission Indirection Extension registers */
	VNCR(PIR_EL1),	 /* Permission Indirection Register 1 (EL1) */
	VNCR(PIRE0_EL1), /*  Permission Indirection Register 0 (EL1) */

	VNCR(HFGRTR_EL2),
	VNCR(HFGWTR_EL2),
	VNCR(HFGITR_EL2),
	VNCR(HDFGRTR_EL2),
	VNCR(HDFGWTR_EL2),
	VNCR(HAFGRTR_EL2),

	VNCR(CNTVOFF_EL2),
	VNCR(CNTV_CVAL_EL0),
	VNCR(CNTV_CTL_EL0),
	VNCR(CNTP_CVAL_EL0),
	VNCR(CNTP_CTL_EL0),

	NR_SYS_REGS	/* Nothing after this line! */
};

struct kvm_sysreg_masks {
	struct {
		u64	res0;
		u64	res1;
	} mask[NR_SYS_REGS - __VNCR_START__];
};

struct kvm_cpu_context {
	struct user_pt_regs regs;	/* sp = sp_el0 */

	u64	spsr_abt;
	u64	spsr_und;
	u64	spsr_irq;
	u64	spsr_fiq;

	struct user_fpsimd_state fp_regs;

	u64 sys_regs[NR_SYS_REGS];

	struct kvm_vcpu *__hyp_running_vcpu;

	/* This pointer has to be 4kB aligned. */
	u64 *vncr_array;
};

struct cpu_sve_state {
	__u64 zcr_el1;

	/*
	 * Ordering is important since __sve_save_state/__sve_restore_state
	 * relies on it.
	 */
	__u32 fpsr;
	__u32 fpcr;

	/* Must be SVE_VQ_BYTES (128 bit) aligned. */
	__u8 sve_regs[];
};

/*
 * This structure is instantiated on a per-CPU basis, and contains
 * data that is:
 *
 * - tied to a single physical CPU, and
 * - either have a lifetime that does not extend past vcpu_put()
 * - or is an invariant for the lifetime of the system
 *
 * Use host_data_ptr(field) as a way to access a pointer to such a
 * field.
 */
struct kvm_host_data {
	struct kvm_cpu_context host_ctxt;

	/*
	 * All pointers in this union are hyp VA.
	 * sve_state is only used in pKVM and if system_supports_sve().
	 */
	union {
		struct user_fpsimd_state *fpsimd_state;
		struct cpu_sve_state *sve_state;
	};

	/* Ownership of the FP regs */
	enum {
		FP_STATE_FREE,
		FP_STATE_HOST_OWNED,
		FP_STATE_GUEST_OWNED,
	} fp_owner;

	/*
	 * host_debug_state contains the host registers which are
	 * saved and restored during world switches.
	 */
	 struct {
		/* {Break,watch}point registers */
		struct kvm_guest_debug_arch regs;
		/* Statistical profiling extension */
		u64 pmscr_el1;
		/* Self-hosted trace */
		u64 trfcr_el1;
		/* Values of trap registers for the host before guest entry. */
		u64 mdcr_el2;
	} host_debug_state;
};

struct kvm_host_psci_config {
	/* PSCI version used by host. */
	u32 version;
	u32 smccc_version;

	/* Function IDs used by host if version is v0.1. */
	struct psci_0_1_function_ids function_ids_0_1;

	bool psci_0_1_cpu_suspend_implemented;
	bool psci_0_1_cpu_on_implemented;
	bool psci_0_1_cpu_off_implemented;
	bool psci_0_1_migrate_implemented;
};

extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)

extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)

extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)

struct vcpu_reset_state {
	unsigned long	pc;
	unsigned long	r0;
	bool		be;
	bool		reset;
};

struct kvm_vcpu_arch {
	struct kvm_cpu_context ctxt;

	/*
	 * Guest floating point state
	 *
	 * The architecture has two main floating point extensions,
	 * the original FPSIMD and SVE.  These have overlapping
	 * register views, with the FPSIMD V registers occupying the
	 * low 128 bits of the SVE Z registers.  When the core
	 * floating point code saves the register state of a task it
	 * records which view it saved in fp_type.
	 */
	void *sve_state;
	enum fp_type fp_type;
	unsigned int sve_max_vl;
	u64 svcr;
	u64 fpmr;

