kvm_host.h 20.8 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/bitmap.h>
15
#include <linux/types.h>
16
#include <linux/jump_label.h>
17
#include <linux/kvm_types.h>
18
#include <linux/percpu.h>
19
#include <asm/arch_gicv3.h>
20
#include <asm/barrier.h>
21
#include <asm/cpufeature.h>
22
#include <asm/cputype.h>
23
#include <asm/daifflags.h>
24
#include <asm/fpsimd.h>
25
#include <asm/kvm.h>
26
#include <asm/kvm_asm.h>
27
#include <asm/kvm_mmio.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

48 49
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

50
extern unsigned int kvm_sve_max_vl;
51
int kvm_arm_init_sve(void);
52

53
int __attribute_const__ kvm_target_cpu(void);
54
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
55
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
56
int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
57
void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
58

59
struct kvm_vmid {
60 61 62
	/* The VMID generation used for the virt. memory system */
	u64    vmid_gen;
	u32    vmid;
63 64 65 66
};

struct kvm_arch {
	struct kvm_vmid vmid;
67

68
	/* stage2 entry level table */
69
	pgd_t *pgd;
70
	phys_addr_t pgd_phys;
71

72 73
	/* VTCR_EL2 value for this VM */
	u64    vtcr;
74

75 76 77
	/* The last vcpu id that ran on each physical CPU */
	int __percpu *last_vcpu_ran;

78 79 80
	/* The maximum number of vCPUs depends on the used GIC model */
	int max_vcpus;

81 82
	/* Interrupt controller */
	struct vgic_dist	vgic;
83 84 85

	/* Mandated version of PSCI */
	u32 psci_version;
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102
};

#define KVM_NR_MEM_OBJS     40

/*
 * We don't want allocation failures within the mmu code, so we preallocate
 * enough memory for a single page fault in a cache.
 */
struct kvm_mmu_memory_cache {
	int nobjs;
	void *objects[KVM_NR_MEM_OBJS];
};

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 */
103
	u64 disr_el1;		/* Deferred [SError] Status Register */
104 105
};

106 107 108 109 110 111 112 113 114 115 116
/*
 * 0 is reserved as an invalid value.
 * Order should be kept in sync with the save/restore code.
 */
enum vcpu_sysreg {
	__INVALID_SYSREG__,
	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 */
117
	ZCR_EL1,	/* SVE Control */
118 119 120 121
	TTBR0_EL1,	/* Translation Table Base Register 0 */
	TTBR1_EL1,	/* Translation Table Base Register 1 */
	TCR_EL1,	/* Translation Control Register */
	ESR_EL1,	/* Exception Syndrome Register */
122 123
	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
124 125 126 127 128 129 130 131 132 133 134 135
	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 */
136
	DISR_EL1,	/* Deferred Interrupt Status Register */
137

138 139
	/* Performance Monitors Registers */
	PMCR_EL0,	/* Control Register */
140
	PMSELR_EL0,	/* Event Counter Selection Register */
141 142 143
	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
	PMCCNTR_EL0,	/* Cycle Counter Register */
144 145 146
	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
147
	PMCNTENSET_EL0,	/* Count Enable Set Register */
148
	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
149
	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
150
	PMSWINC_EL0,	/* Software Increment Register */
151
	PMUSERENR_EL0,	/* User Enable Register */
152

153 154 155 156 157 158 159 160 161 162 163 164
	/* 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,

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
	/* 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)

215 216
struct kvm_cpu_context {
	struct kvm_regs	gp_regs;
217 218
	union {
		u64 sys_regs[NR_SYS_REGS];
219
		u32 copro[NR_COPRO_REGS];
220
	};
221 222

	struct kvm_vcpu *__hyp_running_vcpu;
223 224
};

225 226 227 228 229
struct kvm_pmu_events {
	u32 events_host;
	u32 events_guest;
};

230 231
struct kvm_host_data {
	struct kvm_cpu_context host_ctxt;
232
	struct kvm_pmu_events pmu_events;
233 234 235
};

typedef struct kvm_host_data kvm_host_data_t;
236

237 238 239 240 241 242 243
struct vcpu_reset_state {
	unsigned long	pc;
	unsigned long	r0;
	bool		be;
	bool		reset;
};

244 245
struct kvm_vcpu_arch {
	struct kvm_cpu_context ctxt;
246 247
	void *sve_state;
	unsigned int sve_max_vl;
248 249 250

	/* HYP configuration */
	u64 hcr_el2;
251
	u32 mdcr_el2;
252 253 254 255

	/* Exception Information */
	struct kvm_vcpu_fault_info fault;

