Merge branch 'kvm-arm64/pre-nv-5.9' into kvmarm-master/next-WIP

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/cpucaps.h

@@ -62,7 +62,8 @@
 #define ARM64_HAS_GENERIC_AUTH			52
 #define ARM64_HAS_32BIT_EL1			53
 #define ARM64_BTI				54
+#define ARM64_HAS_ARMv8_4_TTL			55
 
-#define ARM64_NCAPS				55
+#define ARM64_NCAPS				56
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/kvm_asm.h

@@ -95,6 +95,7 @@ extern void *__nvhe_undefined_symbol;
 
 struct kvm;
 struct kvm_vcpu;
+struct kvm_s2_mmu;
 
 DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
@@ -108,9 +109,10 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #endif
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				     int level);
+extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 

arch/arm64/include/asm/kvm_emulate.h

@@ -124,33 +124,12 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
 
 static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
-}
-
-static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1;
-}
-
-static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		return read_sysreg_el1(SYS_ELR);
-	else
-		return *__vcpu_elr_el1(vcpu);
-}
-
-static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		write_sysreg_el1(v, SYS_ELR);
-	else
-		*__vcpu_elr_el1(vcpu) = v;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
 }
 
 static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
 }
 
 static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
@@ -179,14 +158,14 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
-	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs[reg_num];
 }
 
 static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 				unsigned long val)
 {
 	if (reg_num != 31)
-		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
+		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
 static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
@@ -197,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+		return __vcpu_sys_reg(vcpu, SPSR_EL1);
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -210,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
 }
 
 /*
@@ -519,11 +498,11 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
 static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
-	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
+	vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR);
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 
-	write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR);
+	write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR);
 	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
 }
 

arch/arm64/include/asm/kvm_host.h

@@ -66,19 +66,34 @@ struct kvm_vmid {
 	u32    vmid;
 };
 
-struct kvm_arch {
+struct kvm_s2_mmu {
 	struct kvm_vmid vmid;
 
-	/* stage2 entry level table */
-	pgd_t *pgd;
-	phys_addr_t pgd_phys;
-
-	/* VTCR_EL2 value for this VM */
-	u64    vtcr;
+	/*
+	 * 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.
+	 */
+	pgd_t		*pgd;
+	phys_addr_t	pgd_phys;
 
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
+	struct kvm *kvm;
+};
+
+struct kvm_arch {
+	struct kvm_s2_mmu mmu;
+
+	/* VTCR_EL2 value for this VM */
+	u64    vtcr;
+
 	/* The maximum number of vCPUs depends on the used GIC model */
 	int max_vcpus;
 
@@ -170,6 +185,16 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
+	ELR_EL1,
+	SP_EL1,
+	SPSR_EL1,
+
+	CNTVOFF_EL2,
+	CNTV_CVAL_EL0,
+	CNTV_CTL_EL0,
+	CNTP_CVAL_EL0,
+	CNTP_CTL_EL0,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -221,7 +246,15 @@ enum vcpu_sysreg {
 #define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
 struct kvm_cpu_context {
-	struct kvm_regs	gp_regs;
+	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;
+
 	union {
 		u64 sys_regs[NR_SYS_REGS];
 		u32 copro[NR_COPRO_REGS];
@@ -254,6 +287,9 @@ struct kvm_vcpu_arch {
 	void *sve_state;
 	unsigned int sve_max_vl;
 
+	/* Stage 2 paging state used by the hardware on next switch */
+	struct kvm_s2_mmu *hw_mmu;
+
 	/* HYP configuration */
 	u64 hcr_el2;
 	u32 mdcr_el2;
@@ -384,15 +420,20 @@ struct kvm_vcpu_arch {
 				  system_supports_generic_auth()) && \
 				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))
 
-#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
+#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
 
 /*
- * 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.
+ * 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 __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
+#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);
@@ -538,7 +579,7 @@ DECLARE_PER_CPU(kvm_host_data_t, 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 */
-	cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
+	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
 }
 
 static inline bool kvm_arch_requires_vhe(void)

arch/arm64/include/asm/kvm_mmu.h

@@ -134,8 +134,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
-int kvm_alloc_stage2_pgd(struct kvm *kvm);
-void kvm_free_stage2_pgd(struct kvm *kvm);
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
@@ -577,13 +577,13 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
 	return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
 }
 
-static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
+static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 {
-	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	struct kvm_vmid *vmid = &mmu->vmid;
 	u64 vmid_field, baddr;
 	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
 
