summaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm/kvm_host.h
blob: de32152cea0484fb03ea11d6417fb410db577b68 (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
/* 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/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_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_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_NONE,
};
enum kvm_mode kvm_get_mode(void);

DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

extern unsigned int kvm_sve_max_vl;
int 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_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;

	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;
};

struct kvm_arch {
	struct kvm_s2_mmu mmu;

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

	/* Interrupt controller */
	struct vgic_dist	vgic;

	/* Mandated version of PSCI */
	u32 psci_version;

	/*
	 * 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 following two bits are used to indicate the guest's EL1
	 * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
	 * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
	 * Otherwise, the guest's EL1 register width has not yet been
	 * determined yet.
	 */
#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED		3
#define KVM_ARCH_FLAG_EL1_32BIT				4
	/* PSCI SYSTEM_SUSPEND enabled for the guest */
#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		5

	unsigned long flags;

	/*
	 * 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;

	u8 pfr0_csv2;
	u8 pfr0_csv3;

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

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 */
	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 */
	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) */

	/* 32bit specific registers. Keep them at the end of the range */
	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 */

	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;

	/* 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 */
	void *sve_state;
	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;

	/* Miscellaneous vcpu state flags */
	u64 flags;

	/*
	 * 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;
	} guest_debug_preserved;

	/* vcpu power state */
	struct kvm_mp_state mp_state;

	/* Don't run the guest (internal implementation need) */
	bool pause;

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

	/* Target CPU and feature flags */
	int target;
	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;

	/* True when deferrable sysregs are loaded on the physical CPU,
	 * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
	bool sysregs_loaded_on_cpu;

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

/* 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;							\
})

/* vcpu_arch flags field values: */
#define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
#define KVM_ARM64_FP_ENABLED		(1 << 1) /* guest FP regs loaded */
#define KVM_ARM64_FP_HOST		(1 << 2) /* host FP regs loaded */
#define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
#define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
#define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
#define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
#define KVM_ARM64_PENDING_EXCEPTION	(1 << 8) /* Exception pending */
/*
 * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be
 * set together with an exception...
 */
#define KVM_ARM64_INCREMENT_PC		(1 << 9) /* Increment PC */
#define KVM_ARM64_EXCEPT_MASK		(7 << 9) /* Target EL/MODE */
/*
 * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can
 * take the following values:
 *
 * For AArch32 EL1:
 */
#define KVM_ARM64_EXCEPT_AA32_UND	(0 << 9)
#define KVM_ARM64_EXCEPT_AA32_IABT	(1 << 9)
#define KVM_ARM64_EXCEPT_AA32_DABT	(2 << 9)
/* For AArch64: */
#define KVM_ARM64_EXCEPT_AA64_ELx_SYNC	(0 << 9)
#define KVM_ARM64_EXCEPT_AA64_ELx_IRQ	(1 << 9)
#define KVM_ARM64_EXCEPT_AA64_ELx_FIQ	(2 << 9)
#define KVM_ARM64_EXCEPT_AA64_ELx_SERR	(3 << 9)
#define KVM_ARM64_EXCEPT_AA64_EL1	(0 << 11)
#define KVM_ARM64_EXCEPT_AA64_EL2	(1 << 11)

#define KVM_ARM64_DEBUG_STATE_SAVE_SPE	(1 << 12) /* Save SPE context if active  */
#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
#define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
#define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
#define KVM_ARM64_HOST_SME_ENABLED	(1 << 16) /* SME enabled for EL0 */
#define KVM_ARM64_WFIT			(1 << 17) /* WFIT instruction trapped */

#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)->arch.flags & KVM_ARM64_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)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH)
#else
#define vcpu_has_ptrauth(vcpu)		false
#endif

#define vcpu_on_unsupported_cpu(vcpu)					\
	((vcpu)->arch.flags & KVM_ARM64_ON_UNSUPPORTED_CPU)

#define vcpu_set_on_unsupported_cpu(vcpu)				\
	((vcpu)->arch.flags |= KVM_ARM64_ON_UNSUPPORTED_CPU)

#define vcpu_clear_on_unsupported_cpu(vcpu)				\
	((vcpu)->arch.flags &= ~KVM_ARM64_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 CSSELR_EL1:	*val = read_sysreg_s(SYS_CSSELR_EL1);	break;
	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 CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	break;
	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;
};

void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
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_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);

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__ */

void force_vm_exit(const cpumask_t *mask);

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 kvm_sys_reg_table_init(void);

/* 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 kvm_arm_vmid_bits;
int kvm_arm_vmid_alloc_init(void);
void 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 = GPA_INVALID;
}

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

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);
}

void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);

static inline void kvm_arch_hardware_unsetup(void) {}
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) & SYS_OSLSR_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);

long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
				struct kvm_arm_copy_mte_tags *copy_tags);

/* 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);
#else
static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
static inline void kvm_clr_pmu_events(u32 clr) {}
#endif

void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);

int kvm_set_ipa_limit(void);

#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);

int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);

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

void kvm_init_protected_traps(struct kvm_vcpu *vcpu);

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)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)

#define kvm_has_mte(kvm)					\
	(system_supports_mte() &&				\
	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(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__ */