kvm_host.h 18.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 * 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>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#ifndef __ARM64_KVM_HOST_H__
#define __ARM64_KVM_HOST_H__

25
#include <linux/bitmap.h>
26
#include <linux/types.h>
27
#include <linux/jump_label.h>
28
#include <linux/kvm_types.h>
29
#include <linux/percpu.h>
30
#include <asm/arch_gicv3.h>
31
#include <asm/barrier.h>
32
#include <asm/cpufeature.h>
33
#include <asm/daifflags.h>
34
#include <asm/fpsimd.h>
35
#include <asm/kvm.h>
36
#include <asm/kvm_asm.h>
37
#include <asm/kvm_mmio.h>
38
#include <asm/smp_plat.h>
39
#include <asm/thread_info.h>
40

41 42
#define __KVM_HAVE_ARCH_INTC_INITIALIZED

43
#define KVM_USER_MEM_SLOTS 512
44
#define KVM_HALT_POLL_NS_DEFAULT 500000
45 46 47

#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
48
#include <kvm/arm_pmu.h>
49

50 51
#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS

52
#define KVM_VCPU_MAX_FEATURES 4
53

54
#define KVM_REQ_SLEEP \
55
	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
56
#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
57
#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
58

59 60
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

61
int __attribute_const__ kvm_target_cpu(void);
62
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
63
int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
64
void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
65

66
struct kvm_vmid {
67 68 69
	/* The VMID generation used for the virt. memory system */
	u64    vmid_gen;
	u32    vmid;
70 71 72 73
};

struct kvm_arch {
	struct kvm_vmid vmid;
74

75
	/* stage2 entry level table */
76
	pgd_t *pgd;
77
	phys_addr_t pgd_phys;
78

79 80
	/* VTCR_EL2 value for this VM */
	u64    vtcr;
81

82 83 84
	/* The last vcpu id that ran on each physical CPU */
	int __percpu *last_vcpu_ran;

85 86 87
	/* The maximum number of vCPUs depends on the used GIC model */
	int max_vcpus;

88 89
	/* Interrupt controller */
	struct vgic_dist	vgic;
90 91 92

	/* Mandated version of PSCI */
	u32 psci_version;
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
};

#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 */
110
	u64 disr_el1;		/* Deferred [SError] Status Register */
111 112
};

113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
/*
 * 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 */
	TTBR0_EL1,	/* Translation Table Base Register 0 */
	TTBR1_EL1,	/* Translation Table Base Register 1 */
	TCR_EL1,	/* Translation Control Register */
	ESR_EL1,	/* Exception Syndrome Register */
128 129
	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
130 131 132 133 134 135 136 137 138 139 140 141
	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 */
142
	DISR_EL1,	/* Deferred Interrupt Status Register */
143

144 145
	/* Performance Monitors Registers */
	PMCR_EL0,	/* Control Register */
146
	PMSELR_EL0,	/* Event Counter Selection Register */
147 148 149
	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
	PMCCNTR_EL0,	/* Cycle Counter Register */
150 151 152
	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
153
	PMCNTENSET_EL0,	/* Count Enable Set Register */
154
	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
155
	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
156
	PMSWINC_EL0,	/* Software Increment Register */
157
	PMUSERENR_EL0,	/* User Enable Register */
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
	/* 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)

209 210
struct kvm_cpu_context {
	struct kvm_regs	gp_regs;
211 212
	union {
		u64 sys_regs[NR_SYS_REGS];
213
		u32 copro[NR_COPRO_REGS];
214
	};
215 216

	struct kvm_vcpu *__hyp_running_vcpu;
217 218 219 220
};

typedef struct kvm_cpu_context kvm_cpu_context_t;

221 222 223 224 225 226 227
struct vcpu_reset_state {
	unsigned long	pc;
	unsigned long	r0;
	bool		be;
	bool		reset;
};

228 229 230 231 232
struct kvm_vcpu_arch {
	struct kvm_cpu_context ctxt;

	/* HYP configuration */
	u64 hcr_el2;
233
	u32 mdcr_el2;
234 235 236 237

	/* Exception Information */
	struct kvm_vcpu_fault_info fault;

238 239 240
	/* State of various workarounds, see kvm_asm.h for bit assignment */
	u64 workaround_flags;

241 242
	/* Miscellaneous vcpu state flags */
	u64 flags;
243

244 245 246 247 248
	/*
	 * 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
249 250 251 252
	 * 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.
253 254 255 256 257 258
	 *
	 * 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;
259
	struct kvm_guest_debug_arch external_debug_state;
260

261 262
	/* Pointer to host CPU context */
	kvm_cpu_context_t *host_cpu_context;
263 264 265 266

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

267 268 269 270 271 272
	struct {
		/* {Break,watch}point registers */
		struct kvm_guest_debug_arch regs;
		/* Statistical profiling extension */
		u64 pmscr_el1;
	} host_debug_state;
273 274 275 276