-	baddr = kvm->arch.pgd_phys;
+	baddr = mmu->pgd_phys;
 	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
@@ -592,10 +592,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
  * Must be called from hyp code running at EL2 with an updated VTTBR
  * and interrupts disabled.
  */
-static __always_inline void __load_guest_stage2(struct kvm *kvm)
+static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
 {
-	write_sysreg(kvm->arch.vtcr, vtcr_el2);
-	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
+	write_sysreg(kern_hyp_va(mmu->kvm)->arch.vtcr, vtcr_el2);
+	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
 
 	/*
 	 * ARM errata 1165522 and 1530923 require the actual execution of the

arch/arm64/include/asm/pgtable-hwdef.h

@@ -178,10 +178,12 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 #define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
+#define PTE_S2_SW_RESVD		(_AT(pteval_t, 15) << 55) /* Reserved for SW */
 
 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
+#define PMD_S2_SW_RESVD		(_AT(pmdval_t, 15) << 55) /* Reserved for SW */
 
 #define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
 #define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */

arch/arm64/include/asm/stage2_pgtable.h

@@ -256,4 +256,13 @@ stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+/*
+ * Level values for the ARMv8.4-TTL extension, mapping PUD/PMD/PTE and
+ * the architectural page-table level.
+ */
+#define S2_NO_LEVEL_HINT	0
+#define S2_PUD_LEVEL		1
+#define S2_PMD_LEVEL		2
+#define S2_PTE_LEVEL		3
+
 #endif	/* __ARM64_S2_PGTABLE_H_ */

arch/arm64/include/asm/sysreg.h

@@ -746,6 +746,7 @@
 
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_E0PD_SHIFT		60
+#define ID_AA64MMFR2_TTL_SHIFT		48
 #define ID_AA64MMFR2_FWB_SHIFT		40
 #define ID_AA64MMFR2_AT_SHIFT		32
 #define ID_AA64MMFR2_LVA_SHIFT		16

arch/arm64/include/asm/tlbflush.h

@@ -10,6 +10,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bitfield.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 #include <asm/cputype.h>
@@ -59,6 +60,50 @@
 		__ta;						\
 	})
 
+/*
+ * Level-based TLBI operations.
+ *
+ * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
+ * the level at which the invalidation must take place. If the level is
+ * wrong, no invalidation may take place. In the case where the level
+ * cannot be easily determined, a 0 value for the level parameter will
+ * perform a non-hinted invalidation.
+ *
+ * For Stage-2 invalidation, use the level values provided to that effect
+ * in asm/stage2_pgtable.h.
+ */
+#define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
+#define TLBI_TTL_TG_4K		1
+#define TLBI_TTL_TG_16K		2
+#define TLBI_TTL_TG_64K		3
+
+#define __tlbi_level(op, addr, level)					\
+	do {								\
+		u64 arg = addr;						\
+									\
+		if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&	\
+		    level) {						\
+			u64 ttl = level & 3;				\
+									\
+			switch (PAGE_SIZE) {				\
+			case SZ_4K:					\
+				ttl |= TLBI_TTL_TG_4K << 2;		\
+				break;					\
+			case SZ_16K:					\
+				ttl |= TLBI_TTL_TG_16K << 2;		\
+				break;					\
+			case SZ_64K:					\
+				ttl |= TLBI_TTL_TG_64K << 2;		\
+				break;					\
+			}						\
+									\
+			arg &= ~TLBI_TTL_MASK;				\
+			arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);		\
+		}							\
+									\
+		__tlbi(op, arg);					\
+	} while(0)
+
 /*
  *	TLB Invalidation
  *	================

arch/arm64/kernel/asm-offsets.c

@@ -102,13 +102,12 @@ int main(void)
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
-  DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
   DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
   DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
   DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
   DEFINE(CPU_APDBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1]));
   DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
-  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
   DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
 #endif

arch/arm64/kernel/cpufeature.c

@@ -323,6 +323,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_TTL_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
@@ -1882,6 +1883,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = cpu_has_fwb,
 	},
+	{
+		.desc = "ARMv8.4 Translation Table Level",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_ARMv8_4_TTL,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_TTL_SHIFT,
+		.min_field_value = 1,
+		.matches = has_cpuid_feature,
+	},
 #ifdef CONFIG_ARM64_HW_AFDBM
 	{
 		/*

arch/arm64/kvm/arch_timer.c

@@ -51,6 +51,93 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 			      struct arch_timer_context *timer,
 			      enum kvm_arch_timer_regs treg);
 