256 257 258
	/* State of various workarounds, see kvm_asm.h for bit assignment */
	u64 workaround_flags;

259 260
	/* Miscellaneous vcpu state flags */
	u64 flags;
261

262 263 264 265 266
	/*
	 * 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
267 268 269 270
	 * 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.
271 272 273 274 275 276
	 *
	 * 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;
277
	struct kvm_guest_debug_arch external_debug_state;
278

279
	/* Pointer to host CPU context */
280
	struct kvm_cpu_context *host_cpu_context;
281 282 283 284

	struct thread_info *host_thread_info;	/* hyp VA */
	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */

285 286 287 288 289 290
	struct {
		/* {Break,watch}point registers */
		struct kvm_guest_debug_arch regs;
		/* Statistical profiling extension */
		u64 pmscr_el1;
	} host_debug_state;
291 292 293 294

	/* VGIC state */
	struct vgic_cpu vgic_cpu;
	struct arch_timer_cpu timer_cpu;
295
	struct kvm_pmu pmu;
296 297 298 299 300 301

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

302 303 304 305 306 307 308 309 310 311 312
	/*
	 * 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;

313 314
	/* vcpu power-off state */
	bool power_off;
315

316 317 318
	/* Don't run the guest (internal implementation need) */
	bool pause;

319 320 321 322 323 324 325
	/* IO related fields */
	struct kvm_decode mmio_decode;

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

	/* Target CPU and feature flags */
326
	int target;
327 328 329 330
	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);

	/* Detect first run of a vcpu */
	bool has_run_once;
331 332 333

	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
	u64 vsesr_el2;
334

335 336 337
	/* Additional reset state */
	struct vcpu_reset_state	reset_state;

338 339 340
	/* True when deferrable sysregs are loaded on the physical CPU,
	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
	bool sysregs_loaded_on_cpu;
341 342
};

343 344 345 346
/* 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)))

347 348 349 350 351 352 353 354 355 356 357 358 359 360
#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;							\
})

361 362
/* vcpu_arch flags field values: */
#define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
363 364 365
#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 */
366
#define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
367
#define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
368
#define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
369
#define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
370 371 372

#define vcpu_has_sve(vcpu) (system_supports_sve() && \
			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
373

374 375 376 377
#define vcpu_has_ptrauth(vcpu)	((system_supports_address_auth() || \
				  system_supports_generic_auth()) && \
				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))

378
#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
379 380 381 382 383 384 385 386 387

/*
 * Only use __vcpu_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 __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])

388
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
389
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
390

391 392 393 394 395 396
/*
 * CP14 and CP15 live in the same array, as they are backed by the
 * same system registers.
 */
#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
397 398

struct kvm_vm_stat {
399
	ulong remote_tlb_flush;
400 401 402
};

struct kvm_vcpu_stat {
403 404 405 406 407
	u64 halt_successful_poll;
	u64 halt_attempted_poll;
	u64 halt_poll_invalid;
	u64 halt_wakeup;
	u64 hvc_exit_stat;
408 409 410 411 412
	u64 wfe_exit_stat;
	u64 wfi_exit_stat;
	u64 mmio_exit_user;
	u64 mmio_exit_kernel;
	u64 exits;
413 414
};

415
int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
416 417 418 419
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);
420 421
int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
422

423 424
int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
425 426 427 428

#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva_range(struct kvm *kvm,
			unsigned long start, unsigned long end);
429
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
430 431
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
432 433

struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
434
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
435 436
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
437

438
u64 __kvm_call_hyp(void *hypfn, ...);
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

/*
 * 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(kvm_ksym_ref(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(kvm_ksym_ref(f),		\
					     ##__VA_ARGS__);		\
		}							\
									\
		ret;							\
	})
469

470
void force_vm_exit(const cpumask_t *mask);
471
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
472 473 474

int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
		int exception_index);
475 476
void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
		       int exception_index);
477 478 479 480

int kvm_perf_init(void);
int kvm_perf_teardown(void);

481 482
void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);

483 484
struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

485
DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
486

487
static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
488 489
{
	/* The host's MPIDR is immutable, so let's set it up at boot time */
490
	cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
491 492
}

493 494
void __kvm_enable_ssbs(void);

M
Marc Zyngier 已提交
495
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
496 497 498
				       unsigned long hyp_stack_ptr,
				       unsigned long vector_ptr)
{
499 500 501 502 503
	/*
	 * Calculate the raw per-cpu offset without a translation from the
	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
	 * so that we can use adr_l to access per-cpu variables in EL2.
	 */
504 505
	u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_data) -
			 (u64)kvm_ksym_ref(kvm_host_data));
506

