kvm_host.h 20.0 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0-only */
2 3 4 5 6 7 8 9 10 11 12 13
/*
 * 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__

14
#include <linux/arm-smccc.h>
15
#include <linux/bitmap.h>
16
#include <linux/types.h>
17
#include <linux/jump_label.h>
18
#include <linux/kvm_types.h>
19
#include <linux/percpu.h>
20
#include <asm/arch_gicv3.h>
21
#include <asm/barrier.h>
22
#include <asm/cpufeature.h>
23
#include <asm/cputype.h>
24
#include <asm/daifflags.h>
25
#include <asm/fpsimd.h>
26
#include <asm/kvm.h>
27
#include <asm/kvm_asm.h>
28
#include <asm/thread_info.h>
29

30 31
#define __KVM_HAVE_ARCH_INTC_INITIALIZED

32
#define KVM_USER_MEM_SLOTS 512
33
#define KVM_HALT_POLL_NS_DEFAULT 500000
34 35 36

#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
37
#include <kvm/arm_pmu.h>
38

39 40
#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS

41
#define KVM_VCPU_MAX_FEATURES 7
42

43
#define KVM_REQ_SLEEP \
44
	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
45
#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
46
#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
47
#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
48
#define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
49

50 51 52
#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
				     KVM_DIRTY_LOG_INITIALLY_SET)

53 54
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

55
extern unsigned int kvm_sve_max_vl;
56
int kvm_arm_init_sve(void);
57

58
int __attribute_const__ kvm_target_cpu(void);
59
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
60
void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
61
int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
62
void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
63

64
struct kvm_vmid {
65 66 67
	/* The VMID generation used for the virt. memory system */
	u64    vmid_gen;
	u32    vmid;
68 69
};

70
struct kvm_s2_mmu {
71
	struct kvm_vmid vmid;
72

73 74 75 76 77 78 79 80 81 82 83
	/*
	 * 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;
84
	struct kvm_pgtable *pgt;
85

86 87 88
	/* The last vcpu id that ran on each physical CPU */
	int __percpu *last_vcpu_ran;

89 90 91 92 93 94 95 96 97
	struct kvm *kvm;
};

struct kvm_arch {
	struct kvm_s2_mmu mmu;

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

98 99 100
	/* The maximum number of vCPUs depends on the used GIC model */
	int max_vcpus;

101 102
	/* Interrupt controller */
	struct vgic_dist	vgic;
103 104 105

	/* Mandated version of PSCI */
	u32 psci_version;
106 107 108 109 110 111 112 113

	/*
	 * 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.
	 */
	bool return_nisv_io_abort_to_user;
114

115 116 117 118 119
	/*
	 * 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;
120
	unsigned int pmuver;
121 122 123 124 125 126
};

struct kvm_vcpu_fault_info {
	u32 esr_el2;		/* Hyp Syndrom Register */
	u64 far_el2;		/* Hyp Fault Address Register */
	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
127
	u64 disr_el1;		/* Deferred [SError] Status Register */
128 129
};

130
enum vcpu_sysreg {
131
	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
132 133 134 135 136
	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 */
137
	ZCR_EL1,	/* SVE Control */
138 139 140 141
	TTBR0_EL1,	/* Translation Table Base Register 0 */
	TTBR1_EL1,	/* Translation Table Base Register 1 */
	TCR_EL1,	/* Translation Control Register */
	ESR_EL1,	/* Exception Syndrome Register */
142 143
	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
144 145 146 147 148 149 150 151 152 153 154 155
	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 */
156
	DISR_EL1,	/* Deferred Interrupt Status Register */
157

158 159
	/* Performance Monitors Registers */
	PMCR_EL0,	/* Control Register */
160
	PMSELR_EL0,	/* Event Counter Selection Register */
161 162 163
	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
	PMCCNTR_EL0,	/* Cycle Counter Register */
164 165 166
	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
167
	PMCNTENSET_EL0,	/* Count Enable Set Register */
168
	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
169
	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
170
	PMSWINC_EL0,	/* Software Increment Register */
171
	PMUSERENR_EL0,	/* User Enable Register */
172

173 174 175 176 177 178 179 180 181 182 183 184
	/* 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,

185
	ELR_EL1,
186
	SP_EL1,
187
	SPSR_EL1,
188

189 190 191 192 193 194
	CNTVOFF_EL2,
	CNTV_CVAL_EL0,
	CNTV_CTL_EL0,
	CNTP_CVAL_EL0,
	CNTP_CTL_EL0,

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
	/* 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! */
};