+u32 timer_get_ctl(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+u64 timer_get_cval(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+static u64 timer_get_offset(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+	default:
+		return 0;
+	}
+}
+
+static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset;
+		break;
+	default:
+		WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt));
+	}
+}
+
 u64 kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -124,8 +211,8 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
 {
 	u64 cval, now;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	if (now < cval) {
 		u64 ns;
@@ -144,8 +231,8 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
 {
 	WARN_ON(timer_ctx && timer_ctx->loaded);
 	return timer_ctx &&
-	       !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
-		(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE);
+		((timer_get_ctl(timer_ctx) &
+		  (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE);
 }
 
 /*
@@ -256,8 +343,8 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 	if (!kvm_timer_irq_can_fire(timer_ctx))
 		return false;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	return cval <= now;
 }
@@ -350,8 +437,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTV_CTL);
@@ -359,8 +446,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 		break;
 	case TIMER_PTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTP_CTL);
@@ -429,14 +516,14 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
 		break;
 	case TIMER_PTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
 		break;
 	case NR_KVM_TIMERS:
 		BUG();
@@ -528,7 +615,7 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 		kvm_timer_vcpu_load_nogic(vcpu);
 	}
 
-	set_cntvoff(map.direct_vtimer->cntvoff);
+	set_cntvoff(timer_get_offset(map.direct_vtimer));
 
 	kvm_timer_unblocking(vcpu);
 
@@ -615,7 +702,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
 	}
 }
 
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 
@@ -639,8 +726,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	 * resets the timer to be disabled and unmasked and is compliant with
 	 * the ARMv7 architecture.
 	 */
-	vcpu_vtimer(vcpu)->cnt_ctl = 0;
-	vcpu_ptimer(vcpu)->cnt_ctl = 0;
+	timer_set_ctl(vcpu_vtimer(vcpu), 0);
+	timer_set_ctl(vcpu_ptimer(vcpu), 0);
 
 	if (timer->enabled) {
 		kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu));
@@ -668,13 +755,13 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
 
 	mutex_lock(&kvm->lock);
 	kvm_for_each_vcpu(i, tmp, kvm)
-		vcpu_vtimer(tmp)->cntvoff = cntvoff;
+		timer_set_offset(vcpu_vtimer(tmp), cntvoff);
 
 	/*
 	 * When called from the vcpu create path, the CPU being created is not
 	 * included in the loop above, so we just set it here as well.
 	 */
-	vcpu_vtimer(vcpu)->cntvoff = cntvoff;
+	timer_set_offset(vcpu_vtimer(vcpu), cntvoff);
 	mutex_unlock(&kvm->lock);
 }
 
@@ -684,9 +771,12 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
+	vtimer->vcpu = vcpu;
+	ptimer->vcpu = vcpu;
+
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
-	ptimer->cntvoff = 0;
+	timer_set_offset(ptimer, 0);
 
 	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
@@ -704,9 +794,6 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vtimer->host_timer_irq_flags = host_vtimer_irq_flags;
 	ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
-
-	vtimer->vcpu = vcpu;
-	ptimer->vcpu = vcpu;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -756,10 +843,12 @@ static u64 read_timer_ctl(struct arch_timer_context *timer)
 	 * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
 	 * regardless of ENABLE bit for our implementation convenience.
 	 */
+	u32 ctl = timer_get_ctl(timer);
+
 	if (!kvm_timer_compute_delta(timer))
-		return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT;
-	else
-		return timer->cnt_ctl;
+		ctl |= ARCH_TIMER_CTRL_IT_STAT;
+
+	return ctl;
 }
 
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
@@ -795,8 +884,8 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
-		val &= lower_32_bits(val);
+		val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer);
+		val = lower_32_bits(val);
 		break;
 
 	case TIMER_REG_CTL:
@@ -804,11 +893,11 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 		break;
 
 	case TIMER_REG_CVAL:
-		val = timer->cnt_cval;
+		val = timer_get_cval(timer);
 		break;
 
 	case TIMER_REG_CNT:
-		val = kvm_phys_timer_read() - timer->cntvoff;
+		val = kvm_phys_timer_read() - timer_get_offset(timer);
 		break;
 
 	default:
@@ -842,15 +931,15 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val;
+		timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val);
 		break;
 
 	case TIMER_REG_CTL:
-		timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT;
+		timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT);
 		break;
 
 	case TIMER_REG_CVAL:
-		timer->cnt_cval = val;
+		timer_set_cval(timer, val);
 		break;
 
 	default:

arch/arm64/kvm/arm.c

@@ -106,22 +106,15 @@ static int kvm_arm_default_max_vcpus(void)
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	int ret, cpu;
+	int ret;
 
 	ret = kvm_arm_setup_stage2(kvm, type);
 	if (ret)
 		return ret;
 