	/* Stage 2 paging state used by the hardware on next switch */
	struct kvm_s2_mmu *hw_mmu;

	/* Values of trap registers for the guest. */
	u64 hcr_el2;
	u64 hcrx_el2;
	u64 mdcr_el2;
	u64 cptr_el2;

	/* Exception Information */
	struct kvm_vcpu_fault_info fault;

	/* Configuration flags, set once and for all before the vcpu can run */
	u8 cflags;

	/* Input flags to the hypervisor code, potentially cleared after use */
	u8 iflags;

	/* State flags for kernel bookkeeping, unused by the hypervisor code */
	u8 sflags;

	/*
	 * Don't run the guest (internal implementation need).
	 *
	 * Contrary to the flags above, this is set/cleared outside of
	 * a vcpu context, and thus cannot be mixed with the flags
	 * themselves (or the flag accesses need to be made atomic).
	 */
	bool pause;

	/*
	 * We maintain more than a single set of debug registers to support
	 * debugging the guest from the host and to maintain separate host and
	 * guest state during world switches. vcpu_debug_state are the debug
	 * registers of the vcpu as the guest sees them.
	 *
	 * external_debug_state contains the debug values we want to debug the
	 * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl.
	 *
	 * debug_ptr points to the set of debug registers that should be loaded
	 * onto the hardware when running the guest.
	 */
	struct kvm_guest_debug_arch *debug_ptr;
	struct kvm_guest_debug_arch vcpu_debug_state;
	struct kvm_guest_debug_arch external_debug_state;

	/* VGIC state */
	struct vgic_cpu vgic_cpu;
	struct arch_timer_cpu timer_cpu;
	struct kvm_pmu pmu;

	/*
	 * Guest registers we preserve during guest debugging.
	 *
	 * These shadow registers are updated by the kvm_handle_sys_reg
	 * trap handler if the guest accesses or updates them while we
	 * are using guest debug.
	 */
	struct {
		u32	mdscr_el1;
		bool	pstate_ss;
	} guest_debug_preserved;

	/* vcpu power state */
	struct kvm_mp_state mp_state;
	spinlock_t mp_state_lock;

	/* Cache some mmu pages needed inside spinlock regions */
	struct kvm_mmu_memory_cache mmu_page_cache;

	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
	u64 vsesr_el2;

	/* Additional reset state */
	struct vcpu_reset_state	reset_state;

	/* Guest PV state */
	struct {
		u64 last_steal;
		gpa_t base;
	} steal;

	/* Per-vcpu CCSIDR override or NULL */
	u32 *ccsidr;
};

/*
 * Each 'flag' is composed of a comma-separated triplet:
 *
 * - the flag-set it belongs to in the vcpu->arch structure
 * - the value for that flag
 * - the mask for that flag
 *
 *  __vcpu_single_flag() builds such a triplet for a single-bit flag.
 * unpack_vcpu_flag() extract the flag value from the triplet for
 * direct use outside of the flag accessors.
 */
#define __vcpu_single_flag(_set, _f)	_set, (_f), (_f)

#define __unpack_flag(_set, _f, _m)	_f
#define unpack_vcpu_flag(...)		__unpack_flag(__VA_ARGS__)

#define __build_check_flag(v, flagset, f, m)			\
	do {							\
		typeof(v->arch.flagset) *_fset;			\
								\
		/* Check that the flags fit in the mask */	\
		BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m)));	\
		/* Check that the flags fit in the type */	\
		BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m));	\
	} while (0)

#define __vcpu_get_flag(v, flagset, f, m)			\
	({							\
		__build_check_flag(v, flagset, f, m);		\
								\
		READ_ONCE(v->arch.flagset) & (m);		\
	})

/*
 * Note that the set/clear accessors must be preempt-safe in order to
 * avoid nesting them with load/put which also manipulate flags...
 */
#ifdef __KVM_NVHE_HYPERVISOR__
/* the nVHE hypervisor is always non-preemptible */
#define __vcpu_flags_preempt_disable()
#define __vcpu_flags_preempt_enable()
#else
#define __vcpu_flags_preempt_disable()	preempt_disable()
#define __vcpu_flags_preempt_enable()	preempt_enable()
#endif