/* 32bit mapping */
#define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
#define c0_CSSELR	(CSSELR_EL1 * 2)/* Cache Size Selection Register */
#define c1_SCTLR	(SCTLR_EL1 * 2)	/* System Control Register */
#define c1_ACTLR	(ACTLR_EL1 * 2)	/* Auxiliary Control Register */
#define c1_CPACR	(CPACR_EL1 * 2)	/* Coprocessor Access Control */
#define c2_TTBR0	(TTBR0_EL1 * 2)	/* Translation Table Base Register 0 */
#define c2_TTBR0_high	(c2_TTBR0 + 1)	/* TTBR0 top 32 bits */
#define c2_TTBR1	(TTBR1_EL1 * 2)	/* Translation Table Base Register 1 */
#define c2_TTBR1_high	(c2_TTBR1 + 1)	/* TTBR1 top 32 bits */
#define c2_TTBCR	(TCR_EL1 * 2)	/* Translation Table Base Control R. */
#define c3_DACR		(DACR32_EL2 * 2)/* Domain Access Control Register */
#define c5_DFSR		(ESR_EL1 * 2)	/* Data Fault Status Register */
#define c5_IFSR		(IFSR32_EL2 * 2)/* Instruction Fault Status Register */
#define c5_ADFSR	(AFSR0_EL1 * 2)	/* Auxiliary Data Fault Status R */
#define c5_AIFSR	(AFSR1_EL1 * 2)	/* Auxiliary Instr Fault Status R */
#define c6_DFAR		(FAR_EL1 * 2)	/* Data Fault Address Register */
#define c6_IFAR		(c6_DFAR + 1)	/* Instruction Fault Address Register */
#define c7_PAR		(PAR_EL1 * 2)	/* Physical Address Register */
#define c7_PAR_high	(c7_PAR + 1)	/* PAR top 32 bits */
#define c10_PRRR	(MAIR_EL1 * 2)	/* Primary Region Remap Register */
#define c10_NMRR	(c10_PRRR + 1)	/* Normal Memory Remap Register */
#define c12_VBAR	(VBAR_EL1 * 2)	/* Vector Base Address Register */
#define c13_CID		(CONTEXTIDR_EL1 * 2)	/* Context ID Register */
#define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
#define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
#define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
#define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */

#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)

#define NR_COPRO_REGS	(NR_SYS_REGS * 2)

245
struct kvm_cpu_context {
246 247
	struct user_pt_regs regs;	/* sp = sp_el0 */

248 249 250 251
	u64	spsr_abt;
	u64	spsr_und;
	u64	spsr_irq;
	u64	spsr_fiq;
252 253 254

	struct user_fpsimd_state fp_regs;

255 256
	union {
		u64 sys_regs[NR_SYS_REGS];
257
		u32 copro[NR_COPRO_REGS];
258
	};
259 260

	struct kvm_vcpu *__hyp_running_vcpu;
261 262
};

263 264 265 266 267
struct kvm_pmu_events {
	u32 events_host;
	u32 events_guest;
};

268 269
struct kvm_host_data {
	struct kvm_cpu_context host_ctxt;
270
	struct kvm_pmu_events pmu_events;
271 272
};

273 274 275 276 277 278 279
struct vcpu_reset_state {
	unsigned long	pc;
	unsigned long	r0;
	bool		be;
	bool		reset;
};

280 281
struct kvm_vcpu_arch {
	struct kvm_cpu_context ctxt;
282 283
	void *sve_state;
	unsigned int sve_max_vl;
284

285 286 287
	/* Stage 2 paging state used by the hardware on next switch */
	struct kvm_s2_mmu *hw_mmu;

288 289
	/* HYP configuration */
	u64 hcr_el2;
290
	u32 mdcr_el2;
291 292 293 294

	/* Exception Information */
	struct kvm_vcpu_fault_info fault;

295 296 297
	/* State of various workarounds, see kvm_asm.h for bit assignment */
	u64 workaround_flags;

298 299
	/* Miscellaneous vcpu state flags */
	u64 flags;
300

301 302 303 304 305
	/*
	 * 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
306 307 308 309
	 * 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.
310 311 312 313 314 315
	 *
	 * 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;
316
	struct kvm_guest_debug_arch external_debug_state;
317

318 319 320
	struct thread_info *host_thread_info;	/* hyp VA */
	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */

321 322 323 324 325 326
	struct {
		/* {Break,watch}point registers */
		struct kvm_guest_debug_arch regs;
		/* Statistical profiling extension */
		u64 pmscr_el1;
	} host_debug_state;
327 328 329 330

	/* VGIC state */
	struct vgic_cpu vgic_cpu;
	struct arch_timer_cpu timer_cpu;
331
	struct kvm_pmu pmu;
332 333 334 335 336 337

	/*
	 * Anything that is not used directly from assembly code goes
	 * here.
	 */

338 339 340 341 342 343 344 345 346 347 348
	/*
	 * 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;

349 350
	/* vcpu power-off state */
	bool power_off;
351

352 353 354
	/* Don't run the guest (internal implementation need) */
	bool pause;

355 356 357 358
	/* Cache some mmu pages needed inside spinlock regions */
	struct kvm_mmu_memory_cache mmu_page_cache;

	/* Target CPU and feature flags */
359
	int target;
360 361 362 363
	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);

	/* Detect first run of a vcpu */
	bool has_run_once;
364 365 366

	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
	u64 vsesr_el2;
367

368 369 370
	/* Additional reset state */
	struct vcpu_reset_state	reset_state;