-	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
-	if (!kvm->arch.last_vcpu_ran)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
-
-	ret = kvm_alloc_stage2_pgd(kvm);
+	ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu);
 	if (ret)
-		goto out_fail_alloc;
+		return ret;
 
 	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
@@ -129,18 +122,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_vgic_early_init(kvm);
 
-	/* Mark the initial VMID generation invalid */
-	kvm->arch.vmid.vmid_gen = 0;
-
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
 	return ret;
 out_free_stage2_pgd:
-	kvm_free_stage2_pgd(kvm);
-out_fail_alloc:
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 	return ret;
 }
 
@@ -160,9 +147,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 
 	kvm_vgic_destroy(kvm);
 
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
-
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_vcpu_destroy(kvm->vcpus[i]);
@@ -279,6 +263,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
+	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+
 	err = kvm_vgic_vcpu_init(vcpu);
 	if (err)
 		return err;
@@ -334,16 +320,18 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
-	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+	mmu = vcpu->arch.hw_mmu;
+	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 
@@ -680,7 +668,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		cond_resched();
 
-		update_vmid(&vcpu->kvm->arch.vmid);
+		update_vmid(&vcpu->arch.hw_mmu->vmid);
 
 		check_vcpu_requests(vcpu);
 
@@ -729,13 +717,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 
-		if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) ||
+		if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
 			kvm_pmu_sync_hwstate(vcpu);
 			if (static_branch_unlikely(&userspace_irqchip_in_use))
-				kvm_timer_sync_hwstate(vcpu);
+				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
 			preempt_enable();
@@ -780,7 +768,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * timer virtual interrupt state.
 		 */
 		if (static_branch_unlikely(&userspace_irqchip_in_use))
-			kvm_timer_sync_hwstate(vcpu);
+			kvm_timer_sync_user(vcpu);
 
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 

arch/arm64/kvm/fpsimd.c

@@ -85,7 +85,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs,
+		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl);
 
@@ -109,12 +109,10 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	local_irq_save(flags);
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1];
-
 		fpsimd_save_and_flush_cpu_state();
 
 		if (guest_has_sve)
-			*guest_zcr = read_sysreg_s(SYS_ZCR_EL12);
+			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_s(SYS_ZCR_EL12);
 	} else if (host_has_sve) {
 		/*
 		 * The FPSIMD/SVE state in the CPU has not been touched, and we

arch/arm64/kvm/guest.c

@@ -101,19 +101,69 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 	return size;
 }
 
-static int validate_core_offset(const struct kvm_vcpu *vcpu,
-				const struct kvm_one_reg *reg)
+static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u64 off = core_reg_offset_from_id(reg->id);
 	int size = core_reg_size_from_offset(vcpu, off);
 
 	if (size < 0)
-		return -EINVAL;
+		return NULL;
 
 	if (KVM_REG_SIZE(reg->id) != size)
-		return -EINVAL;
+		return NULL;
 
-	return 0;
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		off -= KVM_REG_ARM_CORE_REG(regs.regs[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.regs.regs[off];
+
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return &vcpu->arch.ctxt.regs.sp;
+
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return &vcpu->arch.ctxt.regs.pc;
+
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return &vcpu->arch.ctxt.regs.pstate;
+
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1);
+
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1);
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
+		return &vcpu->arch.ctxt.spsr_abt;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]):
+		return &vcpu->arch.ctxt.spsr_und;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]):
+		return &vcpu->arch.ctxt.spsr_irq;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]):
+		return &vcpu->arch.ctxt.spsr_fiq;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]);
+		off /= 4;
+		return &vcpu->arch.ctxt.fp_regs.vregs[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return &vcpu->arch.ctxt.fp_regs.fpsr;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return &vcpu->arch.ctxt.fp_regs.fpcr;
+
+	default:
+		return NULL;
+	}
 }
 
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -125,8 +175,8 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	 * off the index in the "array".
 	 */
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
+	void *addr;
 	u32 off;
 