#define __vcpu_set_flag(v, flagset, f, m)			\
	do {							\
		typeof(v->arch.flagset) *fset;			\
								\
		__build_check_flag(v, flagset, f, m);		\
								\
		fset = &v->arch.flagset;			\
		__vcpu_flags_preempt_disable();			\
		if (HWEIGHT(m) > 1)				\
			*fset &= ~(m);				\
		*fset |= (f);					\
		__vcpu_flags_preempt_enable();			\
	} while (0)

#define __vcpu_clear_flag(v, flagset, f, m)			\
	do {							\
		typeof(v->arch.flagset) *fset;			\
								\
		__build_check_flag(v, flagset, f, m);		\
								\
		fset = &v->arch.flagset;			\
		__vcpu_flags_preempt_disable();			\
		*fset &= ~(m);					\
		__vcpu_flags_preempt_enable();			\
	} while (0)

#define vcpu_get_flag(v, ...)	__vcpu_get_flag((v), __VA_ARGS__)
#define vcpu_set_flag(v, ...)	__vcpu_set_flag((v), __VA_ARGS__)
#define vcpu_clear_flag(v, ...)	__vcpu_clear_flag((v), __VA_ARGS__)

/* SVE exposed to guest */
#define GUEST_HAS_SVE		__vcpu_single_flag(cflags, BIT(0))
/* SVE config completed */
#define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
/* PTRAUTH exposed to guest */
#define GUEST_HAS_PTRAUTH	__vcpu_single_flag(cflags, BIT(2))
/* KVM_ARM_VCPU_INIT completed */
#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(3))

/* Exception pending */
#define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
/*
 * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't
 * be set together with an exception...
 */
#define INCREMENT_PC		__vcpu_single_flag(iflags, BIT(1))
/* Target EL/MODE (not a single flag, but let's abuse the macro) */
#define EXCEPT_MASK		__vcpu_single_flag(iflags, GENMASK(3, 1))

/* Helpers to encode exceptions with minimum fuss */
#define __EXCEPT_MASK_VAL	unpack_vcpu_flag(EXCEPT_MASK)
#define __EXCEPT_SHIFT		__builtin_ctzl(__EXCEPT_MASK_VAL)
#define __vcpu_except_flags(_f)	iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL

/*
 * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following
 * values:
 *
 * For AArch32 EL1:
 */
#define EXCEPT_AA32_UND		__vcpu_except_flags(0)
#define EXCEPT_AA32_IABT	__vcpu_except_flags(1)
#define EXCEPT_AA32_DABT	__vcpu_except_flags(2)
/* For AArch64: */
#define EXCEPT_AA64_EL1_SYNC	__vcpu_except_flags(0)
#define EXCEPT_AA64_EL1_IRQ	__vcpu_except_flags(1)
#define EXCEPT_AA64_EL1_FIQ	__vcpu_except_flags(2)
#define EXCEPT_AA64_EL1_SERR	__vcpu_except_flags(3)
/* For AArch64 with NV: */
#define EXCEPT_AA64_EL2_SYNC	__vcpu_except_flags(4)
#define EXCEPT_AA64_EL2_IRQ	__vcpu_except_flags(5)
#define EXCEPT_AA64_EL2_FIQ	__vcpu_except_flags(6)
#define EXCEPT_AA64_EL2_SERR	__vcpu_except_flags(7)
/* Guest debug is live */
#define DEBUG_DIRTY		__vcpu_single_flag(iflags, BIT(4))
/* Save SPE context if active  */
#define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
/* Save TRBE context if active  */
#define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))

/* SVE enabled for host EL0 */
#define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
/* SME enabled for EL0 */
#define HOST_SME_ENABLED	__vcpu_single_flag(sflags, BIT(1))
/* Physical CPU not in supported_cpus */
#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(2))
/* WFIT instruction trapped */
#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
/* vcpu system registers loaded on physical CPU */
#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
/* Software step state is Active-pending */
#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
/* PMUSERENR for the guest EL0 is on physical CPU */
#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
/* WFI instruction trapped */
#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))


/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
#define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\
			     sve_ffr_offset((vcpu)->arch.sve_max_vl))

#define vcpu_sve_max_vq(vcpu)	sve_vq_from_vl((vcpu)->arch.sve_max_vl)