371
	/* True when deferrable sysregs are loaded on the physical CPU,
372
	 * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
373
	bool sysregs_loaded_on_cpu;
374 375 376 377 378 379

	/* Guest PV state */
	struct {
		u64 last_steal;
		gpa_t base;
	} steal;
380 381
};

382 383 384 385
/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
#define vcpu_sve_pffr(vcpu) ((void *)((char *)((vcpu)->arch.sve_state) + \
				      sve_ffr_offset((vcpu)->arch.sve_max_vl)))

386 387 388 389 390 391 392 393 394 395 396 397 398 399
#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 = sve_vq_from_vl((vcpu)->arch.sve_max_vl);	\
		__size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq);		\
	}								\
									\
	__size_ret;							\
})

400 401
/* vcpu_arch flags field values: */
#define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
402 403 404
#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_IN_USE	(1 << 3) /* backup for host TIF_SVE */
405
#define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
406
#define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
407
#define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
408
#define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
409 410 411

#define vcpu_has_sve(vcpu) (system_supports_sve() && \
			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
412

413 414 415 416 417 418 419 420
#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
421

422
#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
423 424

/*
425 426 427 428 429
 * 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.
430
 */
431 432 433 434 435
#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)))
436

437
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
438
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
439

440 441 442 443
/*
 * CP14 and CP15 live in the same array, as they are backed by the
 * same system registers.
 */
444 445 446 447
#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)

#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
448 449

struct kvm_vm_stat {
450
	ulong remote_tlb_flush;
451 452 453
};

struct kvm_vcpu_stat {
454 455
	u64 halt_successful_poll;
	u64 halt_attempted_poll;
456 457
	u64 halt_poll_success_ns;
	u64 halt_poll_fail_ns;
458 459 460
	u64 halt_poll_invalid;
	u64 halt_wakeup;
	u64 hvc_exit_stat;
461 462 463 464 465
	u64 wfe_exit_stat;
	u64 wfi_exit_stat;
	u64 mmio_exit_user;
	u64 mmio_exit_kernel;
	u64 exits;
466 467
};

468
int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
469 470 471 472
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);
473 474
int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
475

476 477
int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
478 479 480

#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva_range(struct kvm *kvm,
481
			unsigned long start, unsigned long end, unsigned flags);
482
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
483 484
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
485

486 487
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
488

489
#define kvm_call_hyp_nvhe(f, ...)						\
490
	({								\
491 492 493 494 495 496 497
		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;							\
498 499
	})

500 501 502 503 504 505 506 507 508 509 510
/*
 * 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 {						\
511
			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
512 513 514 515 516 517 518 519 520 521 522
		}							\
	} while(0)

#define kvm_call_hyp_ret(f, ...)					\
	({								\
		typeof(f(__VA_ARGS__)) ret;				\
									\
		if (has_vhe()) {					\
			ret = f(__VA_ARGS__);				\
			isb();						\
		} else {						\
523
			ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__);	\
524 525 526 527
		}							\
									\
		ret;							\
	})
528

529
void force_vm_exit(const cpumask_t *mask);
530
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
531

532 533
int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
534

535 536 537 538
/* 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);

539 540
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu);
int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);
541

542 543 544
int kvm_perf_init(void);
int kvm_perf_teardown(void);

545
long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
546 547 548
gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
void kvm_update_stolen_time(struct kvm_vcpu *vcpu);

549
bool kvm_arm_pvtime_supported(void);
550 551 552 553 554 555 556
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);

557 558 559 560 561 562 563 564 565
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);
}
566

567 568
void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);

569 570
struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

571
DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
572

573
static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
574 575
{
	/* The host's MPIDR is immutable, so let's set it up at boot time */
576
	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
577 578
}

579
static inline bool kvm_arch_requires_vhe(void)
580 581 582 583 584 585 586 587
{
	/*
	 * The Arm architecture specifies that implementation of SVE
	 * requires VHE also to be implemented.  The KVM code for arm64
	 * relies on this when SVE is present:
	 */
	if (system_supports_sve())
		return true;
588 589

	return false;
590 591
}

592 593
void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);

594 595 596
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) {}
597
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
598

599 600 601
void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
602
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
603 604 605 606 607 608
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);
609

610 611 612 613 614 615
/* 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_ctxsync_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);

616 617
static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
{
618
	return (!has_vhe() && attr->exclude_host);
619 620
}

621 622
#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */
static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
623
{
624
	return kvm_arch_vcpu_run_map_fp(vcpu);
625
}
626 627 628

void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
void kvm_clr_pmu_events(u32 clr);
629

630 631
void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
632 633 634
#else
static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
static inline void kvm_clr_pmu_events(u32 clr) {}
635
#endif
636

637 638
void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
639

640
int kvm_set_ipa_limit(void);
641

642 643 644 645
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);

646
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
647

648
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
649 650 651 652
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)
653

654
#endif /* __ARM64_KVM_HOST_H__ */