 	/* Our ID is an index into the kvm_regs struct. */
@@ -135,10 +185,11 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
-	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+	if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
 	return 0;
@@ -147,10 +198,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
 	__uint128_t tmp;
-	void *valp = &tmp;
+	void *valp = &tmp, *addr;
 	u64 off;
 	int err = 0;
 
@@ -160,7 +210,8 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
@@ -198,7 +249,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		}
 	}
 
-	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+	memcpy(addr, valp, KVM_REG_SIZE(reg->id));
 
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i;

arch/arm64/kvm/hyp/entry.S

@@ -16,8 +16,7 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_ptrauth.h>
 
-#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
-#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text

arch/arm64/kvm/hyp/include/hyp/debug-sr.h

@@ -88,9 +88,8 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static inline void __debug_save_state(struct kvm_vcpu *vcpu,
-				      struct kvm_guest_debug_arch *dbg,
-				      struct kvm_cpu_context *ctxt)
+static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
+			       struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -104,12 +103,11 @@ static inline void __debug_save_state(struct kvm_vcpu *vcpu,
 	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
-static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
-					 struct kvm_guest_debug_arch *dbg,
-					 struct kvm_cpu_context *ctxt)
+static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
+				  struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -124,7 +122,7 @@ static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
 	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1);
 }
 
 static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
@@ -142,8 +140,8 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, host_dbg, host_ctxt);
-	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_save_state(host_dbg, host_ctxt);
+	__debug_restore_state(guest_dbg, guest_ctxt);
 }
 
 static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
@@ -161,8 +159,8 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
-	__debug_restore_state(vcpu, host_dbg, host_ctxt);
+	__debug_save_state(guest_dbg, guest_ctxt);
+	__debug_restore_state(host_dbg, host_ctxt);
 
 	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -53,7 +53,7 @@ static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
 }
 
 static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
@@ -122,9 +122,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __activate_vm(struct kvm *kvm)
+static inline void __activate_vm(struct kvm_s2_mmu *mmu)
 {
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 }
 
 static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
@@ -266,17 +266,16 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 
 	if (sve_guest) {
 		sve_load_state(vcpu_sve_pffr(vcpu),
-			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       &vcpu->arch.ctxt.fp_regs.fpsr,
 			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
-		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
 	} else {
-		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+		__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
 	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
-		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
-			     fpexc32_el2);
+		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
 
 	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
 
@@ -365,11 +364,14 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
 	return false;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
+#define __ptrauth_save_key(ctxt, key)					\
+	do {								\
+	u64 __val;                                                      \
+	__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val;                   \
+	__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val;                   \
+} while(0)
 
 static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
@@ -381,11 +383,11 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 		return false;
 
 	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__ptrauth_save_key(ctxt->sys_regs, APIA);
-	__ptrauth_save_key(ctxt->sys_regs, APIB);
-	__ptrauth_save_key(ctxt->sys_regs, APDA);
-	__ptrauth_save_key(ctxt->sys_regs, APDB);
-	__ptrauth_save_key(ctxt->sys_regs, APGA);
+	__ptrauth_save_key(ctxt, APIA);
+	__ptrauth_save_key(ctxt, APIB);
+	__ptrauth_save_key(ctxt, APDA);
+	__ptrauth_save_key(ctxt, APDB);
+	__ptrauth_save_key(ctxt, APGA);
 
 	vcpu_ptrauth_enable(vcpu);
 

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -52,9 +52,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		 * configured and enabled. We can now restore the guest's S1
 		 * configuration: SCTLR, and only then TCR.
 		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
 		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 }
 
@@ -194,7 +194,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_vm(kern_hyp_va(vcpu->arch.hw_mmu));
 	__activate_traps(vcpu);
 
 	__hyp_vgic_restore_state(vcpu);

arch/arm64/kvm/hyp/nvhe/tlb.c

@@ -12,7 +12,8 @@ struct tlb_inv_context {
 	u64		tcr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -30,12 +31,10 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 		isb();
 	}
 
-	/* __load_guest_stage2() includes an ISB for the workaround. */
-	__load_guest_stage2(kvm);
-	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
+	__load_guest_stage2(mmu);
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -47,15 +46,16 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	}
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -63,7 +63,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
@@ -98,39 +98,39 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	if (icache_is_vpipt())
 		__flush_icache_all();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)

arch/arm64/kvm/hyp/vhe/switch.c

@@ -125,7 +125,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
 	 * (among other things).
 	 */
-	__activate_vm(vcpu->kvm);
+	__activate_vm(vcpu->arch.hw_mmu);
 	__activate_traps(vcpu);
 
 	sysreg_restore_guest_state_vhe(guest_ctxt);

arch/arm64/kvm/hyp/vhe/tlb.c

@@ -16,7 +16,8 @@ struct tlb_inv_context {
 	u64		sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	u64 val;
 