#define vcpu_sve_state_size(vcpu) ({					\
	size_t __size_ret;						\
	unsigned int __vcpu_vq;						\
									\
	if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) {		\
		__size_ret = 0;						\
	} else {							\
		__vcpu_vq = vcpu_sve_max_vq(vcpu);			\
		__size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq);		\
	}								\
									\
	__size_ret;							\
})

#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
				 KVM_GUESTDBG_USE_SW_BP | \
				 KVM_GUESTDBG_USE_HW | \
				 KVM_GUESTDBG_SINGLESTEP)

#define vcpu_has_sve(vcpu) (system_supports_sve() &&			\
			    vcpu_get_flag(vcpu, GUEST_HAS_SVE))

#ifdef CONFIG_ARM64_PTR_AUTH
#define vcpu_has_ptrauth(vcpu)						\
	((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) ||		\
	  cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) &&		\
	  vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH))
#else
#define vcpu_has_ptrauth(vcpu)		false
#endif

#define vcpu_on_unsupported_cpu(vcpu)					\
	vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU)

#define vcpu_set_on_unsupported_cpu(vcpu)				\
	vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU)

#define vcpu_clear_on_unsupported_cpu(vcpu)				\
	vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU)

#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)

/*
 * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
 * memory backed version of a register, and not the one most recently
 * accessed by a running VCPU.  For example, for userspace access or
 * for system registers that are never context switched, but only
 * emulated.
 *
 * Don't bother with VNCR-based accesses in the nVHE code, it has no
 * business dealing with NV.
 */
static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
{
#if !defined (__KVM_NVHE_HYPERVISOR__)
	if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
		     r >= __VNCR_START__ && ctxt->vncr_array))
		return &ctxt->vncr_array[r - __VNCR_START__];
#endif
	return (u64 *)&ctxt->sys_regs[r];
}

#define __ctxt_sys_reg(c,r)						\
	({								\
		BUILD_BUG_ON(__builtin_constant_p(r) &&			\
			     (r) >= NR_SYS_REGS);			\
		___ctxt_sys_reg(c, r);					\
	})

#define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))

u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
#define __vcpu_sys_reg(v,r)						\
	(*({								\
		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
		u64 *__r = __ctxt_sys_reg(ctxt, (r));			\
		if (vcpu_has_nv((v)) && (r) >= __VNCR_START__)		\
			*__r = kvm_vcpu_sanitise_vncr_reg((v), (r));	\
		__r;							\
	}))

u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);

static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
{
	/*
	 * *** VHE ONLY ***
	 *
	 * System registers listed in the switch are not saved on every
	 * exit from the guest but are only saved on vcpu_put.
	 *
	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
	 * should never be listed below, because the guest cannot modify its
	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
	 * thread when emulating cross-VCPU communication.
	 */
	if (!has_vhe())
		return false;

	switch (reg) {
	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
	case PAR_EL1:		*val = read_sysreg_par();		break;
	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
	default:		return false;
	}

	return true;
}

static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
{
	/*
	 * *** VHE ONLY ***
	 *
	 * System registers listed in the switch are not restored on every
	 * entry to the guest but are only restored on vcpu_load.
	 *
	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
	 * should never be listed below, because the MPIDR should only be set
	 * once, before running the VCPU, and never changed later.
	 */
	if (!has_vhe())
		return false;

	switch (reg) {
	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
	default:		return false;
	}

	return true;
}

struct kvm_vm_stat {
	struct kvm_vm_stat_generic generic;
};

struct kvm_vcpu_stat {
	struct kvm_vcpu_stat_generic generic;
	u64 hvc_exit_stat;
	u64 wfe_exit_stat;
	u64 wfi_exit_stat;
	u64 mmio_exit_user;
	u64 mmio_exit_kernel;
	u64 signal_exits;
	u64 exits;
};

unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);

unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu);
int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);

int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);

int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);

void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);

#define vcpu_has_run_once(vcpu)	!!rcu_access_pointer((vcpu)->pid)

#ifndef __KVM_NVHE_HYPERVISOR__
#define kvm_call_hyp_nvhe(f, ...)						\
	({								\
		struct arm_smccc_res res;				\
									\
		arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f),		\
				  ##__VA_ARGS__, &res);			\
		WARN_ON(res.a0 != SMCCC_RET_SUCCESS);			\
									\
		res.a1;							\
	})

