Linux Audio

Check our new training course

Embedded Linux Audio

Check our new training course
with Creative Commons CC-BY-SA
lecture materials

Bootlin logo

Elixir Cross Referencer

Loading...
   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
/* 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>

#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;
int __init kvm_arm_init_sve(void);

u32 __attribute_const__ kvm_target_cpu(void);
int 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;

	/* 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;
};

struct kvm_arch {
	struct kvm_s2_mmu mmu;

	/* VTCR_EL2 value for this VM */
	u64    vtcr;

	/* 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
	/* SMCCC filter initialized for the VM */
#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED		7
	/* Initial ID reg values loaded */
#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		8
	unsigned long flags;

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

	/*
	 * 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;

	/* 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 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];

	/*
	 * 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 */
};

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 */
	SCTLR_EL1,	/* System Control Register */
	ACTLR_EL1,	/* Auxiliary Control Register */
	CPACR_EL1,	/* Coprocessor Access Control */
	ZCR_EL1,	/* SVE Control */
	TTBR0_EL1,	/* Translation Table Base Register 0 */
	TTBR1_EL1,	/* Translation Table Base Register 1 */
	TCR_EL1,	/* Translation Control Register */
	TCR2_EL1,	/* Extended Translation Control Register */
	ESR_EL1,	/* Exception Syndrome Register */
	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
	FAR_EL1,	/* Fault Address Register */
	MAIR_EL1,	/* Memory Attribute Indirection Register */
	VBAR_EL1,	/* Vector Base Address Register */
	CONTEXTIDR_EL1,	/* Context ID Register */
	TPIDR_EL0,	/* Thread ID, User R/W */
	TPIDRRO_EL0,	/* Thread ID, User R/O */
	TPIDR_EL1,	/* Thread ID, Privileged */
	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
	PAR_EL1,	/* Physical Address Register */
	MDSCR_EL1,	/* Monitor Debug System Control 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,

	ELR_EL1,
	SP_EL1,
	SPSR_EL1,

	CNTVOFF_EL2,
	CNTV_CVAL_EL0,
	CNTV_CTL_EL0,
	CNTP_CVAL_EL0,
	CNTP_CTL_EL0,

	/* Memory Tagging Extension registers */
	RGSR_EL1,	/* Random Allocation Tag Seed Register */
	GCR_EL1,	/* Tag Control Register */
	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */

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

	/* 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 */
	VPIDR_EL2,	/* Virtualization Processor ID Register */
	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
	SCTLR_EL2,	/* System Control Register (EL2) */
	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
	HCR_EL2,	/* Hypervisor Configuration Register */
	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
	HSTR_EL2,	/* Hypervisor System Trap Register */
	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
	HCRX_EL2,	/* Extended Hypervisor Configuration Register */
	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
	TCR_EL2,	/* Translation Control Register (EL2) */
	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
	VTCR_EL2,	/* Virtualization Translation Control Register */
	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) */
	TPIDR_EL2,	/* EL2 Software Thread ID Register */
	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
	SP_EL2,		/* EL2 Stack Pointer */
	HFGRTR_EL2,
	HFGWTR_EL2,
	HFGITR_EL2,
	HDFGRTR_EL2,
	HDFGWTR_EL2,
	CNTHP_CTL_EL2,
	CNTHP_CVAL_EL2,
	CNTHV_CTL_EL2,
	CNTHV_CVAL_EL2,

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

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;
};

struct kvm_host_data {
	struct kvm_cpu_context host_ctxt;
};

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;

	/* 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 mdcr_el2;
	u64 cptr_el2;

	/* Values of trap registers for the host before guest entry. */
	u64 mdcr_el2_host;

	/* Exception Information */
	struct kvm_vcpu_fault_info fault;

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

	/* 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.  host_debug_state are
	 * the host registers which are saved and restored during
	 * world switches. 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;

	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
	struct task_struct *parent_task;

	struct {
		/* {Break,watch}point registers */
		struct kvm_guest_debug_arch regs;
		/* Statistical profiling extension */
		u64 pmscr_el1;
		/* Self-hosted trace */
		u64 trfcr_el1;
	} host_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;

	/* feature flags */
	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);

	/* 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))
/* vcpu running in HYP context */
#define VCPU_HYP_CONTEXT	__vcpu_single_flag(iflags, BIT(7))

/* 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.
 */
#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])

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

#define __vcpu_sys_reg(v,r)	(ctxt_sys_reg(&(v)->arch.ctxt, (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 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 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);

#define KVM_ARCH_WANT_MMU_NOTIFIER

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_reset_sys_regs(struct kvm_vcpu *vcpu);

int __init kvm_sys_reg_table_init(void);
int __init populate_nv_trap_config(void);

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

/* 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);
void 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);

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_const_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);

/* 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);
void kvm_vcpu_unshare_task_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_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_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

static inline bool kvm_vm_is_protected(struct kvm *kvm)
{
	return false;
}

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))

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);

#endif /* __ARM64_KVM_HOST_H__ */