@@ -52,14 +53,14 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 	 * place before clearing TGE. __load_guest_stage2() already
 	 * has an ISB in order to deal with this.
 	 */
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 	val = read_sysreg(hcr_el2);
 	val &= ~HCR_TGE;
 	write_sysreg(val, hcr_el2);
 	isb();
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	/*
 	 * We're done with the TLB operation, let's restore the host's
@@ -78,14 +79,15 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	local_irq_restore(cxt->flags);
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -93,7 +95,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
@@ -106,38 +108,37 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)

arch/arm64/kvm/inject_fault.c

@@ -64,7 +64,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	case PSR_MODE_EL1h:
 		vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1);
 		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
-		vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
+		vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
 		break;
 	default:
 		/* Don't do that */

arch/arm64/kvm/regmap.c

@@ -100,7 +100,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
  */
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs;
 	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 
 	switch (mode) {
@@ -147,8 +147,20 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 {
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
-	if (!vcpu->arch.sysregs_loaded_on_cpu)
-		return vcpu_gp_regs(vcpu)->spsr[spsr_idx];
+	if (!vcpu->arch.sysregs_loaded_on_cpu) {
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			return __vcpu_sys_reg(vcpu, SPSR_EL1);
+		case KVM_SPSR_ABT:
+			return vcpu->arch.ctxt.spsr_abt;
+		case KVM_SPSR_UND:
+			return vcpu->arch.ctxt.spsr_und;
+		case KVM_SPSR_IRQ:
+			return vcpu->arch.ctxt.spsr_irq;
+		case KVM_SPSR_FIQ:
+			return vcpu->arch.ctxt.spsr_fiq;
+		}
+	}
 
 	switch (spsr_idx) {
 	case KVM_SPSR_SVC:
@@ -171,7 +183,24 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		vcpu_gp_regs(vcpu)->spsr[spsr_idx] = v;
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
+			break;
+		case KVM_SPSR_ABT:
+			vcpu->arch.ctxt.spsr_abt = v;
+			break;
+		case KVM_SPSR_UND:
+			vcpu->arch.ctxt.spsr_und = v;
+			break;
+		case KVM_SPSR_IRQ:
+			vcpu->arch.ctxt.spsr_irq = v;
+			break;
+		case KVM_SPSR_FIQ:
+			vcpu->arch.ctxt.spsr_fiq = v;
+			break;
+		}
+
 		return;
 	}
 

arch/arm64/kvm/reset.c

@@ -288,7 +288,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	/* Reset core registers */
 	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
-	vcpu_gp_regs(vcpu)->regs.pstate = pstate;
+	vcpu_gp_regs(vcpu)->pstate = pstate;
 
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);

arch/arm64/kvm/sys_regs.c

@@ -94,6 +94,7 @@ static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	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_s(SYS_PAR_EL1);	break;
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
@@ -133,6 +134,7 @@ static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	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;

arch/arm64/kvm/trace_arm.h

@@ -301,8 +301,8 @@ TRACE_EVENT(kvm_timer_save_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 
@@ -323,8 +323,8 @@ TRACE_EVENT(kvm_timer_restore_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 

include/kvm/arm_arch_timer.h

@@ -26,16 +26,9 @@ enum kvm_arch_timer_regs {
 struct arch_timer_context {
 	struct kvm_vcpu			*vcpu;
 
-	/* Registers: control register, timer value */
-	u32				cnt_ctl;
-	u64				cnt_cval;
-
 	/* Timer IRQ */
 	struct kvm_irq_level		irq;
 
-	/* Virtual offset */
-	u64				cntvoff;
-
 	/* Emulated Timer (may be unused) */
 	struct hrtimer			hrtimer;
 
@@ -71,7 +64,7 @@ int kvm_timer_hyp_init(bool);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
@@ -109,4 +102,8 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
 				enum kvm_arch_timer_regs treg,
 				u64 val);
 
+/* Needed for tracing */
+u32 timer_get_ctl(struct arch_timer_context *ctxt);
+u64 timer_get_cval(struct arch_timer_context *ctxt);
+
 #endif