/*
 * The couple of isb() below are there to guarantee the same behaviour
 * on VHE as on !VHE, where the eret to EL1 acts as a context
 * synchronization event.
 */
#define kvm_call_hyp(f, ...)						\
	do {								\
		if (has_vhe()) {					\
			f(__VA_ARGS__);					\
			isb();						\
		} else {						\
			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
		}							\
	} while(0)

#define kvm_call_hyp_ret(f, ...)					\
	({								\
		typeof(f(__VA_ARGS__)) ret;				\
									\
		if (has_vhe()) {					\
			ret = f(__VA_ARGS__);				\
			isb();						\
		} else {						\
			ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__);	\
		}							\
									\
		ret;							\
	})
#else /* __KVM_NVHE_HYPERVISOR__ */
#define kvm_call_hyp(f, ...) f(__VA_ARGS__)
#define kvm_call_hyp_ret(f, ...) f(__VA_ARGS__)
#define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__)
#endif /* __KVM_NVHE_HYPERVISOR__ */

int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);

int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);

void kvm_sys_regs_create_debugfs(struct kvm *kvm);
void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);

int __init kvm_sys_reg_table_init(void);
struct sys_reg_desc;
int __init populate_sysreg_config(const struct sys_reg_desc *sr,
				  unsigned int idx);
int __init populate_nv_trap_config(void);

bool lock_all_vcpus(struct kvm *kvm);
void unlock_all_vcpus(struct kvm *kvm);

void kvm_init_sysreg(struct kvm_vcpu *);

/* MMIO helpers */
void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);

int kvm_handle_mmio_return(struct kvm_vcpu *vcpu);
int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);

/*
 * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
 * arrived in guest context.  For arm64, any event that arrives while a vCPU is
 * loaded is considered to be "in guest".
 */
static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
{
	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
}

long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
void kvm_update_stolen_time(struct kvm_vcpu *vcpu);

bool kvm_arm_pvtime_supported(void);
int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
			    struct kvm_device_attr *attr);
int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
			    struct kvm_device_attr *attr);
int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
			    struct kvm_device_attr *attr);

extern unsigned int __ro_after_init kvm_arm_vmid_bits;
int __init kvm_arm_vmid_alloc_init(void);
void __init kvm_arm_vmid_alloc_free(void);
bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
void kvm_arm_vmid_clear_active(void);

static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
{
	vcpu_arch->steal.base = INVALID_GPA;
}

static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
{
	return (vcpu_arch->steal.base != INVALID_GPA);
}

void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);

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

DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);

/*
 * How we access per-CPU host data depends on the where we access it from,
 * and the mode we're in:
 *
 * - VHE and nVHE hypervisor bits use their locally defined instance
 *
 * - the rest of the kernel use either the VHE or nVHE one, depending on
 *   the mode we're running in.
 *
 *   Unless we're in protected mode, fully deprivileged, and the nVHE
 *   per-CPU stuff is exclusively accessible to the protected EL2 code.
 *   In this case, the EL1 code uses the *VHE* data as its private state
 *   (which makes sense in a way as there shouldn't be any shared state
 *   between the host and the hypervisor).
 *
 * Yes, this is all totally trivial. Shoot me now.
 */
#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
#define host_data_ptr(f)	(&this_cpu_ptr(&kvm_host_data)->f)
#else
#define host_data_ptr(f)						\
	(static_branch_unlikely(&kvm_protected_mode_initialized) ?	\
	 &this_cpu_ptr(&kvm_host_data)->f :				\
	 &this_cpu_ptr_hyp_sym(kvm_host_data)->f)
#endif

/* Check whether the FP regs are owned by the guest */
static inline bool guest_owns_fp_regs(void)
{
	return *host_data_ptr(fp_owner) == FP_STATE_GUEST_OWNED;
}

/* Check whether the FP regs are owned by the host */
static inline bool host_owns_fp_regs(void)
{
	return *host_data_ptr(fp_owner) == FP_STATE_HOST_OWNED;
}

static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
{
	/* The host's MPIDR is immutable, so let's set it up at boot time */
	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
}

static inline bool kvm_system_needs_idmapped_vectors(void)
{
	return cpus_have_final_cap(ARM64_SPECTRE_V3A);
}

static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}

void kvm_arm_init_debug(void);
void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);