	/* VGIC state */
	struct vgic_cpu vgic_cpu;
	struct arch_timer_cpu timer_cpu;
277
	struct kvm_pmu pmu;
278 279 280 281 282 283

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

284 285 286 287 288 289 290 291 292 293 294
	/*
	 * 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;

295 296
	/* vcpu power-off state */
	bool power_off;
297

298 299 300
	/* Don't run the guest (internal implementation need) */
	bool pause;

301 302 303 304 305 306 307
	/* 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 */
308
	int target;
309 310 311 312
	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);

	/* Detect first run of a vcpu */
	bool has_run_once;
313 314 315

	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
	u64 vsesr_el2;
316

317 318 319
	/* Additional reset state */
	struct vcpu_reset_state	reset_state;

320 321 322
	/* 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;
323 324
};

325 326
/* vcpu_arch flags field values: */
#define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
327 328 329
#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 */
330
#define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
331 332 333 334
#define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */

#define vcpu_has_sve(vcpu) (system_supports_sve() && \
			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
335

336
#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
337 338 339 340 341 342 343 344 345

/*
 * 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)])

346
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
347
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
348

349 350 351 352 353 354
/*
 * 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)])
355 356

struct kvm_vm_stat {
357
	ulong remote_tlb_flush;
358 359 360
};

struct kvm_vcpu_stat {
361 362 363 364 365
	u64 halt_successful_poll;
	u64 halt_attempted_poll;
	u64 halt_poll_invalid;
	u64 halt_wakeup;
	u64 hvc_exit_stat;
366 367 368 369 370
	u64 wfe_exit_stat;
	u64 wfi_exit_stat;
	u64 mmio_exit_user;
	u64 mmio_exit_kernel;
	u64 exits;
371 372
};

373
int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
374 375 376 377
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);
378 379
int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
380

381 382
int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
			      struct kvm_vcpu_events *events);
383 384 385 386

#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva_range(struct kvm *kvm,
			unsigned long start, unsigned long end);
387
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
388 389
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
390 391

struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
392
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
393 394
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
395

396
u64 __kvm_call_hyp(void *hypfn, ...);
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

/*
 * 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;							\
	})
427

428
void force_vm_exit(const cpumask_t *mask);
429
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
430 431 432

int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
		int exception_index);
433 434
void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
		       int exception_index);
435 436 437 438

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

439 440
void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);

441 442
struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

443 444
DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);

445 446 447 448 449 450 451
static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
					     int cpu)
{
	/* The host's MPIDR is immutable, so let's set it up at boot time */
	cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu);
}

452 453
void __kvm_enable_ssbs(void);

M
Marc Zyngier 已提交
454
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
455 456 457
				       unsigned long hyp_stack_ptr,
				       unsigned long vector_ptr)
{
458 459 460 461 462 463 464
	/*
	 * 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.
	 */
	u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_cpu_state) -
			 (u64)kvm_ksym_ref(kvm_host_cpu_state));
465

466
	/*
467 468 469 470
	 * 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.
471
	 */
472
	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
473
	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
474 475 476 477 478 479 480 481 482

	/*
	 * 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);
	}
483
}
484

485
static inline bool kvm_arch_requires_vhe(void)
486 487 488 489 490 491 492 493
{
	/*
	 * 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;
494

495 496 497 498
	/* Some implementations have defects that confine them to VHE */
	if (cpus_have_cap(ARM64_WORKAROUND_1165522))
		return true;

499
	return false;
500 501
}

502 503 504 505
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
506
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
507

508 509 510
void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
511
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
512 513 514 515 516 517
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);
518

519
static inline void __cpu_init_stage2(void) {}
520

521 522 523 524 525 526 527 528
/* 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);

#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)
529
{
530
	return kvm_arch_vcpu_run_map_fp(vcpu);
531
}
532
#endif
533

534 535 536
static inline void kvm_arm_vhe_guest_enter(void)
{
	local_daif_mask();
537 538 539 540 541 542 543 544 545 546 547

	/*
	 * 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.
	 */
	if (system_uses_irq_prio_masking()) {
		gic_write_pmr(GIC_PRIO_IRQON);
		dsb(sy);
	}
548 549 550 551
}

static inline void kvm_arm_vhe_guest_exit(void)
{
552 553 554 555
	/*
	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
	 * and the GIC PMR if the host is using IRQ priorities.
	 */
556
	local_daif_restore(DAIF_PROCCTX_NOIRQ);
557 558 559 560 561 562 563

	/*
	 * 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();
564
}
565 566 567 568 569 570

static inline bool kvm_arm_harden_branch_predictor(void)
{
	return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
}

571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
#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;
	}
}

594 595 596
void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);

597 598
void kvm_set_ipa_limit(void);

599 600 601 602
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);

603
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
604

605
#endif /* __ARM64_KVM_HOST_H__ */