507
	/*
508 509 510 511
	 * Call initialization code, and switch to the full blown HYP code.
	 * If the cpucaps haven't been finalized yet, something has gone very
	 * wrong, and hyp will crash and burn when it uses any
	 * cpus_have_const_cap() wrapper.
512
	 */
513
	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
514
	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
515 516 517 518 519 520 521 522 523

	/*
	 * Disabling SSBD on a non-VHE system requires us to enable SSBS
	 * at EL2.
	 */
	if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
		kvm_call_hyp(__kvm_enable_ssbs);
	}
524
}
525

526
static inline bool kvm_arch_requires_vhe(void)
527 528 529 530 531 532 533 534
{
	/*
	 * 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;
535

536 537 538 539
	/* Some implementations have defects that confine them to VHE */
	if (cpus_have_cap(ARM64_WORKAROUND_1165522))
		return true;

540
	return false;
541 542
}

543 544
void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);

545 546 547
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) {}
548
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
549

550 551 552
void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
553
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
554 555 556 557 558 559
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);
560

561
static inline void __cpu_init_stage2(void) {}
562

563 564 565 566 567 568
/* 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);

569 570
static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
{
571
	return (!has_vhe() && attr->exclude_host);
572 573
}

574 575
#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)
576
{
577
	return kvm_arch_vcpu_run_map_fp(vcpu);
578
}
579 580 581

void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
void kvm_clr_pmu_events(u32 clr);
582

583 584
void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
585 586 587
#else
static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
static inline void kvm_clr_pmu_events(u32 clr) {}
588
#endif
589

590 591 592
static inline void kvm_arm_vhe_guest_enter(void)
{
	local_daif_mask();
593 594 595 596 597 598

	/*
	 * Having IRQs masked via PMR when entering the guest means the GIC
	 * will not signal the CPU of interrupts of lower priority, and the
	 * only way to get out will be via guest exceptions.
	 * Naturally, we want to avoid this.
599 600 601
	 *
	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
602
	 */
603
	if (system_uses_irq_prio_masking())
604
		dsb(sy);
605 606 607 608
}

static inline void kvm_arm_vhe_guest_exit(void)
{
609 610 611 612
	/*
	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
	 * and the GIC PMR if the host is using IRQ priorities.
	 */
613
	local_daif_restore(DAIF_PROCCTX_NOIRQ);
614 615 616 617 618 619 620

	/*
	 * When we exit from the guest we change a number of CPU configuration
	 * parameters, such as traps.  Make sure these changes take effect
	 * before running the host or additional guests.
	 */
	isb();
621
}
622

623 624 625 626 627
#define KVM_BP_HARDEN_UNKNOWN		-1
#define KVM_BP_HARDEN_WA_NEEDED		0
#define KVM_BP_HARDEN_NOT_REQUIRED	1

static inline int kvm_arm_harden_branch_predictor(void)
628
{
629 630 631 632 633 634 635 636 637
	switch (get_spectre_v2_workaround_state()) {
	case ARM64_BP_HARDEN_WA_NEEDED:
		return KVM_BP_HARDEN_WA_NEEDED;
	case ARM64_BP_HARDEN_NOT_REQUIRED:
		return KVM_BP_HARDEN_NOT_REQUIRED;
	case ARM64_BP_HARDEN_UNKNOWN:
	default:
		return KVM_BP_HARDEN_UNKNOWN;
	}
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
#define KVM_SSBD_UNKNOWN		-1
#define KVM_SSBD_FORCE_DISABLE		0
#define KVM_SSBD_KERNEL		1
#define KVM_SSBD_FORCE_ENABLE		2
#define KVM_SSBD_MITIGATED		3

static inline int kvm_arm_have_ssbd(void)
{
	switch (arm64_get_ssbd_state()) {
	case ARM64_SSBD_FORCE_DISABLE:
		return KVM_SSBD_FORCE_DISABLE;
	case ARM64_SSBD_KERNEL:
		return KVM_SSBD_KERNEL;
	case ARM64_SSBD_FORCE_ENABLE:
		return KVM_SSBD_FORCE_ENABLE;
	case ARM64_SSBD_MITIGATED:
		return KVM_SSBD_MITIGATED;
	case ARM64_SSBD_UNKNOWN:
	default:
		return KVM_SSBD_UNKNOWN;
	}
}

663 664 665
void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);

666 667
void kvm_set_ipa_limit(void);

668 669 670 671
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);

672
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
673

674
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
675 676 677 678
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)
679

680
#endif /* __ARM64_KVM_HOST_H__ */