#define kvm_vcpu_os_lock_enabled(vcpu)		\
	(!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK))

int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
			       struct kvm_device_attr *attr);
int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
			       struct kvm_device_attr *attr);
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
			       struct kvm_device_attr *attr);

int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
			       struct kvm_arm_copy_mte_tags *copy_tags);
int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
				    struct kvm_arm_counter_offset *offset);
int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
					struct reg_mask_range *range);

/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);

static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
{
	return (!has_vhe() && attr->exclude_host);
}

/* Flags for host debug state */
void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);

#ifdef CONFIG_KVM
void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
void kvm_clr_pmu_events(u32 clr);
bool kvm_set_pmuserenr(u64 val);
#else
static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
static inline void kvm_clr_pmu_events(u32 clr) {}
static inline bool kvm_set_pmuserenr(u64 val)
{
	return false;
}
#endif

void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu);

int __init kvm_set_ipa_limit(void);

#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);

#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS

#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE

#define kvm_vm_is_protected(kvm)	(is_protected_kvm_enabled() && (kvm)->arch.pkvm.enabled)

#define vcpu_is_protected(vcpu)		kvm_vm_is_protected((vcpu)->kvm)

int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);

#define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED)

#define kvm_has_mte(kvm)					\
	(system_supports_mte() &&				\
	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))

#define kvm_supports_32bit_el0()				\
	(system_supports_32bit_el0() &&				\
	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))

#define kvm_vm_has_ran_once(kvm)					\
	(test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags))

static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature)
{
	return test_bit(feature, ka->vcpu_features);
}

#define vcpu_has_feature(v, f)	__vcpu_has_feature(&(v)->kvm->arch, (f))

#define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED)

int kvm_trng_call(struct kvm_vcpu *vcpu);
#ifdef CONFIG_KVM
extern phys_addr_t hyp_mem_base;
extern phys_addr_t hyp_mem_size;
void __init kvm_hyp_reserve(void);
#else
static inline void kvm_hyp_reserve(void) { }
#endif

void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);

#define __expand_field_sign_unsigned(id, fld, val)			\
	((u64)SYS_FIELD_VALUE(id, fld, val))

#define __expand_field_sign_signed(id, fld, val)			\
	({								\
		u64 __val = SYS_FIELD_VALUE(id, fld, val);		\
		sign_extend64(__val, id##_##fld##_WIDTH - 1);		\
	})

#define expand_field_sign(id, fld, val)					\
	(id##_##fld##_SIGNED ?						\
	 __expand_field_sign_signed(id, fld, val) :			\
	 __expand_field_sign_unsigned(id, fld, val))

#define get_idreg_field_unsigned(kvm, id, fld)				\
	({								\
		u64 __val = IDREG((kvm), SYS_##id);			\
		FIELD_GET(id##_##fld##_MASK, __val);			\
	})

#define get_idreg_field_signed(kvm, id, fld)				\
	({								\
		u64 __val = get_idreg_field_unsigned(kvm, id, fld);	\
		sign_extend64(__val, id##_##fld##_WIDTH - 1);		\
	})

#define get_idreg_field_enum(kvm, id, fld)				\
	get_idreg_field_unsigned(kvm, id, fld)

#define get_idreg_field(kvm, id, fld)					\
	(id##_##fld##_SIGNED ?						\
	 get_idreg_field_signed(kvm, id, fld) :				\
	 get_idreg_field_unsigned(kvm, id, fld))

#define kvm_has_feat(kvm, id, fld, limit)				\
	(get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit))

#define kvm_has_feat_enum(kvm, id, fld, val)				\
	(get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val))

#define kvm_has_feat_range(kvm, id, fld, min, max)			\
	(get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \
	 get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max))

/* Check for a given level of PAuth support */
#define kvm_has_pauth(k, l)						\
	({								\
		bool pa, pi, pa3;					\
									\
		pa  = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l);	\
		pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP);	\
		pi  = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l);	\
		pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP);	\
		pa3  = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l);	\
		pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP);	\
									\
		(pa + pi + pa3) == 1;					\
	})

#endif /* __ARM64_KVM_HOST_H__ */